A soybean combined intelligent harvesting device

Abstract

The present invention discloses a soybean combined intelligent harvesting device, which relates to the field of intelligent agricultural machinery. The device comprises: a processing unit for analyzing soybean plant images to obtain soybean plant maturity; a moving unit for carrying corresponding units to move based on control instructions; a harvesting unit for controlling the rotation speed of the harvesting unit and the hardness of harvesting components based on the maturity of the soybean plants to harvest the soybean plants; a threshing unit for threshing the soybean plants; and a cutting unit for cutting stems, leaves, stalks and pods to obtain miscellaneous materials. The device can adjust the rotation speed of the harvesting unit and the hardness of the harvesting components according to the maturity of the soybean plants to adapt to the maturity of the soybean plants and reduce harvesting losses caused by harvesting.

Description

Technical Field

[0001] The present invention relates to the field of intelligent agricultural machinery, and in particular to a soybean combined intelligent harvesting device. Background Art

[0002] A soybean combine harvester is an intelligent soybean harvesting equipment, generally including a harvesting platform located in the front, a conveyor belt, a threshing mechanism, a cutting mechanism, a spreading mechanism, a storage mechanism and a transfer mechanism, such as CN114902863A and CN117426201A; wherein, during operation, the harvester operator drives the harvester in the cab, lowers the harvesting platform to harvest the soybean plants, transfers the harvested soybean plants to the threshing mechanism through the conveyor belt for threshing, stores the threshed soybeans in the storage mechanism, and transfers them to the corresponding transport vehicle through the transfer mechanism after the storage is full.

[0003] The applicant found that the existing soybean combine harvester has the following technical problems:

[0004] The rotation speed of the harvesting table and the hardness of the harvesting parts of the existing soybean combine harvester are constant and cannot be adjusted, which will lead to the following problems: usually, when the soybeans are not too mature, the pods have a certain toughness. During harvesting, the pods will not burst because they still have good toughness. The high-speed rotation of the harvesting table and the collision with the relatively hard harvesting parts will not cause a large number of pods to burst, that is, it will not cause much harvesting loss. However, after the soybeans are too mature or in the late maturity stage, the pods will become brittle. At this time, since the soybeans are harvested by rotating the harvesting table to wrap around and pull up the soybean plants, the harvesting parts of the harvesting table will come into contact with the stems and pods of the soybean plants. When the high-speed rotation of the harvesting table and the relatively hard harvesting parts collide with the relatively brittle pods, more pods will burst, which will cause more harvesting losses.

[0005] Therefore, the existing soybean combine harvester has the technical problem of being unable to adjust the rotation speed of the harvesting platform and the hardness of the harvesting components, which will cause a lot of harvesting losses when harvesting over-mature or late-mature soybeans. Summary of the Invention

[0006] The purpose of the present invention is to provide a soybean combined intelligent harvesting device, which can adjust the rotation speed of its harvesting unit and the hardness of the harvesting components according to the maturity of the soybean plants to adapt to the maturity of the soybean plants and reduce the harvesting losses caused by harvesting.

[0007] To achieve the above-mentioned object of the invention, the present invention provides a soybean combined intelligent harvesting device, the device comprising:

[0008] a processing unit, the processing unit being mounted on the mobile unit and configured to collect images of soybean plants in the area to be harvested and analyze the images of the soybean plants to obtain maturity of the soybean plants;

[0009] A mobile unit, configured to carry a corresponding unit to move based on a control instruction;

[0010] A harvesting unit mounted on the mobile unit and configured to harvest the soybean plants by controlling the rotation speed of the harvesting unit and the hardness of a harvesting component based on the maturity of the soybean plants, wherein the harvesting component is a component configured to contact the soybean plants to achieve harvesting;

[0011] a first transmission unit, the first transmission unit being installed on the moving unit and configured to transmit the soybean plants harvested by the harvesting unit to the threshing unit;

[0012] A threshing unit, mounted on the mobile unit, for threshing soybean plants to obtain soybeans, stems, leaves, stalks and pods;

[0013] a second transport unit, the second transport unit being mounted on the moving unit and configured to transport the threshed soybeans to the storage unit for storage, and to transport the stems, leaves, stalks and pods to the cutting unit;

[0014] The cutting unit is installed on the moving unit and is used for cutting the stems, leaves, stalks and pods to obtain miscellaneous materials.

[0015] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0016] The soybean combined intelligent harvesting device in the present invention can detect the maturity of the soybean plants to be harvested, and then control the rotation speed of the harvesting unit and the hardness of the harvesting parts according to the maturity of the soybean plants to harvest the soybean plants. When facing soybean plants with low or medium maturity, it can be harvested at a normal speed and hardness. When facing soybean plants with high maturity, it can be harvested at a lower rotation speed and hardness, thereby reducing the probability of pods bursting and reducing harvesting losses caused by harvesting. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation of the embodiments of the present invention;

[0018] Figure 1 This is a schematic diagram of the composition of a soybean combined intelligent harvesting device;

[0019] Figure 2 It is a partial structural schematic diagram of the harvesting platform in the present invention;

[0020] Figure 3 This is a schematic diagram of the distribution of harvesting hole groups;

[0021] Figure 4 Schematic diagram of the distribution of the first, second and third plowing claws;

[0022] Figure 5 Schematic diagram of the cross section of a plowing claw;

[0023] Among them, 1-cutting table frame, 2-roller, 3-plowing claw, 4-first harvesting hole, 5-second harvesting hole, 6-third harvesting hole, 7-cavity, 8-first plowing claw, 9-second plowing claw, 10-third plowing claw, 11-plowing claw body, 12-surface layer. DETAILED DESCRIPTION

[0024] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features therein can be combined with each other without conflict.

[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0026] Those skilled in the art should understand that, in the disclosure of the present invention, the terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like to indicate orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the above terms should not be understood as limiting the present invention.

[0027] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the elements may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0028] Embodiment 1;

[0029] Please refer to Figure 1 , Figure 1 The figure is a schematic diagram of the composition of a soybean combined intelligent harvesting device. The present invention provides a soybean combined intelligent harvesting device, which includes:

[0030] a processing unit, the processing unit being mounted on the mobile unit and configured to collect images of soybean plants in the area to be harvested and analyze the images of the soybean plants to obtain maturity of the soybean plants;

[0031] A mobile unit, configured to carry a corresponding unit to move based on a control instruction;

[0032] A harvesting unit mounted on the mobile unit and configured to harvest the soybean plants by controlling the rotation speed of the harvesting unit and the hardness of a harvesting component based on the maturity of the soybean plants, wherein the harvesting component is a component configured to contact the soybean plants to achieve harvesting;

[0033] a first transmission unit, the first transmission unit being installed on the moving unit and configured to transmit the soybean plants harvested by the harvesting unit to the threshing unit;

[0034] A threshing unit, mounted on the mobile unit, for threshing soybean plants to obtain soybeans, stems, leaves, stalks and pods;

[0035] a second transport unit, the second transport unit being mounted on the moving unit and configured to transport the threshed soybeans to the storage unit for storage, and to transport the stems, leaves, stalks and pods to the cutting unit;

[0036] The cutting unit is installed on the moving unit and is used for cutting the stems, leaves, stalks and pods to obtain miscellaneous materials.

[0037] Among them, the soybean combined intelligent harvesting device in the embodiment of the present invention is an improvement on the current soybean combine. For the non-improved parts, reference can be made to the structure and implementation methods in the prior art. The embodiment of the present invention will not make corresponding redundant descriptions, such as the corresponding public patents corresponding to the existing soybean combine harvesters described in the background technology.

[0038] Among them, the processing unit can be a camera with a computer. The camera is installed above the cab of the soybean combined intelligent harvesting device to shoot the area to be harvested and transmit the captured images to the computer. The computer is installed in the cab and can be equipped with corresponding input, output and display devices. The specific types and quantities of accessories are not limited accordingly in the embodiment of the present invention. The computer is provided with a corresponding model or software for analyzing the soybean plant image to obtain the maturity of the soybean plant. The maturity of the soybean plant is an indicator for measuring the maturity of the soybean plant. For example, the maturity of the early mature soybean plant is 1, the maturity of the mid-term mature soybean plant is 2, and the maturity of the late mature soybean plant is 3. The specific maturity value or size or expression method can be adjusted according to actual needs. The embodiment of the present invention does not make specific limitations. For example, the maturity can be divided into three stages: low, medium and high.

[0039] Among them, in the embodiment of the present invention, the mobile unit is a movable device, such as a movable carrier, such as a harvester or a tractor or an electric car, etc., and its function is to carry other equipment in the device to move in the planting area. The present invention does not specifically limit the specific implementation method of the mobile unit. In actual applications, corresponding accessories or functions of the mobile unit can be added according to actual needs, such as the installation of a navigation or control room or cab or monitoring equipment, etc.

[0040] Among them, the harvesting unit can be a harvesting platform, which rotates the soybean plants to harvest under the drive of a motor. The harvesting components are the plowing claws on the harvesting platform or devices similar to the plowing claws that are fixed or extended from the harvesting platform drum. The embodiments of the present invention do not make corresponding limitations and can be adjusted according to actual needs.

[0041] The core of the present invention is that after the processing unit obtains the maturity of the soybean plant, the harvesting unit generates corresponding control instructions based on the maturity of the soybean plant, controls the rotation speed of the harvesting unit and the hardness of the harvesting components to harvest the soybean plants. For example, if the maturity of the soybean plant is low, it can be harvested with a high rotation speed and a harder harvesting component. At this time, the soybean plant has just matured and the pods still have strong toughness and are not easy to burst during harvesting, so they can be harvested quickly. For example, if the maturity of the soybean plant is medium, it can be harvested with a medium rotation speed and a harvesting component of general hardness. At this time, the soybean plant has been mature for some time. The pods are still tough but not very tough anymore. Therefore, the speed and hardness of the harvesting parts need to be controlled during harvesting to avoid the pods from bursting easily during harvesting. Therefore, medium-speed harvesting can be performed. For example, if the soybean plants are highly mature, that is, fully mature, they can be harvested with a low speed and softer harvesting parts. At this time, the soybean plants have been mature for a long time, and the toughness of the pods is relatively poor. Therefore, the speed and hardness of the harvesting parts need to be controlled during harvesting to avoid the pods from bursting easily during harvesting. Therefore, low-speed harvesting can be performed, wherein the speed of the harvesting unit is achieved by controlling the speed of the motor through the controller.

[0042] The first transmission unit and the second transmission unit in the embodiment of the present invention may be corresponding transmission belts or transmission devices, which are not specifically limited in the present invention.

[0043] Among them, the threshing unit in the embodiment of the present invention can be a corresponding threshing mechanism or a separator. The present invention does not make specific limitations. The present invention does not improve the unit. The corresponding implementation scheme in the prior art can be referred to. After threshing by the threshing unit, the soybeans are transferred to the storage unit for storage, and the soybeans, stems, leaves, stalks and pods are cut into powder by the cutting unit to obtain miscellaneous materials.

[0044] In this embodiment of the present invention, the processing unit specifically includes:

[0045] A collection unit, used to collect images of soybean plants in the area to be harvested; the collection unit can be a camera or a video camera, which is not specifically limited in the embodiment of the present invention;

[0046] An analysis unit, configured to analyze the soybean plant image to obtain soybean plant maturity; the analysis unit may be a processor or a computer, which is equipped with and runs a soybean plant maturity analysis model;

[0047] The analysis unit is provided with a soybean plant maturity analysis model, and the soybean plant maturity analysis model is obtained as follows:

[0048] Obtain several original images of soybean plants at different maturity levels, and crop the original images of soybean plants to obtain cropped images. Cropping can improve the image quality, crop out unnecessary and interfering parts, and control the image size to reduce the amount of calculation.

[0049] The cropped image is labeled with soybean maturity to obtain a labeled image; the maturity can be labeled with numbers such as 1-3 or text low, medium, high, or other labeling methods, which are not specifically limited in the embodiment of the present invention and can be adjusted according to actual needs in actual applications;

[0050] A training set is obtained based on the labeled images, and a target recognition model is trained based on the training set to obtain the soybean plant maturity analysis model.

[0051] In practical applications, labeled images can also be used to construct validation sets and test sets to improve model performance.

[0052] Among them, the target recognition model is an existing model. The target recognition model in the present invention can identify the target and obtain the characteristics of the target, or any model that can achieve the above functions. The present invention does not specifically limit the type and implementation method of the model, and can be adjusted according to actual needs in actual applications.

[0053] Among them, in the embodiment of the present invention, the harvesting unit is a harvesting platform, and the harvesting platform includes a harvesting platform body. Usually, the harvesting platform body includes a harvesting platform frame, a roller and corresponding driving and connecting mechanisms. For other mechanisms in the harvesting platform body, the embodiment of the present invention will not be described in detail. You can refer to the corresponding structure of the existing harvesting platform. The difference from the existing harvesting platform is that please refer to Figure 2 , Figure 2 This is a partial structural diagram of the harvesting platform in the present invention. Figure 2 It includes the header frame 1, roller 2 and reed claw 3. Figure 3 , Figure 3The diagram of the distribution of harvesting hole groups is shown in FIG. The header body is provided with a plurality of evenly distributed harvesting hole groups, wherein the distribution is usually evenly distributed along the axial or circumferential direction of the drum. Each harvesting hole group includes an evenly arranged first harvesting hole 4, a second harvesting hole 5 and a third harvesting hole 6. The apertures of the first harvesting hole, the second harvesting hole and the third harvesting hole can be adjusted according to actual needs, such as adjusting according to the size of the header or adjusting according to the size of the plowing claw. The embodiment of the present invention is not specifically limited. Please refer to FIG. Figure 4 , Figure 4 This is a distribution diagram of the first, second and third plowing claws. The first, second and third harvesting holes are all connected to the cavity 7 in the header body. The purpose of the connection is to use the cavity to provide storage space for the first, second and third plowing claws 8, 9 and 10, and to use the connected channels to provide corresponding channels or paths for the extension and retraction of the first, second and third plowing claws. Each harvesting hole group is correspondingly installed with a plowing claw group, and each plowing claw group includes: a first plowing claw corresponding to the first harvesting hole, a second plowing claw corresponding to the second harvesting hole and a third plowing claw corresponding to the third harvesting hole. During each harvest, one plowing claw can be selected from the first, second and third plowing claws to extend from the corresponding hole for harvesting. Figure 4 The second claw is extended in the middle. The selection is based on the maturity of the soybean plant. The surface hardness of the first, second and third claws is different. The different surface hardness is used to reflect the different hardness of the first, second and third claws. Because the claws usually contact the soybean plant through the surface layer, the hardness of the surface layer can reflect the hardness difference of the harvesting parts. Please refer to Figure 5 , Figure 5 Schematic diagram of the cross section of a plowing claw, in which the surface layer 12 is sleeved on the plowing claw body 11 .

[0054] The method of harvesting soybean plants by controlling the rotation speed of the harvesting unit and the hardness of the harvesting components based on the maturity of the soybean plants includes:

[0055] Control the speed of the header body based on the maturity of the soybean plants;

[0056] A paddle claw having a surface hardness matching the maturity of the soybean plant is selected from the first to third paddle claws, and the paddle claw is extended out of the cavity from the corresponding harvesting hole to harvest the soybean plant. If the first paddle claw is selected, the first paddle claw is controlled to extend out of the first harvesting hole.

[0057] In the embodiment of the present invention, the first, second, and third plowing claws are each a telescopic rod-shaped structure, such as an electric, hydraulic, or pneumatic telescopic rod. The first, second, and third plowing claws are each provided with a protective layer on their surfaces, wherein the hardness of the protective layers on the first, second, and third plowing claws differs. The difference in hardness can be achieved by selecting different materials for the protective layers, such as metal, wood, rubber, sponge, or other materials. This embodiment of the present invention does not impose any specific limitations, and in actual applications, adjustments can be made based on actual needs.

[0058] In an embodiment of the present invention, the device further includes:

[0059] The processing unit is installed on the mobile unit, and is used to collect the miscellaneous materials, then add a corresponding amount of biological agent and water to the collected miscellaneous materials to obtain a mixture, then stir the mixture, and place the stirred mixture in the area after harvesting.

[0060] Among them, when the existing soybean combine harvester is operating, the applicant found that if the stems and branches obtained after threshing and separation are cut into powder by a cutting unit and then thrown into the field, the purpose of doing so is, on the one hand, to save the need to transport the stems back to the warehouse, and on the other hand, the cut debris can be used as fertilizer in the planting area. Directly returning the fertilizer to the field is easy to improve soil fertility. However, this will cause air pollution. Soybean harvesting is usually carried out in weather without rain, because rain will wet the soybeans, and soybeans will easily deteriorate, reducing storage time. Soybeans wet by rain will cause problems such as rottenness and mildew. The powder directly thrown into the field can easily float in the air under the action of airflow and become suspended particles to pollute the air, making the effect as fertilizer worse and polluting the environment. In order to solve the above problems, the present invention designs a processing unit, the purpose of which is to process the debris so that it becomes a better fertilizer and then does not cause pollution to the environment. The specific method is: adding a corresponding amount of biological agent and water to the collected debris to obtain a mixture, then stirring the mixture, and throwing the stirred mixture into the area after the harvest is completed. Biological agents can promote the degradation and decomposition of organic matter in soybean stalk powder, improving the quality and effectiveness of organic fertilizers. The mixture formed by adding water condenses and transforms from a powdery state into a mass. This prevents it from being blown away by windy weather, becoming airborne debris and causing environmental pollution.

[0061] The biological agent may be yeast, lactic acid bacteria, thermophilic bacteria, etc., which is not specifically limited in the embodiment of the present invention and can be adjusted according to actual needs in actual applications.

[0062] Among them, the processing unit may include a storage bin with an opening for the entry of miscellaneous materials, a weighing device in the storage bin for obtaining the real-time weight of the miscellaneous materials in the storage bin, and a stirring device for stirring the miscellaneous materials in the storage bin. When the weighing device detects that the miscellaneous materials in the storage bin have reached a corresponding weight, the miscellaneous materials are stopped from entering the storage bin, and then biological agents and water are added and stirred to obtain a mixture. After the mixture is obtained, the unloading port at the bottom of the storage bin is opened to dump the mixture into the area after the harvest is completed.

[0063] Among them, the storage bin carrying the weighing device and the stirring device is a storage bin in the prior art, and the embodiment of the present invention does not introduce its structure accordingly.

[0064] In an embodiment of the present invention, the device further includes:

[0065] The watering unit is installed on the mobile unit and is used to spray water in a preset range or direction of the device when the cutting unit is turned on.

[0066] Among them, when the cutting unit is turned on, dust will float out of the device. In order to reduce the dust in the air, the device is designed with a sprinkler unit. When the cutting unit is turned on, water can be sprinkled in the preset range or direction of the device to reduce the dust in the air. The sprinkler unit can be a sprinkler or an automatic sprinkler, which is connected to the water tank on the mobile unit through a water pipe. It should be noted that the range or direction of watering needs to avoid unharvested soybean plants and the storage unit for harvested soybeans, so as to avoid wetting the soybeans.

[0067] The device further includes a dust collection unit mounted on the mobile unit and configured to collect dust generated during the harvesting process by the harvesting unit. The dust collection unit can be used to collect dust generated during the harvesting process by the harvesting unit, replacing the use of sprinklers or automatic watering cans. Because the use of sprinklers or automatic watering can still carry a certain risk of wetting the soybeans, which can easily deteriorate and reduce storage time, and wet soybeans can lead to problems such as spoilage and mildew, a vacuum cleaner can be used to collect dust generated during the harvesting process by the harvesting unit. The power, type, and installation location of the vacuum cleaner can be adjusted according to actual needs and are not specifically limited in this embodiment of the present invention.

[0068] In an embodiment of the present invention, the dust suction unit is also used to remove the sucked dust. The dust removal process can be to spray water on the sucked dust to remove the dust into granular or lumpy dust, and then discharge it to the area after harvesting.

[0069] In the embodiment of the present invention, the step of labeling the cropped image with soybean maturity specifically includes:

[0070] Soybean maturity is labeled based on the number of leaves of the soybean plant in the cropped image to obtain a first training set. The applicant's research found that soybean leaves fall off when they mature, so the number of leaves of mature and immature soybeans can be compared to determine whether the soybeans are mature. Therefore, the number of leaves of the soybean plant can be used as an indicator to determine the maturity of the soybean plant.

[0071] Soybean maturity is annotated based on the leaf color of the soybean plant in the cropped image to obtain a second training set. The applicant's research found that when soybeans mature, their leaves turn from green to yellow or brown. Therefore, the leaf color of mature and immature soybeans can be compared to determine whether the soybeans are mature. Therefore, the leaf color of soybean plants can be used as an indicator to determine the maturity of soybean plants.

[0072] Soybean maturity is annotated based on the color of the soybean plant stems in the cropped image to obtain a third training set. The applicant's research found that when soybeans mature, the color of the soybean stems changes from green to yellow or brown. Therefore, the color of the soybean stems when mature and immature can be compared to determine whether the soybeans are mature. Therefore, the color of the soybean plant stems can be used as an indicator for determining the maturity of the soybean plants.

[0073] Soybean maturity is annotated based on the color of soybean pods in the cropped images to obtain a fourth training set. The applicant's research found that when soybeans mature, the color of the pods changes from green to yellow or brown. Therefore, the color of mature and immature soybean pods can be compared to determine whether the soybeans are mature. Therefore, the color of soybean pods can be used as an indicator for determining the maturity of soybean plants.

[0074] The soybean plant maturity analysis model is obtained as follows:

[0075] The first to fourth target recognition models are trained using the first to fourth training sets, respectively, to obtain trained first to fourth target recognition models. The soybean plant maturity analysis model is obtained based on the trained first to fourth target recognition models and a fusion model, wherein the fusion model is used to fuse the outputs of the first to fourth target recognition models. Fusion of the outputs of the first to fourth models using the fusion model can improve the comprehensive recognition capability of the target recognition model, and can obtain a more comprehensive and accurate soybean plant maturity compared to a single maturity indicator.

[0076] In the embodiment of the present invention, the soybean plant maturity analysis model is used to analyze the soybean plant image to obtain the soybean plant maturity, specifically:

[0077] analyzing the number of leaves of the soybean plant in the soybean plant image based on the first object recognition model to obtain a first maturity;

[0078] analyzing leaf colors of soybean plants in the soybean plant image based on the second object recognition model to obtain a second maturity;

[0079] The third maturity is obtained by analyzing the color of the soybean plant stems in the soybean plant image based on the third object recognition model;

[0080] analyzing the color of soybean pods in the soybean plant image based on the fourth object recognition model to obtain a fourth maturity;

[0081] The fusion model obtains soybean plant maturity based on the first to fourth maturity levels as follows:

[0082] A=(a*C1+b*C2+c*C3+d*C4) / (C1+C2+C3+C4);

[0083] Wherein, A is the maturity of soybean plants, C1-C4 are the first to fourth maturity respectively, and ad is the weight coefficient, wherein c=d>a=b. Among them, the fusion model designs corresponding weight considerations when obtaining the maturity of soybean plants based on the first to fourth maturity, and sets the weights of the third maturity and the fourth maturity to be greater than the weights of the first maturity and the second maturity. The specific reason is subtle. The applicant's research found that in some diseased or drought-stricken areas, when soybean plants are immature, due to disease and drought, the leaves of soybean plants will fall off and turn yellow. Therefore, the color change reaction of the stems and pods to disease and drought will be later than the falling and yellowing of the leaves. Therefore, in order to obtain accurate soybean plant maturity, the weight of the number of leaves and the color of the leaves in the maturity fusion is less than the stem color and the pod color. The specific weight coefficient size can be adjusted according to actual needs, and the embodiment of the present invention does not make specific limitations.

[0084] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0085] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A soybean combined intelligent harvesting device, characterized in that: The device comprises: a processing unit, the processing unit being mounted on the mobile unit and configured to collect images of soybean plants in the area to be harvested and analyze the images of the soybean plants to obtain maturity of the soybean plants; A mobile unit, configured to carry a corresponding unit to move based on a control instruction; A harvesting unit mounted on the mobile unit and configured to harvest the soybean plants by controlling the rotation speed of the harvesting unit and the hardness of a harvesting component based on the maturity of the soybean plants, wherein the harvesting component is a component configured to contact the soybean plants to achieve harvesting; a first transmission unit, the first transmission unit being installed on the moving unit and configured to transmit the soybean plants harvested by the harvesting unit to the threshing unit; A threshing unit, mounted on the mobile unit, for threshing soybean plants to obtain soybeans, stems, leaves, stalks and pods; a second transport unit, the second transport unit being mounted on the moving unit and configured to transport the threshed soybeans to the storage unit for storage, and to transport the stems, leaves, stalks and pods to the cutting unit; A cutting unit, which is mounted on the mobile unit and is used to cut the stems, leaves, stalks and pods to obtain miscellaneous materials; The harvesting unit is a harvesting platform, which includes a harvesting platform body. The harvesting platform body is provided with a plurality of evenly distributed harvesting hole groups, each harvesting hole group includes an evenly arranged first harvesting hole, a second harvesting hole, and a third harvesting hole, and the first harvesting hole, the second harvesting hole, and the third harvesting hole are all connected to the cavity in the harvesting platform body; each harvesting hole group is correspondingly equipped with a plowing claw group, and each plowing claw group includes: a first plowing claw corresponding to the first harvesting hole, a second plowing claw corresponding to the second harvesting hole, and a third plowing claw corresponding to the third harvesting hole, and the surface hardness of the first plowing claw, the second plowing claw, and the third plowing claw are different; The method of harvesting soybean plants by controlling the rotation speed of the harvesting unit and the hardness of the harvesting components based on the maturity of the soybean plants includes: Control the speed of the header body based on the maturity of the soybean plants; A paddle claw with a surface hardness that matches the maturity of the soybean plant is selected from the first to third paddle claws, and a cavity is extended from the corresponding harvesting hole to harvest the soybean plant; the first paddle claw, the second paddle claw and the third paddle claw are all rod-shaped structures with telescopic capabilities, and the surfaces of the first paddle claw, the second paddle claw and the third paddle claw are respectively provided with a protective layer, wherein the hardness of the surface protective layer of the first paddle claw, the second paddle claw and the third paddle claw is different.

2. The soybean intelligent combined harvesting device according to claim 1, characterized in that: The processing unit specifically includes: a collection unit for collecting images of soybean plants in an area to be harvested; an analysis unit, configured to analyze the soybean plant image to obtain the soybean plant maturity; The analysis unit is provided with a soybean plant maturity analysis model, and the soybean plant maturity analysis model is obtained as follows: Obtaining a number of original images of soybean plants at different maturity levels, and cropping the original images of the soybean plants to obtain cropped images; Label the cropped image for soybean maturity to obtain a labeled image; A training set is obtained based on the labeled images, and a target recognition model is trained based on the training set to obtain the soybean plant maturity analysis model.

3. The soybean intelligent combined harvesting device according to claim 1, characterized in that: The device further comprises: The processing unit is installed on the mobile unit, and is used to collect the miscellaneous materials, then add a corresponding amount of biological agent and water to the collected miscellaneous materials to obtain a mixture, then stir the mixture, and place the stirred mixture in the area after harvesting.

4. The soybean intelligent combined harvesting device according to claim 1, characterized in that: The device further comprises: The watering unit is installed on the mobile unit and is used to spray water in a preset range or direction of the device when the cutting unit is turned on.

5. The soybean intelligent combined harvesting device according to claim 1, characterized in that: The device further comprises: The dust suction unit is installed on the mobile unit and is used to absorb dust generated by the harvesting unit during the harvesting process.

6. The soybean intelligent combined harvesting device according to claim 5, characterized in that: The dust suction unit is also used to remove the sucked dust.

7. The soybean intelligent combined harvesting device according to claim 2, characterized in that: The soybean maturity labeling of the cropped image specifically includes: Soybean maturity is labeled based on the number of leaves of soybean plants in the cropped image to obtain the first training set; Soybean maturity is labeled based on the leaf color of the soybean plant in the cropped image to obtain the second training set; The soybean maturity is labeled based on the color of the soybean plant stems in the cropped images to obtain the third training set; Soybean maturity is labeled based on the color of soybean pods in the cropped image to obtain the fourth training set; The soybean plant maturity analysis model is obtained as follows: The first to fourth target recognition models are trained using the first to fourth training sets respectively to obtain the trained first to fourth target recognition models. The soybean plant maturity analysis model is obtained based on the trained first to fourth target recognition models and the fusion model, and the fusion model is used to fuse the outputs of the first to fourth target recognition models.

8. The soybean intelligent combined harvesting device according to claim 7, characterized in that: The soybean plant maturity analysis model is used to analyze the soybean plant image to obtain the soybean plant maturity, specifically: analyzing the number of leaves of the soybean plant in the soybean plant image based on the first object recognition model to obtain a first maturity; analyzing leaf colors of soybean plants in the soybean plant image based on the second object recognition model to obtain a second maturity; The third maturity is obtained by analyzing the color of the soybean plant stems in the soybean plant image based on the third object recognition model; analyzing the color of soybean pods in the soybean plant image based on the fourth object recognition model to obtain a fourth maturity; The fusion model obtains soybean plant maturity based on the first to fourth maturity levels as follows: A=(a*C1+b*C2+c*C3+d*C4) / (C1+C2+C3+C4); Where A is the maturity of soybean plants, C1-C4 are the first to fourth maturity, and ad are weight coefficients, where c=d>a=b.

Images