Combine harvester speed control method and control system

Abstract

The present invention relates to a speed control method and control system for a combine harvester, and belongs to the technical field of intelligent agricultural equipment. The speed control method for a combine harvester includes: obtaining phenotypic characteristics of crops and the operating speed and cutting width of a harvester; inputting the phenotypic characteristics, the operating speed and the operating cutting width into a feed amount prediction model to output a feed amount prediction value; calculating a first speed control value according to the feed amount prediction value and the feed amount rated value to adjust the speed of the harvester to a first speed; obtaining the mechanical characteristics of the harvester after the crops enter the harvester; inputting the phenotypic characteristics and the mechanical characteristics into a feed amount detection model to output a feed amount precise value; the feed amount detection model is a multimodal detection model obtained through data pre-training; calculating a second speed control value through a speed fine-tuning model according to the feed amount precise value and the feed amount rated value to adjust the speed of the harvester to a second speed.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent agricultural equipment, and in particular relates to a speed control method and a control system for a combine harvester. Background Art

[0002] It is imperative to develop agricultural production machinery with intelligence and modernization as the main body. As one of the most important agricultural harvesting machinery, the development level of intelligent technology of combine harvesters largely reflects the degree of agricultural modernization and agricultural mechanization development in a country. The intelligent control of the speed of combine harvesters can significantly improve the operating efficiency of harvesters and reduce labor intensity. The harvesting speed of most existing combine harvesters is still subjectively controlled by the driver according to the feed amount. Inexperienced drivers have difficulty in perceiving the overall load of the machine, which is prone to overload and underload conditions, resulting in low harvesting efficiency.

[0003] Accurate detection of feed volume is a key indicator parameter for achieving operation speed control. Feed volume refers to the amount of crops processed by the combine harvester per unit time. It is affected by many factors during actual field operations. During operation, operating parameters need to be adjusted in real time to ensure the optimal feed volume.

[0004] There are two main types of existing research methods for the feed amount of combine harvesters: mechanical detection methods, which detect relevant mechanical parameters based on sensors installed in different positions and fit the feed amount through regression models; visual detection methods, which use images to identify the phenotypic characteristics of crops to be harvested online and then predict the feed amount. This method is predictive, but most of the existing image detection methods use cameras to identify the pixel values ​​of the ear layer of crops to be harvested per unit area to fit the feeding density at the next moment; there are technical problems such as hysteresis and low accuracy. Summary of the invention

[0005] In view of the above analysis, an embodiment of the present invention aims to provide a combine harvester speed control method and control system to solve one or more of the above problems existing in the prior art.

[0006] The object of the present invention is achieved in that:

[0007] A first aspect of the present invention provides a combine harvester speed control method, comprising:

[0008] Before the crops to be harvested enter the harvester, the phenotypic characteristics of the crops and the operating speed and cutting width of the harvester are obtained;

[0009] The phenotypic characteristics, the operating speed and the operating cutting width are input into a feed quantity prediction model to output a feed quantity prediction value at the next moment;

[0010] Calculating a first speed control value according to the feed amount prediction value and the feed amount rated value to adjust the speed of the harvester to a first speed;

[0011] After the harvested crops enter the harvester, the mechanical characteristics of the harvester are obtained;

[0012] Input the phenotypic characteristics and the mechanical characteristics into a multimodal feeding amount detection model to output an accurate value of the feeding amount;

[0013] A second speed control value is calculated according to the precise value of the feed amount and the rated value of the feed amount to adjust the speed of the harvester to the second speed.

[0014] Furthermore, the phenotypic characteristics of crops are obtained, including: collecting phenotypic images of crops through a depth camera; inputting the phenotypic images into a maturity detection model to detect the maturity stage of the crops; the maturity stage includes milky stage, waxy stage, fully mature stage and dry mature stage; and determining the moisture content of the crops according to the maturity stage of the crops and the current moment.

[0015] Furthermore, obtaining the phenotypic characteristics of crops also includes: inputting the phenotypic image into a lodging detection model to detect whether the crops have lodged; if the crops have lodged, determining the density of the lodged crops according to the lodging type and lodging degree of the crops; the lodging types include root lodging, stem lodging and stem breakage; the lodging degree includes mild lodging, moderate lodging and severe lodging; the density of the lodged crops is obtained by arranging and combining the lodging types and the lodging degrees.

[0016] Furthermore, if the crops have not lodged, the phenotypic image is input into a density detection model to detect the density of the crops that have not lodged; the density of the crops that have not lodged includes four levels: low density, medium density, high density and extra-high density.

[0017] Furthermore, obtaining the phenotypic characteristics of the crop also includes: collecting point cloud information of the crop through a depth camera; and inputting the point cloud information into a height detection model to detect the plant height.

[0018] Furthermore, the mechanical characteristics include torque, rotation speed, pressure and vibration acceleration.

[0019] Furthermore, the mechanical characteristics of the harvester are obtained, including: detecting the torque of the feeding auger driving shaft and the conveying bridge driving shaft of the harvester through a torque sensor; detecting the rotation speed of the feeding auger driving shaft and the conveying bridge driving shaft through a speed sensor; detecting the pressure of the bottom plate of the conveying bridge through a pressure sensor; and detecting the vibration acceleration of the conveying bridge through a three-axis gyroscope.

[0020] Furthermore, if the crop falls over, the predicted value of the feeding amount is expressed as:

[0021] Qpre =a1·W·L·V·H·S+a2

[0022] If the crop does not fall over, the predicted value of the feeding amount is expressed as:

[0023] Q pre =a3·W·D·V·H·S+a4

[0024] Among them, Q pre represents the predicted value of feeding amount, a1, a2, a3 and a4 represent polynomial coefficients respectively, W represents moisture content, L represents density of fallen crops, D represents density of non-lodged crops, V represents operating speed, H represents plant height, and S represents operating cutting width.

[0025] Furthermore, the inputs of the feed amount detection model are moisture content, density of fallen crops or density of non-fallen crops, plant height, torque of the feeding auger driving shaft, speed of the feeding auger driving shaft, torque of the conveying bridge driving shaft, speed of the conveying bridge driving shaft, pressure of the conveying bridge driving shaft and vibration acceleration of the conveying bridge driving shaft, and the output is the precise value of the feed amount.

[0026] A second aspect of the present invention provides a combine harvester speed control system, comprising:

[0027] The first acquisition module is used to acquire the phenotypic characteristics of the crop and the operating speed and cutting width of the harvester;

[0028] A feed amount prediction module, used for inputting the phenotypic characteristics, the operating speed and the operating cutting width into a feed amount prediction model to output a feed amount prediction value;

[0029] A first speed adjustment module, used for calculating a first speed control value according to the feed amount prediction value and the feed amount rated value, so as to adjust the speed of the harvester to a first speed;

[0030] The second acquisition module is used to acquire the mechanical characteristics of the harvester after the crops enter the harvester;

[0031] A feeding amount detection module is used to input the phenotypic characteristics and the mechanical characteristics into a feeding amount detection model to output an accurate value of the feeding amount; the feeding amount detection model is a multimodal detection model obtained through data pre-training;

[0032] The second speed adjustment module is used to calculate a second speed control value according to the precise value of the feed amount and the rated value of the feed amount, so as to adjust the speed of the harvester to a second speed.

[0033] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0034] The speed control method for a combine harvester provided by the present invention predicts a predicted value of a feed amount through phenotypic characteristics of crops, and pre-regulates the speed of the harvester according to the predicted value of the feed amount. After the crops enter the harvester, the precise value of the feed amount is accurately detected through the phenotypic characteristics and the mechanical characteristics of the harvester, and the speed of the harvester is fine-regulated according to the precise value of the feed amount. By regulating the speed of the harvester in two stages, the feed amount is maintained at an optimal value, the hysteresis of the speed control is eliminated, and the accuracy of the speed control is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this specification. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0036] Figure 1 A flow chart of a combine harvester speed control method provided in Example 1 of the present invention;

[0037] Figure 2 A flow chart of feed amount prediction provided in Example 1 of the present invention;

[0038] Figure 3 A flowchart of pre-training of multiple detection models provided in Example 1 of the present invention;

[0039] Figure 4 A schematic diagram of the installation position of the depth camera provided in Embodiment 1 of the present invention;

[0040] Figure 5 A schematic diagram of the structure of the integrated sensor for the torque and speed of the driving shaft of the feeding auger provided in Example 1 of the present invention;

[0041] Figure 6 A schematic diagram of the structure of a transmission bridge driving shaft torque and speed integrated sensor provided in Example 1 of the present invention;

[0042] Figure 7 A flow chart for detecting the precise value of the feeding amount provided in Example 1 of the present invention;

[0043] Figure 8 A flow chart of speed adaptive control provided in Example 1 of the present invention;

[0044] Fig. 9 A schematic diagram of the working state of the harvester provided in Example 1 of the present invention;

[0045] Fig.10 This is a schematic diagram of a combine harvester speed control system provided in Example 2 of the present invention.

[0046] Reference numerals:

[0047] 1-sprocket drive teeth; 2-first elastic body; 3-first rotor coil; 4-first stator coil; 5-first circuit board protection cover; 6-first Hall speed meter; 7-first magnet mounting seat; 8-shaft locking sleeve; 9-first stator fixing bracket; 10-first torque signal acquisition board; 11-pulley spoke; 12-second elastic body; 13-second stator coil; 14-second rotor coil; 15-second torque signal acquisition circuit board; 16-second circuit board protection cover; 17-second Hall speed meter; 18-second magnet mounting seat; 19-bearing end cover; 20-second stator fixing bracket. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments disclosed in this disclosure can be combined, separated, interchanged and / or rearranged with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] In the accompanying drawings, the size and relative size of components may be exaggerated for clarity and / or descriptive purposes. When the exemplary embodiments may be implemented differently, a specific process sequence may be performed in a different order than described. For example, two successively described processes may be performed substantially simultaneously or in an order opposite to the order described. In addition, the same reference numerals represent the same components.

[0050] Example 1

[0051] A specific embodiment of the present invention, as Figure 1-2 As shown, a combine harvester speed control method is disclosed, comprising the following steps:

[0052] S1. Obtain the phenotypic characteristics of the crop and the operating speed and cutting width of the harvester.

[0053] In this embodiment, the phenotypic characteristics include moisture content, density and plant height.

[0054] Exemplarily, in order to obtain the phenotypic characteristics, first, it is necessary to collect the phenotypic image and point cloud information of the crop through a depth camera, and then obtain the phenotypic characteristics from the phenotypic image and point cloud information, which specifically includes the following steps:

[0055] S101, inputting the phenotypic image into a maturity detection model to detect the maturity stage of the crop; the maturity stage includes milky stage, waxy stage, full maturity stage and dry maturity stage; determining the moisture content of the crop according to the maturity stage of the crop and the current moment.

[0056] Specifically, different maturity stages have different moisture contents W at different times. The moisture content values ​​during the working period, generally from 7 to 21 o'clock, are used to calibrate the moisture content of crops at different maturity stages. Among them, the moisture content at different times in the milky stage is W r7 ,W r8 ,...W r21 The moisture content at different times in the wax maturity stage is W l7 ,W l8 ,...W l21 The moisture content at different times during the maturity stage is W w7 ,W w8 ,...W w21 The moisture content at different times during the dry-ripening period is W k7 ,W k8 ,...W k21 .

[0057] S102, inputting the phenotypic image into a lodging detection model to detect whether the crop has lodged; if the crop has lodged, determining the density of the lodged crop according to the lodging type and lodging degree of the crop; the lodging type includes root lodging, stem lodging and stem breakage; the lodging degree includes mild lodging, moderate lodging and severe lodging; the density of the lodged crop is obtained by arranging and combining the lodging type and the lodging degree; if the crop has not lodged, inputting the phenotypic image into a density detection model to detect the density of the non-lodged crop; the density of the non-lodged crop includes four levels: low density, medium density, high density and extra-high density.

[0058] Specifically, different lodging states correspond to different crop densities. When crop lodging is detected, the density needs to be determined based on the type and degree of lodging of the crop. The type and degree of lodging are obtained by first performing image segmentation and then classification by the lodging detection model. The lodging type includes root lodging, g , stem inverted L j and stem fold L z , the degree of lodging includes mild lodging L l , moderate lodging m and severe lodging h , lodging type and lodging degree are combined to obtain the following 9 lodging states:

[0059] {L g L l ,L g L m ,Lg L h ,L j L l ,L j L m ,L j L h ,L z L l ,L z L m ,L z L h}

[0060] The corresponding densities of lodged crops are:

[0061] {L1,L2,L3,L4,L5,L6,L7,L8,L9}

[0062] When it is detected that the crops have not fallen, the density detection model needs to be used to classify the concentration of the crops that have not fallen according to the crop mass per unit area, including four levels: low density D1∈(0<ρ<0.8), medium density D2∈(0.8≤ρ<1.5), high density D3∈(1.5≤ρ<2.2) and ultra-high density D4∈(ρ≥2.2), where ρ represents the density of the crops per unit area in kg / m 2 .

[0063] Exemplarily, the maturity detection model, the lodging detection model and the density detection model are constructed by the Transformer framework, and all three detection models need to be pre-trained. The specific process of pre-training is as follows:

[0064] like Figure 3 As shown, a data set is collected using a vehicle-mounted depth camera and a drone, and the data set is enhanced to adapt to different harvesting environments. The data set is divided into a training set and a test set, 80% of which is used as a training set and 20% as a test set. The model is trained using the divided training set to obtain a pre-trained model, which is then verified on the test set to obtain an accuracy rate P. When the difference between the accuracy rate P and the true value P′ is less than a preset threshold ε, the training phase is terminated to obtain a detection model that meets the requirements. Otherwise, the model is retrained until the requirements are met.

[0065] S103, collecting point cloud information of crops through a depth camera; inputting the point cloud information into a height detection model to detect plant height.

[0066] Specifically, the working principle of this step is:

[0067] Use a depth camera to scan the target crop to obtain the three-dimensional point cloud data of the crop. The depth camera captures detailed information on the crop surface, including three-dimensional features such as height, width and shape; pre-process the collected point cloud data, including denoising, filtering and segmentation, to ensure the accuracy and validity of the data; input the pre-processed point cloud data into a pre-trained height detection model. The height detection model calculates the height of the crop based on the input point cloud data. The model will identify the distance between the highest point and the lowest point in the point cloud data and output the distance as the plant height.

[0068] For example, Figure 4 It is a schematic diagram of the installation angle of the depth camera. The installation position and angle of the depth camera will directly affect the style of the collected image, the image processing algorithm, and the accuracy of the feed amount prediction. Assuming that the distance between the collected image and the combine harvester itself is x, the principle is to capture the near-field information as much as possible. x is related to the installation position h and the installation depression angle φ of the depth camera. f(x)=[h,φ]. The distance between the captured crop information and the combine harvester under the current viewing angle can be obtained by changing [h,φ]. The present invention determines through experiments that the image acquisition effect is better when h∈[3m,4m],φ=30. When shooting the crop density data set, a small red flag is set every 10m, and the corresponding position of the image is matched by measuring the crop density in the red flag interval.

[0069] It should be noted that the operating speed may be acquired by a GNSS device, and the operating cutting width may be determined by the harvester model or may be set manually, which is not limited in this embodiment.

[0070] S2. Input the phenotypic characteristics, the operating speed and the operating cutting width into a feed quantity prediction model to output a feed quantity prediction value.

[0071] Specifically, when predicting the feed amount at the next moment based on the phenotypic characteristics, operating speed, and operating cutting width at the current moment, it can be divided into the following two situations:

[0072] (I) If the crop falls over, the predicted value of the feeding amount is expressed as:

[0073] Q pre =a1·W·L·V·H·S+a2

[0074] (II) If the crop does not fall over, the predicted value of the feeding amount is expressed as:

[0075] Q pre =a3·W·D·V·H·S+a4

[0076] Among them, Q prerepresents the predicted value of feeding amount, a1, a2, a3 and a4 represent polynomial coefficients respectively, W represents moisture content, L represents density of fallen crops, D represents density of non-lodged crops, V represents operating speed, H represents plant height, and S represents operating cutting width.

[0077] It should be noted that the feed amount prediction model needs to be pre-trained before use, specifically: the moisture content of crops, crop lodging and non-lodging density, and plant height phenotypic characteristics in the test area are collected through a five-point sampling method, and the corresponding operating speed and operating cutting width are obtained to form a data set, and the data set is divided into a training set and a test set; the training set is used to train the feed amount prediction model, and the test set is used for verification until the accuracy of the model is greater than the preset threshold, and the training is stopped to obtain a feed amount prediction model that meets the requirements.

[0078] S3. Calculate a first speed control value according to the feed amount prediction value and the feed amount rated value to adjust the speed of the harvester to a first speed.

[0079] In this embodiment, after the predicted value of the feed amount is obtained in step S2, a first speed control value of the harvester speed is calculated according to the predicted value, and the speed of the harvester is adjusted to the first speed according to the value, which specifically includes the following steps:

[0080] S301, input data, feed amount prediction value Q pre And the feed quantity rated value Q rat Input into the speed pre-regulation model.

[0081] Specifically, the feed rate Q rat Depending on the model of the harvester when it leaves the factory, the speed pre-control model can be a fuzzy adaptive PID control model.

[0082] S302, difference calculation, calculation of feed amount prediction value Q pre And the feed quantity rated value Q rat The first difference between is expressed as follows:

[0083] ΔQ1=Q pre -Q rat

[0084] Among them, ΔQ1 represents the first difference, Q pre Indicates the predicted value of feed quantity, Q rat Indicates the rated value of feed volume.

[0085] S303, calculating the first speed control value through fuzzy adaptive PID control according to the first difference, which is expressed as follows:

[0086]

[0087] Among them, ΔV1 represents the first speed control value, ΔQ1 represents the first difference, K p Represents the proportionality coefficient, K i Indicates the integral coefficient, K d represents the differential coefficient.

[0088] By dynamically adjusting the proportionality factor K p , integral coefficient K i and the differential coefficient K d , to obtain the optimized first speed control value ΔV1.

[0089] S304. Adjust the speed of the harvester to a first speed according to the first speed control value.

[0090] Specifically, if Figure 8 As shown, after obtaining the first speed control value ΔV1 in step S303, the operation speed controller outputs a voltage signal of a new speed according to the first speed control value ΔV1 to adjust the opening of the electromagnetic proportional valve, control the flow of hydraulic oil to the hydraulic motor, and thus realize the pre-control of the harvester speed, which is expressed as follows:

[0091] V1=V0+ΔV1

[0092] Among them, V1 represents the first speed, V0 represents the current operating speed, and ΔV1 represents the first speed control value.

[0093] S4. Acquire mechanical characteristics of the harvester after the crops enter the harvester.

[0094] In this embodiment, the mechanical characteristics include torque, rotation speed, pressure and vibration acceleration.

[0095] The acquisition of mechanical features specifically includes the following steps:

[0096] S401, detecting the torque of the feeding auger driving shaft and the conveying bridge driving shaft of the harvester through a torque sensor.

[0097] S402, detecting the rotation speed of the feeding auger driving shaft and the conveying bridge driving shaft through the rotation speed sensor.

[0098] For example, the torque sensor and the speed sensor may be designed as an integrated unit. Figure 5 The structural schematic diagram of the torque and speed integrated sensor of the feeding auger driving shaft shown in the figure includes a sprocket transmission tooth 1, a first elastic body 2, a first rotor coil 3, a first stator coil 4, a first torque signal acquisition board 10, a first circuit board protection cover 5, a first Hall speed meter 6, a first magnet mounting seat 7, a shaft locking sleeve 8, and a first stator fixing bracket 9.

[0099] The first elastic body 2 of the sprocket structure is fixedly connected to the feeding auger driving shaft through a flat key, the chain drives the sprocket transmission tooth 1 to rotate, thereby driving the driving shaft to rotate, the shaft locking sleeve 8 is used to lock the driving shaft and the first elastic body 2 to prevent relative rotation, resulting in inaccurate torque measurement, the first elastic body 2 senses torsional deformation under the action of the load, the first torque signal acquisition board 10 converts the mechanical deformation into an electrical signal, and performs AD conversion output, because the actual field harvesting environment is complex, the first circuit protection cover 5 is used to protect the first torque signal acquisition board 10; the first rotor coil 3 is located on the first elastic body 2, the first Hall speed meter 6 is rotatably connected to the first rotor coil 3, the first stator coil 4 is kept at a certain distance from the first rotor coil 3 through the bearing, and is fixedly connected to the harvester housing through the first stator fixing bracket 9, the first magnet mounting seat 7 is mounted on the first stator coil 4, and is fixed to the harvester housing together with the first stator coil 4, and the first Hall speed meter 6 calculates the driving shaft speed by detecting the first magnet mounting seat 7 during the rotation process.

[0100] The structural diagram of the torque and speed integrated sensor for the driving shaft of the transmission bridge is as follows: Figure 6 As shown, it includes a pulley spoke 11, a second elastic body 12, a second stator coil 13, a second rotor coil 14, a second torque signal acquisition circuit board 15, a second circuit board protection cover 16, a second Hall speed meter 17, a second magnet mounting seat 18, a bearing end cover 19, and a second stator fixing bracket 20. The second elastic body 12 is fixedly connected to the driving shaft of the conveying bridge through a flat key, the belt drives the pulley spoke 11 to rotate, thereby driving the driving shaft to rotate, the bearing end cover 19 locks the driving shaft and the second elastic body 12 through bolts to prevent relative rotation, resulting in inaccurate torque measurement, the second elastic body 12 senses torsional deformation under the action of the load, the second torque signal acquisition board 15 converts the mechanical deformation into an electrical signal, and performs AD conversion output, because the actual field harvesting environment is complex, the second circuit board protection cover 16 is used to protect the second torque signal acquisition board 15; the second rotor coil 14 is mounted on the second elastic body 12, the second Hall speed meter 17 is rotatably connected to the second rotor coil 14, the second stator coil 13 maintains a certain distance from the second rotor coil 14 through the bearing, and is fixed to the harvester housing structure through the second stator fixing bracket 20, the second magnet mounting seat 18 is mounted on the second stator coil 13, and is fixed to the harvester housing structure together with the second stator coil 13, and the second Hall speed meter 17 calculates the driving shaft speed by detecting the second magnet mounting seat 18 during the rotation process.

[0101] S403, detecting the pressure of the conveying bridge bottom plate through a pressure sensor.

[0102] Specifically, during the conveying operation, the pressure sensor collects pressure data on the base plate in real time, converts the mechanical pressure into an electrical signal, and transmits it to the data acquisition system. The collected pressure data is preprocessed, including filtering, denoising, and calibration operations to ensure the accuracy and reliability of the data. Further analysis is then performed to obtain the pressure value used to predict the feed amount.

[0103] S404, detecting the vibration acceleration of the conveyor bridge by means of a three-axis gyroscope.

[0104] Specifically, during the conveying operation, the three-axis gyroscope is used to collect vibration acceleration data of the conveyor bridge in real time, convert mechanical vibration into electrical signals, and transmit them to the data acquisition system. The collected data is preprocessed, including filtering, denoising and calibration, to ensure the accuracy and reliability of the data. Further analysis is then performed to obtain the vibration acceleration value used to predict the feed amount.

[0105] S5. Using the phenotypic characteristics and the mechanical characteristics to detect the precise value of the feeding amount through a feeding amount detection model.

[0106] Specifically, after the speed of the harvester is adjusted to the first speed in step S3, when the crops to be harvested enter the harvester, the mechanical characteristics of the harvester are obtained in step S4, such as Figure 7 As shown, the phenotypic characteristics of moisture content, the density of lodged crops or the density of non-lodged crops, plant height and mechanical characteristics of the torque of the feeding auger driving shaft, the speed of the feeding auger driving shaft, the torque of the conveying bridge driving shaft, the speed of the conveying bridge driving shaft, the pressure of the conveying bridge driving shaft and the vibration acceleration of the conveying bridge driving shaft are input into the feeding amount detection model to detect the accurate value of the feeding amount, so as to output the accurate value of the feeding amount, which is expressed as follows:

[0107] Q act =f(W,L,H,T aug ,ω aug ,T con ,ω con ,P con ,A con )

[0108] Or, Q act =f(W,D,H,T aug ,ω aug ,T con ,ω con ,P con ,A con )

[0109] Among them, Q actrepresents the exact value of the feeding amount, f(·) represents the feeding amount detection model, W represents the moisture content, L represents the density of the fallen crops, D represents the density of the non-fallen crops, H represents the plant height, T aug Indicates the torque of the feed auger driving shaft, ω aug Indicates the speed of the feeding auger driving shaft, T con Indicates the torque of the driving shaft transmitted across the bridge, ω con Indicates the transmission bridge driving shaft speed, P con Indicates the pressure of the bridge bottom plate, A con Indicates the vibration acceleration of the transmission bridge.

[0110] The feed amount detection model is a multimodal detection model obtained through data pre-training. The specific process is: the phenotypic characteristics of the moisture content, crop lodging and non-lodging density, and plant height of the crops in the test area are collected by a five-point sampling method, and the mechanical characteristics of the feeding auger driving shaft torque, the feeding auger driving shaft speed, the conveying bridge driving shaft torque, the conveying bridge driving shaft speed, the conveying bridge bottom plate pressure and the conveying bridge vibration acceleration are synchronously recorded by using CAN bus technology. The actual value of the feed amount is obtained by a manual material connection method, and the above data is used as a group of associated data sets to obtain more than 50 groups of data sets, and the data sets are divided into training sets and test sets. Then, a multi-sensor decision-level fusion feed amount detection model is established, and the phenotypic characteristics and mechanical characteristics of the training set are used as input, and the precise value of the feed amount is used as output for training, and the test set is used for verification until the accuracy of the model is greater than the preset threshold, and the training is stopped to obtain a feed amount detection model that meets the requirements.

[0111] S6. Calculate a second speed control value according to the precise value of the feed amount and the rated value of the feed amount to adjust the speed of the harvester to a second speed.

[0112] In this embodiment, after the accurate value of the feeding amount is obtained in step S5, Figure 8 As shown, the second speed control value of the harvester speed is calculated according to the precise value, and the speed of the harvester is adjusted to the second speed according to the value, which specifically includes the following steps:

[0113] S601, input data, and set the precise value of feed quantity Q act And the feed quantity rated value Q rat Input speed fine-tuning model.

[0114] Specifically, the feed rate Q rat Depending on the model of the harvester when it leaves the factory, the speed fine-control model can also be a fuzzy adaptive PID control model.

[0115] S602, difference calculation, calculate the exact value of the feeding amount Q act And the feed quantity rated value Q ratThe second difference between is expressed as follows:

[0116] ΔQ2=Q act -Q rat

[0117] Among them, ΔQ2 represents the second difference, Q act Indicates the predicted value of feed quantity, Q rat Indicates the rated value of feed volume.

[0118] S603, calculating the second speed control value through fuzzy adaptive PID control according to the second difference, which is expressed as follows:

[0119]

[0120] Among them, ΔV2 represents the second speed control value, ΔQ2 represents the first difference, K′ p Represents the proportionality coefficient, K i ′ represents the integral coefficient, K d ′ represents the differential coefficient.

[0121] By dynamically adjusting the proportionality factor K′ p , integral coefficient K i ′ and differential coefficient K d ′, to obtain the optimized second speed control value ΔV2.

[0122] S604. Adjust the speed of the harvester to a second speed according to the second speed control value.

[0123] Specifically, after obtaining the second speed control value ΔV2 in step S603, the operating speed controller calculates the voltage signal of the second speed according to the second speed control value ΔV2 and the first speed to fine-tune the opening of the electromagnetic proportional valve and control the flow of hydraulic oil to the hydraulic motor, thereby achieving fine-tuning of the harvester speed, as shown below:

[0124] V2=V1+ΔV2

[0125] Wherein, V2 represents the final speed, V1 represents the new speed after pre-control, and ΔV2 represents the second speed control value.

[0126] Compared with the prior art, the combine harvester speed control method provided in this embodiment predicts the feed amount prediction value through the phenotypic characteristics of the crops, and pre-regulates the speed of the harvester according to the feed amount prediction value. After the crops enter the harvester, the precise value of the feed amount is accurately detected through the phenotypic characteristics and the mechanical characteristics of the harvester, and the speed of the harvester is fine-tuned according to the precise value of the feed amount. By controlling the speed of the harvester in two stages, the feed amount is maintained at the optimal value, the lag of speed control is eliminated, and the accuracy of speed control is ensured.

[0127] Example 2

[0128] This embodiment provides a combine harvester speed control system, such as Figure 7 As shown, including:

[0129] The first acquisition module is used to acquire the phenotypic characteristics of the crop and the operating speed and cutting width of the harvester;

[0130] A feed amount prediction module, used for inputting the phenotypic characteristics, the operating speed and the operating cutting width into a feed amount prediction model to output a feed amount prediction value;

[0131] A first speed adjustment module, used for calculating a first speed control value according to the feed amount prediction value and the feed amount rated value, so as to adjust the speed of the harvester to a first speed;

[0132] The second acquisition module is used to acquire the mechanical characteristics of the harvester after the crops enter the harvester;

[0133] A feeding amount detection module is used to input the phenotypic characteristics and the mechanical characteristics into a feeding amount detection model to output an accurate value of the feeding amount; the feeding amount detection model is a multimodal detection model obtained through data pre-training;

[0134] The second speed adjustment module is used to calculate a second speed control value according to the precise value of the feed amount and the rated value of the feed amount, so as to adjust the speed of the harvester to a second speed.

[0135] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A speed control method for a combine harvester, It is characterized in that include: Acquiring phenotypic characteristics of crops and the operating speed and cutting width of a harvester; the phenotypic characteristics include moisture content, density and plant height; The phenotypic characteristics, the operating speed and the operating cutting width are input into a feed quantity prediction model to output a feed quantity prediction value; Calculating a first speed control value according to the feed amount prediction value and the feed amount rated value to adjust the speed of the harvester to the first speed, including: inputting the feed amount prediction value and the feed amount rated value into a speed pre-control model; calculating a first difference between the feed amount prediction value and the feed amount rated value; calculating a first speed control value according to the first difference through fuzzy adaptive PID control; adjusting the speed of the harvester to the first speed according to the first speed control value; Acquiring mechanical characteristics of the harvester after the crops enter the harvester; the mechanical characteristics include torque, rotation speed, pressure and vibration acceleration; Input the phenotypic characteristics and the mechanical characteristics into a feeding amount detection model to output an accurate value of the feeding amount; The feed amount detection model is a multimodal detection model obtained through data pre-training; The second speed control value is calculated according to the precise value of the feed amount and the rated value of the feed amount to adjust the speed of the harvester to the second speed, including: inputting the precise value of the feed amount and the rated value of the feed amount into the speed fine-control model; calculating the second difference between the precise value of the feed amount and the rated value of the feed amount; calculating the second speed control value through fuzzy adaptive PID control according to the second difference; and adjusting the speed of the harvester to the second speed according to the second speed control value.

2. The combine harvester speed control method according to claim 1, It is characterized in that Obtain phenotypic characteristics of crops, including: Capture crop phenotypic images through depth cameras; Inputting the phenotypic image into a maturity detection model to detect the maturity stage of the crop; The maturity stage includes milky stage, waxy stage, full-ripe stage and dry-ripe stage; Determine the moisture content of the crop based on the crop's maturity stage and the current moment.

3. The combine harvester speed control method according to claim 2, It is characterized in that Obtain phenotypic characteristics of crops, including: Inputting the phenotypic image into a lodging detection model to detect whether the crop has lodging; If crops lodged, the density of the lodged crops was determined according to the type and degree of lodging; The lodging types include root lodging, stem lodging and stem breakage; The degree of lodging includes mild lodging, moderate lodging and severe lodging; The density of the lodging crops is obtained by arranging and combining the lodging types and the lodging degrees.

4. The combine harvester speed control method according to claim 3, It is characterized in that If the crop has not lodged, the phenotypic image is input into a density detection model to detect the density of the crop that has not lodged; The density of the non-lodged crops includes four levels: low density, medium density, high density and extra-high density.

5. The combine harvester speed control method according to claim 4, It is characterized in that Obtain phenotypic characteristics of crops, including: Collect point cloud information of crops through depth cameras; The point cloud information is input into a height detection model to detect the plant height.

6. The combine harvester speed control method according to claim 1, It is characterized in that Get the mechanical characteristics of the harvester, including: The torque of the feeding auger driving shaft and the conveying bridge driving shaft of the harvester is detected by the torque sensor; The speed of the feeding auger driving shaft and the conveying bridge driving shaft is detected by the speed sensor; The pressure of the conveying bridge bottom plate is detected by a pressure sensor; The vibration acceleration of the conveyor bridge is detected by a three-axis gyroscope.

7. The combine harvester speed control method according to claim 4, It is characterized in that If the crop falls over, the predicted value of the feeding amount is expressed as: Q pre =a 1 ·W·L·V·H·S+a 2 If the crop does not fall over, the predicted value of the feeding amount is expressed as: Q pre =a 3 ·W·D·V·H·S+a 4 Among them, Q pre Indicates the predicted value of feed amount, a 1 、a 2 、a 3 and a 4 They represent polynomial coefficients respectively, W represents moisture content, L represents density of fallen crops, D represents density of non-lodged crops, V represents operating speed, H represents plant height, and S represents operating cutting width.

8. The combine harvester speed control method according to claim 6, It is characterized in that The input of the feed amount detection model is moisture content, density of fallen crops or density of non-fallen crops, plant height, torque of the feeding auger driving shaft, speed of the feeding auger driving shaft, torque of the conveying bridge driving shaft, speed of the conveying bridge driving shaft, pressure of the conveying bridge driving shaft and vibration acceleration of the conveying bridge driving shaft, and the output is the precise value of the feed amount.

9. A speed control system for a combine harvester, It is characterized in that include: A first acquisition module is used to acquire phenotypic characteristics of the crop and the operating speed and cutting width of the harvester; the phenotypic characteristics include moisture content, density and plant height; A feed amount prediction module, used for inputting the phenotypic characteristics, the operating speed and the operating cutting width into a feed amount prediction model to output a feed amount prediction value; The first speed adjustment module is used to calculate the first speed control value according to the feed amount prediction value and the feed amount rated value to adjust the speed of the harvester to the first speed, including: inputting the feed amount prediction value and the feed amount rated value into the speed pre-control model; calculating the first difference between the feed amount prediction value and the feed amount rated value; calculating the first speed control value through fuzzy adaptive PID control according to the first difference; adjusting the speed of the harvester to the first speed according to the first speed control value; A second acquisition module is used to acquire mechanical characteristics of the harvester after the crops enter the harvester; the mechanical characteristics include torque, rotation speed, pressure and vibration acceleration; A feeding amount detection module is used to input the phenotypic characteristics and the mechanical characteristics into a feeding amount detection model to output an accurate value of the feeding amount; the feeding amount detection model is a multimodal detection model obtained through data pre-training; The second speed adjustment module is used to calculate the second speed control value according to the precise value of the feed amount and the rated value of the feed amount to adjust the speed of the harvester to the second speed, including: inputting the precise value of the feed amount and the rated value of the feed amount into the speed fine-tuning model; calculating the second difference between the precise value of the feed amount and the rated value of the feed amount; calculating the second speed control value through fuzzy adaptive PID control according to the second difference; and adjusting the speed of the harvester to the second speed according to the second speed control value.

Images