A threshing state management system, a management method, a management program, a recording medium in which the program is recorded, a harvester management system, a harvester, a harvester management method, a management program, a recording medium in which the program is recorded, a work vehicle, a work vehicle management method, a management system, a management program, a recording medium in which the program is recorded, a management system, and a management method. Management program and recording medium having the program recorded thereon

Abstract

A threshing state management system is provided with: an imaging unit (80) that captures an image of a threshed object of a threshing device; a state detection neural network (72) that outputs a threshing processing state of the threshing device on the basis of image input data generated from a captured image from the imaging unit (80); a parameter determination unit (73) that determines a control parameter of the threshing device on the basis of the threshing processing state; and a threshing control unit (TU) that controls the threshing device on the basis of the control parameters.

Description

Technical Field

[0002] The present invention relates to a technology for managing the state of a threshing device that threshes harvested grain stalks.

[0003] In addition, the present invention relates to a technology for managing the loss of harvested products of a harvester, wherein the harvester includes a harvesting section that harvests crops in a field and a storage section that stores the harvested products harvested by the harvesting section.

[0004] In addition, the present invention relates to a technology for performing ground work on a predetermined work object.

[0005] Furthermore, the present invention relates to a technology for managing a work vehicle that performs ground work on a predetermined work object. Background Art

[0006] 1-1. Background technology [1]

[0007] In recent years, threshing control of a combine harvester using AI technology has been proposed. For example, in the threshing control of a combine harvester disclosed in Patent Document 1, a reinforcement learning model is used, and the reinforcement learning model calculates adjustment values ​​of vehicle speed, screen opening, wind separator speed, etc. based on the measured values ​​of a sorting loss sensor, a grain quality sensor, etc. to perform threshing control.

[0008] 1-2. Background technology 〔2〕

[0009] In addition, the combine harvester performs the cutting of standing grain stalks, threshing of cut grain stalks, sorting of grains, and storage of sorted grains. The threshing processed material of the threshing cylinder section includes grains, stalks (grains with stalks), straw chips, straw, etc. The grains sorted from the threshing processed material by the sorting section are transported to the grain box for storage. In addition, the threshing processed material (stalks, straw chips, etc.) other than normal grains are collectively referred to as non-grain materials in this specification. Straw and straw chips are discharged from the threshing cylinder section or the sorting section from the rear part of the machine body. Ideally, it is better that only the threshing processed material other than the grains is discharged from the threshing cylinder section to the outside of the machine body, but the grains are also discharged together. This grain loss is called threshing cylinder loss. Moreover, the threshing processed material discharged from the threshing cylinder section to the sorting section is not only grains, but also bad grains such as stalks and straw chips are mixed. The bad grains and straw scraps mixed into the sorting section are returned to the threshing process as secondary processed products. The generation of such secondary processed products in the sorting section is called sorting loss. In this specification, the threshing drum loss and sorting loss are collectively referred to as threshing loss. In the combine harvester, the operating equipment of the threshing device is adjusted to reduce the threshing loss.

[0010] Patent document 2 discloses a combine harvester that performs feedback control based on the loss amount calculated by a threshing cylinder loss sensor and a swing loss sensor, and adjusts the dust delivery valve, upper screen, and vehicle speed so that the loss amount is within a target range. The threshing cylinder loss sensor detects the amount of grains by load detection accompanied by contact with the grains, and detects the amount of grains falling from the terminal end of the screen installed below the threshing cylinder. The swing loss sensor, which is a pressure sensor, detects the amount of grains falling from the rear of the swing sorting device to the secondary processed material recovery unit.

[0011] Patent Document 3 discloses a combine harvester that performs image processing on a captured image of grains stored in a grain tank to inspect the state of the grains and the presence of foreign matter, and adjusts a dust delivery valve and an upper screen of a threshing device based on the inspection results.

[0012] 1-3. Background technology 〔3〕

[0013] In addition, in the past, working vehicles for ground work have been used. Among such working vehicles, for example, there is a combine harvester described in Patent Document 3, which is equipped with a threshing device for threshing grain stalks cut during driving and a grain box for storing grain threshed by the threshing device.

[0014] The combined harvester described in Patent Document 3 is provided with a loading plate for loading grains in a grain box, two light sources for irradiating light to both sides of the loading plate, and a shooting unit for shooting a first image and a second image, wherein the first image is an image obtained by shooting the grains on the loading plate when light is irradiated from one of the two light sources, and the second image is an image obtained by shooting the grains on the loading plate when light is irradiated from the other of the two light sources. The image processing unit extracts an image representing foreign matter from the first image to calculate the number of foreign matter, and calculates the number of damaged grains and the number of branches and stalks based on the second image. The adjustment unit adjusts the angle of the upper screen and the opening and closing of the dust delivery valve and the processing cylinder valve based on the calculated number of foreign matter, the number of damaged grains, and the number of branches and stalks.

[0015] Prior art literature

[0016] Patent Literature

[0017] Patent Document 1: U.S. Patent Application Publication No. 2018 / 0271015

[0018] Patent Document 2: Japanese Patent Application Publication No. 2017-176060

[0019] Patent Document 3: Japanese Patent Application Publication No. 2013-027340 Summary of the invention

[0020] Problems to be solved by the invention

[0021] 2-1.Topic〔1〕

[0022] The issues corresponding to the background technology [1] are as follows.

[0023] In the reinforcement learning model for threshing control carried by the combine harvester of patent document 1, the measured values ​​of multiple sensors for detecting the state of the combine harvester are input, and appropriate adjustment values ​​for multiple action components are output. By controlling the action components based on the adjustment values, the threshing performance is improved, and the harvesting performance is improved as a result. However, the number of sensors for measuring the measured values ​​input to the reinforcement learning model is large, and the computational load in the sensor signal processing is large.

[0024] Therefore, a technology capable of performing good threshing control even if the number of detection sensors for detecting the threshing state is small is required.

[0025] 2-2. Topic 〔2〕

[0026] The issues corresponding to background technology 〔2〕 are as follows.

[0027] In the threshing control of Patent Document 2, the instantaneous threshing loss amount is measured by a threshing loss sensor composed of a threshing cylinder loss sensor and a swing loss sensor, and the threshing device is adjusted when the measured value deviates from the target range. However, the threshing processing volume changes all the time. For example, the threshing loss amount is not necessarily large if the threshing processing volume is large. Therefore, when the threshing device is adjusted based on the instantaneous threshing loss amount, there will be a problem that appropriate threshing control may not be performed.

[0028] In the threshing control of Patent Document 3, the state of grains and the mixing of foreign matter are checked by image processing of the images captured by the camera. In this threshing control, the installation space of the camera is smaller than that of the mechanically operated threshing loss sensor shown in Patent Document 1. However, the mixing amount of foreign matter to be checked is also detected as the instantaneous threshing loss amount, which has the same problem as Patent Document 3.

[0029] Therefore, a technique for properly managing harvest losses is required.

[0030] 2-3. Topic 〔3〕

[0031] The issues corresponding to background technology 〔3〕 are as follows.

[0032] As described above, the technology described in Patent Document 3 calculates the number of foreign matter, the number of grains, and the number of branches when conveying the grains harvested into the grain box, and adjusts the angle of the upper screen and the opening and closing of the dust delivery valve and the processing cylinder valve based on the calculated number of foreign matter, the number of damaged grains, and the number of branches. Therefore, the mixing of foreign matter, grains, and branches into the grain box is not zero, so there is room for improvement in reducing the amount of foreign matter, grains, and branches mixed into the grain box. That is, there is room for improvement in the aspect of a work vehicle (such as a combine harvester) performing ground work (such as harvesting work) on a predetermined work object (such as a field).

[0033] Therefore, a technology capable of appropriately performing ground operations is required.

[0034] 2-4. Topic 〔4〕

[0035] In addition, as a subject corresponding to the background technology [3], there is the following subject.

[0036] As described above, the technology described in Patent Document 3 calculates the number of foreign matter, the number of grains, and the number of branches when conveying grains harvested into a grain box, and adjusts the angle of the upper screen and the opening and closing of the dust delivery valve and the processing cylinder valve based on the calculated number of foreign matter, the number of damaged grains, and the number of branches. On the other hand, in various devices, regular maintenance is performed to prevent deterioration and failure of various components, but it is not easy for users to easily determine when maintenance should be performed.

[0037] Therefore, a technology for managing a work vehicle capable of performing ground work is required.

[0038] Means for solving problems

[0039] 3-1. Solution〔1〕

[0040] The solution to problem [1] is as follows.

[0041] The threshing state management system of the present invention, which manages the state of a threshing device that threshes harvested grain stalks while traveling, comprises: a photographing unit that photographs the threshed material of the threshing device; a state detection neural network that outputs the threshing process state of the threshing device based on image input data generated according to the photographed image from the photographing unit; a parameter determination unit that determines control parameters of the threshing device based on the threshing process state; and a threshing control unit that controls the threshing device based on the control parameters.

[0042] According to this structure, image input data (a group of pixel values ​​of a captured image or a group of representative values ​​of pixel values ​​in a partition in which the captured image is divided into a specified number of partitions, etc.) generated by capturing a captured image of a threshing material processed by a threshing device is input, thereby outputting a threshing process state. The threshing process state includes, for example, grains and non-grains in the threshing material (grains other than those specified, such as broken grains, branches, straw scraps, etc.), the amount of threshing material, threshing loss, etc. If you are an expert in threshing, you can observe the state of the threshing material in the threshing device to estimate the threshing process state, but the state detection neural network of the present invention can make this estimate more accurately and quickly. The parameter determination unit inputs the output threshing process state from the state detection neural network, and if the current threshing process state should be further improved, determines the control parameters of the threshing device to achieve its improvement. The threshing control unit controls the threshing device based on the determined control parameters.

[0043] By considering not only the setting state of the action components of the threshing device but also the driving state such as the speed of the machine body (vehicle speed) and the engine speed as factors affecting the threshing process state, the estimation of the threshing process state will become more accurate. From this point of view, in a preferred embodiment of the present invention, a driving state sensor for detecting the driving state is provided, and state input data representing the driving state generated based on the detection signal from the driving state sensor is input into the state detection neural network.

[0044] In a preferred embodiment of the present invention, the state detection neural network learns the learning image captured during the threshing process and the estimated threshing process state estimated based on the learning image as learning data. The estimated threshing process state estimated based on the learning image can be artificially used as correct data for learning data by an expert in the threshing process or the like. The state detection neural network that has been learned using such learning data can estimate the threshing process state equivalent to that of an expert in the threshing process.

[0045] In a preferred embodiment of the present invention, the parameter determination unit is a control neural network configured to input a feature vector representing the threshing process state and output the control parameter. In this structure, the parameter determination unit that receives the threshing process state from the state detection neural network is also composed of a neural network, so that feature vectors that are easy to handle with each other can be used as the threshing process state as their respective outputs and inputs. In other words, the feature vector that is the output of the state detection neural network becomes the input of the control neural network. In this structure, the state detection neural network can be combined with the control neural network. In the combined state detection neural network and control neural network, batch learning can be performed by using the control parameter set that is most suitable for the threshing process state shown in the learning captured image and the learning captured image as learning data.

[0046] In order to estimate the threshing process state using the captured images of the threshing process material processed by the threshing device, it is preferred to capture the threshing process material at multiple positions and in multiple directions. This is because if such multiple captured images are used, the amount of information used for estimation becomes larger. From this point of view, in a preferred embodiment of the present invention, the shooting unit includes multiple cameras each having a different shooting field of view, and one state detection neural network corresponds to the multiple cameras, and all the image input data corresponding to the captured images from the multiple cameras are input into the state detection neural network.

[0047] In the threshing device, there are areas where a large amount of grains are mixed with a small amount of non-grain matter (straw scraps, etc.) and areas where a large amount of non-grain matter is mixed with a small amount of grains. If a plurality of captured images with such areas as the shooting field of view are used as image input data of the state detection neural network, the estimation of the threshing process state may become inaccurate. From this point of view, in a preferred embodiment, the shooting unit includes a plurality of cameras having different shooting fields of view, and a plurality of the state detection neural networks are arranged in a manner corresponding to the plurality of cameras, respectively, and each image input data corresponding to the captured images from the plurality of cameras is input to the state detection neural network corresponding to the camera as the shooting source, and the threshing process state outputted from each is provided to the parameter determination unit.

[0048] In addition, the threshing state management method of the present invention is a threshing state management method for managing the state of a threshing device that threshes cut grain stalks while traveling, wherein the method comprises: a photographing step, which utilizes a photographing unit to photograph the threshed material of the threshing device; a threshing processing state outputting step, which utilizes a state detection neural network to output the threshing processing state of the threshing device based on image input data generated according to the photographed image from the photographing unit; a parameter determination step, which determines the control parameters of the threshing device based on the threshing processing state; and a control step, which utilizes a threshing control unit to control the threshing device based on the control parameters.

[0049] Even with such a threshing and sorting method, good threshing control can be performed.

[0050] In addition, the threshing state management program of the present invention is a threshing state management program for managing the state of a threshing device that threshes cut grain stalks while traveling, and is characterized in that a computer is enabled to execute the following functions: a photographing function, which utilizes a photographing unit to photograph the threshed material of the threshing device; a threshing processing state output function, which utilizes a state detection neural network to output the threshing processing state of the threshing device based on image input data generated according to the photographed image from the photographing unit; a parameter determination function, which determines the control parameters of the threshing device based on the threshing processing state; and a control function, which utilizes a threshing control unit to control the threshing device based on the control parameters.

[0051] By causing the computer installed with such a threshing state management program to execute the program, favorable threshing control can be performed.

[0052] In addition, the recording medium of the present invention that records the threshing status management program is a recording medium that records the threshing status management program for managing the state of a threshing device that threshes cut grain stalks while traveling, wherein the threshing status management program is used to enable a computer to execute the following functions: a shooting function, which uses a shooting unit to shoot the threshed material of the threshing device; a threshing processing state output function, which uses a state detection neural network to output the threshing processing state of the threshing device based on image input data generated according to the captured image from the shooting unit; a parameter determination function, which determines the control parameters of the threshing device based on the threshing processing state; and a control function, which uses a threshing control unit to control the threshing device based on the control parameters.

[0053] By installing the threshing state management program in a computer via such a recording medium and causing the computer to implement the program, favorable threshing control can be performed.

[0054] 3-2. Solution〔2〕

[0055] The solution to problem [2] is as follows.

[0056] The harvester management system of the present invention manages the loss of harvested products of the harvester, wherein the harvester comprises a harvesting part for harvesting crops in a field and a storage part for storing the harvested products harvested by the harvesting part, and the harvester management system comprises: a harvesting amount measuring unit for measuring the harvesting amount of the harvested products; a loss amount calculating unit for calculating the loss amount, which represents the amount of loss generated during the transportation of the harvested products from the harvesting part to the storage part; and a loss rate calculating unit for calculating the loss rate based on the harvesting amount and the loss amount, and the loss rate is the loss amount per unit harvesting amount.

[0057] According to this structure, the harvest amount measured by the harvest amount measuring unit and the loss amount calculated by the loss amount calculating unit are provided to the loss rate calculating unit. The loss rate calculating unit sequentially calculates the loss amount per unit harvest amount during the harvesting operation, that is, the loss rate. If the loss rate is calculated sequentially in this way, harvester control based on the loss rate can be performed. The loss rate is a value obtained by dividing the loss amount by the harvest amount. Therefore, in the harvester control based on the loss rate, compared with the control directly based on the change of the loss amount, even if a sudden change in the loss amount occurs, the impact on the control is smaller. As a result, the harvester control based on the loss rate eliminates the problems that may occur in the control based on the instantaneous loss amount.

[0058] In a preferred embodiment of the present invention, a detection unit for detecting the loss is provided in the loss area where the loss occurs, and the loss amount calculation unit is configured to output the loss amount based on the detection result from the detection unit. In this configuration, a loss area known in advance where loss occurs during the transportation of the harvested material from the harvesting unit to the storage unit is determined, and a detection unit for detecting the loss is provided in the loss area, so that the detection unit can quickly detect the loss in the specific loss area with little adverse effects such as external interference.

[0059] In the past, the threshing loss in the threshing device was measured using a collision sensor, which has the disadvantage of requiring a large installation space. In order to eliminate such a problem, the present invention proposes to calculate the loss amount using a captured image of the loss area and a neural network as a machine learning unit. That is, in a preferred embodiment of the present invention, as the detection unit, there is a photographing unit that photographs the loss area where the loss occurs.

[0060] The loss amount calculation unit is configured as a neural network that outputs the loss amount based on image input data generated from the captured image from the camera unit. The neural network is a machine learning model that is learned to output the loss amount based on the ratio of the real harvest (e.g., grains) and pseudo harvest (e.g., non-grain materials such as stalks and straw scraps) reflected in the captured image. At this time, in order to improve the reliability of the neural network, it is preferred to input the image input data obtained by performing pre-processing such as standardization on the captured images sent sequentially as input data of the neural network.

[0061] In a preferred embodiment of the present invention, the neural network uses the learning image input data generated based on the learning image captured during the harvesting operation of the harvester and the estimated loss amount actually estimated based on the learning image (the estimated value of an experienced or expert in the harvesting process) as learning data for learning. That is, during learning, the learning image input data generated based on the learning image captured during the harvesting operation is used as input learning data, and the loss amount artificially estimated based on the learning image is used as output learning data (correct data). In this structure, since the image captured during the actual harvesting operation is used as the learning image and the estimated loss amount actually estimated by an experienced or expert in the harvesting process based on the learning image is used as correct data, the threshing control based on the loss amount output from the neural network after learning is supported by the judgment of an experienced or expert in the harvesting process.

[0062] One of the loss areas suitable for confirming the loss is an area where a large amount of real harvest is mixed with a small amount of pseudo harvest, and the other is an area where a large amount of pseudo harvest is mixed with a small amount of real harvest. Therefore, if the image input data based on the captured images with such two different areas as the shooting field of view is used as the input of the same neural network, it may be difficult to calculate the loss amount. From this point of view, in a preferred embodiment of the present invention, the shooting unit includes a plurality of cameras having different shooting fields of view, and a plurality of the neural networks are arranged in a manner corresponding to the plurality of cameras, respectively, and each of the image input data corresponding to the captured images from the plurality of cameras is input to each of the neural networks corresponding to the camera as the shooting source. In this structure, the loss amount of each area is outputted using a dedicated neural network configured to be respectively suitable for the captured images of different areas. Since the loss amounts of different areas are calculated by the most suitable captured images and the dedicated neural network, a loss amount with higher reliability can be obtained.

[0063] In photographing the loss area where the loss occurs, by photographing the harvested products in the area at various positions and in various shooting directions, the amount of information obtained from the photographed images will increase. From this point of view, in a preferred embodiment of the present invention, the photographing unit includes a plurality of cameras each having a different shooting field of view, and one neural network corresponds to the plurality of cameras, and all the image input data corresponding to the photographed images from the plurality of cameras are input into the neural network. In this structure, based on the photographed images of the harvested products taken from various positions and in various directions, a more reliable loss amount is output.

[0064] In a preferred embodiment of the present invention, the harvester is provided with a threshing device for threshing the harvested material, the harvested material measuring unit measures the amount of grains obtained from the harvested material, i.e., the yield, as the harvested material, and the loss amount calculating unit calculates the amount of threshing loss in the threshing device as the loss amount. In the threshing process as one of the harvested material processes of the harvester, the cut grain stalks are separated into grains and straws while passing through a threshing cylinder. The threshed materials such as grains falling downward from the threshing cylinder are further sorted. The straws are sent to the rear of the threshing cylinder and discharged from the rear of the machine body. At this time, the amount of grains (real harvested material) mixed into the straws (pseudo-harvest material) sent from the rear of the threshing cylinder to the outside of the machine is equivalent to the threshing cylinder loss. If the amount of the mixed grains is large, the threshing cylinder loss is large. In addition, the amount of grains (real harvest) discharged outside the machine after sorting the threshed material falling from the threshing drum and mixed with non-grain materials (pseudo harvest) such as straw scraps is equivalent to sorting loss. If the amount of grains discharged outside the machine is large, the sorting loss is large. Sorting loss and threshing drum loss are collectively referred to as threshing loss. From this point of view, it is more effective to use threshing loss as the loss amount.

[0065] Since the sorting loss and the threshing cylinder loss have different definitions, when calculating the sorting loss and the threshing cylinder loss based on the captured images, the captured images captured in different threshing areas (loss areas) are used respectively. Therefore, in a preferred embodiment of the present invention, the loss area where the loss occurs includes the threshing cylinder terminal end area and the screen box rear end area. In another embodiment, the loss area where the loss occurs includes the discharge area where non-grain materials (straw, straw scraps, etc.) other than grains are discharged from the threshing device.

[0066] If the action equipment of the harvester is automatically adjusted so that the loss rate calculated using the loss amount (sorting loss amount, threshing barrel loss amount, etc.) calculated by the neural network is within the allowable range, appropriate control of the harvester will be achieved. Therefore, in a preferred embodiment of the present invention, a parameter determination unit is provided for determining the control parameters of the harvester based on the loss amount. Of course, the parameter determination unit can also determine the control parameters of the harvester based on a combination of the loss amount and the loss rate, or based only on the loss rate.

[0067] The present invention described above is also applied to a harvester. Such a harvester includes: a harvesting section that harvests crops in a field; a storage section that stores the harvested material harvested by the harvesting section; a harvesting amount measuring unit that measures the harvesting amount of the harvested material; a loss amount calculating unit that calculates the loss amount, which represents the amount of loss generated during the transportation of the harvested material from the harvesting section to the storage section; and a loss rate calculating unit that calculates the loss rate based on the harvesting amount and the loss amount, which is the loss amount per unit harvesting amount. The harvester of the present invention can also obtain the above-mentioned various functions and effects.

[0068] In a preferred embodiment of the harvester of the present invention, the harvester is provided with: a travel device; a conveying device for conveying the harvested material; and a threshing device for threshing the harvested material; and a parameter determination unit for determining a control parameter of at least one of the travel device, the harvesting unit, the conveying device, and the threshing device based on the loss rate. With this structure, the harvester can improve its harvesting performance by automatically adjusting each action device so that the loss rate is within the allowable range.

[0069] The present invention is also applied to the harvester management method used in the above-mentioned harvester management system. Such a harvester management method is for a harvester having a harvesting part for harvesting crops in a field and a storage part for storing the harvested material harvested by the harvesting part, while using the harvester to perform a harvesting operation, while measuring the harvested material harvest amount, and while using the harvester to perform the harvesting operation, while calculating the loss amount, which represents the amount of loss generated during the transportation of the harvested material from the harvesting part to the storage part, and while using the harvester to perform the harvesting operation, calculating the loss rate based on the harvested material and the loss amount, which is the loss amount per unit harvested material. The harvester management method of the present invention can also obtain the above-mentioned various functions and effects.

[0070] In a preferred embodiment of the harvester management method of the present invention, the control parameters of the harvester are determined based on the loss rate while the harvester is used to perform the harvesting operation. Through the harvester management method, each action device of the harvester is automatically adjusted to keep the loss rate within the allowable range, and its harvesting performance is improved.

[0071] In addition, the harvester management program of the present invention is characterized in that it enables a computer to execute the following functions: a measuring function, which measures the harvested amount of the harvested material while using the harvester to perform the harvesting operation, for a harvester equipped with a harvesting section for harvesting crops in a field and a storage section for storing the harvested material harvested by the harvesting section; a loss amount calculating function, which calculates the loss amount while using the harvester to perform the harvesting operation, and the loss amount represents the amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section; and a loss rate calculating function, which calculates the loss rate based on the harvested amount and the loss amount while using the harvester to perform the harvesting operation, and the loss rate is the loss amount per unit harvested amount.

[0072] By having a computer installed with such a harvester management program and executing it, harvest loss can be appropriately managed.

[0073] In addition, the recording medium of the present invention that records the harvester management program records the harvester management program for causing a computer to execute the following functions: a measuring function, which measures the harvested amount of the harvested material while performing a harvesting operation using the harvester, for a harvester that has a harvesting section that harvests crops in a field and a storage section that stores the harvested material harvested by the harvesting section; a loss amount calculating function, which calculates the loss amount while performing the harvesting operation using the harvester, the loss amount representing the amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section; and a loss rate calculating function, which calculates the loss rate based on the harvested amount and the loss amount while performing the harvesting operation using the harvester, the loss rate being the loss amount per unit of harvested amount.

[0074] By installing the harvester management program in a computer via such a recording medium and causing the computer to implement the program, it is possible to appropriately manage harvest loss.

[0075] 3-3. Solution〔3〕

[0076] The solution to problem [3] is as follows.

[0077] The characteristic structure of the work vehicle of the present invention is that it is a work vehicle that performs ground work on a predetermined work object, wherein it comprises: a first information acquisition unit, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting values ​​for setting the capabilities of the equipment used in the past ground work, and the work results of the ground work performed in the past ground work; a second information acquisition unit, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation unit, which estimates the equipment setting values ​​of the equipment used in the ground work to be performed next based on the first information and the second information.

[0078] If such a characteristic configuration is adopted, it is possible to easily set appropriate equipment setting values ​​for equipment used in the next ground work to be performed based on the working conditions, equipment setting values, and working results of the ground work performed in the past and the working conditions of the next ground work to be performed. Therefore, the ground work can be performed appropriately.

[0079] In addition, it is preferred that there is a setting value indicating unit for applying the calculated device setting value to the device when the ground work is to be performed next, and the setting value indicating unit applies the device setting value when the working site where the past ground work was performed is the same as the working site where the ground work is to be performed next.

[0080] According to such a configuration, when the work locations are the same, the device setting values ​​estimated by the estimation unit can be automatically set. Therefore, the setting of the device setting values ​​can be simplified.

[0081] In addition, it is preferable that the device setting value estimation unit continuously estimates the device setting value during the implementation of the ground work.

[0082] With such a configuration, even in the same work site, device setting values ​​can be set in real time, and appropriate device setting values ​​can be set.

[0083] Furthermore, it is preferable that the device setting value estimation unit automatically estimates the device setting value as the ground work is performed.

[0084] With such a configuration, the estimated device setting values ​​can be automatically set, thereby reducing the trouble of setting.

[0085] In addition, it is preferable that the working conditions of the working object include position information indicating the position of a working place where the ground working is performed.

[0086] With such a configuration, for example, appropriate equipment setting values ​​and work results can be managed according to the position in the work site, so that equipment setting values ​​used in the next work on the ground can be appropriately set.

[0087] In addition, it is preferable that the above-mentioned work on the ground is a threshing work of performing a threshing process on cut grain stalks cut in a field, and the above-mentioned equipment setting value is a control parameter of a threshing device that performs the threshing process.

[0088] In addition, preferably, the estimation of the equipment setting value of the equipment used in the ground operation to be performed next is carried out by inputting the first information and the second information into a neural network, and the neural network is a learning neural network that estimates the equipment setting value based on the first information and the specified working conditions.

[0089] With such a configuration, the equipment setting value can be estimated more appropriately, and thus ground work can be performed more appropriately.

[0090] In addition, the work vehicle management method of the present invention is a work vehicle management method for managing a work vehicle that performs ground work on a predetermined work object, wherein the method comprises: a first information acquisition step, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, equipment setting values ​​for setting the capabilities of the equipment used in the past ground work, and the work results of the ground work performed in the past ground work; a second information acquisition step, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation step, which estimates the equipment setting values ​​of the equipment used in the ground work to be performed next based on the first information and the second information.

[0091] Even with such a work vehicle management method, ground work can be appropriately performed.

[0092] In addition, the work vehicle management system of the present invention is a work vehicle management system for managing work vehicles that perform ground work on predetermined work objects, wherein the management system comprises: a first information acquisition unit, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting values ​​for setting the capabilities of the equipment used in the past ground work, and the work results of the ground work performed in the past ground work; a second information acquisition unit, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation unit, which estimates the equipment setting values ​​of the equipment used in the ground work to be performed next based on the first information and the second information.

[0093] Even with such a work vehicle management system, ground work can be appropriately performed.

[0094] In addition, the work vehicle management program of the present invention is a work vehicle management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, and is characterized in that it enables the computer to execute the following functions: a first information acquisition function, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting values ​​for setting the capabilities of the equipment used in the past ground work, and the work results of the ground work performed in the past ground work; a second information acquisition function, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation function, which estimates the equipment setting values ​​of the equipment used in the ground work to be performed next based on the first information and the second information.

[0095] By causing a computer installed with such a work vehicle management program to execute the program, ground work can be appropriately performed.

[0096] In addition, the recording medium of the present invention records the work vehicle management program, which records the work vehicle management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, wherein the work vehicle management program is used to enable the computer to perform the following functions: a first information acquisition function, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting values ​​for setting the capabilities of the equipment used in the past ground work, and the work results of the ground work performed in the past ground work; a second information acquisition function, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation function, which estimates the equipment setting values ​​of the equipment used in the ground work to be performed next based on the first information and the second information.

[0097] By installing the work vehicle management program in a computer via such a recording medium and causing the computer to implement the program, it is possible to appropriately perform work on the ground.

[0098] 3-4. Solution〔4〕

[0099] The solution to problem [4] is as follows.

[0100] The characteristic structure of the management system of the present invention is that it is a management system that manages a work vehicle that performs ground work on a predetermined work object, wherein it comprises: a first information acquisition unit that acquires first information related to the ground work that was stored when the ground work was performed in the past; a second information acquisition unit that acquires second information related to the ground work currently being performed; and a determination unit that compares the first information with the second information to determine the status of the work vehicle.

[0101] With such a characteristic configuration, the state of a work vehicle performing ground work is determined based on information on ground work performed in the past and information on ground work currently being performed, so that the work vehicle can be appropriately managed according to the state of the work vehicle.

[0102] In addition, preferably, the first information includes information related to the work object in the completed ground work and information related to the work vehicle when performing the ground work, and the second information includes information related to the work object in the ground work currently being performed.

[0103] With such a configuration, the state of the work vehicle can be determined using not only information about past and present work objects but also information about past ground work. Therefore, the state of the work vehicle can be determined more appropriately.

[0104] In addition, it is preferable that the determination unit determines whether or not the work vehicle is abnormal as the state of the work vehicle.

[0105] With such a configuration, it is possible to continuously perform work on the ground when the work vehicle is not abnormal, and to perform maintenance when the work vehicle is abnormal.

[0106] In addition, it is preferable that the determination unit determines a maintenance time of the work vehicle as the state of the work vehicle.

[0107] With such a configuration, even when maintenance is urgently required, it is possible to predict the time when maintenance of the work vehicle is required, thereby preventing a breakdown of the work vehicle.

[0108] Furthermore, it is preferable that a reporting unit for reporting a determination result of the determination unit is provided.

[0109] With such a configuration, the operator can be informed of the determination result, and thus, even when the work vehicle has an abnormality or requires maintenance, it is possible to prevent omission.

[0110] Furthermore, it is preferable to include a storage unit for continuously storing the determination result of the determination unit.

[0111] According to such a configuration, by confirming the determination result stored in the storage unit, the cause of the failure and the reason why maintenance is required can be easily identified.

[0112] In addition, preferably, the state of the work vehicle is determined by inputting the first information and the second information into a neural network, and the neural network is a neural network that learns to determine the state of the work vehicle based on the first information and information related to the specified ground operation.

[0113] With such a configuration, the state of the work vehicle can be determined more appropriately, and thus the work vehicle can be managed more appropriately.

[0114] In addition, another characteristic configuration of the management system of the present invention is a management system that manages a work vehicle that performs ground work on a predetermined work object, wherein the management system comprises: a first information acquisition unit that acquires first information related to the ground work that was stored when the ground work was performed in the past; a second information acquisition unit that acquires second information related to the ground work currently being performed; and a determination unit that compares the first information with the second information to determine the state of the work vehicle; the determination unit is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least any one of the following learning: when information related to the ground work when the work vehicle is abnormal is input as teacher data, learning of outputting a determination result that the work vehicle is abnormal; and when information related to the ground work when the work vehicle requires maintenance is input as teacher data, learning of outputting a determination result that the maintenance time of the work vehicle is required.

[0115] Even with such a characteristic configuration, the work vehicle can be managed more appropriately, similarly to the above-mentioned management system.

[0116] In addition, the management method of the present invention is a management method for managing a work vehicle that performs ground work on a predetermined work object, which comprises: a first information acquisition step, which acquires first information related to the ground work that was stored when the ground work was performed in the past; a second information acquisition step, which acquires second information related to the ground work currently being performed; and a determination step, which compares the first information with the second information to determine the status of the work vehicle.

[0117] Even with such a management method, it is possible to manage work vehicles that can perform ground work.

[0118] In addition, the management program of the present invention is a management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, and is characterized in that the computer is caused to execute the following functions: a first information acquisition function, which acquires first information related to the ground work that was stored when the ground work was performed in the past; a second information acquisition function, which acquires second information related to the ground work currently being performed; and a judgment function, which compares the first information with the second information to determine the status of the work vehicle.

[0119] By causing a computer installed with such a management program to execute the program, it is possible to manage work vehicles that can perform work on the ground.

[0120] In addition, the recording medium of the present invention records a management program, which is executed by a computer and manages a work vehicle that performs ground work on a predetermined work object, wherein the management program is used to enable the computer to perform the following functions: a first information acquisition function, which acquires first information related to the ground work that was stored when the ground work was performed in the past; a second information acquisition function, which acquires second information related to the ground work currently being performed; and a judgment function, which compares the first information with the second information to determine the status of the work vehicle.

[0121] By installing the management program in a computer via such a recording medium and causing the computer to implement the management program, it is possible to manage the work vehicles that can perform ground work.

[0122] Moreover, the management method of the present invention is a management method for managing a work vehicle that performs ground work on a predetermined work object, wherein the method comprises: a first information acquisition step, which acquires first information related to the ground work that was stored when the ground work was performed in the past; a second information acquisition step, which acquires second information related to the ground work currently being performed; and a judgment step, which compares the first information with the second information to determine the state of the work vehicle; the judgment step is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least any one of the following learning: when the information related to the ground work when the work vehicle is abnormal is input as teacher data, the learning of outputting the judgment result that the work vehicle is abnormal; and when the information related to the ground work when the work vehicle needs maintenance is input as teacher data, the learning of outputting the judgment result of the maintenance time of the work vehicle.

[0123] Even with such a management method, it is possible to manage work vehicles that can perform ground work.

[0124] In addition, the management program of the present invention is a management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, wherein the management program comprises: a first information acquisition function, which acquires first information related to the ground work stored when the ground work was performed in the past; a second information acquisition function, which acquires second information related to the ground work currently being performed; and a judgment function, which compares the first information with the second information to judge the state of the work vehicle; the judgment function is performed by inputting the first information and the second information into a neural network, which is a neural network that has performed at least one of the following learnings: when information related to the ground work when the work vehicle is abnormal is input as teacher data, learning of outputting a judgment result that the work vehicle is abnormal; and when information related to the ground work when the work vehicle needs maintenance is input as teacher data, learning of outputting a judgment result of the maintenance time of the work vehicle.

[0125] By causing a computer installed with such a management program to execute the program, it is possible to manage work vehicles that can perform work on the ground.

[0126] In addition, the recording medium of the present invention records a management program, which records a management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, wherein the management program has: a first information acquisition function, which acquires first information related to the ground work stored when the ground work was performed in the past; a second information acquisition function, which acquires second information related to the ground work currently being performed; and a judgment function, which compares the first information with the second information to determine the state of the work vehicle; the judgment function is performed by inputting the first information and the second information into a neural network, which is a neural network that performs at least any one of the following learning: when the information related to the ground work when the work vehicle is abnormal is input as teacher data, the learning of outputting the judgment result that the work vehicle is abnormal; and when the information related to the ground work when the work vehicle needs maintenance is input as teacher data, the learning of outputting the judgment result of the maintenance time of the work vehicle.

[0127] By installing the management program in a computer via such a recording medium and causing the computer to implement the management program, it is possible to manage the work vehicles that can perform ground work. BRIEF DESCRIPTION OF THE DRAWINGS

[0128] Figure 1 It is a side view of the combine including the threshing device of 1st Embodiment.

[0129] Figure 2It is a top view of the combine including the threshing device according to the first embodiment.

[0130] Figure 3 It is a longitudinal sectional side view of the threshing device which concerns on 1st Embodiment.

[0131] Figure 4 It is a layout diagram of the secondary processed material discharge port in the first embodiment.

[0132] Figure 5 This is a functional block diagram of the control system of the combine harvester according to the first embodiment.

[0133] Figure 6 It is a structural diagram of the threshing state management unit of the first embodiment.

[0134] Figure 7 This is a schematic diagram of an enlarged image of a photographed image of a threshed product according to the first embodiment.

[0135] Figure 8 This is an enlarged schematic diagram of the label image of the threshed material according to the first embodiment.

[0136] Fig. 9 This is a diagram showing the configuration of a threshing state management unit according to another embodiment of the first embodiment.

[0137] Fig.10 This is a diagram showing the configuration of a threshing state management unit according to another embodiment of the first embodiment.

[0138] Fig.11 This is a diagram showing the configuration of a threshing state management unit according to another embodiment of the first embodiment.

[0139] Fig.12 It is a side view of the combine including the threshing device of 2nd Embodiment.

[0140] Fig.13 It is a top view of the combine including the threshing device of 2nd Embodiment.

[0141] Fig.14 It is a longitudinal sectional side view of the threshing device which concerns on 2nd Embodiment.

[0142] Fig.15 It is a schematic diagram which shows the arrangement|positioning of the yield measuring device and the taste value measuring device in the grain tank of 2nd Embodiment.

[0143] Fig.16 This is a functional block diagram of a control system for a combine harvester according to a second embodiment.

[0144] Fig.17 It is a block diagram of the threshing loss management unit of the second embodiment.

[0145] Fig.18 This is a schematic diagram of an enlarged image of a photographed image of a threshed product according to the second embodiment.

[0146] Fig.19 This is an enlarged schematic diagram of a label image of a threshed material according to the second embodiment.

[0147] Fig. 20 This is a configuration diagram showing another configuration of the threshing loss management unit according to the second embodiment.

[0148] Fig.21 This is a configuration diagram showing still another configuration of the threshing loss management unit according to the second embodiment.

[0149] Fig. 22 It is a side view of the combine harvester according to the third embodiment.

[0150] Fig.23 It is a top view of the combine harvester according to the third embodiment.

[0151] Fig.24 It is a longitudinal sectional side view of the threshing device with which the combine harvester which concerns on 3rd Embodiment is equipped.

[0152] Fig.25 This is a block diagram showing a functional unit that performs processing related to estimation of device setting values ​​according to the third embodiment.

[0153] Fig.26 This is a diagram for explaining the effect of the device setting value according to the third embodiment.

[0154] Fig. 27 It is a side view of the combine harvester according to the fourth embodiment.

[0155] Fig.28 It is a top view of the combine harvester according to the fourth embodiment.

[0156] Fig.29 It is a longitudinal sectional side view of the threshing device with which the combine harvester which concerns on 4th Embodiment is equipped.

[0157] Fig.30 This is a block diagram showing a functional unit that performs processing related to determination of the state of a work vehicle according to the fourth embodiment. DETAILED DESCRIPTION

[0158] 4-1. First embodiment

[0159] Hereinafter, a preferred embodiment of the present invention will be described with reference to the accompanying drawings. In this embodiment, a threshing state management system is mounted on a combine harvester that threshes harvested grain stalks while traveling, and control parameters for threshing are determined based on the threshing state output based on a captured image of the threshed material.

[0160] Figure 1 It is a side view of a combine harvester. Figure 2 This is a top view of a combine harvester. Figure 3 It is a cross-sectional view of the threshing device 1. In addition, below, the combine harvester of this embodiment is a full-feed combine harvester, but it is a matter of course that it may be a half-feed combine harvester.

[0161] Here, for easy understanding, in this embodiment, unless otherwise specified, the "front" ( Figure 1 The direction of the arrow F shown in the figure means the front in the front-rear direction (driving direction) of the machine body, and the rear ( Figure 1 The direction of the arrow B shown in the figure) refers to the rear in the front-rear direction of the machine body (the direction of travel). Figure 1 direction of the arrow U shown) and "down" ( Figure 1 The left and right directions (the direction of the arrow D shown in the figure) are the vertical directions (vertical directions) of the machine body, indicating the height relationship from the ground. In addition, the left-right direction or the lateral direction refers to the cross-sectional direction of the machine body (the width direction of the machine body) that is orthogonal to the front-rear direction of the machine body, that is, the left ( Figure 2 direction of the arrow L shown) and "right" ( Figure 2 The directions of the arrows R shown in the figure respectively refer to the left and right directions of the machine body.

[0162] like Figure 1 and Figure 2 As shown, the combine harvester includes a machine frame 2 and a crawler travel device 3. A harvesting section 4 for harvesting standing grain stems is provided in front of a travel machine body 17.

[0163] A threshing device 1 for threshing the harvested grain stalks is provided at the rear of the harvesting section 4, and an intermediate conveying device 11 for conveying the harvested grain stalks to the threshing device 1 is provided across the harvesting section 4 and the threshing device 1. A grain box 12 for storing grains after threshing is provided at the side of the threshing device 1, and a straw discharging and breaking device 13 is provided at the rear of the threshing device 1.

[0164] A driving section 9 covered by a cab 10 is disposed on the right side of the front portion of the travel body 17. An engine E is provided below the driving section 9. The power of the engine E is transmitted to the crawler travel device 3 and the threshing device 1 through a power transmission structure (not shown). In addition, a grain discharge device 14 is provided for discharging grains in the grain box 12 to the outside.

[0165] The grain discharge device 14 includes a longitudinal conveying section 15 for conveying the grains in the grain box 12 upward and a transverse conveying section 16 for conveying the grains from the longitudinal conveying section 15 to the outside of the machine body. The grain discharge device 14 is configured to be rotatable around the axis of the longitudinal conveying section 15. The lower end of the longitudinal conveying section 15 is connected to the bottom of the grain box 12. The end of the transverse conveying section 16 on the longitudinal conveying section 15 side is connected to the upper end of the longitudinal conveying section 15 and is supported to be able to swing up and down.

[0166] like Figure 3 As shown, the threshing device 1 includes a threshing cylinder 41 for threshing the harvested grain stalks and a sorting unit 42. The threshing cylinder 41 is arranged at the upper part of the threshing device 1, and the sorting unit 42 is arranged below the threshing cylinder 41. The sorting unit 42 includes a swing sorting mechanism 24, a primary processed material recovery unit 26, a secondary processed material recovery unit 27, and a secondary processed material return unit 32.

[0167] The threshing cylinder part 41 has a threshing cylinder 22 accommodated in the threshing chamber 21 and a screen 23 installed at the bottom of the threshing cylinder 22. The threshing chamber 21 is formed as a space surrounded by a front wall 51 on the front side, a rear wall 52 on the rear side, left and right side walls, and a top plate 53 covering the upper part. A supply port 54a to which the cut grain stalks are supplied is formed below the front wall 51 in the threshing chamber 21, and a guide bottom plate 59 is arranged below the supply port 54a. In addition, a dust discharge port 54b is formed below the rear wall 52 in the threshing chamber 21.

[0168] The threshing cylinder 22 has a cylinder body 60 and a rotation support shaft 55 that are integrally rotated by a driving rotation force from a rotation drive mechanism 56. The cylinder body 60 is integrally formed with a pull-in portion 57 at a front end portion and a threshing processing portion 58 at a rear position of the pull-in portion 57.

[0169] A plurality of plate-shaped dust sending valves 53a are provided at predetermined intervals in the front-rear direction on the inner surface (lower surface) of the top plate 53. The plurality of dust sending valves 53a are configured to be able to adjust the rearward movement force acting on the harvested grain stems rotating together with the threshing drum 22 in the threshing chamber 21.

[0170] The threshed material processed by the threshing cylinder 41 includes grains, branches, straw chips, etc. In addition, the so-called primary processed material is a threshed material mainly containing grains, and the so-called secondary processed material is a threshed material containing grains that are not fully granulated and branches, straw chips, etc.

[0171] In the threshing cylinder part 41, the harvested material from the intermediate conveyance device 11 is supplied to the threshing chamber 21 through the supply port 54a. The supplied cut grain stems are pulled in by the spiral blades of the pulling-in part 57 along the guide bottom plate 59, and are threshed.

[0172] The threshed grains and short straw chips fall through the screen 23 and drop into the sorting section 42. On the other hand, the processed materials (grain straws, long straw chips, etc.) that cannot fall through the screen 23 are discharged to the outside of the threshing chamber 21 from the dust discharge port 54b.

[0173] The swing sorting mechanism 24 swings the frame-shaped screen box 33 in the front-rear direction by using an eccentric cam mechanism using an eccentric shaft or the like. A wind separator 25 that generates sorting wind from front to back is provided in the sorting section 42. In an environment where the sorting wind is supplied from the wind separator 25, the screen box 33 swings, thereby sorting grains (primary processed materials) from the threshing processed materials. In addition, a primary processed material recovery section 26 and a secondary processed material recovery section 27 are arranged below the screen box 33.

[0174] The primary processed material collected by the primary processed material collecting section 26 is conveyed (fly-fed) upward toward the grain tank 12 by the primary processed material collecting and conveying section 29. The primary processed material conveyed by the primary processed material collecting and conveying section 29 is stored by the auger 30 (see Figure 1 ) is transported to the right and supplied to the grain tank 12 (refer to Figure 1 ).

[0175] The secondary processed material recovery unit 27 is configured as a secondary processed material auger that conveys the recovered secondary processed material in the horizontal direction. The secondary processed material recovered by the secondary processed material recovery unit 27 is conveyed obliquely forward and upward by the secondary processed material return unit 32 and returned to the top of the screen box 33.

[0176] The screen box 33 includes a first grain shaking plate 34 , a plurality of first screen lines 35 , a second screen line 36 , a first upper screen 38 , a second upper screen 39 , a lower screen 40 , an upper grain shaking plate 61 , and a lower grain shaking plate 65 .

[0177] A first upper screen 38 having a plurality of chaff screens 38A is arranged at a position further back than the upper grain shaking plate 61, and a second upper screen 39 is arranged at a position further back than the first upper screen 38. In addition, the plurality of chaff screens 38A are arranged along the conveying direction (rearward direction) of the conveyed material, and the plurality of chaff screens 38A are arranged in an inclined posture that is inclined upward as they are closer to the rear end side. The lower grain shaking plate 65 is arranged below the front end portion of the first upper screen 38, and a lower screen 40 composed of a mesh body is arranged at a position connected to the rear thereof. The second upper screen 39 is arranged behind the lower screen 40 below the rear end portion of the first upper screen 38. The rear end portion (at the rear of the screen box 33) of the screen box 33 is provided. Figure 3 The right end in the middle) and the rear end of the screen 23 form a discharge portion 28.

[0178] The first upper screen 38 allows the grains contained in the threshing material to fall while conveying the threshing material to the rear side through air separation using the sorting wind and specific gravity separation accompanied by swinging. The stalks such as straw scraps are handed over to the second upper screen 39, sent from the rear end of the second upper screen 39 to the rear of the screen box 33, and discharged from the discharge section 28 to the discharge straw crushing device 13. The stalks discharged from the discharge section 28 are crushed by the discharge straw crushing device 13 and discharged to the outside of the threshing device 1. In addition, the grains that fall directly to the second upper screen 39 through the screen 23 are sorted by the second upper screen 39 into grains and stalks such as straw scraps.

[0179] A large amount of processed material including grains is caught by the upper surface of the lower screen 40. Straw scraps and the like are sent backward on the upper surface of the lower screen 40, so most of the threshed processed material that leaks from the lower screen 40 is grain, flows down to the primary processed material recovery unit 26 and is recovered, and is stored in the grain box 12 by the primary processed material recovery conveyor unit 29. Straw scraps and the like in the threshed processed material that does not leak from the lower screen 40 are sent backward by the sorting wind.

[0180] In contrast, the threshed material leaking from the rearmost part of the lower screen 40 or the threshed material falling from the second upper screen 39 flows down to the secondary material recovery unit 27 and is recovered, and is returned to the upstream side of the swing sorting mechanism 24 by the secondary material return unit 32. In addition, the garbage such as straw scraps generated as the tertiary material by the sorting process is sent backward from the rear end of the screen box 33 and discharged from the discharge unit 28 to the discharge straw crushing device 13.

[0181] like Figure 4 As shown, the secondary processed material is returned to the position on the side of the screen 23 in the threshing cylinder part 41. The secondary processed material discharge port 32A of the secondary processed material return part 32 is provided at a position radially outside the arc-shaped screen 23, and the secondary processed material is discharged at this position.

[0182] As described above, the sorting section 42 has the function of sorting grains from the threshed material, but its sorting capacity can be changed. The sorting capacity of the swing sorting mechanism 24 can be represented by the ratio of the amount of the primary processed material recovered by the primary processed material recovery section 26 to the amount of the threshed processed material leaking from the screen 23, that is, the sorting degree (or sorting efficiency).

[0183] The sorting capacity of sorting grains from the threshed material by the sorting section 42 can be changed by adjusting the opening of each of the plurality of chaff screens 38A provided on the first upper screen 38, and by adjusting the air volume of the air separator 25. In addition, in the present embodiment, the dust sending valve 53a is configured to be able to change its installation angle relative to the top plate 53, so the sorting capacity can also be changed by adjusting the angle of the dust sending valve 53a. Moreover, the change in sorting capacity caused by adjusting the opening of the chaff screen 38A or the air volume of the air separator 25 is also related to the amount of threshed material and the return amount of the secondary processed material. The amount of threshed material increases as the amount of grain stalks cut increases, but if the state of the crop is the same, the faster the vehicle speed, the more grain stalks cut. From this point of view, as parameters that affect the threshing performance of the threshing device 1 including the sorting ability, the opening of the chaff screen 38A, the air volume of the air separator 25, the angle of the dust sending valve 53a, the return amount of the secondary processed material, the vehicle speed, etc. can be listed. The threshing processing state of the threshing device 1 required to determine these parameters can be detected by the components of the threshing state management system.

[0184] Figure 5 This is a functional block diagram of the control system of a combine harvester. Figure 5 , the control device 100, the imaging unit 80, the threshing state management unit 7, various sensors, and various operating devices are shown. The threshing state management system for managing the state of the threshing device 1 is constructed by using the imaging unit 80 and the threshing state management unit 7.

[0185] Various motion devices include a travel motion device D1, a harvesting motion device D2, a threshing motion device D3, a discharge motion device D4, etc. The travel motion device D1 includes an engine motion device, a speed change motion device, and a steering motion device. The harvesting motion device D2 includes a motion device that causes the harvesting section 4 and the intermediate conveying device 11 to move. The threshing motion device D3 includes a motion device that causes the threshing cylinder 22, the swing sorting mechanism 24, the chaff screen 38A, the air separator 25, the dust valve 53a, the primary processed material recovery conveying section 29, the secondary processed material return section 32, etc. to move. The discharge motion device D4 includes a motion device that causes the grain discharge device 14 to move.

[0186] Among various sensors, the sensors particularly relevant to the present invention are the driving state sensor S1 and the threshing state sensor S2. The driving state sensor S1 detects the operating states of various driving motion devices D1. The threshing motion device D3 detects the operating states of the threshing cylinder 22, the swing sorting mechanism 24, the chaff screen 38A, the winnowing machine 25, the primary processed material recovery and conveying section 29, the secondary processed material return section 32, etc. In addition, in this embodiment, the driving state sensor S1 includes a GNSS sensor having a satellite positioning function that receives satellite radio waves and calculates position coordinates.

[0187] The control device 100 includes a driving control unit RU, a harvesting control unit CU, a threshing control unit TU, and a discharge control unit UU. The driving control unit RU generates a control signal related to the driving control, and sends it to the driving action device D1 via the input / output signal processing unit IO to control the driving of the driving body 17. In this embodiment, the driving control unit RU also has a vehicle position calculation function for calculating the vehicle position in the field based on the position coordinates output from the GNSS unit, a driving trajectory calculation function for calculating the driving trajectory based on the vehicle position over time, and an automatic driving function for automatic driving based on the vehicle position. The harvesting control unit CU generates a control signal related to the harvesting control, and sends it to the harvesting action device D2 via the input / output signal processing unit IO to control the action of the harvesting operation.

[0188] The threshing control unit TU generates a control signal related to threshing control, and sends it to the threshing action device D3 via the input / output signal processing unit IO to control the action of the threshing operation. The threshing control unit TU has a husk opening control unit T1 for adjusting the opening of the husk screen 38A, a husk wind force control unit T2 for adjusting the wind force of the wind classifier 25, and a valve angle control unit T3 for adjusting the valve angle of the dust sending valve 53a.

[0189] The discharge control unit UU generates a control signal related to the discharge control of the grains from the grain tank 12, and sends it to the discharge operation device D4 via the input / output signal processing unit IO to control the operation of the grain discharge operation.

[0190] The driving state sensor S1 and the threshing state sensor S2 also send signals and data to the control device 100 via the input / output signal processing unit IO.

[0191] The threshing state management unit 7 inputs the captured image of the threshing process material of the threshing device 1 sent from the imaging unit 80, and outputs the threshing process state of the threshing device 1. The imaging unit 80 has at least one camera 81 using a CCD image sensor or a CMOS image sensor and a lighting unit 82 for illuminating the imaging field of the camera 81.

[0192] The camera 81 is arranged at a position where an image showing the state of the threshed material can be taken, for example, a position where an image of the area above the first upper sieve 38 can be taken or a position where a gap area between the first upper sieve 38 and the lower sieve 40 can be taken (see Figure 3 ).

[0193] The threshing state management unit 7 includes a pre-processing unit 71, a state detection neural network 72, and a parameter determination unit 73. The pre-processing unit 71 performs pre-processing such as trimming, color adjustment, and resolution change on the captured image from the shooting unit 80. In addition, the threshing device 1 is closed from the outside, and since dust other than grains is flying, it is difficult to maintain constant shooting conditions even if the inside is illuminated. Therefore, the captured image is standardized by the pre-processing unit 71. The pre-processing unit 71 further converts the pre-processed captured image into data suitable for input to the neural network, and provides it to the state detection neural network 72 as image input data.

[0194] exist Figure 6 In the first embodiment of the threshing state management unit 7 shown, the state detection neural network 72 is formed by a convolutional neural network, preferably by deep learning, and includes a plurality of convolutional layers, a plurality of pooling layers and one or more fully connected layers, an input layer is provided on the input side, and an output layer is provided on the output side. The convolutional layer and the pooling layer are formed to be repeated multiple times.

[0195] The state detection neural network 72 takes the image input data generated by the pre-processing unit 71 based on the color captured image as input, and outputs the threshing process state feature quantity representing the threshing process state. An example of the output threshing process state feature quantity is a label image (threshing process material distribution image). In the label image, for example, the threshing process material in the captured image is divided into grains and non-grains. "1" is assigned to pixels representing grains, "2" is assigned to pixels representing non-grains, and "0" is assigned to pixels representing the background. In addition, non-grains include not only branches and straw chips, but also grains with shapes and grain colors other than those specified. Figure 7 In FIG. 1 , a partially enlarged schematic diagram of a photographed image of the threshed product is shown by shades. Figure 8 is with Figure 7 The label image corresponding to the partially enlarged part of the captured image shown. Figure 7 and Figure 8 This is a schematic diagram for easy understanding and does not correspond to the actual state.

[0196] The construction of the state detection neural network 72 is achieved through supervised learning using a large number of learning samples (learning captured images and their label images) as learning data. The learning samples are composed of actual captured images and label images (estimated threshing process states), and the label images are made based on the captured images based on the estimated threshing process states, and the estimated threshing process states are artificially estimated by experts based on the learning captured images. In addition, in a neural network such as deep learning, the more learning samples there are, the higher the reliability of the output. Therefore, in order to make the number of learning samples larger, not only the learning captured images and their label images that follow the actual captured images are used as learning samples, but also the captured images and label images obtained by rotating and translating these image processes on the learning samples are used as additional learning samples. In addition, in fact, what is input to the state detection neural network 72 as learning data is the learning image input data generated by the pre-processing unit 71 based on the learning captured images.

[0197] Furthermore, as the output of the state detection neural network 72, i.e., the threshing process state, the parameters of the standard distribution or Gaussian distribution representing the distribution of grains or non-grain materials in the threshing process material may be output. Alternatively, the state detection neural network 72 may be constructed in a semantic segmentation manner, and the estimated degrees of grains, non-grain materials, and background may be outputted on a pixel-by-pixel basis, and image data (vector data) in which grains, non-grain materials, and background are distinguished by their contours may be outputted.

[0198] In addition, since most of the threshed processed materials to be identified in the captured image are grains, in order to perform more precise identification, the captured image may be divided into a plurality of regions (small regions) in the pre-processing unit 71, and image input data may be generated according to the regions. Alternatively, the image input data may be divided into a plurality of small blocks in the input layer of the state detection neural network 72.

[0199] The parameter determination unit 73 obtains the distribution state of the threshing processed material based on the label image output from the output layer of the state detection neural network 72 (actually, vector data in which the pixel values ​​in which the identification values ​​of the threshing processed material are substituted as elements). Moreover, when the distribution state of the threshing processed material is different from the distribution state for reference by more than a prescribed amount and it is determined that the threshing performance needs to be improved, the threshing control parameters of the threshing device 1 for improving the threshing performance are determined based on the distribution state. For example, the greater the proportion of non-grain matter in the threshing processed material, the more insufficient the threshing process is considered, and a more refined threshing process is performed by adjusting the dust conveying valve 53a and the like. In addition, when the proportion of branches, straw chips, etc. is large, the opening of the chaff screen 38A is reduced and the wind force of the air separator 25 is increased, so that the branches and straw chips do not fall into the primary processed material recovery unit 26.

[0200] exist Fig. 9In the second embodiment shown, not only the captured image but also the detection signal of the driving state sensor S1 is input to the threshing state management unit 7. The pre-processing unit 71 generates state input data representing the driving state (vehicle speed, engine speed, etc.) according to the detection signal of the driving state sensor S1. The state detection neural network 72 inputs the input image data and the state input data, and outputs the threshing process state feature quantity. The threshing process state feature quantity also includes the relationship between the driving state and the threshing process state, so the parameter determination unit 73 obtains the threshing process material distribution state according to the threshing process state feature quantity, and determines the driving control parameter and the threshing control parameter. In this embodiment, in order to improve the threshing performance, not only the threshing device 1 can be adjusted, but also the vehicle speed and the engine speed can be adjusted.

[0201] exist Fig.10 In the third embodiment shown, each captured image from two cameras 81 having different shooting fields of view is input to the pre-processing unit 71. In this embodiment, the shooting fields of each camera 81 are set to the upper area of ​​the first upper sieve 38 and the gap area between the first upper sieve 38 and the lower sieve 40 (the lower area of ​​the first upper sieve 38). In these two areas, the mixing of grains and non-grain materials is different, so a first state detection neural network 72A for the upper area and a second state detection neural network 72B for the lower area are prepared separately. In the first state detection neural network 72A, the first input image data based on the captured image of the upper area is input, and the first threshing process state feature quantity is output. In the second state detection neural network 72B, the second input image data based on the captured image of the lower area is input, and the second threshing process state feature quantity is output. The parameter determination unit 73 obtains the distribution state of the threshing process material based on the first threshing process state feature quantity and the second threshing process state feature quantity, and determines the threshing control parameter. In addition, as a variation of this embodiment, three or more cameras 81 can also be prepared, and captured images with three or more different shooting fields of view can be used. In this structure, the first input image data, the second input image data, ..., which are the respective image input data corresponding to the captured images from the respective cameras 81, are input to the first state detection neural network 72A, the second state detection neural network 72B, ..., which correspond to the two cameras 81 as the capturing sources. Furthermore, the first threshing process state feature quantity (first threshing process state), the second threshing process state feature quantity (second threshing process state), ..., which are output from the first state detection neural network 72A, the second state detection neural network 72B, ..., are provided to the parameter determination unit 73.

[0202] exist Fig.10In the third embodiment shown, the state detection neural network 72 is prepared according to the images captured by the plurality of cameras 81. Alternatively, a configuration may be adopted in which all input image data generated based on the plurality of captured images having different capturing fields of view are input to the same state detection neural network 72.

[0203] exist Fig.11 In the fourth embodiment shown, the parameter determination unit 73 is also constructed by a neural network. That is, the threshing state management unit 7 of this embodiment is composed of a pre-processing unit 71, a state detection neural network 72, and a parameter determination unit 73 that functions as a control neural network. The output layer of the state detection neural network 72 is directly connected to the input layer of the control neural network (parameter determination unit 73), so the output data of the state detection neural network 72 becomes the input data of the control neural network. Therefore, the output data of the state detection neural network 72 and the input data of the control neural network become a universal feature vector.

[0204] [Other implementation methods]

[0205] In the above embodiment, deep learning is used as a neural network that takes input image data based on one captured image or multiple captured images captured simultaneously as input. Alternatively, a neural network that takes a time series input image data group based on time series captured images as input may be used.

[0206] In the above embodiment, the preprocessing unit 71 and the state detection neural network 72 are independent structures, but the preprocessing unit 71 may be integrated with the state detection neural network 72. Furthermore, the preprocessing unit 71, the state detection neural network 72 and the parameter determination unit 73 may be integrally configured.

[0207] In the above embodiment, the threshing state management system is described by taking the case where the threshing device 1 is mounted on a combine harvester as an example. Alternatively, the threshing state management system of the present invention may be mounted on a working vehicle different from the threshing device 1 and the combine harvester, or the threshing state management system of the present invention may be integrated into a fixed threshing device 1.

[0208] In the above embodiment, a combine harvester is described, but the processing performed by each functional unit in the above embodiment can also be configured as a threshing state management method. In this case, the threshing state management method can be a threshing state management method for managing the state of a threshing device 1 that threshes harvested grain stalks while traveling, wherein the method is configured to include: a photographing step, which uses a photographing unit 80 to photograph the threshed material of the threshing device 1; a threshing process state output step, which uses a state detection neural network to output the threshing process state of the threshing device 1 based on image input data generated from the photographed image from the photographing unit 80; a parameter determination step, which determines the control parameters of the threshing device 1 based on the threshing process state; and a control step, which uses a threshing control unit to control the threshing device 1 based on the control parameters.

[0209] In addition, each functional unit in the above embodiment can also be configured as a threshing state management program. In this case, the threshing state management program can be a threshing state management program that manages the state of the threshing device 1 that threshes the harvested grain stalks while traveling, wherein the program is configured to cause the computer to execute the following functions: a photographing function that photographs the threshed material of the threshing device 1 using the photographing unit 80; a threshing process state output function that outputs the threshing process state of the threshing device 1 based on image input data generated from the photographed image from the photographing unit 80 using a state detection neural network; a parameter determination function that determines the control parameters of the threshing device 1 based on the threshing process state; and a control function that controls the threshing device 1 based on the control parameters using a threshing control unit.

[0210] Moreover, such a threshing state management program may be configured to be recorded in a recording medium.

[0211] 4-2. Second Embodiment

[0212] Hereinafter, a preferred embodiment of the present invention will be described with reference to the accompanying drawings. In this embodiment, the harvester is a combine harvester that threshes harvested grain stalks while traveling, and the harvester management system is a threshing management system provided in the combine harvester.

[0213] Fig.12 It is a side view of a combine harvester. Fig.13 This is a top view of a combine harvester. Fig.14 It is a cross-sectional view of the threshing device 201. In addition, below, the combine harvester of this embodiment is a full-feed combine harvester, but it is a matter of course that it may be a half-feed combine harvester.

[0214] Here, for easy understanding, in this embodiment, unless otherwise specified, the "front" ( Fig.12The direction of the arrow F shown in the figure means the front in the front-rear direction (driving direction) of the machine body, and the rear ( Fig.12 The direction of the arrow B shown in the figure) refers to the rear in the front-rear direction of the machine body (the direction of travel). Fig.12 direction of the arrow U shown) and "down" ( Fig.12 The left and right directions (the direction of the arrow D shown in the figure) are the vertical directions (vertical directions) of the machine body, indicating the height relationship from the ground. In addition, the left-right direction or the lateral direction refers to the cross-sectional direction of the machine body (the width direction of the machine body) that is orthogonal to the front-rear direction of the machine body, that is, the left ( Fig.13 direction of the arrow L shown) and "right" ( Fig.13 The directions of the arrows R shown in the figure respectively refer to the left and right directions of the machine body.

[0215] like Fig.12 and Fig.13 As shown, the combine harvester includes a machine frame 202 and a crawler travel device (an example of a travel device) 203. A harvesting section (an example of a harvesting section) 204 for harvesting standing grain stems is provided in front of a travel machine body 217.

[0216] A threshing device 201 for threshing the harvested grain stalks is provided at the rear of the harvesting section 204, and an intermediate conveying device (an example of a conveying device) 211 for conveying the harvested grain stalks to the threshing device 201 is provided across the harvesting section 204 and the threshing device 201. A grain box (an example of a storage unit) 212 for storing grains after threshing is provided on the side of the threshing device 201, and a straw discharging and breaking device 213 is provided at the rear of the threshing device 201.

[0217] A driving unit 209 covered by a cab 210 is disposed on the right side of the front portion of the traveling machine body 217. An engine 200E is provided below the driving unit 209. The power of the engine 200E is transmitted to the crawler traveling device 203 and the threshing device 201, etc. through a power transmission structure (not shown). In addition, a grain discharge device 214 is provided to discharge the grains in the grain box 212 to the outside.

[0218] The grain discharge device 214 includes a longitudinal conveying section 215 for conveying the grains in the grain box 212 upward and a transverse conveying section 216 for conveying the grains from the longitudinal conveying section 215 to the outside of the machine body. The grain discharge device 214 is configured to be rotatable around the axis of the longitudinal conveying section 215. The lower end of the longitudinal conveying section 215 is connected to the bottom of the grain box 212. The end of the transverse conveying section 216 on the longitudinal conveying section 215 side is connected to the upper end of the longitudinal conveying section 215 and is supported to be able to swing up and down.

[0219] like Fig.14As shown, the threshing device 201 includes a threshing cylinder 241 for threshing the harvested grain stalks and a sorting unit 242. The threshing cylinder 241 is arranged at the upper part of the threshing device 201, and the sorting unit 242 is arranged at the lower part of the threshing cylinder 241. The sorting unit 242 includes a swing sorting mechanism 224, a primary processed material recovery unit 226, a secondary processed material recovery unit 227, and a secondary processed material return unit 232.

[0220] The threshing cylinder part 241 has a threshing cylinder 222 accommodated in the threshing chamber 221 and a screen 223 installed at the bottom of the threshing cylinder 222. The threshing chamber 221 is formed as a space surrounded by a front wall 251 on the front side, a rear wall 252 on the rear side, left and right side walls, and a top plate 253 covering the upper part. A supply port 254a to which the cut grain stalks are supplied is formed below the front wall 251 in the threshing chamber 221, and a guide bottom plate 259 is arranged below the supply port 254a. In addition, a dust discharge port 254b is formed below the rear wall 252 in the threshing chamber 221.

[0221] The threshing cylinder 222 has a cylinder body 260 and a rotation support shaft 255 that are integrally rotated by the driving rotation force from the rotation drive mechanism 256. The cylinder body 260 is integrally formed with a pull-in portion 257 at the front end and a threshing processing portion 258 at the rear of the pull-in portion 257.

[0222] A plurality of plate-shaped dust sending valves 253a are provided at predetermined intervals in the front-rear direction on the inner surface (lower surface) of the top plate 253. In the threshing chamber 221, a rearward moving force acts on the harvested grain stalks rotating together with the threshing drum 222. The plurality of dust sending valves 253a are configured to be able to adjust the rearward moving force.

[0223] The threshed material processed by the threshing cylinder 241 includes grains, branches, straw chips, etc. In addition, the so-called primary processed material is a threshed material mainly containing grains, and the so-called secondary processed material is a threshed material containing grains that are not fully granulated and branches, straw chips, etc.

[0224] In the threshing cylinder part 241, the harvested material from the intermediate conveyance device 211 is supplied to the threshing chamber 221 through the supply port 254a. The supplied cut grain stems are pulled in by the spiral blades of the pulling-in part 257 along the guide bottom plate 259, and are threshed.

[0225] The grains and short straw chips obtained by threshing fall through the screen 223 and fall into the sorting section 242. On the other hand, the processed materials (grain straws, long straw chips, etc.) that cannot fall through the screen 223 are discharged to the outside of the threshing chamber 221 from the dust discharge port 254b.

[0226] The swing sorting mechanism 224 swings the frame-shaped screen box 233 in the front-rear direction by using an eccentric cam mechanism using an eccentric shaft or the like. A wind separator 225 that generates sorting air from front to back is provided in the sorting section 242. In an environment where the sorting air is supplied from the wind separator 225, the screen box 233 swings, thereby sorting grains (primary processed materials) from the threshing processed materials. In addition, a primary processed material recovery section 226 and a secondary processed material recovery section 227 are arranged below the screen box 233.

[0227] The primary processed material collected by the primary processed material collecting section 226 is conveyed (fly-fed) upward toward the grain tank 212 by the primary processed material collecting and conveying section 229. The primary processed material conveyed by the primary processed material collecting and conveying section 229 is stored by the auger 230 (see Fig.12 ) is transported to the right and supplied to the grain box 212 (refer to Fig.12 ).

[0228] The secondary processed material recovery unit 227 is configured as a secondary processed material auger that conveys the recovered secondary processed material in the horizontal direction. The secondary processed material recovered by the secondary processed material recovery unit 227 is conveyed obliquely forward and upward by the secondary processed material return unit 232 and returned to the top of the screen box 233.

[0229] The screen box 233 includes a first grain shaking plate 234 , a plurality of first screen lines 235 , a second screen line 236 , a first upper screen 238 , a second upper screen 239 , a lower screen 240 , an upper grain shaking plate 261 , and a lower grain shaking plate 265 .

[0230] A first upper screen 238 having a plurality of chaff screens 238A is disposed at a position further back than the upper grain shaking plate 261, and a second upper screen 239 is disposed at a position further back than the first upper screen 238. In addition, the plurality of chaff screens 238A are arranged along the conveying direction (rearward direction) of the conveyed material, and the plurality of chaff screens 238A are disposed in an inclined posture that is inclined upward as they approach the rear end side. The lower grain shaking plate 265 is disposed below the front end portion of the first upper screen 238, and a lower screen 240 composed of a mesh body is disposed at a position connected to the rear of the lower screen 240. The second upper screen 239 is disposed behind the lower screen 240 and below the rear end portion of the first upper screen 238. The rear end portion (at the rear of the screen box 233) of the screen box 233 is provided. Fig.14 The right end in the middle) and the rear end of the screen 223 form a discharge portion 228.

[0231] The first upper screen 238 allows the grains contained in the threshed material to fall while conveying the threshed material to the rear side through air separation using the separation wind and specific gravity separation accompanied by swinging. The stalks such as straw scraps are handed over to the second upper screen 239, sent from the rear end of the second upper screen 239 to the rear of the screen box 233, and discharged from the discharge section 228 to the discharge straw crushing device 213. The stalks discharged from the discharge section 228 are crushed by the discharge straw crushing device 213 and discharged to the outside of the threshing device 201. In addition, the grains that fall directly to the second upper screen 239 through the screen 223 are sorted by the second upper screen 239 into grains and stalks such as straw scraps.

[0232] A large amount of processed material including grains is caught by the upper surface of the lower screen 240. Straw scraps and the like are sent backward on the upper surface of the lower screen 240, so most of the threshed processed material that leaks from the lower screen 240 is grain, flows down to the primary processed material recovery unit 226 and is recovered, and is stored in the grain box 212 by the primary processed material recovery conveyor unit 229. Straw scraps in the threshed processed material that does not leak from the lower screen 240 are sent backward by the sorting wind.

[0233] In contrast, the threshed material leaking from the rearmost part of the lower screen 240 or the threshed material falling from the second upper screen 239 flows down to the secondary processed material recovery unit 227 and is recovered, and is returned to the upstream side of the swing sorting mechanism 224 by the secondary processed material return unit 232. In addition, the garbage such as straw scraps generated by the sorting process is sent to the rear from the rear end of the screen box 233 and discharged from the discharge unit 228 to the discharge straw crushing device 213.

[0234] The secondary processed material is returned to the side of the screen 223 in the threshing cylinder 241 and cannot pass through the screen 223. The secondary processed material discharge port 232A of the secondary processed material return unit 232 for returning the secondary processed material is provided at a position radially outside the arc-shaped screen 223, and the secondary processed material is discharged at this position.

[0235] The sorting capacity of sorting grains from the threshed material by the sorting section 242 can be changed by adjusting the opening of each of the plurality of chaff screens 238A provided on the first upper screen 238 and adjusting the air volume of the air separator 225. In addition, in the present embodiment, the dust sending valve 253a is configured to be able to change its installation angle relative to the top plate 253, so the sorting capacity can also be changed by adjusting the angle of the dust sending valve 253a. Moreover, the change in sorting capacity caused by adjusting the opening of the chaff screen 238A or the air volume of the air separator 225 is also related to the amount of threshed material and the return amount of the secondary processed material. The more the amount of grain stalks cut, the more the amount of threshed material, but if the state of the crop is the same, the faster the vehicle speed, the more the amount of grain stalks cut. From this point of view, the parameters that affect the threshing performance including the sorting ability in the threshing device 201 include the opening of the chaff screen 238A, the air volume of the air separator 225, the angle of the dust valve 253a, the return amount of the secondary processed material, the vehicle speed, etc.

[0236] exist Fig.15 As an example of the yield measuring unit, a yield measuring device 200M1 for measuring the yield (yield) obtained by transporting the threshing device 201 through the primary processed material recovery conveying unit 229 (see Fig.12 ) and the amount of grains put into the grain box 212 by the storage auger 230. In addition, a taste value measuring device 200M2 for measuring the quality (moisture content, protein content, etc.) of the grains put into the grain box 212 is also shown.

[0237] The yield measuring device 200M1 is assembled to the grain discharge device 230a provided at the terminal end of the storage auger 230. The grain discharge device 230a utilizes a rotating plate to diffuse and discharge the transported grains into the interior of the grain box 212. The yield measuring device 200M1 calculates the flow rate of the grains based on the signal of the force sensor, which is deformed by the collision force of the diffused and discharged grains each time the rotating plate rotates one circle. Moreover, the yield measuring device 200M1 calculates the unit yield, i.e., the yield per unit time (a type of unit harvest yield), based on the rotation cycle of the rotating plate of the grains put into the grain box 212, i.e., the flow rate of the grains within a prescribed cycle.

[0238] The taste value measuring device 200M2 temporarily stores a portion of the grains diffused and discharged by the grain discharge device 230a, irradiates the stored grains with light, and performs spectroscopic analysis on the light returned through the grains to measure the taste value (moisture content, protein) of the grains. This temporary storage of grains and measurement of taste values ​​are performed periodically.

[0239] In this embodiment, the crop loss is the loss of grains, and in particular, the threshing loss (threshing loss amount) used as an indicator to represent the threshing performance of the threshing device 201 is adopted. The threshing loss amount can be divided into the threshing cylinder loss amount and the sorting loss amount. In this embodiment, the threshing cylinder loss amount is the amount of grains discharged from the rear end of the threshing chamber 221 together with the straw scraps (discharged straw). The threshing cylinder loss amount includes the amount of grains discharged together with the straw without threshing, and the amount of grains discharged from the rear end of the threshing chamber 221 together with the straw scraps although threshing is performed. Moreover, the sorting loss amount is the amount of grains discharged from the rear end of the sorting section 242 together with the straw scraps although threshing is performed and falls on the sorting section 242. Such threshing loss amount can be measured using a collision detection sensor such as a known pressure sensor, but in this embodiment, as described in detail below, it is calculated using a neural network that takes a captured image as input. Then, the threshing loss amount per unit harvest, that is, the threshing loss amount per unit yield is calculated using the calculated threshing loss amount and the yield measured by the yield measuring device 200M1.

[0240] For example, the loss rate (loss rate per unit of travel) is calculated based on the ratio of the yield (unit yield) measured by the combine harvester traveling a predetermined time or a predetermined distance during the harvesting operation to the threshing loss calculated during the travel. The loss rate in a predetermined area of ​​the field and the loss rate of the field as a whole are calculated by assigning the loss rate to the travel track. In this embodiment, in the loss area where the loss occurs, a photographing unit 280 that photographs the loss area is used as a detection unit that detects the loss.

[0241] The photographic image for calculating the threshing loss amount is an image taken by the photographing unit 280 with the loss area where the threshing loss occurs as the photographing field of view. In this embodiment, the loss area suitable for identifying the threshing cylinder loss is the rear end of the threshing cylinder 222 or the rear of the threshing cylinder 222, and the loss area suitable for identifying the sorting loss is the rear end of the screen box 233 and above the second upper screen 239. Of course, other areas capable of identifying threshing loss can be used as loss areas. The amount of grains mixed in the discharged straw discharged from the vehicle body is also a kind of threshing loss, so the cutting track behind the vehicle body can also be used as a loss area.

[0242] Fig.16 This is a functional block diagram of the control system of a combine harvester. Fig.16 , the control device 300, the imaging unit 280, the threshing loss management unit 207, the yield measuring device 200M1, the taste value measuring device 200M2, various sensors, and various operating devices are shown. Here, the threshing loss management system is constructed using the imaging unit 280, the threshing loss management unit 207, and the yield measuring device 200M1.

[0243] Various motion devices include a traveling motion device 200D1, a harvesting motion device 200D2, a threshing motion device 200D3, a discharge motion device 200D4, etc. The traveling motion device 200D1 includes an engine motion device, a speed change motion device, and a steering motion device. The harvesting motion device 200D2 includes a motion device that causes the harvesting section 204 and the intermediate conveying device 211 to move. The threshing motion device 200D3 includes a motion device that causes the threshing cylinder 222, the swing sorting mechanism 224, the chaff screen 238A, the air separator 225, the dust delivery valve 253a, the primary processed material recovery and conveying section 229, the secondary processed material return section 232, etc. to move. The discharge motion device 200D4 includes a motion device that causes the grain discharge device 214 to move.

[0244] Among various sensors, sensors particularly relevant to the present invention are the driving state sensor 200S1 and the threshing state sensor 200S2. The driving state sensor 200S1 detects the operating states of various driving motion devices 200D1. The threshing state sensor 200S2 detects the operating states of the threshing cylinder 222, the swing sorting mechanism 224, the chaff screen 238A, the winnowing machine 225, the primary processed material recovery and conveying section 229, the secondary processed material return section 232, etc. In addition, in this embodiment, the driving state sensor 200S1 includes a GNSS sensor having a satellite positioning function that receives satellite radio waves and calculates position coordinates.

[0245] The control device 300 includes a travel control unit 200RU, a harvesting control unit 200CU, a threshing control unit 200TU, and a discharge control unit 200UU. The travel control unit 200RU generates a control signal related to the travel control, and sends it to the travel action device 200D1 via the input / output signal processing unit 200IO to control the travel of the travel machine 217. In this embodiment, the travel control unit 200RU also has a vehicle position calculation function for calculating the vehicle position in the field based on the position coordinates output from the GNSS unit, a travel trajectory calculation function for calculating the travel trajectory based on the vehicle position over time, and an automatic travel function for automatic travel based on the vehicle position. The harvesting control unit CU generates a control signal related to the harvesting control, and sends it to the harvesting action device 200D2 via the input / output signal processing unit 200IO to control the action of the harvesting operation.

[0246] The threshing control unit 200TU generates a control signal related to threshing control, and sends it to the threshing action device 200D3 via the input / output signal processing unit 200IO to control the action of the threshing operation. The threshing control unit 200TU has a husk opening control unit 200T1 for adjusting the opening of the husk screen 238A, a husk wind force control unit 200T2 for adjusting the wind force of the husk machine 225, and a valve angle control unit 200T3 for adjusting the valve angle of the dust sending valve 253a.

[0247] The discharge control unit 200UU generates a control signal related to the discharge control of the grains from the grain tank 212, and sends it to the discharge action device 200D4 via the input / output signal processing unit 200IO to control the action of the grain discharge operation.

[0248] The above-mentioned running state sensor 200S1 and threshing state sensor 200S2 also send signals and data to the control device 300 via the input / output signal processing unit 200IO.

[0249] The threshing loss management unit 207 inputs the captured image of the loss area sent from the shooting unit 280, and outputs the loss amount per unit of collection, that is, the loss rate. In this embodiment, the shooting unit 280 has a first camera 281 and a second camera 282. The lighting unit 284 is attached to each camera. The first camera 281 shoots the terminal end area of ​​the threshing cylinder 222 as the loss area suitable for the threshing cylinder loss (including the threshing cylinder terminal end area behind the threshing cylinder 222). The second camera 282 shoots the rear end area of ​​the screen box 233 as the loss area suitable for the sorting loss (including the screen box rear end area above the second upper screen 239). In addition, it can also be configured as follows: prepare a plurality of first cameras 281, shoot the loss area suitable for the threshing cylinder loss at a plurality of shooting angles, and send out a plurality of different shooting images of the field of view. Similarly, it can also be configured as follows: prepare a plurality of second cameras 282, shoot the loss area suitable for the sorting loss at a plurality of shooting angles, and send out a plurality of different shooting images of the field of view. There is no limit on the number of cameras.

[0250] The threshing loss management unit 207 includes a pre-processing unit 271, a loss amount neural network 272 as a loss amount calculation unit, and a loss rate calculation unit 273. The pre-processing unit 271 performs pre-processing such as trimming, color adjustment, and resolution change on the captured image from the shooting unit 280. In addition, the threshing device 201 is closed from the outside, and since dust other than grains is flying, it is difficult to maintain constant shooting conditions even if the inside is illuminated. Therefore, the pre-processing unit 271 is used to standardize the captured image. The pre-processing unit 271 further converts the pre-processed captured image into data suitable for input to the neural network, and provides it to the loss amount neural network 272 as image input data.

[0251] like Fig.17 As shown, the loss neural network 272 is formed by a convolutional neural network, preferably by deep learning, and includes multiple convolutional layers, multiple pooling layers, and one or more fully connected layers, with an input layer on the input side and an output layer on the output side. The convolutional layers and the pooling layers are repeated multiple times.

[0252] exist Fig.17 In the example of , for simplicity of explanation, as captured images, a color captured image (first captured image) of the first camera 281 and a color captured image (second captured image) of the second camera 282 are used. The pre-processing unit 271 generates first image input data based on the first captured image, and generates second image input data based on the second captured image. The loss amount neural network 272 takes the first image input data and the second image data as inputs, and outputs a loss amount.

[0253] The construction of the loss neural network 272 is achieved through supervised learning using a large number of learning samples (learning captured images and their losses) as learning data. The learning samples are composed of actual captured images and estimated losses actually estimated by experts based on the captured images. In addition, in a neural network such as deep learning, the more learning samples there are, the higher the reliability of the output. Therefore, in order to increase the number of learning samples, not only are learning captured images that use actual captured images used as learning samples, but images obtained by rotating and translating the learning samples are also used as additional learning samples with the same estimated losses. In addition, in fact, what is input to the loss neural network 272 as learning data is the learning image input data generated by the pre-processing unit 71 based on the learning captured images.

[0254] Instead of inputting image input data and directly outputting the loss amount, a method of outputting a label image that distinguishes the threshed material in the captured image into grains and non-grains and calculating the loss amount based on the label image is also possible. In this method, the fully connected layer is divided, the fully connected layer of the previous level outputs the label image, and the fully connected layer of the next level outputs the loss amount based on the label image. In this case, as learning data, the actual captured image and the loss amount calculated based on the label image can be used, and the label image is produced based on the distinction between grains and non-grains made by an expert based on the captured image. Fig.18 In FIG. 1 , a partially enlarged schematic diagram of a photographed image of the threshed product is shown by shades. Fig.19 is with Fig.18 The label image corresponding to the local enlarged part of the captured image shown in FIG. Fig.19 In the label image shown, grains are represented by "1", abnormal grains are represented by "2", and the background is represented by "0". Grains show the unique shape and color of grains, and non-grain materials include not only branches, straw scraps, etc., but also defective grains showing shapes and colors outside the regulations. Fig.18 and Fig.19 This is a schematic diagram for easy understanding and does not correspond to the actual state.

[0255] Furthermore, the following structure may be adopted: instead of the loss amount which is the output of the loss amount neural network 272, the parameters of the standard distribution or Gaussian distribution which represents the distribution of grains or non-grain materials in the threshing process are calculated as the threshing process state, and the loss amount is calculated based on the distribution. Alternatively, if the loss amount neural network 272 is configured as a semantic segmentation network, a label image showing the estimated degree of grains, non-grain materials, and background is generated for each pixel, and therefore the loss amount may be calculated based on the label image and output.

[0256] In addition, since most of the threshed processed materials to be identified in the captured image are grains, in order to perform more precise identification, the captured image may be divided into a plurality of regions (small regions) in the pre-processing unit 271, and image input data may be generated according to the regions. Alternatively, the image input data may be divided into a plurality of small blocks in the input layer of the loss amount neural network 272.

[0257] The loss rate calculation unit 273 is provided with not only the loss amount from the loss amount neural network 272 but also the yield from the yield measuring device 200M1. Thus, the loss rate calculation unit 273 calculates the loss amount per unit yield, i.e., the loss rate. The loss rate also includes the loss rate calculated based on the yield per unit time, the loss rate calculated based on the yield per unit travel, and the loss rate calculated based on the yield of the entire field. Moreover, the loss rate calculation unit 273 is also provided with driving track information from the driving control unit 200RU, so it can also calculate the loss rate calculated based on the yield in the specified area of ​​the field. Such a loss rate can be linked to the driving track calculated by the driving control unit 200RU. Thus, the yield, taste value, and loss amount are recorded according to the micro-divisions of the field.

[0258] The loss rate is an important factor indicating the threshing performance. Therefore, based on the loss rate calculated during the operation, the parameter determination unit 274 determines the threshing control parameters of the threshing device 201 for improving the threshing performance during the operation, and provides them to the threshing control unit 200TU. For example, the threshing control unit 200TU adjusts the opening of the chaff screen 238A, the wind force of the air separator 225, the vehicle speed, and the dust delivery valve 253a during the operation, so that the received loss rate is close to the appropriate loss rate. From this point of view, the loss rate is calculated continuously or at a specified repetition time during the operation of the combine harvester. In addition, the loss amount and loss rate obtained during the operation of a field are recorded together with the driving information and operation information of the combine harvester.

[0259] exist Fig.17 In the structure of the loss neural network 272 shown in FIG. 1 , the first input image data and the second input image data generated based on the first captured image and the second captured image are input to an input layer of a common loss neural network 272. Fig. 20 As shown, a first loss neural network 272A and a second loss neural network 272B may be provided as the loss neural network 272 corresponding to the shooting sources of the first shot image and the second shot image, namely the first camera 281 and the second camera 282. In this structure, the first input image data based on the first shot image is input to the first loss neural network 272A, and the second input image data based on the second shot image is input to the second loss neural network 272B. As a result, the first loss neural network 272A calculates the loss of the threshing cylinder, and the second loss neural network 272B calculates the sorting loss. The loss rate calculation unit 273 calculates a comprehensive loss rate based on the threshing cylinder loss and the sorting loss. Here, the first shot image and the second shot image may also include shots at different shooting angles and shots of different shooting fields of view.

[0260] Moreover, in Fig.21 In the structure shown, except Fig. 20 In addition to the first camera 281 and the second camera 282 shown, a third camera 283 is also provided. The third camera 283 is arranged in the discharge area where non-grain materials such as straw are discharged from the threshing device 201, for example, at the entrance of the straw chopping device 213. Alternatively, the third camera 283 may be arranged in a position to shoot the cutting track behind the vehicle body. Fig.21 In the structure shown, a third loss neural network 272C is provided. The third loss neural network 272C inputs the third input image data and outputs the discharge loss. The third input image data is generated based on the image captured by the third camera 283 that captures the discharge area of ​​the threshing device 201 or the cutting track behind the vehicle body, and the discharge loss represents the amount of grain mixed in the discharged straw discharged from the vehicle body to the ground of the field. The loss rate calculation unit 273 calculates the loss rate based on the threshing cylinder loss, the sorting loss, the discharge loss and the yield. Of course, the loss rate calculation unit 273 can also additionally calculate the discharge loss rate based on the discharge loss and the yield. Here, the first captured image, the second captured image, and the third captured image may also include images of different shooting angles and images of different shooting fields of view. In addition, a fourth camera, a fifth camera, etc. may be prepared, and the threshing loss management unit 207 may be provided with a corresponding number of loss neural network groups.

[0261] exist Fig. 20 , Fig.21 In the structure shown, the loss rate calculation unit 273 calculates a plurality of types of loss rates. In order to determine the threshing control parameters of the threshing device 201 based on such a plurality of types of loss rates, the parameter determination unit 274 may be made neural network. The neural network loss rate calculation unit 273 takes the loss rates in various regions as input data and outputs the threshing control parameters.

[0262] [Other implementation methods]

[0263] In the above embodiment, the loss rate calculated by the loss rate calculation unit 273 is used to adjust the control parameters of various control devices constituting the combine harvester. Alternatively, the following structure may be adopted: the loss rate calculated by the loss rate calculation unit 273 at all times during the operation is displayed on the instrument panel or the display, and the driver adjusts the control parameters of various control devices appropriately while observing the displayed loss rate. In this case, it is more preferred that the loss rate is displayed together with an index indicating the driving state such as the engine speed and the vehicle speed and an index indicating the working state such as the cutting height.

[0264] In the above embodiment, as the objects of the control parameters determined based on the loss rate, the adjustment amount of various devices of the threshing device 201 (the opening of the chaff screen 238A, the air volume of the air separator 225, the angle of the dust valve 253a, the return amount of the secondary processed material), the travel control amount (vehicle speed), etc. are used. In addition, the parameter determination unit 274 can also determine the control parameters of at least one of the crawler travel device 203, the harvesting unit 204, and various conveying devices.

[0265] In the above embodiment, the detection unit for detecting the loss is the shooting unit 280 composed of a camera, and the image captured by the camera is used to calculate the loss amount. The detection unit is not limited to the shooting unit 280, and various sensors provided in the components of the combine harvester such as the harvesting unit 204, the intermediate conveying device 211, the threshing device 201, and the primary processed material recovery conveying unit 229 may function as the detection unit, and the detection signals thereof as the detection results of the detection unit may be used to calculate the loss amount. Moreover, the detection unit may be a combination of the shooting unit 280 and various sensors.

[0266] In the above-mentioned embodiment, the loss amount calculation unit calculates the threshing drum loss amount and the sorting loss amount. However, for example, when the grain stalks are transported in the cutting section 204 and when the grain stalks are transported by the intermediate conveying device 211, losses will also occur. Therefore, the loss amount calculation unit can also calculate the losses in various conveying devices such as the cutting section 204 or the intermediate conveying device 211, the primary processed material recovery conveying section 229, etc. In this case, the threshing loss management unit 207 is configured as a harvester loss management unit, and the loss rate calculation unit 273 is also configured to calculate the loss rate corresponding to each loss amount. For example, the following structure can also be adopted: the cut grain stalks and grains that disappear during the cutting and conveying process of the cut grain stalks sent from the cutting section 204 to the threshing device 201 by the intermediate conveying device 211 are regarded as initial losses, and the amount of the initial loss and its loss rate are calculated.

[0267] In the above embodiment, the loss amount calculation unit is constituted by a neural network, but instead of the neural network, an image recognition unit may be used which recognizes grains and non-grain objects in a captured image and calculates the loss amount based on the recognition information.

[0268] In the above embodiment, deep learning is used as a neural network that takes input image data based on one captured image or multiple captured images captured simultaneously as input. Alternatively, a neural network that takes time series input image data based on time series captured images as input may be used.

[0269] In the above embodiment, the preprocessing unit 271 and the loss neural network 272 are independent structures, but the preprocessing unit 271 can be integrated with the loss neural network 272. In addition, the preprocessing unit 271, the loss neural network 272 and the loss rate calculation unit 273 can also be integrally configured.

[0270] In the above embodiment, the threshing state management system is described by taking the case where the threshing device 201 is mounted on a combine harvester as an example. Alternatively, the threshing management system of the present invention may be mounted on a working vehicle different from the threshing device 201 and the combine harvester, or the threshing management system of the present invention may be integrated into a fixed threshing device 201.

[0271] In the above-mentioned embodiment, a combine harvester is used as the harvester, but the present invention can also be applied to other harvesters, for example, a harvester for harvesting other crops such as corn, potatoes, carrots, etc.

[0272] Each functional unit in the above embodiment may also be configured as a harvester management program. In this case, the harvester management program may be configured to enable a computer to implement the following functions: a measurement function for measuring the harvest amount of the harvested material while performing a harvesting operation using the harvester, which includes a harvesting unit for harvesting crops in a field and a storage unit for storing the harvested material harvested by the harvesting unit; a loss amount calculation function for calculating the loss amount while performing the harvesting operation using the harvester, the loss amount indicating the amount of loss generated during the transportation of the harvested material from the harvesting unit to the storage unit; and a loss rate calculation function for calculating the loss rate based on the harvest amount and the loss amount while performing the harvesting operation using the harvester, the loss rate being the loss amount per unit of harvested material.

[0273] In addition, such a harvester management program may be recorded on a recording medium.

[0274] 4-3. Third Embodiment

[0275] The work vehicle of the present invention is configured to perform ground work on a preset work object. The so-called preset work object is an object on which the work vehicle performs work using the functional parts, devices, etc. possessed by the work vehicle. Specifically, if the work vehicle is a combine harvester, the harvesting object is equivalent to it, if the work vehicle is a rice transplanter, the planting object is equivalent to it, and in the case of a tractor performing tillage and mowing, the field, etc. are equivalent to it. In addition, if the work vehicle is a construction machine, soil, rock, wood, etc. are equivalent to it. The so-called ground work is work performed on a field or a work site. In this embodiment, a combine harvester 420 is cited as an example of a work vehicle for explanation.

[0276] The combine harvester of the present invention is configured to be able to inspect the quality of grains during the grain harvesting process. Hereinafter, the combine harvester 420 of this embodiment will be described.

[0277] Fig. 22 is a side view of the combine harvester 420, Fig.23 is a top view of the combine harvester 420. In addition, Fig.24 It is a cross-sectional view of the threshing device 401 equipped in the combine harvester 420. In addition, below, the combine harvester 420 is described by taking a so-called full-feed combine harvester as an example. Of course, the combine harvester 420 may also be a half-feed combine harvester.

[0278] Here, for easy understanding, in this embodiment, unless otherwise specified, the "front" ( Fig. 22 The direction of the arrow F shown in the figure means the front in the front-rear direction (driving direction) of the machine body, and the rear ( Fig. 22 The direction of the arrow B shown in the figure) refers to the rear in the front-rear direction of the machine body (the direction of travel). Fig. 22 direction of the arrow U shown) and "down" ( Fig. 22 The left and right directions (the direction of the arrow D shown in the figure) are the vertical directions (vertical directions) of the machine body, indicating the height relationship from the ground. In addition, the left-right direction or the lateral direction refers to the cross-sectional direction of the machine body (the width direction of the machine body) that is orthogonal to the front-rear direction of the machine body, that is, the left ( Fig.23 direction of the arrow L shown) and "right" ( Fig.23 The directions of the arrows R shown in the figure respectively refer to the left and right directions of the machine body.

[0279] like Fig. 22 and Fig.23 As shown, the combine harvester 420 includes a machine frame 402 and a crawler travel device 403. A harvesting section 404 for harvesting standing grain stalks is provided in front of the travel machine body 417. The harvesting section 404 includes a reel 405 for feeding standing grain stalks, a cutter 406 for cutting standing grain stalks, and an auger 407 for feeding harvested grain stalks.

[0280] A driving unit 408 is provided on the right side of the front part of the traveling machine body 417. The driving unit 408 is provided with a cab 410 for the driver to ride. An engine room 400ER is provided below the cab 410. In the engine room 400ER, in addition to the engine 400E, an exhaust gas purification device, a cooling fan, a radiator, etc. are also accommodated. The power of the engine 400E is transmitted to the crawler traveling device 403, the threshing unit 441 described later, the sorting unit 442, etc. through a power transmission structure (not shown).

[0281] A threshing device 401 for threshing the cut grain stalks is provided at the rear of the harvesting section 404. An intermediate conveying device 411 for conveying the cut grain stalks to the threshing device 401 is provided across the harvesting section 404 and the threshing device 401. A grain box 412 for storing grains after threshing is provided on the side of the threshing device 401. The grain box 412 is configured to be able to swing open and close between an operating position and a maintenance position around an axis extending in the vertical direction. A discharge straw breaking device 413 equipped with a rotating knife 413a is provided at the rear of the threshing device 401.

[0282] The combine harvester 420 is provided with a grain discharge device 414 for discharging grains in the grain box 412 to the outside. The grain discharge device 414 includes a longitudinal conveying section 415 for conveying grains in the grain box 412 upward and a transverse conveying section 416 for conveying grains from the longitudinal conveying section 415 to the outside of the machine body. The grain discharge device 414 is configured to be rotatable around the axis of the longitudinal conveying section 415. The lower end of the longitudinal conveying section 415 is connected to the bottom of the grain box 412. The end of the transverse conveying section 416 on the longitudinal conveying section 415 side is connected to the upper end of the longitudinal conveying section 415 and is supported so as to be able to swing up and down.

[0283] In the present embodiment, the threshing device 401 is provided on the traveling body 417. As described above, the threshing device 401 includes the threshing unit 441 and the sorting unit 442. The threshing unit 441 thres the harvested grain stalks harvested by the harvesting section 404. The grains obtained by the threshing process by the threshing unit 441 are discharged as threshed processed materials. The sorting unit 442 sorts the threshed processed materials discharged from the threshing unit 441 into sorted processed materials. Therefore, the threshing unit 441 and the sorting unit 442 are provided on the traveling body 417. The threshing unit 441 is arranged on the upper part of the threshing device 401, and the screen 423 is provided on the lower part of the threshing unit 441. The sorting unit 442 is arranged below the threshing unit 441, and is configured to sort out grains from the threshing processed materials leaking from the screen 423. The sorting unit 442 includes a swing sorting device 424 , a primary processed material recovery unit 426 , a secondary processed material recovery unit 427 , and a secondary processed material return unit 432 .

[0284] The threshing unit 441 accommodates the threshing cylinder 422 in the threshing chamber 421, and has a screen 423 at the bottom of the threshing cylinder 422. The threshing chamber 421 is formed as a space surrounded by a front wall 451 on the front side, a rear wall 452 on the rear side, left and right side walls, and a top plate 453 covering the upper part. A supply port 454a to which the harvest is supplied is formed at the lower position of the front wall 451 in the threshing chamber 421, and a guide bottom plate 459 is arranged at the lower side of the supply port 454a. In addition, a dust discharge port 454b is formed at the lower side of the rear wall 452 in the threshing chamber 421.

[0285] The threshing cylinder 422 has a cylinder body 460 and a rotating support shaft 455. Fig.24 As shown, the barrel 460 is formed integrally by the dial-in portion 457 at the front end and the threshing processing portion 458 at the rear position of the dial-in portion 457. The dial-in portion 457 is provided with a double spiral spiral blade 457b at the outer periphery of the base portion 457a of the front end thinner shape whose diameter becomes smaller as it approaches the front end side of the threshing barrel 422. The threshing processing portion 458 has a plurality of rod-shaped threshing tooth support parts 458a and a plurality of threshing teeth 458b. The plurality of rod-shaped threshing tooth support parts 458a are respectively arranged at predetermined intervals apart from each other along the circumference of the cylindrical barrel 460. The plurality of threshing teeth 458b are respectively protruded from the outer peripheries of the plurality of threshing tooth support parts 458a, and are installed at predetermined intervals apart from each other along the rotation axis 400X of the front-back posture.

[0286] The cylinder 460 rotates integrally with the rotating support shaft 455 which has the same axis as the rotating axis 400X and penetrates the front wall 451 and the rear wall 452 in the front-back direction. That is, the front end of the rotating support shaft 455 is rotatably supported by the front wall 451 via a bearing, and similarly, the rear end of the rotating support shaft 455 is rotatably supported by the rear wall 452 via a bearing. In the threshing unit 441, the driving rotational force is transmitted from the rotation driving mechanism 456 to the front end of the rotating support shaft 455.

[0287] On the inner surface (lower surface) of the top plate 453, a plurality of plate-shaped dust delivery valves 453a are provided at predetermined intervals along the front-back direction. The plurality of dust delivery valves 453a are provided in the threshing chamber 421 in a tilted posture relative to the rotation axis 400X when viewed from above, so as to act on the processed material rotating with the threshing cylinder 422 to move it to the rear side. In the present embodiment, the dust delivery valve 453a is configured to be able to change its installation angle relative to the top plate 453. By changing this angle, the feed amount of the processed material in the cylinder 460 can be changed.

[0288] The screen 423 has a structure in which a gap through which the processed material can fall is formed by combining a plurality of longitudinal frames and transverse frames oriented in a front-to-back posture. The plurality of longitudinal frames are in an arc shape when observed along the rotation axis 400X so as to surround the threshing barrel 422 from the bottom in an area spanning both side portions, and are arranged at prescribed intervals in the front-to-back direction, and the transverse frames are supported by each longitudinal frame.

[0289] In the combine harvester 420 of the present embodiment, the harvested straw supplied to the threshing chamber 421 is called a harvested product, and the harvested product obtained by threshing in the threshing chamber 421 is called a processed product (equivalent to "threshed processed product"). The processed product includes grains and chopped straws, etc. In addition, the so-called primary processed product is a processed product mainly including grains, and the so-called secondary processed product is a processed product including grains that are not fully granulated and chopped straws, etc.

[0290] In the threshing unit 441, the harvested material from the intermediate conveying device 411 is supplied to the threshing chamber 421 through the supply port 454a. The supplied harvested material is pushed in toward the rear of the threshing cylinder 422 along the guide bottom plate 459 by the spiral blade 457b of the pushing-in portion 457, and is supplied to the threshing processing portion 458. In the threshing processing portion 458, the harvested material is threshed by the threshing teeth 458b and the screen 423 as the threshing cylinder 422 rotates, thereby threshing.

[0291] When threshing is performed in this way, the processed material is rotated together with the threshing drum 422, and the threshing process is performed while the processed material is contacted with the dust delivery valve 453a and is transported to the rear part of the threshing chamber 421. The grains and short straw stalks obtained by the threshing process fall on the screen 423 and fall into the sorting unit 442. In contrast, the processed material (grain stalks, long straw stalks, etc.) that cannot fall on the screen 423 is discharged from the dust discharge port 454b to the outside of the threshing chamber 421.

[0292] like Fig.24 As shown, the sorting unit 442 is configured to include a swing sorting device 424, which sorts grains (primary processed materials) from processed materials by swinging in an environment where sorting wind is supplied from a wind separator 425. In addition, a primary processed material recovery unit 426 and a secondary processed material recovery unit 427 are arranged at the lower side of the swing sorting device 424.

[0293] The air separator 425 is provided in the sorting unit 442, and generates sorting air along the conveying direction of the processed material. The air separator 425 is formed by accommodating an air separator body having a plurality of rotating blades 425b inside a fan housing 425a. An upper discharge port 425c for sending out the sorting air along the upper surface of the upper grain shaking plate 461 and a rear discharge port 425d for sending out the sorting air to the rear are formed at the upper portion of the fan housing 425a.

[0294] The primary processed material recovery section 426 recovers the processed material as the primary processed material. The structure is such that the processed material is guided to the primary processed material recovery section 426 by the primary processed material guide section 462. The primary processed material recovery section 426 is structured as a primary processed material auger that transports the primary processed material (grains of the primary processed material) guided by the primary processed material guide section 462 in the horizontal direction. The primary processed material recovered by the primary processed material recovery section 426 is transported (won) upward toward the grain box 412 by the primary processed material recovery conveying section 429. Therefore, the sorted processed material sorted by the sorting unit 442 is transported to the grain box 412 for storage. The primary processed material transported by the primary processed material recovery conveying section 429 is transported to the right by the storage auger 430 and supplied to the grain box 412. The primary processed material recovery conveying section 429 is equivalent to a bucket conveyor.

[0295] The secondary processed material recovery section 427 recovers the processed materials in the threshing processed materials that have not been sorted as the sorted processed materials as secondary processed materials. The so-called sorted processed materials, as described in detail later, are the grains sorted by the swing sorting device 424. Therefore, the so-called processed materials that have not been sorted as the sorted processed materials, which are equivalent to the grains, stalks, and longer broken straws that have not been sorted in the swing sorting device 424, are called secondary processed materials. It is constructed so that such secondary processed materials are guided to the secondary processed material recovery section 427 by the secondary processed material guide section 463. The secondary processed material recovery section 427 is constructed as a secondary processed material auger that transports the secondary processed materials guided by the secondary processed material guide section 463 in the horizontal direction. The secondary processed materials recovered by the secondary processed material recovery section 427 are transported obliquely forward and upward by the secondary processed material return section 432 and returned to the upper side (upstream side) of the swing sorting device 424. The secondary processed material return section 432 is equivalent to an auger-type conveyor.

[0296] The primary processed material collecting unit 426 and the secondary processed material collecting unit 427 are driven by the power of the engine 400E transmitted via a power transmission structure (not shown).

[0297] The power of the engine 400E is transmitted to the primary processed material recovery unit 426, transmitted from the primary processed material recovery unit 426 to the primary processed material recovery conveying unit 429, and transmitted from the primary processed material recovery conveying unit 429 to the storage auger 430. The primary processed material recovery conveying unit 429 is provided on the right side of the threshing device 401 (outside the right wall).

[0298] The power of the engine 400E is transmitted to the secondary processed material collecting part 427, and is transmitted from the secondary processed material collecting part 427 to the secondary processed material returning part 432. The secondary processed material returning part 432 is provided on the right side of the threshing device 401 (outside of the right wall).

[0299] The swing sorting device 424 sorts grains from the processed material. The swing sorting device 424 is arranged on the lower side of the screen 423, and the processed material leaks from the screen 423. The swing sorting device 424 includes a frame-shaped screen box 433, which is swung in the front-rear direction by an eccentric cam-type swing driving mechanism 443 using an eccentric shaft or the like, and is formed into a rectangular shape when viewed from above.

[0300] The screen box 433 includes a first grain shaking plate 434 , a plurality of first screen lines 435 , a second screen line 436 , a first upper screen 438 , a second upper screen 439 , a lower screen 440 , an upper grain shaking plate 461 , and a lower grain shaking plate 465 .

[0301] A first upper screen 438 having a plurality of chaff screens 438A is arranged at a rearward position relative to the upper grain shaking plate 461, and a second upper screen 439 is arranged at a rearward position relative to the first upper screen 438. In addition, the plurality of chaff screens 438A are arranged along the conveying direction (rearward direction) of the processed material, and the plurality of chaff screens 438A are arranged in an inclined posture that faces obliquely upward as they approach the rear end side. In the present embodiment, the opening of each chaff screen 438A can be changed. The opening can be changed, which means that the inclined posture can be changed. Specifically, the closer the chaff screen 438A is parallel to the front-back direction, the smaller its opening is, and the closer the chaff screen 438A is parallel to the up-down direction, the larger its opening is. The lower grain shaking plate 465 is arranged at the lower side of the front end of the first upper screen 438, and a lower screen 440 composed of a mesh body is arranged at a position connected to the rear side thereof. The second upper screen 439 is disposed on the rear side of the lower screen 440 and below the rear end portion of the first upper screen 438 .

[0302] In the screen box 433, there are formed an air path for supplying the sorting air supplied from the upper discharge port 425c of the air separator 425 along the upper surface of the upper grain shaking plate 461 and an air path for supplying the sorting air supplied from the rear discharge port 425d of the air separator 425 along the upper surface of the lower grain shaking plate 465. Fig.24 The right end in the middle) and the rear end of the screen 423 form a discharge portion 428.

[0303] In the swing sorting device 424 of the present embodiment, the sorting air from the air separator 425 is supplied from the front side of the machine body to the rear side of the machine body, and the screen box 433 is swung by the swing driving mechanism 443, so that the processed material inside the screen box 433 is transported to the rear side of the machine body. For this reason, in the following description, in the swing sorting device 424, the upstream side of the transport direction of the processed material is referred to as the front end or the front side, and the downstream side of the transport direction of the processed material is referred to as the rear end or the rear side.

[0304] The lower screen 440 is formed by combining a plurality of wires formed of metal into a mesh, and is configured to allow grains to fall through the mesh. A first upper screen 438 is provided above the lower screen 440, and is configured to allow grains flowing between the chaff screens 438A of the first upper screen 438 to fall through the lower screen 440.

[0305] With such a structure, the processed materials that have fallen from the screen 423 on the sorting unit 442 and are caught by the upper grain shaking plate 461 are supplied to the front end of the first upper screen 438 along with the swing of the screen box 433. In addition, the screen box 433 catches most of the processed materials that have fallen from the screen 423.

[0306] The first upper screen 438 causes the grains contained in the processed material to fall while conveying the processed material to the rear side through air separation using the sorting wind and specific gravity separation accompanied by swinging. The stalks such as broken straw in the processed material that has been sorted in this way are handed over to the second upper screen 439, sent from the rear end of the second upper screen 439 to the rear of the screen box 433, and discharged from the discharge section 428 to the discharge straw crushing device 413. The stalks discharged from the discharge section 428 are crushed by the discharge straw crushing device 413 and discharged to the outside of the threshing device 401. In addition, the grains that fall directly to the second upper screen 439 through the screen 423 are sorted by the second upper screen 439 into grains and stalks such as broken straw.

[0307] Here, if the state of the processed material leaking from the screen 423 is considered, the grains in the harvest supplied to the threshing chamber 421, the grains that are not fully granulated, or the straw fragments will leak from the screen 423 earlier when being transported inside the threshing chamber 421. For this reason, the amount of processed material leaking from the upstream area of ​​the conveying direction in the screen 423 tends to be greater than that from the downstream area of ​​the conveying direction. In addition, as described above, the processed material is supplied from the upper grain shaking plate 461 to the front end of the first upper screen 438, so the amount of processed material leaking from the front end of the first upper screen 438 is greater than that from the rear end side.

[0308] In addition, a portion of the processed material leaking from the front end side of the first upper screen 438 is sent to the rear side by the sorting wind and removed immediately after it leaks, and a large amount of processed material containing grains is received by the upper surface of the lower screen 440. Moreover, since the wind pressure and swing force of the sorting wind act on the processed material supplied to the lower screen 440, straws and the like contained in the processed material are sent to the rear on the upper surface of the lower screen 440, and a large amount of grains are contained in the processed material leaking from the lower screen 440. The grains leaking from the lower screen 440 flow down from the primary processed material guide 462 to the primary processed material recovery section 426 and are recovered, and are stored in the grain box 412 by the primary processed material recovery conveying section 429.

[0309] In addition, the processed material from the area behind the first upper screen 438 is supplied to the lower screen 440, and the broken straw in the processed material that has not been missed on the lower screen 440 is sent to the rear by the sorting wind, so that the sorting process can be carried out without significantly reducing the sorting efficiency of the area behind the lower screen 440.

[0310] The primary processed material (grains) leaking out from the front side of the rearmost end of the lower screen 440 flows down from the primary processed material guide 462 to the primary processed material recovery section 426 and is recovered, and is stored in the grain box 412 by the primary processed material recovery conveying section 429 .

[0311] In contrast, the processed material leaking from the rearmost part of the lower screen 440 or the processed material falling from the second upper screen 439 flows down from the secondary processed material guide part 463 to the secondary processed material recovery part 427 and is recovered, and is returned to the upstream side of the swing sorting device 424 by the secondary processed material return part 432. In addition, the waste such as straw scraps as the tertiary processed material generated by the sorting process is sent backward from the rear end of the swing sorting device 424 and discharged from the discharge part 428 to the discharge straw crushing device 413.

[0312] As described above, the secondary processed material is returned to the front part, i.e., the upstream side, of the swing sorting device 424 by the secondary processed material return section 432. Specifically, the secondary processed material is returned to the side of the screen 423 in the threshing unit 441 and to a position where the secondary processed material does not pass through the screen 423 (does not flow). Therefore, the secondary processed material discharge port 432A of the secondary processed material return section 432 is provided at a position radially outside the arc-shaped screen 423, and the secondary processed material is discharged at this position.

[0313] As described above, the combine harvester 420 performs threshing operation on harvested grain stalks harvested in the field using the threshing unit 441 and the sorting unit 442 included in the threshing device 401. Therefore, in the combine harvester 420, the threshing operation corresponds to the above-mentioned "ground operation".

[0314] In addition, as described above, the grains or straw fragments that are not fully granulated in the harvested material supplied to the threshing chamber 421 will leak on the screen 423 early when being transported inside the threshing chamber 421, and part of the leaked processed material is removed by being sent to the rear side by the sorting air. In addition, the processed material containing a large amount of grains is received by the upper surface of the lower screen 440, and the straw and the like contained in the processed material are removed by being sent to the rear on the upper surface of the lower screen 440. However, depending on the amount of cut grain stalks supplied to the threshing device 401 and the parameters for setting the capacities of the various parts of the threshing unit 441 and the sorting unit 442 (for example, the air volume of the above-mentioned sorting air, the opening degree of the chaff screen 438A, etc.), grains, straw, etc. that are not fully single-grained (hereinafter referred to as "foreign matter") may sometimes reach the primary processed material recovery and conveying section 429 via the primary processed material guide section 462. In this case, such foreign matter will be stored in the grain box 412.

[0315] Such foreign matter will reduce the sorting degree (or sorting efficiency) of the threshing device 401, so the amount of foreign matter delivered to the grain box 412 is preferably small. Therefore, the combine harvester 420 of this embodiment is configured to reduce the amount of foreign matter stored in the grain box 412. Fig.25 Such reduction in the amount of foreign matter will be described.

[0316] In order to achieve the above-mentioned functions, the combine harvester 420 has a first information acquisition unit 471, which acquires first information, and the first information includes the working conditions of the working object in the ground operations performed in the past, the equipment setting values ​​for setting the capabilities of the equipment used in the past ground operations, and the working results of the ground operations performed in the past ground operations.

[0317] The so-called working object in the ground operation implemented in the past is the threshing operation performed by the combine harvester 420 when harvesting crops in the field in the past. The so-called working conditions, in this embodiment, are location information indicating the location of the working place where the ground operation is performed. Therefore, the so-called working conditions of the working object in the ground operation implemented in the past are equivalent to the location information indicating the location of the field where the combine harvester 420 performed threshing operations in the field when harvesting crops in the field in the past. Such location information is information indicating the latitude, longitude, and altitude of the field. For example, the combine harvester 420 can obtain such location information using a GPS device (not shown) when performing harvesting operations in the field, and store it in the storage unit of the combine harvester 420, or it can be stored in a server connected via a network.

[0318] In addition, the so-called equipment used in the past ground operation is the equipment used in the threshing operation performed by the combine harvester 420 when harvesting crops in the field, that is, the threshing device 401. Therefore, the so-called equipment setting value for setting the capacity of the equipment is the control parameter of the threshing device 401 that performs the threshing process, and specifically, the following parameters are equivalent to it: a threshing setting parameter that can set the threshing capacity of the threshing unit 441 of the threshing device 401; a sorting parameter that can set the sorting capacity of the sorting unit 442. The so-called threshing parameter that can set the threshing capacity of the threshing unit 441 is equivalent to the following setting values: a setting value for setting the rotation speed of the rotating support shaft 455 of the threshing barrel 422; a setting value for setting the installation angle of the dust sending valve 453a relative to the top plate 453. In addition, the so-called sorting parameters that can set the sorting capacity of the sorting unit 442 are equivalent to the following set values: the set value for setting the air volume of the sorting air from the wind separator 425; the set value for setting the opening of the husk screen 438A; the set value for setting the swing speed and swing amount of the swing driving mechanism 443 that swings the swing sorting device 424.

[0319] Therefore, the equipment setting values ​​for setting the capabilities of the equipment used in the past ground operation are equivalent to the following setting values: the setting value for setting the rotation speed of the rotating support shaft 455 of the threshing drum 422 used in the threshing operation performed by the combine harvester 420 in the past when harvesting crops in the field; the setting value for setting the installation angle of the dust delivery valve 453a relative to the top plate 453; the setting value for setting the air volume of the sorting air from the air separator 425; the setting value for setting the opening of the chaff screen 438A; and the setting value for setting the swing speed and swing amount of the swing driving mechanism 443 that swings the swing sorting device 424. Such setting values ​​can also be stored in the storage unit of the combine harvester 420 or in a server connected via a network.

[0320] In addition, the so-called result of the ground work performed in the past is the result of the threshing operation performed by the combine harvester 420 when harvesting crops in the field in the past. Specifically, it is the result of the estimation of the amount of foreign matter stored in the grain box 412. The amount of such foreign matter can be estimated based on, for example, a captured image of the processed material when it is threshed in the threshing device 1 and transported to the grain box 412; or, it can also be estimated based on a captured image of the state when the stored grains are discharged from the grain box 412 of the combine harvester 420 via the grain discharge device 414 to the grain transport vehicle. Of course, it can also be estimated by other methods.

[0321] In this embodiment, the above-mentioned location information indicating the location of the field where threshing operations were performed when crops were harvested in the field in the past, the setting values ​​of the equipment used in the threshing operations performed in the past, and the results of the threshing operations performed when crops were harvested in the field in the past are processed into first information and acquired through the first information acquisition unit 471.

[0322] In addition, the combine harvester 420 is also equipped with a second information acquisition unit 472, which acquires second information, and the second information includes the operating conditions of the operating object in the next ground operation to be implemented. The above-mentioned first information is information related to the ground operation implemented in the past. On the other hand, the second information acquisition unit 472 acquires information related to the next ground operation as the second information. Specifically, the so-called operating conditions of the operating object in the next ground operation to be implemented is the position information indicating the position of the working place where the ground operation will be performed next, and the position information indicating the position of the field where the combine harvester 420 performs threshing when harvesting crops in the field next is equivalent to it. Such position information is information indicating the latitude, longitude, and altitude of the field, for example, it can be obtained by using a GPS device (not shown) when the combine harvester 420 performs harvesting operations in the field, or, when the combine harvester 420 is pre-assigned with an operation plan, it can also be configured to be obtained based on information storing such an operation plan.

[0323] The combine harvester 420 is provided with an equipment setting value estimation unit 473 that estimates equipment setting values ​​of equipment used in the next ground operation based on the first information acquired by the first information acquisition unit 471 and the second information acquired by the second information acquisition unit 472. The equipment setting values ​​of equipment used in the next ground operation correspond to the following setting values: a setting value for setting the rotation speed of the rotating support shaft 455 of the threshing drum 422 used in the threshing operation to be performed by the combine harvester 420 in the field; a setting value for setting the installation angle of the dust sending valve 453a with respect to the top plate 453; a setting value for setting the air volume of the sorting air from the air classifier 425; a setting value for setting the opening of the chaff screen 438A; and a setting value for setting the swing speed and swing amount of the swing driving mechanism 443 that swings the swing sorting device 424.

[0324] Here, the first information includes, as described above, position information indicating the position of a field where threshing was performed in the past when harvesting crops in the field, setting values ​​of equipment used in the past threshing, and results of threshing performed in the past when harvesting crops in the field. On the other hand, the second information includes position information indicating the position of a field where the combine harvester 420 will perform threshing next. Therefore, the equipment setting value calculation unit 473 extracts the first information including position information that is consistent with or similar to the position information included in the second information, and further calculates the setting value of the equipment when there is less mixing of foreign matter from the result of the threshing included in the first information. In addition, in this case, it is preferred that the equipment setting value calculation unit 473 extracts not only the position information but also the first information that is consistent with the type of harvested object to calculate the setting value.

[0325] Here, it is preferred that the device setting value estimation unit 473 estimates the device setting value of the device used in the ground operation to be performed next by inputting the first information and the second information into a neural network, and the neural network is a neural network that has learned to estimate the device setting value based on the first information and the prescribed working conditions. Here, the so-called neural network is an algorithm that simulates the human brain and is executed by a computer. For example, when the first information and the second information are input, the estimated result of the device setting value is output as a result of discrimination like the human brain. The neural network of this embodiment uses a neural network that has been learned in advance so that the device setting value with less mixing of foreign matter can be estimated.

[0326] Specifically, in the present embodiment, the neural network may use the following neural network: regardless of whether there is or is no foreign matter mixed in, when the specified operating conditions are input as teacher data, learning is performed in a manner that outputs the estimated results of the equipment setting values ​​of the equipment that does not contain foreign matter. That is, before the above-mentioned second information is input into the neural network, labels are provided in advance for the equipment setting values ​​that are not mixed with foreign matter, labels are provided for the equipment setting values ​​that contain foreign matter, and the characteristics of the equipment setting values ​​of each label are learned. Thus, when the second information is provided, it is possible to easily calculate the equipment setting values ​​that are not mixed with foreign matter (equipment setting values ​​with less foreign matter). In addition, the learning can also be continuously performed in the combine harvester 20 when the threshing process is actually performed without using teacher data. In this way, the equipment setting value estimation unit 473 uses a neural network to estimate the equipment setting value.

[0327] Preferably, the device setting value estimation unit 473 continuously estimates the device setting value during the implementation of the ground operation. That is, the device setting value estimation unit 473 can continuously estimate the device setting value when the combine harvester 420 performs the harvesting operation (threshing operation). Thus, even if the second information changes, the device setting value corresponding to the changed second information can be estimated.

[0328] Furthermore, it is preferred that the equipment setting value estimation unit 473 automatically estimates the equipment setting value as the ground operation is performed. That is, the equipment setting value estimation unit 473 can continuously estimate the equipment setting value when the combine harvester 420 is performing a harvesting operation (threshing operation), for example, regardless of whether there is an instruction from the operator.

[0329] Preferably, the combine harvester 420 is provided with a setting value indicating unit 474, which applies the calculated device setting value to the device when the ground operation is performed next. The device setting value of the device is calculated by the above-mentioned device setting value calculating unit 473 and transmitted to the setting value indicating unit 474 before the combine harvester 420 performs the threshing operation. The setting value indicating unit 474 sets the calculated device setting value to the device before the combine harvester 420 performs the threshing operation.

[0330] As described above, in this embodiment, the position information of the field is included as the condition of the operation object. Therefore, it is preferable that the setting value indicating unit 474 applies the equipment setting value when the operation site where the previous ground operation was performed is the same as the operation site where the next ground operation is to be performed. Thus, the equipment setting value suitable for the threshing operation can be set in the threshing unit 441 and the sorting unit 442, so that the threshing operation can be appropriately performed.

[0331] As described above, in this embodiment, the device setting values ​​of the equipment used in the next ground work are set based on the device setting values ​​used in the past ground work. Fig.26 As shown in the example, the change amount (in Fig.26 The change amount (in X1) when the equipment setting value (II) used in the previous ground operation is set to the equipment setting value (III) of the equipment to be used in the next ground operation is set. Fig.26 Therefore, the device setting value can be set quickly, and the change amount can be made small, so it can be set to the setting value with high accuracy.

[0332] [Other implementation methods]

[0333] In the above embodiment, the working vehicle is described by taking a full-feed combine harvester as an example, but it may also be a half-feed combine harvester. In addition, the working vehicle may be a rice transplanter or a tractor. In addition, it may also be other agricultural machinery or a construction machine.

[0334] In the above embodiment, it is described that the combine harvester 420 is provided with the setting value indicating unit 474 for applying the estimated device setting value to the device when the ground operation is performed next, but the combine harvester 420 may not be provided with the setting value indicating unit 474. In this case, for example, a display device may be provided in the combine harvester 420, and the device setting value estimated by the device setting value estimating unit 473 may be displayed as a suggestion to the operator on the display device. Thus, the operator can manually change the device setting value of the device and can appropriately perform the ground operation.

[0335] In addition, in the above-mentioned embodiment, it is explained that the setting value indicating unit 474 applies the equipment setting value when the working place where the ground work was carried out in the past is the same as the working place where the ground work is to be carried out next, but the setting value indicating unit 474 can also be configured as follows: even if the working place where the ground work was carried out in the past is different from the working place where the ground work is to be carried out next, the equipment setting value will be applied when the interval between the working place where the ground work was carried out in the past and the working place where the ground work is to be carried out next is within a specified distance, or the equipment setting value can also be applied regardless of the interval.

[0336] In the above embodiment, the device setting value estimation unit 473 continuously estimates the device setting value during the implementation of the ground operation, but the device setting value estimation unit 473 can also be configured to estimate the device setting value only at a specified time (for example, when the ground operation starts, etc.).

[0337] In the above embodiment, the device setting value estimation unit 473 automatically estimates the device setting value as the ground work is performed, but the device setting value estimation unit 473 may be configured to estimate the device setting value based on the operator's instructions (e.g., based on switch operation).

[0338] In the above embodiment, it is described that the working conditions of the working object include the location information indicating the location of the working site where the ground work is performed, but it is also possible to configure the working conditions of the working object not to include the location information. In this case, for example, as described in the above embodiment, it is also possible to configure to include the type of crops to be harvested, or include information indicating the status of the working site (field), or include information indicating the season, temperature, weather, etc.

[0339] In the above embodiment, the ground operation is described as threshing operation for threshing the cut grain stalks cut in the field, but as mentioned above, the ground operation may not be threshing operation, for example, it may be transplanting operation, tillage operation, or mowing operation. In addition, it may be just sorting operation.

[0340] In the above-mentioned embodiment, the estimation of the device setting value using the neural network is described, but the estimation may be performed without using the neural network.

[0341] As described above, the work vehicle has been described by taking the combine harvester 420 as an example, but when the work vehicle is the combine harvester 420, the equipment setting value may be estimated based on the quality of the grains transported from the threshing device 401 to the grain tank 412. The work vehicle may be configured as follows.

[0342] The work vehicle comprises: a threshing unit 441, which thres the cut grain stalks and discharges the threshed material; a sorting unit 442, which sorts grains from the discharged threshed material as the sorted material; a grain box 412, to which the sorted material is transported and stores the sorted material; a photographing unit, which acquires a photographed image taken within a transport path from the sorting unit 442 to the grain box 412; a first operating condition information acquisition unit, which acquires first operating condition information, the first operating condition information indicating operating conditions when threshing the cut grain stalks and sorting the grains; a control parameter information acquisition unit, which acquires control parameter information indicating control parameters for threshing and control parameters for sorting, the threshing control parameters being threshing parameters set for the threshing unit 441 when threshing the cut grain stalks. A control parameter for the threshing ability of the grain unit 441, wherein the control parameter for sorting is a control parameter for the sorting ability of the sorting unit 442 set for the sorting unit 442 when sorting the sorted processed material; an evaluation result acquisition unit, which acquires an evaluation result, which is a result of evaluating whether the sorted processed material included in the captured image is a normal grain that meets the desired quality; a second operating condition information acquisition unit, which acquires second operating condition information, which second operating condition information indicates the operating conditions for threshing and sorting the cut grain stalks; and a control parameter estimation unit, which estimates the threshing control parameters set when threshing the cut grain stalks and the sorting control parameters set when sorting the grains based on the first operating condition information, the control parameter information, the evaluation result and the second operating condition information.

[0343] In addition, in the above-mentioned structure, it is preferred that the estimated control parameters for threshing and control parameters for sorting are used for threshing and sorting of cut grain stalks harvested in the following field: the field is the same field as the field where the cut grain stalks were harvested for the estimation.

[0344] Moreover, in the said structure, it is preferable that the control parameter estimation part continuously performs estimation in the threshing process of harvesting grain stems and the process of sorting grains.

[0345] In the above configuration, it is preferable that the estimated threshing control parameter and the sorting control parameter are automatically applied when the threshing unit 441 and the sorting unit 442 are operated.

[0346] In addition, in the above structure, it is preferred that the first operating condition information includes first position information, which indicates the position in the field where the sorted and processed materials have been harvested, and the second operating condition information includes second position information, which indicates the position in the harvested field where the cut grain stalks to be threshed next are.

[0347] In addition, in the above structure, it is preferred that the threshing unit 441 is provided with a threshing cylinder 422, which has a cylindrical cylinder body 460 with a plurality of threshing teeth 458b installed on the outer periphery and a threshing cylinder shaft supporting the cylinder body 460, the threshing control parameters are control parameters for setting the feed amount of cut grain stalks in the cylinder body, the sorting unit 442 is provided with an upper screen and a wind separator 425, the upper screen has a plurality of husk screens 438A arranged along the conveying direction of conveying the threshed processed material and each of which has a changeable opening, the wind separator 425 generates sorting wind along the conveying direction, and the sorting control parameters are control parameters for setting the opening of the husk screen 438A and the air volume of the sorting wind.

[0348] In addition, in the above-mentioned structure, it is preferred that the evaluation of whether the sorted processed products contained in the captured image are normal grains is performed by inputting image data generated based on the captured image into a neural network, and the neural network is a neural network that has learned to distinguish normal grains based on the sorted processed products.

[0349] In addition, preferably, the neural network learns in a manner that outputs a discrimination result that the sorted processed material contains normal grains when learning image data generated from captured images containing normal grains are input as teacher data, and learns in a manner that outputs a discrimination result that the sorted processed material contains foreign matter when learning image data generated from captured images containing foreign matter other than normal grains are input as teacher data.

[0350] In the above embodiment, the work vehicle is described, but the processing performed by each functional unit in the above embodiment can also be constituted as a work vehicle management method. In this case, the work vehicle management method is a work vehicle management method for managing a work vehicle that performs ground work on a predetermined work object, wherein the method comprises: a first information acquisition step, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting value for setting the capacity of the equipment used in the past ground work, and the working result of the ground work performed in the past ground work; a second information acquisition step, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation step, which estimates the equipment setting value of the equipment used in the ground work to be performed next based on the first information and the second information.

[0351] In the above embodiment, the work vehicle is described, but the processing performed by each functional unit in the above embodiment can also be constituted as a work vehicle management system. In this case, the work vehicle management system is a work vehicle management system that manages a work vehicle that performs ground work on a predetermined work object, wherein it has: a first information acquisition unit 471, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting value for setting the capacity of the equipment used in the past ground work, and the working result of the ground work performed in the past ground work; a second information acquisition unit 472, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation unit 473, which estimates the equipment setting value of the equipment used in the ground work to be performed next based on the first information and the second information.

[0352] In addition, each functional unit in the above-mentioned embodiment can also be configured as a work vehicle management program. In this case, the work vehicle management program is a work vehicle management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, wherein it can be configured to enable the computer to implement the following functions: a first information acquisition function, which acquires first information, the first information including the working conditions of the work object in the ground work performed in the past, the equipment setting value for setting the capacity of the equipment used in the past ground work, and the working result of the ground work performed in the past ground work; a second information acquisition function, which acquires second information, the second information including the working conditions of the work object in the ground work to be performed next; and an equipment setting value estimation function, which estimates the equipment setting value of the equipment used in the ground work to be performed next based on the first information and the second information.

[0353] In addition, such a work vehicle management program may be configured to be recorded on a recording medium.

[0354] 4-4. Fourth Embodiment

[0355] The management system of the present invention manages work vehicles that perform ground operations on pre-set work objects. The so-called pre-set work object is an object on which the work vehicle performs operations using the functional parts, devices, etc. possessed by the work vehicle. Specifically, if the work vehicle is a combine harvester, the harvesting object is equivalent to it, if the work vehicle is a rice transplanter, the planting object is equivalent to it, and in the case of a tractor performing tillage and mowing, the field, etc. are equivalent to it. In addition, if the work vehicle is a construction machine, soil, rock, wood, etc. are equivalent to it. The so-called ground operation is the operation performed on a field or a work site. In this embodiment, a combine harvester 20 is cited as an example of a work vehicle for explanation.

[0356] The management system of the present invention is configured to be able to determine the state of a work vehicle. Hereinafter, the management system 700 of this embodiment will be described.

[0357] Fig. 27 is a side view of a combine harvester 620 which is a management target of the management system 700. Fig.28 is a top view of the combine harvester 620. In addition, Fig.29 It is a cross-sectional view of the threshing device 601 equipped in the combine harvester 620. In addition, below, the combine harvester 620 is described by taking a so-called full-feed combine harvester as an example. Of course, the combine harvester 620 may also be a half-feed combine harvester.

[0358] Here, for easy understanding, in this embodiment, unless otherwise specified, the "front" ( Fig. 27The arrow F in the direction of the vehicle body (in the direction of travel) refers to the front, and the rear (in the direction of travel) refers to the front of the vehicle body. Fig. 27 The direction of the arrow B shown in the figure) refers to the rear in the front-rear direction of the machine body (the direction of travel). Fig. 27 direction of the arrow U shown) and "down" ( Fig. 27 The left and right directions (the direction of the arrow D shown in the figure) are the vertical directions (vertical directions) of the machine body, indicating the height relationship from the ground. In addition, the left-right direction or the lateral direction refers to the cross-sectional direction of the machine body (the width direction of the machine body) that is orthogonal to the front-rear direction of the machine body, that is, the left ( Fig.28 direction of the arrow L shown) and "right" ( Fig.28 The directions of the arrows R shown in the figure respectively refer to the left and right directions of the machine body.

[0359] like Fig. 27 and Fig.28 As shown, the combine harvester 620 includes a machine frame 602 and a crawler travel device 603. A harvesting unit 604 for harvesting standing grain stalks is provided in front of the travel machine body 617. The harvesting unit 604 includes a reel 605 for feeding standing grain stalks, a cutter 606 for cutting standing grain stalks, and an auger 607 for feeding harvested grain stalks.

[0360] A driving unit 608 is provided on the right side of the front part of the traveling machine body 617. The driving unit 608 is provided with a cab 610 for the driver to ride. An engine room 600ER is provided below the cab 610. In the engine room 600ER, in addition to the engine 600E, an exhaust purification device, a cooling fan, a radiator, etc. are also accommodated. The power of the engine 600E is transmitted to the crawler traveling device 603, the threshing unit 641 described later, the sorting unit 642, etc. through a power transmission structure (not shown).

[0361] A threshing device 601 for threshing the cut grain stalks is provided at the rear of the harvesting section 604. An intermediate conveying device 611 for conveying the cut grain stalks to the threshing device 601 is provided across the harvesting section 604 and the threshing device 601. A grain box 612 for storing the grains after the threshing process is provided on the side of the threshing device 601. The grain box 612 is configured to be able to swing open and close around an axis extending in the vertical direction across the working position and the maintenance position. At the rear of the threshing device 601, a discharge straw breaking device 613 with a rotating knife 613a is provided.

[0362] The combine harvester 620 is provided with a grain discharge device 614 for discharging grains in the grain tank 612 to the outside. The grain discharge device 614 includes a longitudinal conveying section 615 for conveying grains in the grain tank 612 upward and a transverse conveying section 616 for conveying grains from the longitudinal conveying section 615 to the outside of the machine body. The grain discharge device 614 is configured to be rotatable around the axis of the longitudinal conveying section 615. The lower end of the longitudinal conveying section 615 is connected to the bottom of the grain tank 612. The end of the transverse conveying section 616 on the longitudinal conveying section 615 side is connected to the upper end of the longitudinal conveying section 615 and is supported to swing up and down.

[0363] In the present embodiment, the threshing device 601 is provided on the traveling body 617. As described above, the threshing device 601 includes a threshing unit 641 and a sorting unit 642. The threshing unit 641 thres the harvested grain stalks harvested by the harvesting section 604. The grains obtained by the threshing process of the threshing unit 641 are discharged as threshed processed materials. The sorting unit 642 sorts the threshed processed materials discharged from the threshing unit 641 into sorted processed materials. Therefore, the threshing unit 641 and the sorting unit 642 are provided on the traveling body 617. The threshing unit 641 is arranged on the upper part of the threshing device 601, and a screen 623 is provided on the lower part of the threshing unit 641. The sorting unit 642 is arranged below the threshing unit 641, and is configured to sort out grains from the threshing processed materials leaking from the screen 623. The sorting unit 642 includes a swing sorting device 624 , a primary processed material recovery unit 626 , a secondary processed material recovery unit 627 , and a secondary processed material return unit 632 .

[0364] The threshing unit 641 accommodates the threshing cylinder 622 in the threshing chamber 621, and has a screen 623 at the bottom of the threshing cylinder 622. The threshing chamber 621 is formed as a space surrounded by a front wall 651 on the front side, a rear wall 652 on the rear side, left and right side walls, and a top plate 653 covering the upper part. A supply port 654a to which the harvest is supplied is formed at the lower position of the front wall 651 in the threshing chamber 621, and a guide bottom plate 659 is arranged at the lower side of the supply port 654a. In addition, a dust discharge port 654b is formed at the lower side of the rear wall 652 in the threshing chamber 621.

[0365] The threshing cylinder 622 has a cylinder body 660 and a rotating support shaft 655. Fig.29As shown, the barrel 660 is formed integrally by a dial-in portion 657 at the front end and a threshing processing portion 658 at the rear position of the dial-in portion 657. The dial-in portion 657 is provided with a double spiral spiral blade 657b at the outer periphery of a base portion 657a of a front end thinner shape whose diameter becomes smaller as it approaches the front end side of the threshing barrel 622. The threshing processing portion 658 has a plurality of rod-shaped threshing tooth support parts 658a and a plurality of threshing teeth 658b. The plurality of rod-shaped threshing tooth support parts 658a are respectively arranged at predetermined intervals apart from each other along the circumference of the cylindrical barrel 660. The plurality of threshing teeth 658b are respectively protruding from the outer peripheries of the plurality of threshing tooth support parts 658a, and are installed at predetermined intervals apart from each other along the rotation axis 600X of the front-back orientation posture.

[0366] The cylinder 660 rotates integrally with the rotating support shaft 655 which penetrates the front wall 651 and the rear wall 652 in the front-back direction with the same axis as the rotating axis 600X. That is, the front end of the rotating support shaft 655 is rotatably supported by the front wall 651 via a bearing, and similarly, the rear end of the rotating support shaft 655 is rotatably supported by the rear wall 652 via a bearing. In the threshing unit 641, the driving rotational force is transmitted from the rotation driving mechanism 656 to the front end of the rotating support shaft 655.

[0367] On the inner surface (lower surface) of the top plate 653, a plurality of plate-shaped dust delivery valves 653a are provided at predetermined intervals along the front-back direction. The plurality of dust delivery valves 653a are provided in the threshing chamber 621 in a tilted posture relative to the rotation axis 600X when viewed from above, so as to act on the processed material rotating with the threshing cylinder 622 to move it to the rear side. In the present embodiment, the dust delivery valve 653a is configured to be able to change its installation angle relative to the top plate 653. By changing this angle, the feed amount of the processed material in the cylinder 660 can be changed.

[0368] The screen 623 has a structure in which a gap through which the processed material can fall is formed by combining a plurality of longitudinal frames and transverse frames oriented in a front-to-back posture. The plurality of longitudinal frames are in an arc shape when observed along the rotation axis 600X so as to surround the threshing barrel 622 from the bottom in an area spanning both side portions, and are arranged at prescribed intervals in the front-to-back direction, and the transverse frames are supported by each longitudinal frame.

[0369] In the combine harvester 620 of the present embodiment, the harvested straw supplied to the threshing chamber 621 is called a harvested product, and the harvested product obtained by threshing in the threshing chamber 621 is called a processed product (equivalent to "threshed processed product"). The processed product includes grains and chopped straws, etc. In addition, the so-called primary processed product is a processed product mainly including grains, and the so-called secondary processed product is a processed product including grains that are not fully granulated and chopped straws, etc.

[0370] In the threshing unit 641, the harvested material from the intermediate conveying device 611 is supplied to the threshing chamber 621 through the supply port 654a. The supplied harvested material is pushed in toward the rear of the threshing cylinder 622 along the guide bottom plate 659 by the spiral blade 657b of the pushing-in portion 657, and is supplied to the threshing processing portion 658. In the threshing processing portion 658, the harvested material is threshed by the threshing teeth 658b and the screen 623 as the threshing cylinder 622 rotates, thereby threshing.

[0371] When threshing is performed in this way, the processed material is rotated together with the threshing drum 622, and the threshing process is performed while the processed material is contacted with the dust delivery valve 653a and is transported to the rear part of the threshing chamber 621. The grains and short straw stalks obtained by the threshing process fall on the screen 623 and fall into the sorting unit 642. In contrast, the processed material (grain stalks, long straw stalks, etc.) that cannot fall on the screen 623 is discharged from the dust discharge port 654b to the outside of the threshing chamber 621.

[0372] like Fig.29 As shown, the sorting unit 642 is configured to include a swing sorting device 624, which sorts grains (primary processed materials) from processed materials by swinging in an environment where sorting wind is supplied from a wind separator 625. In addition, a primary processed material recovery unit 626 and a secondary processed material recovery unit 627 are arranged at the lower side of the swing sorting device 624.

[0373] The air separator 625 is provided in the sorting unit 642, and generates sorting air along the conveying direction of the processed material. The air separator 625 is formed by accommodating an air separator body having a plurality of rotating blades 625b inside a fan housing 625a. An upper discharge port 625c for sending out the sorting air along the upper surface of the upper grain shaking plate 661 and a rear discharge port 625d for sending out the sorting air to the rear are formed at the upper portion of the fan housing 625a.

[0374] The primary processed material recovery section 626 recovers the processed material as the primary processed material. The structure is such that the processed material is guided to the primary processed material recovery section 626 by the primary processed material guide section 662. The primary processed material recovery section 626 is structured as a primary processed material auger that transports the primary processed material (grains of the primary processed material) guided by the primary processed material guide section 662 in the horizontal direction. The primary processed material recovered by the primary processed material recovery section 626 is transported (fly-fed) upward toward the grain box 612 by the primary processed material recovery conveying section 629. Therefore, the sorted processed material sorted by the sorting unit 642 is transported to the grain box 612 for storage. The primary processed material transported by the primary processed material recovery conveying section 629 is transported to the right by the storage auger 630 and supplied to the grain box 612. The primary processed material recovery conveying section 629 is equivalent to a bucket conveyor.

[0375] The secondary processed material recovery section 627 recovers the processed materials in the threshing processed materials that have not been sorted as the sorted processed materials as secondary processed materials. The so-called sorted processed materials, as described in detail later, are the grains sorted by the swing sorting device 624. Therefore, the so-called processed materials that have not been sorted as the sorted processed materials, which are equivalent to the grains, stalks, and longer broken straws that have not been sorted in the swing sorting device 624, are called secondary processed materials. It is configured so that such secondary processed materials are guided to the secondary processed material recovery section 627 by the secondary processed material guide section 663. The secondary processed material recovery section 627 is configured as a secondary processed material auger that transports the secondary processed materials guided by the secondary processed material guide section 663 in the horizontal direction. The secondary processed materials recovered by the secondary processed material recovery section 627 are transported obliquely forward and upward by the secondary processed material return section 632 and returned to the upper side (upstream side) of the swing sorting device 624. The secondary processed material return section 632 is equivalent to an auger-type conveyor.

[0376] The primary processed material collecting unit 626 and the secondary processed material collecting unit 627 are driven by the power of the engine 600E transmitted via a power transmission structure (not shown).

[0377] The power of the engine 600E is transmitted to the primary processed material recovery unit 626, from the primary processed material recovery unit 626 to the primary processed material recovery conveying unit 629, and from the primary processed material recovery conveying unit 629 to the storage auger 630. The primary processed material recovery conveying unit 629 is provided on the right side of the threshing device 601 (outside the right wall).

[0378] The power of the engine 600E is transmitted to the secondary processed material collecting part 627, and is transmitted from the secondary processed material collecting part 627 to the secondary processed material returning part 632. The secondary processed material returning part 632 is provided on the right side of the threshing device 601 (outside of the right wall).

[0379] The swing sorting device 624 sorts grains from the processed material. The swing sorting device 624 is arranged on the lower side of the screen 623, and the processed material falls through the screen 623. The swing sorting device 624 includes a frame-shaped screen box 633, which is swung in the front-rear direction by an eccentric cam-type swing driving mechanism 643 using an eccentric shaft or the like, and is formed into a rectangular shape when viewed from above.

[0380] The screen box 633 includes a first grain shaking plate 634 , a plurality of first screen lines 635 , a second screen line 636 , a first upper screen 638 , a second upper screen 639 , a lower screen 640 , an upper grain shaking plate 661 , and a lower grain shaking plate 665 .

[0381] A first upper screen 638 having a plurality of chaff screens 638A is arranged at a rearward position of the upper grain shaking plate 661, and a second upper screen 639 is arranged at a rearward position of the first upper screen 638. In addition, the plurality of chaff screens 638A are arranged along the conveying direction (rearward direction) of the processed material, and the plurality of chaff screens 638A are arranged in an inclined posture that faces obliquely upward as they approach the rear end side. In the present embodiment, the opening of each chaff screen 638A can be changed. The opening can be changed means that the inclined posture can be changed. Specifically, the closer the chaff screen 638A is to be parallel to the front-back direction, the smaller its opening is, and the closer the chaff screen 638A is to be parallel to the up-down direction, the larger its opening is. The lower grain shaking plate 665 is arranged at the lower side of the front end of the first upper screen 638, and a lower screen 640 composed of a mesh body is arranged at a position connected to the rear side thereof. The second upper screen 639 is disposed on the rear side of the lower screen 640 and below the rear end portion of the first upper screen 638 .

[0382] In the screen box 633, there are formed an air path for supplying the sorting air supplied from the upper discharge port 625c of the air separator 625 along the upper surface of the upper grain shaking plate 661 and an air path for supplying the sorting air supplied from the rear discharge port 625d of the air separator 625 along the upper surface of the lower grain shaking plate 665. Fig.29 The right end in the middle) and the rear end of the screen 623 form a discharge portion 628.

[0383] In the swing sorting device 624 of the present embodiment, the sorting air from the air separator 625 is supplied from the front side of the machine body to the rear side of the machine body, and the screen box 633 is swung by the swing driving mechanism 643, so that the processed material inside the screen box 633 is transported to the rear side of the machine body. For this reason, in the following description, in the swing sorting device 624, the upstream side of the transport direction of the processed material is referred to as the front end or the front side, and the downstream side of the transport direction of the processed material is referred to as the rear end or the rear side.

[0384] The lower screen 640 is a mesh body formed by combining a plurality of metal wires into a mesh, and is configured to allow grains to fall through the mesh. A first upper screen 638 is provided above the lower screen 640 , and is configured to allow grains flowing between the chaff screens 638A of the first upper screen 638 to fall through the lower screen 640 .

[0385] With such a structure, the processed materials that have fallen from the screen 623 on the sorting unit 642 and are caught by the upper grain shaking plate 661 are supplied to the front end of the first upper screen 638 as the screen box 633 swings. In addition, the screen box 633 catches most of the processed materials that have fallen from the screen 623.

[0386] The first upper screen 638 causes the grains contained in the processed material to fall through the air separation using the sorting wind and the specific gravity separation accompanied by the swing while conveying the processed material to the rear side. The stalks such as the broken straw in the processed material that has been sorted in this way are handed over to the second upper screen 639, sent from the rear end of the second upper screen 639 to the rear of the screen box 633, and discharged from the discharge part 628 to the discharge straw crushing device 613. The stalks discharged from the discharge part 628 are broken by the discharge straw crushing device 613 and discharged to the outside of the threshing device 601. In addition, the grains that fall directly to the second upper screen 639 through the screen 623 are sorted by the second upper screen 639 into grains and stalks such as the broken straw.

[0387] Here, if the state of the processed material leaking from the screen 623 is considered, the grains in the harvest supplied to the threshing chamber 621, the grains that are not fully granulated, or the straw fragments will leak from the screen 623 earlier when being transported inside the threshing chamber 621. For this reason, the amount of processed material leaking from the upstream area of ​​the conveying direction in the screen 623 tends to be greater than that from the downstream area of ​​the conveying direction. In addition, as described above, the processed material is supplied from the upper grain shaking plate 661 to the front end of the first upper screen 638, so the amount of processed material leaking from the front end of the first upper screen 638 is greater than that from the rear end side.

[0388] In addition, a portion of the processed material leaking from the front end side of the first upper screen 638 is sent to the rear side by the sorting wind and removed immediately after it leaks, and a large amount of processed material containing grains is received by the upper surface of the lower screen 640. Moreover, since the wind pressure and swing force of the sorting wind act on the processed material supplied to the lower screen 640, straws and the like contained in the processed material are sent to the rear on the upper surface of the lower screen 640, and a large amount of grains are contained in the processed material leaking from the lower screen 640. The grains leaking from the lower screen 640 flow down from the primary processed material guide 662 to the primary processed material recovery section 626 and are recovered, and are stored in the grain box 612 by the primary processed material recovery conveying section 629.

[0389] In addition, the processed material from the area behind the first upper screen 638 is supplied to the lower screen 640, and the broken straw in the processed material that has not been missed on the lower screen 640 is sent to the rear by the sorting wind, so that the sorting process can be carried out without significantly reducing the sorting efficiency of the area behind the lower screen 640.

[0390] The primary processed material (grains) leaking out from the front side of the rearmost end of the lower screen 640 flows down from the primary processed material guide 662 to the primary processed material recovery section 626 and is recovered, and is stored in the grain box 612 by the primary processed material recovery conveying section 629 .

[0391] In contrast, the processed material leaking from the rearmost part of the lower screen 640 or the processed material falling from the second upper screen 639 flows down from the secondary processed material guide part 663 to the secondary processed material recovery part 627 and is recovered, and is returned to the upstream side of the swing sorting device 624 by the secondary processed material return part 632. In addition, the waste such as straw scraps as the tertiary processed material generated by the sorting process is sent to the rear from the rear end of the swing sorting device 624 and discharged from the discharge part 628 to the discharge straw crushing device 613.

[0392] As described above, the secondary processed material is returned to the front part, i.e., the upstream side, of the swing sorting device 624 by the secondary processed material return section 632. Specifically, the secondary processed material is returned to the side of the screen 623 in the threshing unit 641 and to a position where the secondary processed material does not pass through the screen 623 (does not flow). Therefore, the secondary processed material discharge port 632A of the secondary processed material return section 632 is provided at a position radially outside the arc-shaped screen 623, and the secondary processed material is discharged at this position.

[0393] As described above, the combine harvester 620 performs threshing operation on harvested grain stalks harvested in the field using the threshing unit 641 and the sorting unit 642 included in the threshing device 601. Therefore, in the combine harvester 620, the threshing operation corresponds to the above-mentioned "ground operation".

[0394] In such threshing operation, since the threshing unit 641 and the sorting unit 642 are used, the state of the threshing unit 641 and the sorting unit 642 may change from the new state due to changes over the years. In this case, if a satisfactory result of the ground operation (threshing operation in this embodiment) cannot be obtained, it is assumed that maintenance is also performed.

[0395] Therefore, the management system 700 of the present embodiment is configured to be able to determine the state of the combine harvester 620. Fig.30 The determination of the state of the combine harvester 620 is described. The management system 700 of this embodiment is configured to include functional units such as a first information acquisition unit 671, a second information acquisition unit 672, a determination unit 673, a reporting unit 674, and a storage unit 675. These functional units are constructed as a core component using hardware or software or both to perform processing related to the determination of the state of the combine harvester 620.

[0396] The first information acquisition unit 671 acquires first information related to the ground operation stored when the ground operation was performed in the past. The so-called past ground operation is the harvesting operation when the combine harvester 620 harvested crops in the field in the past. Therefore, the so-called first information related to the ground operation is information related to the harvesting operation performed by the combine harvester 620 in the past, and is referred to as the first information in this embodiment.

[0397] In the present embodiment, the first information includes information related to the work object in the completed ground operation and information related to the combine harvester 620 when the ground operation is performed. The so-called work object in the completed ground operation is the threshing operation performed when harvesting crops in the field. Therefore, the so-called information related to the work object in the completed ground operation is information related to the threshing operation performed by the combine harvester 620 in the past when harvesting crops in the field. The so-called information related to the threshing operation is, for example, position information indicating the position of the field where the crops for the threshing operation are harvested, and result information indicating the result of the threshing operation performed when harvesting crops in the field. The so-called information related to the combine harvester 620 when performing the ground operation is equipment setting value information indicating the equipment setting value, and the equipment setting value is a setting value for setting the capacity of the threshing device 601 used in the threshing operation performed when harvesting crops in the field.

[0398] The so-called location information indicating the location of a field is information indicating the latitude, longitude, and altitude of the field. For example, the combine harvester 620 may obtain the location information using a GPS device (not shown) when performing harvesting operations in the field and store the location information in the storage unit of the combine harvester 620, or may store the location information in a management system 700 connected via a network.

[0399] The result of the threshing operation performed when harvesting crops in the field is the result of the threshing operation performed by the combine harvester 620 when harvesting crops in the field in the past. Specifically, it is the result of the estimation of the amount of foreign matter stored in the grain box 612. The amount of such foreign matter can be estimated, for example, based on the following captured image, which is obtained by photographing the processed material when it is threshed in the threshing device 601 and transported to the grain box 612; or it can also be estimated based on the following captured image, which is obtained by photographing the state when the stored grains are discharged from the grain box 612 of the combine harvester 620 via the grain discharge device 614 to the grain transport vehicle. Of course, it can also be estimated by other methods.

[0400] In addition, the so-called equipment setting value for setting the capacity of the threshing device 601 is a control parameter of the threshing device 601 that performs threshing processing, and specifically, the following parameters correspond to it: a threshing setting parameter that can set the threshing capacity of the threshing unit 641 of the threshing device 601; a sorting parameter that can set the sorting capacity of the sorting unit 642. The so-called threshing parameter that can set the threshing capacity of the threshing unit 641 corresponds to the following setting values: a setting value that sets the rotation speed of the rotating support shaft 655 of the threshing cylinder 622; a setting value that sets the installation angle of the dust sending valve 653a relative to the top plate 653. In addition, the so-called sorting parameters that can set the sorting ability of the sorting unit 642 have the following setting values ​​equivalent to them: the setting value for setting the air volume of the sorting air from the wind separator 625; the setting value for setting the opening of the husk screen 638A; the setting value for setting the swinging speed and swinging amount of the swinging drive mechanism 643 that swings the swinging sorting device 624.

[0401] Therefore, the equipment setting value for setting the capacity of the threshing device 601 used in the threshing operation performed when harvesting crops in the field corresponds to the following setting values: the setting value for setting the rotation speed of the rotating support shaft 655 of the threshing drum 622 used in the threshing operation performed by the combine harvester 620 in the past when harvesting crops in the field; the setting value for setting the installation angle of the dust sending valve 653a relative to the top plate 653; the setting value for setting the air volume of the sorting air from the air separator 625; the setting value for setting the opening of the chaff screen 638A; and the setting value for setting the swing speed and swing amount of the swing driving mechanism 643 for swinging the swing sorting device 624. Such setting values ​​can also be stored in the storage unit of the combine harvester 620 or in the management system 700 connected via the network.

[0402] In this embodiment, the above-mentioned location information indicating the position of the field where threshing operations were performed when crops were harvested in the field in the past, the result information indicating the results of the threshing operations performed when crops were harvested in the field in the past, and the equipment setting value information indicating the setting values ​​of the equipment used in the threshing operations performed in the past are processed as first information and acquired by the first information acquisition unit 671.

[0403] The second information acquisition unit 672 acquires information related to the ground operation currently being performed. The above-mentioned first information is information related to the ground operation performed in the past. On the other hand, the second information acquisition unit 672 acquires information related to the operation object in the ground operation currently being performed as the second information. Specifically, it is the threshing operation currently being performed when harvesting in the field. Therefore, the so-called information related to the ground operation currently being performed is information related to the threshing operation performed when the combine harvester 620 is currently harvesting crops in the field. The so-called information related to the threshing operation is, for example, position information indicating the position of the field currently being harvested and result information indicating the result of the threshing operation currently being performed. As the position information and result information have been described above, the description is omitted.

[0404] The determination unit 673 compares the first information with the second information to determine the state of the combine harvester 620. The first information is transmitted from the first information acquisition unit 671, and the second information is transmitted from the second information acquisition unit 672. The state of the combine harvester 620 refers to the state of the combine harvester 620 from the perspective of whether the combine harvester 620 can perform ground work on a predetermined work object as a work vehicle, and the determination unit 673 determines the state.

[0405] Specifically, the determination unit 673 determines whether the combine harvester 620 is abnormal as the state of the combine harvester 620. The so-called abnormality of the combine harvester 620 refers to the state in which the combine harvester 620 cannot properly travel in the field for harvesting operations, the state in which the threshing operation of the harvested crops cannot be properly performed, and the state in which the grains in the grain box 612 cannot be properly discharged to the outside via the grain discharge device 614. In addition, in the present embodiment, the above-mentioned travel, threshing operations, and discharge are not only abnormal in that they cannot be performed at all, but also abnormal in that they cannot exert their original capabilities. The determination unit 673 compares the first information with the second information to determine whether the current state of the combine harvester 620 is abnormal, that is, whether the current state of each functional unit of the combine harvester 620 is the same as the state of the past functional unit (whether the output of the current functional unit is within a specified range relative to the output of the past functional unit).

[0406] In addition, the determination unit 673 determines the maintenance time of the combine harvester 620 as the state of the combine harvester 620. The so-called maintenance time of the combine harvester 620 is a time when the state of each functional unit of the above-mentioned current combine harvester 620 becomes different from the state of the past functional unit (becomes not within the prescribed range). Such time, for example, can be predicted by continuously comparing the current state with the past state and based on the increase or decrease of the difference. In this way, the determination unit 673 compares the first information with the second information to determine the time when the combine harvester 620 needs maintenance.

[0407] Here, it is preferable that the determination unit 673 determines the state of the combine harvester 620 by inputting the first information and the second information into a neural network, and the neural network is a neural network that has been learned to determine the state of the combine harvester 620 based on the first information and information related to the predetermined ground operation. Here, the so-called neural network is an algorithm that simulates the human brain and is executed by a computer. For example, when the first information and the second information are input, the determination result of the state of the combine harvester 620 is output as a result obtained by the human brain. The neural network of this embodiment uses a neural network that has been learned in advance so that the state of the combine harvester 620 can be appropriately determined.

[0408] Specifically, in the present embodiment, the neural network may use the following neural network: when the information related to the ground operation in the prescribed state of the combine harvester 620 is input as the teacher data, the learning is performed in a manner of outputting the determination result of the degree of abnormality (abnormality) of the combine harvester 620 matching the prescribed state and the determination result of the maintenance time. That is, before the second information is input into the neural network, a label is provided in advance, for example, for the information related to the ground operation of the combine harvester 620 with the prescribed abnormality, and a label is provided for the information related to the ground operation of the combine harvester 620 that is not abnormal, and the characteristics of the abnormality of each label are learned. Thus, when the second information is provided, it is possible to easily determine whether the combine harvester 620 is abnormal. In addition, the learning can also be performed continuously in the combine harvester 620.

[0409] In addition, the determination of the maintenance time is also carried out in advance, for example, by providing a label to information related to ground work of the combine harvester 620 that has enough time until maintenance, providing a label to information related to ground work of the combine harvester 620 that should be maintained, and learning the characteristics of the maintenance time of each label. Thus, when the second information is provided, the maintenance time of the combine harvester 620 can be easily determined.

[0410] In other words, the judgment unit 673 can input the first information and the second information into the neural network, and the neural network is a neural network that performs the following learning: when information related to ground operations when the combine harvester 620 is abnormal is input as teacher data, the learning output is a judgment result that the combine harvester 620 is abnormal; and when information related to ground operations when the combine harvester 620 needs maintenance is input as teacher data, the learning output is a judgment result of the maintenance time of the combine harvester 620.

[0411] The reporting unit 674 reports the determination result of the determination unit 673. The determination result is transmitted from the determination unit 673 to the reporting unit 674. The reporting unit 674 may be configured, for example, to be provided with a display device in the combine harvester 620, and to display the determination result of the determination unit 673 on the display device. Thus, the operator can understand the state of the combine harvester 620 and can take appropriate measures.

[0412] The storage unit 675 continuously stores the determination result of the determination unit 673. The determination result of the determination unit 673 is stored in the storage unit 675 of the management system 700, so that the operator can effectively use it by referring to it when analyzing the state of the combine harvester 620, for example. Of course, it can be configured so that the determination result stored in the storage unit 675 is deleted if a predetermined time has passed since the storage.

[0413] In the above embodiment, the working vehicle is described by taking a full-feed combine harvester as an example, but it may also be a half-feed combine harvester. In addition, the working vehicle may be a rice transplanter or a tractor. In addition, it may also be other agricultural machinery or a construction machine.

[0414] In the above-mentioned embodiment, it is described that the first information includes information related to the work object in the completed ground operation and information related to the combine harvester 620 when performing the ground operation, and the second information includes information related to the work object in the ground operation currently being performed, but it can also be constructed so that the first information and the second information respectively include information other than the above-mentioned information.

[0415] In the above-mentioned embodiment, it is described that the determination unit 673 determines whether the combine harvester 620 is abnormal and determines the maintenance time of the combine harvester 620, but the determination unit 673 can also be configured to perform either the determination of whether the combine harvester 620 is abnormal or the determination of the maintenance time of the combine harvester 620, and can also be configured to perform a determination different from the above.

[0416] In the above embodiment, the management system 700 is described as including the reporting unit 674 and the storage unit 675 , but the management system 700 may be configured not to include both the reporting unit 674 and the storage unit 675 , or may be configured to include only one of them.

[0417] In the above-mentioned embodiment, it is described that the state of the combine harvester 620 is determined by inputting the first information and the second information into the neural network, and the neural network is a neural network that has learned to determine the state of the combine harvester 620 based on the first information and information related to specified ground operations, but it can also be configured to determine the state of the combine harvester 620 without using a neural network.

[0418] In the above-mentioned embodiment, it is described that the determination unit 673 can input the first information and the second information into the neural network, and the neural network is a neural network that performs the following learning: when the information related to the ground operation when the combine harvester 620 is abnormal is input as the teacher data, the learning of outputting the determination result that the combine harvester 620 is abnormal; and when the information related to the ground operation when the combine harvester 620 needs maintenance is input as the teacher data, the learning of outputting the determination result of the maintenance time of the combine harvester 620; but it can be either the learning of outputting the determination result that the combine harvester 620 is abnormal or the learning of outputting the determination result of the maintenance time of the combine harvester 620.

[0419] In the above embodiment, the management system is described, but the processing performed by each functional unit in the above embodiment can also be constituted as a management method. In this case, the management method is a management method for managing a work vehicle that performs ground work on a predetermined work object, wherein the management method comprises: a first information acquisition step, which acquires first information related to the ground work stored when the ground work was performed in the past; a second information acquisition step, which acquires second information related to the ground work currently being performed; and a determination step, which compares the first information with the second information to determine the state of the work vehicle.

[0420] In addition, each functional unit in the above-mentioned embodiment can also be configured as a management program. In this case, the management program is a management program executed by a computer for managing a work vehicle that performs ground work on a predetermined work object, wherein the computer is caused to execute the following functions: a first information acquisition function that acquires first information related to the ground work stored when the ground work was performed in the past; a second information acquisition function that acquires second information related to the ground work currently being performed; and a determination function that compares the first information with the second information to determine the state of the work vehicle.

[0421] Furthermore, such a management program may be configured to be recorded on a recording medium.

[0422] In addition, it can also be configured as a management method for managing a work vehicle that performs ground work on a predetermined work object, wherein the management method comprises: a first information acquisition step, which acquires first information related to the ground work stored during the past ground work; a second information acquisition step, which acquires second information related to the ground work currently being performed; and a judgment step, which compares the first information with the second information to determine the state of the work vehicle; the judgment step is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least any one of the following learning: when the information related to the ground work when the work vehicle is abnormal is input as teacher data, the learning of outputting the judgment result that the work vehicle is abnormal; and when the information related to the ground work when the work vehicle needs maintenance is input as teacher data, the learning of outputting the judgment result of the maintenance time of the work vehicle.

[0423] Moreover, it can also be constructed as a management program that is executed by a computer and manages a work vehicle that performs ground work on a predetermined work object, wherein the management program has: a first information acquisition function, which acquires first information related to the ground work stored when the ground work was performed in the past; a second information acquisition function, which acquires second information related to the ground work currently being performed; and a judgment function, which compares the first information with the second information to determine the state of the work vehicle; the judgment function is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least any one of the following learning: when the information related to the ground work when the work vehicle is abnormal is input as teacher data, the learning of outputting the judgment result that the work vehicle is abnormal; and when the information related to the ground work when the work vehicle needs maintenance is input as teacher data, the learning of outputting the judgment result of the maintenance time of the work vehicle.

[0424] Furthermore, such a management program may be configured to be recorded on a recording medium.

[0425] Industrial Applicability

[0426] The present invention can be applied to a technology for managing the state of a threshing device that performs threshing processing.

[0427] In addition, the present invention can be applied to a harvester management system used for a harvester that harvests crops, a harvester having such a harvester management system, and a technology used for such a harvester.

[0428] Furthermore, the present invention can be applied to a technique for performing ground work on a predetermined work object.

[0429] Description of Reference Numerals

[0430] [First embodiment]

[0431] 1: Threshing device

[0432] 21: Threshing room

[0433] 22: Threshing cylinder

[0434] 25: Winnowing machine

[0435] 33: Screen box

[0436] 38A: Husk sieve

[0437] 39: Second Screen

[0438] 40: Lower sieve

[0439] 41: Threshing cylinder

[0440] 42: Sorting Department

[0441] 53a: Dust delivery valve

[0442] 7: Threshing status management unit

[0443] 71: Pre-processing unit

[0444] 72: State Detection Neural Network

[0445] 72A: First State Detection Neural Network

[0446] 72B: Second state detection neural network

[0447] 73: Parameter determination unit

[0448] 80: Photography Department

[0449] 81: Camera

[0450] 100: Control device

[0451] CU: Cutting Control Unit

[0452] D1: Driving action equipment

[0453] D3: Threshing action equipment

[0454] RU: Driving Control Unit

[0455] S1: Driving status sensor

[0456] S2: Threshing status sensor

[0457] TU: Threshing Control Unit

[0458] T1: Husk opening control unit

[0459] T2: Wind control unit of air separator

[0460] T3: Valve angle control unit

[0461] [Second embodiment]

[0462] 201: Threshing device

[0463] 204: Harvesting Department

[0464] 212: Grain box (storage unit)

[0465] 221: Threshing Room

[0466] 222: Threshing cylinder

[0467] 224: Screen Box

[0468] 240: Lower Screen

[0469] 241: Threshing cylinder

[0470] 242: Sorting Department

[0471] 243: Swing sorting mechanism

[0472] 253a: Dust delivery valve

[0473] 207: Threshing loss management unit

[0474] 271: Pre-processing unit

[0475] 272: Loss Neural Network

[0476] 272A: First Loss Neural Network

[0477] 272B: Second Loss Neural Network

[0478] 272C: Third Loss Neural Network

[0479] 273: Loss rate calculation department

[0480] 274: Parameter determination unit

[0481] 280: Photography unit (detection unit)

[0482] 281: First Camera

[0483] 282: Second Camera

[0484] 283: Third Camera

[0485] 300: Control device

[0486] 200CU: Cutting control unit

[0487] 200M1: Receipt measurement device

[0488] [Third embodiment]

[0489] 401: Threshing device (equipment)

[0490] 420: Combine harvester (working vehicle)

[0491] 471: First Information Acquisition Department

[0492] 472: Second information acquisition unit

[0493] 473: Equipment setting value estimation unit

[0494] 474: Setting value indication unit

[0495] [Fourth embodiment]

[0496] 620: Combine harvester (working vehicle)

[0497] 671: First Information Acquisition Department

[0498] 672: Second information acquisition unit

[0499] 673: Judgment Department

[0500] 674: Reporting Department

[0501] 675: Storage

[0502] 700: Management System

Claims

1. A threshing state management system for managing the state of a threshing device that threshes harvested grain stalks while traveling, wherein: have: a photographing unit for photographing the threshed material of the threshing device; a state detection neural network that outputs a threshing processing state of the threshing device based on image input data generated from the captured image from the capturing unit; a parameter determination unit that determines a control parameter of the threshing device based on the threshing process state; as well as A threshing control unit controls the threshing device based on the control parameters.

2. The threshing state management system according to claim 1, wherein: The threshing state management system is provided with a driving state sensor for detecting the driving state. A state representing the driving state generated based on the detection signal from the driving state sensor is input into the data input state detection neural network.

3. The threshing state management system according to claim 1 or 2, wherein: The state detection neural network performs learning using, as learning data, a learning image captured during the threshing process and an estimated threshing process state estimated from the learning image.

4. The threshing state management system according to any one of claims 1 to 3, wherein: The parameter determination unit is a control neural network configured to receive a feature vector indicating the threshing process state as input and output the control parameter.

5. The threshing state management system according to any one of claims 1 to 4, wherein: The photographing unit includes a plurality of cameras each having a different photographing field of view, and one state detection neural network corresponds to the plurality of cameras. All of the image input data corresponding to the captured images from the plurality of cameras are input to the state detection neural network.

6. The threshing state management system according to any one of claims 1 to 4, wherein: The photographing unit includes a plurality of cameras each having a different photographing field of view, and a plurality of the state detection neural networks are provided in a manner corresponding to the plurality of cameras, respectively. Respective image input data corresponding to the captured images from the plurality of cameras are input to the state detection neural network corresponding to the cameras as the capturing sources, and the threshing process states outputted from the respective ones are provided to the parameter determination unit.

7. A threshing state management method for managing the state of a threshing device that threshes harvested grain stalks while traveling, wherein: have: A photographing step, which uses a photographing unit to photograph the threshed material of the threshing device; a threshing process state outputting step of outputting the threshing process state of the threshing device based on image input data generated from the captured image from the capturing unit using a state detection neural network; a parameter determination step, which determines the control parameters of the threshing device based on the threshing process state; as well as A control step is performed to control the threshing device based on the control parameters using a threshing control unit.

8. A threshing state management program for managing the state of a threshing device that threshes harvested grain stalks while traveling, wherein: Enables the computer to perform the following functions: A photographing function, which uses a photographing unit to photograph the threshed material of the threshing device; a threshing process state output function for outputting the threshing process state of the threshing device based on image input data generated from the captured image from the capturing unit using a state detection neural network; a parameter determination function, which determines the control parameters of the threshing device based on the threshing process state; as well as A control function controls the threshing device based on the control parameters using a threshing control unit.

9. A recording medium having a threshing state management program recorded thereon, the threshing state management program for managing the state of a threshing device that threshes harvested grain stalks while traveling, wherein: The threshing state management program enables the computer to perform the following functions: A photographing function, which uses a photographing unit to photograph the threshed material of the threshing device; a threshing process state output function for outputting the threshing process state of the threshing device based on image input data generated from the captured image from the capturing unit using a state detection neural network; a parameter determination function, which determines the control parameters of the threshing device based on the threshing process state; as well as A control function controls the threshing device based on the control parameters using a threshing control unit.

10. A harvester management system for managing the loss of harvested products of a harvester, wherein the harvester comprises a harvesting unit for harvesting crops in a field and a storage unit for storing the harvested products harvested by the harvesting unit, wherein: The harvester management system has: A yield measuring unit, which measures the yield of the harvest; a loss amount calculation unit for calculating a loss amount indicating an amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section; as well as A loss rate calculation unit calculates a loss rate based on the harvest amount and the loss amount, wherein the loss rate is the loss amount per unit harvest amount.

11. The harvester management system according to claim 10, wherein: A detection unit for detecting the loss is provided in a loss area where the loss occurs, The loss amount calculation unit is configured to output the loss amount based on the detection result from the detection unit.

12. The harvester management system according to claim 11, wherein: The detection unit includes a photographing unit for photographing a loss area where the loss occurs. The loss amount calculation unit is configured as a neural network that outputs the loss amount based on image input data generated from the captured image from the imaging unit.

13. The harvester management system according to claim 12, wherein: The neural network performs learning using learning image input data generated based on learning images captured during the harvesting operation of the harvester and an estimated loss amount actually estimated based on the learning images as learning data.

14. The harvester management system according to claim 12 or 13, wherein: The photographing unit includes a plurality of cameras each having a different photographing field of view, and a plurality of the neural networks are provided in a manner corresponding to the plurality of cameras, respectively. Each of the image input data corresponding to the captured images from the plurality of cameras is input to each of the neural networks corresponding to the camera as a capturing source.

15. The harvester management system according to claim 12 or 13, wherein: The photographing unit includes a plurality of cameras each having a different photographing field of view, and one of the neural networks corresponds to the plurality of cameras. All of the image input data corresponding to the captured images from the plurality of cameras are input to the neural network.

16. The harvester management system according to any one of claims 10 to 15, wherein: The harvester is provided with a threshing device for threshing the harvested material. The yield measuring unit measures the amount of grains obtained from the harvest, that is, the yield as the yield. The loss amount calculation unit calculates an amount of threshing loss in the threshing device as the loss amount.

17. The harvester management system according to claim 16, wherein: The loss area where the loss occurs includes the threshing drum terminal end area and the screen box rear end area of ​​the threshing device.

18. The harvester management system according to claim 16 or 17, wherein: The loss region where the loss occurs includes a discharge portion region that discharges non-grain materials other than grains from the threshing device.

19. The harvester management system according to any one of claims 10 to 18, wherein: The harvester management system includes a parameter determination unit that determines a control parameter of the harvester based on the loss amount.

20. A harvester, wherein: have: The harvesting department harvests the crops in the fields; a storage unit for storing the harvested material harvested by the harvesting unit; A yield measuring unit, which measures the yield of the harvest; a loss amount calculation unit for calculating a loss amount indicating an amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section; as well as A loss rate calculation unit calculates a loss rate based on the harvest amount and the loss amount, wherein the loss rate is the loss amount per unit harvest amount.

21. The harvester of claim 20, wherein: have: Travel device; a conveying device for conveying the harvest; and A threshing device, which performs threshing on the harvest; The harvester includes a parameter determination unit that determines a control parameter of at least one of the travel device, the harvesting unit, the conveying device, and the threshing device based on the loss rate.

22. A harvester management method, wherein: A harvester having a harvesting section for harvesting crops in a field and a storage section for storing the harvested products harvested by the harvesting section is used to measure the harvest amount of the harvested products while performing harvesting operations using the harvester. Furthermore, while the harvesting operation is performed using the harvester, a loss amount is calculated, the loss amount indicating the amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section. Furthermore, while the harvesting operation is performed using the harvester, a loss rate is calculated based on the harvested amount and the loss amount, and the loss rate is the loss amount per unit harvested amount.

23. The harvester management method according to claim 22, wherein: While the harvesting operation is being performed using the harvester, control parameters of the harvester are determined based on the loss rate.

24. A harvester management program, wherein: Enables the computer to perform the following functions: A measuring function for measuring the harvest amount of the harvested crops while performing a harvesting operation using a harvester having a harvesting section for harvesting crops in a field and a storage section for storing the harvested crops harvested by the harvesting section; a loss amount calculation function for calculating a loss amount while performing the harvesting operation using the harvester, the loss amount indicating an amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section; and A loss rate calculation function calculates a loss rate based on the harvested amount and the loss amount while performing the harvesting operation using the harvester, wherein the loss rate is the loss amount per unit harvested amount.

25. A recording medium having a harvester management program recorded thereon, wherein: The harvester management program enables the computer to perform the following functions: A measuring function for measuring the harvest amount of the harvested crops while performing a harvesting operation using a harvester having a harvesting section for harvesting crops in a field and a storage section for storing the harvested crops harvested by the harvesting section; a loss amount calculation function for calculating a loss amount while performing the harvesting operation using the harvester, the loss amount indicating an amount of loss generated during the period when the harvested material is transported from the harvesting section to the storage section; and A loss rate calculation function calculates a loss rate based on the harvested amount and the loss amount while performing the harvesting operation using the harvester, wherein the loss rate is the loss amount per unit harvested amount.

26. A working vehicle for performing ground work on a predetermined working object, wherein: have: a first information acquisition unit that acquires first information including an operation condition of the operation object in the ground operation performed in the past, a device setting value for setting a capability of a device used in the past ground operation, and an operation result of the ground operation performed in the past ground operation; A second information acquisition unit, which acquires second information, the second information including an operation condition of the operation object in the ground operation to be performed next; as well as A device setting value estimating unit estimates the device setting value of the device used in the ground work to be performed next based on the first information and the second information.

27. The work vehicle according to claim 26, wherein: The work vehicle includes a setting value instruction unit for applying the estimated device setting value to the device when the ground work is next performed, The setting value instruction unit applies the device setting value when the work site where the past ground work was performed is the same as the work site where the ground work is to be performed next.

28. The work vehicle according to claim 26 or 27, wherein: The device setting value estimating unit continuously estimates the device setting value during the execution of the ground work.

29. The work vehicle according to any one of claims 26 to 28, wherein: The device setting value estimation unit automatically estimates the device setting value as the ground work is performed.

30. The work vehicle according to any one of claims 26 to 29, wherein: The working conditions of the working object include position information indicating the position of the working place where the ground working is performed.

31. The work vehicle according to any one of claims 26 to 30, wherein: The field operation is a threshing operation for threshing the harvested grain stalks harvested in the field. The equipment setting value is a control parameter of a threshing device that performs the threshing process.

32. The work vehicle according to any one of claims 26 to 31, wherein: The estimation of the equipment setting value of the equipment used in the ground operation to be performed next is carried out by inputting the first information and the second information into a neural network, and the neural network is a learning neural network that estimates the equipment setting value based on the first information and the specified working conditions.

33. A method for managing a work vehicle, for managing a work vehicle that performs ground work on a predetermined work object, wherein: have: A first information acquisition step of acquiring first information including an operation condition of the operation object in the ground operation performed in the past, a device setting value for setting the capability of the device used in the past ground operation, and an operation result of the ground operation performed in the past ground operation; A second information acquisition step, which acquires second information, the second information including the operation conditions of the operation object in the ground operation to be performed next; as well as The device setting value estimating step is to estimate the device setting value of the device used in the ground work to be performed next based on the first information and the second information.

34. A work vehicle management system, which manages work vehicles that perform ground operations on pre-defined work objects, wherein: have: a first information acquisition unit that acquires first information including an operation condition of the operation object in the ground operation performed in the past, a device setting value for setting a capability of a device used in the past ground operation, and an operation result of the ground operation performed in the past ground operation; A second information acquisition unit, which acquires second information, the second information including an operation condition of the operation object in the ground operation to be performed next; as well as A device setting value estimating unit estimates the device setting value of the device used in the ground work to be performed next based on the first information and the second information.

35. A work vehicle management program for managing work vehicles that perform ground work on a predetermined work object and executed by a computer, wherein: Enables the computer to perform the following functions: a first information acquisition function for acquiring first information including an operation condition of the operation object in the ground operation performed in the past, a device setting value for setting the capability of the device used in the past ground operation, and an operation result of the ground operation performed in the past ground operation; A second information acquisition function, which acquires second information, the second information including the operation conditions of the operation object in the ground operation to be performed next; as well as An equipment setting value estimation function estimates the equipment setting value of the equipment used in the ground work to be performed next based on the first information and the second information.

36. A recording medium having a work vehicle management program recorded thereon, the work vehicle management program managing a work vehicle that performs ground work on a predetermined work object and being executed by a computer, wherein: The work vehicle management program enables the computer to perform the following functions: a first information acquisition function for acquiring first information including an operation condition of the operation object in the ground operation performed in the past, a device setting value for setting the capability of the device used in the past ground operation, and an operation result of the ground operation performed in the past ground operation; A second information acquisition function, which acquires second information, the second information including the operation conditions of the operation object in the ground operation to be performed next; as well as An equipment setting value estimation function estimates the equipment setting value of the equipment used in the ground work to be performed next based on the first information and the second information.

37. A management system for managing a vehicle that performs ground operations on a predetermined operation object, wherein: have: a first information acquisition unit that acquires first information related to the ground operation that is stored when the ground operation was performed in the past; A second information acquisition unit, which acquires second information related to the ground operation currently being performed; as well as A determination unit compares the first information with the second information to determine a state of the work vehicle.

38. The management system of claim 37, wherein: The first information includes information related to the work object in the completed ground work and information related to the work vehicle when performing the ground work. The second information includes information related to the work object in the ground work currently being performed.

39. A management system according to claim 37 or 38, wherein: The determination unit determines whether the work vehicle is abnormal as the state of the work vehicle.

40. A management system as claimed in any one of claims 37 to 39, wherein: The determination unit determines a maintenance time of the work vehicle as a state of the work vehicle.

41. A management system as claimed in any one of claims 37 to 40, wherein: The management system includes a reporting unit that reports a determination result of the determination unit.

42. A management system as claimed in any one of claims 37 to 41, wherein: The management system includes a storage unit that continuously stores a determination result of the determination unit.

43. A management system as claimed in any one of claims 37 to 42, wherein: The state of the work vehicle is determined by inputting the first information and the second information into a neural network that has learned to determine the state of the work vehicle based on the first information and information related to the prescribed ground work.

44. A management system for managing a vehicle that performs ground operations on a predetermined operation object, wherein: have: a first information acquisition unit that acquires first information related to the ground operation that is stored when the ground operation was performed in the past; A second information acquisition unit, which acquires second information related to the ground operation currently being performed; as well as a determination unit that compares the first information with the second information to determine a state of the work vehicle; The determination unit is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least one of the following learnings: when information related to the ground work when the work vehicle is abnormal is input as teacher data, learning to output a determination result that the work vehicle is abnormal; And when information related to the ground work when the work vehicle needs maintenance is input as teacher data, learning is outputted for determining the maintenance time of the work vehicle.

45. A management method for managing a work vehicle that performs ground work on a predetermined work object, wherein: have: A first information acquisition step of acquiring first information related to the ground operation stored when the ground operation was performed in the past; A second information acquisition step, which acquires second information related to the ground operation currently being performed; as well as A determination step of comparing the first information with the second information to determine the state of the work vehicle.

46. ​​A management program for managing a work vehicle that performs ground work on a predetermined work object and executed by a computer, wherein: Enables the computer to perform the following functions: A first information acquisition function for acquiring first information related to the ground operation stored when the ground operation was performed in the past; A second information acquisition function, which acquires second information related to the ground operation currently being implemented; as well as A determination function compares the first information with the second information to determine the state of the work vehicle.

47. A recording medium having a management program recorded thereon, the management program managing a work vehicle that performs ground work on a predetermined work object and executed by a computer, wherein: The management program enables the computer to perform the following functions: A first information acquisition function for acquiring first information related to the ground operation stored when the ground operation was performed in the past; A second information acquisition function, which acquires second information related to the ground operation currently being implemented; as well as A determination function compares the first information with the second information to determine the state of the work vehicle.

48. A management method for managing a vehicle that performs ground operations on a predetermined operation object, wherein: have: A first information acquisition step of acquiring first information related to the ground operation stored when the ground operation was performed in the past; A second information acquisition step, which acquires second information related to the ground operation currently being performed; as well as a determination step of comparing the first information with the second information to determine the state of the work vehicle; The determination step is performed by inputting the first information and the second information into a neural network, the neural network being a neural network that performs at least one of the following learnings: when information related to the ground work when the work vehicle is abnormal is input as teacher data, learning to output a determination result that the work vehicle is abnormal; And when information related to the ground work when the work vehicle needs maintenance is input as teacher data, learning is outputted for determining the maintenance time of the work vehicle.

49. A management program for managing a work vehicle that performs ground work on a predetermined work object and executed by a computer, wherein: have: A first information acquisition function for acquiring first information related to the ground operation stored when the ground operation was performed in the past; A second information acquisition function, which acquires second information related to the ground operation currently being implemented; as well as a determination function that compares the first information with the second information to determine the state of the work vehicle; The determination function is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least one of the following learnings: when information related to the ground work when the work vehicle is abnormal is input as teacher data, learning to output a determination result that the work vehicle is abnormal; And when information related to the ground work when the work vehicle needs maintenance is input as teacher data, learning is outputted for determining the maintenance time of the work vehicle.

50. A recording medium having a management program recorded thereon, the management program managing a work vehicle that performs ground work on a predetermined work object and executed by a computer, wherein: The management program has: A first information acquisition function for acquiring first information related to the ground operation stored when the ground operation was performed in the past; A second information acquisition function, which acquires second information related to the ground operation currently being implemented; as well as a determination function that compares the first information with the second information to determine the state of the work vehicle; The determination function is performed by inputting the first information and the second information into a neural network, and the neural network is a neural network that performs at least one of the following learnings: when information related to the ground work when the work vehicle is abnormal is input as teacher data, learning to output a determination result that the work vehicle is abnormal; And when information related to the ground work when the work vehicle needs maintenance is input as teacher data, learning is outputted for determining the maintenance time of the work vehicle.

Images