An adaptive feeding system for peanut harvesters

Abstract

The present invention relates to the technical field of peanut harvesters, and more specifically, to an adaptive feeding system for peanut harvesters, comprising a data acquisition module, a crop harvest damage prediction module, an adjustment control module, and a power drive module, wherein: the data acquisition module monitors the operating environment data of the peanut harvester in real time; the crop harvest damage prediction module collects crop growth parameters in real time and, based on the growth parameters, predicts the damage caused to the crops during the harvesting process; the adjustment control module generates automatic adjustment instructions based on the operating environment data; and the power drive module drives each unit in the adjustable feeding assembly according to the generated automatic adjustment instructions. This invention reduces the problems of cracking, squeezing, accumulation, or jamming caused by crop damage or environmental changes, while significantly improving the stability and efficiency of the feeding process.

Description

Technical Field

[0001] The invention relates to the technical field of peanut harvesters, and in particular to an adaptive feeding system for peanut harvesters. Background Art

[0002] Peanuts are an important cash crop, and their harvest quality directly impacts the economic value of agricultural products and farmers' income. During mechanized peanut harvesting, the feeding system, as a key link connecting the crop and subsequent processing equipment, has a significant impact on crop transportation stability, damage control, and operational efficiency. However, due to the complex and variable growing environment of peanuts, including varying terrain slopes, soil moisture, and differences in crop maturity and density, traditional fixed-parameter feeding systems struggle to adapt to these complex conditions, easily leading to crop accumulation, stagnation, or damage, impacting harvest efficiency and crop quality.

[0003] Existing peanut feeding systems typically rely on fixed parameters or simple mechanical adjustments, lacking comprehensive perception and intelligent response capabilities to the real-time operating environment and crop status. Under complex terrain and environmental conditions, traditional systems struggle to adjust feeding speed, force, and angle in a timely manner, resulting in crops susceptible to damage such as cracking, squeezing, and falling during the feeding process. This problem is particularly prominent when crop density is uneven or soil moisture is high. Furthermore, existing technologies for dynamic adjustment of the feeding process mostly rely on single parameter control, failing to achieve comprehensive optimization of speed, force, and angle, and failing to effectively improve harvesting efficiency and crop protection levels. Therefore, existing feeding systems still have significant deficiencies in adaptability, intelligence, and crop protection.

[0004] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide an adaptive feeding system for a peanut harvester, which can significantly improve the adaptability of the feeding system to complex operating environments, realize intelligent and dynamic operation control, and improve harvest quality and efficiency while reducing crop damage. Summary of the Invention

[0005] The invention provides an adaptive feeding system for a peanut harvester.

[0006] A peanut harvester adaptive feeding system includes a data acquisition module, a crop harvest damage prediction module, a regulation and control module, and a power drive module, wherein;

[0007] The data acquisition module monitors the peanut harvester's operating environment data in real time, including ground slope and soil moisture;

[0008] The crop harvest damage prediction module collects crop growth parameters in real time, including crop maturity and density, and predicts the damage to the crops during the harvest process based on the growth parameters;

[0009] The adjustment control module generates automatic adjustment instructions based on the predicted crop damage results and combined with the working environment data, including adjusting the feeding speed, force and angle;

[0010] The power drive module drives each unit in the adjustable feeding assembly (feeder, vibration device and power adjustment unit), including the electric motor, hydraulic pump and servo motor, according to the generated automatic adjustment instructions.

[0011] Optionally, the data acquisition module includes:

[0012] Ground slope collection: Use the laser radar installed on the peanut harvester to measure the slope of the working ground in real time and obtain ground inclination angle data;

[0013] Soil moisture collection: Use a soil moisture sensor to monitor the soil moisture level in real time and obtain the current soil moisture value to determine the softness or hardness of the soil.

[0014] Optionally, the crop harvest damage prediction module includes:

[0015] Crop maturity collection: Real-time collection of crop maturity information, including the shape, hardness, and color of peanut shells;

[0016] Crop density monitoring: real-time monitoring of crop density distribution to obtain the density of crops in different operation areas;

[0017] Crop damage prediction: Based on the results of crop maturity and crop density, it predicts the damage that crops will encounter during the harvest process, including crop breakage, falling off, squeezing or excessive friction.

[0018] Optionally, the crop maturity collection includes:

[0019] Shape acquisition: The shape data of peanut crops is collected through a camera installed on the peanut harvester. The Canny edge detection algorithm is used to extract the outline of the peanuts and generate the shape parameter S;

[0020] Hardness testing: An ultrasonic sensor is used to collect the hardness of peanuts in real time. The compression test method is used to measure the deformation of the peanut shell under a predetermined pressure to generate the hardness parameter H.

[0021] Color analysis: Collect the color data of peanuts and generate color parameters C using the HSV model;

[0022] Maturity assessment: Based on the generated shape parameters, hardness parameters and color parameters, the maturity of the peanuts is comprehensively assessed. The maturity assessment adopts a weighted average method to calculate a comprehensive maturity index M.

[0023] Optionally, the crop density monitoring includes:

[0024] Depth data acquisition: Using cameras and lidar equipment installed on peanut harvesters, real-time image and depth data of crops within the operating area are acquired;

[0025] Image processing and region segmentation: Use K-means clustering algorithm to process crop image data collected by the camera, extract crop distribution area and generate binary image, the number of pixels in the crop distribution area Represents the crop coverage in the unit area;

[0026] Density calculation: Combined with the depth data of the LiDAR, the density of crops in each area is calculated to generate the crop density parameter D;

[0027] Density distribution generation: Based on the crop density parameter D, a density distribution map of the operating area is generated, and the crop density in different areas is represented by color or gradient.

[0028] Optionally, the crop damage prediction includes:

[0029] Damage risk index calculation: Based on the generated comprehensive maturity index M and crop density parameter D, the probability of crops encountering breakage, shedding, squeezing, or excessive friction during harvest is quantified to generate the damage risk index R;

[0030] Crop damage type prediction: Based on the generated damage risk index R, the crop damage type is predicted, including rupture, shedding, squeezing, or excessive friction. Specifically,

[0031] Low risk: When R<0.3, it indicates low risk and no damage to crops;

[0032] Medium risk: When , it indicates medium risk, with crops cracking or squeezing;

[0033] High risk: When When , it indicates a high risk of crop shedding or excessive friction.

[0034] Optionally, the regulation control module includes:

[0035] Feeding parameter generation: Based on the results of crop damage type prediction and combined with operating environment data, comprehensive analysis of the current state of the crop and the operating environment is performed to generate adjustment values ​​for feeding parameters;

[0036] Dynamic command generation: Generates automatic adjustment commands in real time based on the generated adjustment values ​​of the input parameters.

[0037] Optionally, the feeding parameter generation includes:

[0038] Low-risk generation feeding parameters: When the crop damage type is predicted to be low risk, the feeding speed v is kept at the maximum value, the feeding force F is adjusted according to the soil moisture, and the feeding angle Adjust based on ground slope;

[0039] Medium risk generation feeding parameters: When the crop damage type is predicted to be medium risk, the feeding speed v is adjusted according to the soil moisture, the feeding force F is adjusted according to the soil moisture and crop density parameter D, and the feeding angle is adjusted. Adjustment is made based on the ground slope and crop density parameter D;

[0040] High-risk generation feeding parameters: When the crop damage type is predicted to be high risk, the feeding speed v is adjusted in combination with soil moisture, the feeding force F is adjusted in combination with soil moisture and crop density parameter D, and the feeding angle is adjusted in combination with soil moisture and crop density parameter D. Adjustments are made based on the crop density parameter D.

[0041] Optionally, the dynamic instruction generation includes:

[0042] Speed ​​adjustment instruction generation: Generate feeding speed adjustment instruction according to feeding speed parameter v;

[0043] Force adjustment command generation: Generate feed force adjustment command based on feed force parameter F;

[0044] Angle adjustment command generation: according to the input angle parameters , generate feeding angle adjustment instructions.

[0045] Optionally, the power drive module includes:

[0046] Feeding speed control: According to the generated feeding speed adjustment instruction, the motor is driven to adjust the running speed of the feeder;

[0047] Feeding force control: According to the generated feeding force adjustment instruction, the output pressure of the hydraulic pump is controlled and the vibration intensity of the vibration device is adjusted in real time;

[0048] Feeding angle adjustment: According to the generated feeding angle adjustment instruction, the servo motor is controlled to adjust the inclination angle of the feeding component so that the feeding device can adapt to changes in ground slope and crop density.

[0049] Beneficial effects of the present invention:

[0050] The present invention dynamically optimizes feeding speed, force, and angle by adjusting the control module according to the crop damage risk type prediction results and combining them with real-time collected environmental data. Through classification strategies, precise adaptation to low-, medium-, and high-risk crops is achieved. The feeding parameter generation process comprehensively considers the influence of soil moisture, ground slope, and crop density on the feeding process, ensuring data-driven dynamic adjustment capabilities, significantly reducing the problems of cracking, squeezing, accumulation, or jamming caused by crop damage or environmental changes, and greatly improving the stability and efficiency of the feeding process.

[0051] The present invention realizes real-time dynamic adjustment of the feeder, vibrating device and tilt angle by executing automatically generated feeding speed, force and angle adjustment instructions, ensuring that the system can adapt to complex and changeable working environments and crop conditions. The coordinated work of the electric motor, hydraulic pump and servo motor realizes efficient linkage from instruction to execution, which not only ensures uniform feeding of crops during the harvesting process, but also effectively reduces the risk of crop damage caused by excessive force, excessive speed or unsuitable angle. The entire system has good adaptability and intelligence, and can maintain stable and efficient performance in complex working environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 Schematic diagram of system function modules according to an embodiment of the present invention;

[0054] Figure 2 This is a schematic diagram of a crop harvest damage prediction module according to an embodiment of the present invention;

[0055] Figure 3 This is a schematic diagram of the peanut harvester structure. DETAILED DESCRIPTION

[0056] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0057] like Figure 1-Figure 3As shown, a peanut harvester adaptive feeding system includes a data acquisition module, a crop harvest damage prediction module, a regulation control module and a power drive module, wherein;

[0058] The data acquisition module monitors the peanut harvester's operating environment data in real time, including ground slope and soil moisture;

[0059] The crop harvest damage prediction module collects crop growth parameters in real time, including crop maturity and density, and predicts the damage to crops during the harvest process based on the growth parameters;

[0060] The regulation control module generates automatic adjustment instructions based on predicted crop damage results and operating environment data, including adjusting the feeding speed, force, and angle to ensure smooth and even feeding of peanuts and avoid peanut accumulation or jamming.

[0061] The power drive module drives each unit in the adjustable feeding assembly (feeder, vibrating device and power adjustment unit), including the electric motor, hydraulic pump and servo motor, according to the generated automatic adjustment instructions;

[0062] Through the above content, it is possible to monitor the working environment and crop growth status in real time, accurately predict the possible damage risks during the harvest process, and automatically adjust the feeding parameters according to the prediction results, thereby ensuring the smooth and uniform feeding process of peanuts, effectively avoiding crop damage, accumulation and jamming problems, improving working efficiency and crop protection, with good adaptability and intelligence, and can maintain stable and efficient performance in complex working environments.

[0063] The data acquisition module includes:

[0064] Ground slope collection: Use the laser radar installed on the peanut harvester to measure the slope of the working ground in real time and obtain ground inclination angle data;

[0065] Soil moisture collection: Use soil moisture sensors to monitor soil moisture levels in real time and obtain the current soil moisture value to determine the hardness of the soil.

[0066] Through the above content, accurate working environment information can be provided for the peanut harvester. The measurement of ground slope helps the system understand the terrain changes in the working area, thereby optimizing the working path and operating angle to avoid unstable operation due to excessive slope. Real-time monitoring of soil moisture can evaluate the softness and hardness of the soil, help adjust the feeding speed and force, and reduce damage to crops.

[0067] The crop harvest damage prediction module includes:

[0068] Crop maturity collection: Real-time collection of crop maturity information, including the shape, hardness, and color of peanut shells;

[0069] Crop density monitoring: real-time monitoring of crop density distribution to obtain the density of crops in different operation areas;

[0070] Crop damage prediction: Based on the results of crop maturity and crop density, it predicts the damage that crops will encounter during the harvest process, including crop breakage, falling off, squeezing or excessive friction;

[0071] Through the above content, the type and degree of damage that may occur during the harvest process can be accurately predicted, and the damage risk under different crop conditions can be effectively assessed, thereby providing a reliable basis for adjustment and control during the harvest process, avoiding problems such as cracking, falling off or squeezing caused by over-maturity, excessive density or uneven distribution of crops. It can not only improve work efficiency, but also protect crops to the greatest extent, reduce losses, and improve harvest quality and yield.

[0072] Crop maturity collection includes:

[0073] Shape acquisition: The shape data of peanut crops is collected by a camera installed on the peanut harvester. The Canny edge detection algorithm is used to extract the outline of the peanuts and generate the shape parameter S, which is expressed as:

[0074] ;

[0075] Among them, A is the contour area of ​​the peanut, and P is the contour perimeter;

[0076] Hardness testing: An ultrasonic sensor is used to collect the hardness of peanuts in real time. The compression test method is used to measure the deformation of the peanut shell under a predetermined pressure to generate a hardness parameter H, which is expressed as:

[0077] ;

[0078] Where F is the applied force and B is the contact surface area;

[0079] Color analysis: Collect the color data of peanuts and use the HSV model to generate the color parameter C, which is expressed as:

[0080] ;

[0081] Among them, H is the hue value of each pixel in the image, and mean represents the average value of the calculated hue;

[0082] Maturity assessment: Based on the generated shape parameters, hardness parameters, and color parameters, the maturity of peanuts is comprehensively assessed. The maturity assessment adopts the weighted average method to calculate the comprehensive maturity index M, which is expressed as:

[0083] ;

[0084] in, , , are the weight coefficients of shape, hardness and color respectively;

[0085] Through the above content, a comprehensive maturity assessment result is generated to provide an accurate basis for peanut harvesting. Shape collection helps evaluate appearance characteristics, hardness detection reflects the physical state of peanuts, and color analysis captures key indicators of the maturity stage. Through weighted comprehensive evaluation, a comprehensive and accurate judgment of crop maturity is ensured, the accuracy of harvest timing judgment is improved, and the loss of immature or over-mature peanuts is reduced. At the same time, scientific decision-making support is provided for subsequent harvest control, which helps to improve work efficiency and harvest quality.

[0086] Crop density monitoring includes:

[0087] Depth data acquisition: Using cameras and lidar equipment installed on peanut harvesters, real-time image and depth data of crops within the operating area are acquired;

[0088] Image processing and region segmentation: Use K-means clustering algorithm to process crop image data collected by the camera, extract crop distribution area and generate binary image, the number of pixels in the crop distribution area Represents the crop coverage in the unit area;

[0089] Density calculation: Combined with the depth data of the lidar, the density of crops in each area is calculated to generate the crop density parameter D, which is expressed as:

[0090] ;

[0091] Among them, E is the corresponding operating area area, is the crop volume;

[0092] ;

[0093] in, is the depth value of each point;

[0094] Density distribution generation: Based on the crop density parameter D, a density distribution map of the operating area is generated, using colors or gradients to represent the crop density in different areas;

[0095] The K-means clustering algorithm specifically includes:

[0096] (1) Data initialization: The collected crop image data is converted into a pixel feature matrix, which is defined as ,in Represents the feature vector (color value or grayscale value) of each pixel in the image;

[0097] (2) Set the number of clusters: define k cluster centers, and initially randomly select k pixels as the initial cluster centers, denoted as ;

[0098] (3) Calculate the distance between the pixel and the cluster center: for each pixel , calculate its relationship with all cluster centers Euclidean distance , expressed as:

[0099] ;

[0100] in, Represents pixel points The mth eigenvalue (R, G, B) of Represents the cluster center The mth eigenvalue of , where M is the feature dimension (3 for the RGB model);

[0101] (4) Assign pixels to the nearest cluster center: Each pixel Assigned to the cluster corresponding to the nearest cluster center , expressed as:

[0102] ;

[0103] Where k represents the total number of clusters;

[0104] (5) Update cluster center: Calculate the mean of all pixels in each cluster as the new cluster center, expressed as:

[0105] ;

[0106] in, is the updated cluster center, is the number of pixels in the jth cluster;

[0107] (6) Iteration process: Repeat steps (3)-(5) until the change of all cluster centers is less than the set threshold or the maximum number of iterations is reached;

[0108] (7) Segmentation result generation: All pixels are marked according to the clusters they belong to, forming a segmented binary image. The number of pixels representing the crop area in the clustering result is ;

[0109] Through the above content, it is possible to accurately evaluate the density of crops in the operating area in real time, use K-means clustering for regional segmentation, effectively extract the crop distribution area, and calculate the crop density parameters per unit area through depth data to ensure the optimal adjustment of feeding speed, angle and force. It can dynamically adapt to changes in the operating environment and avoid problems such as accumulation or jamming, thereby significantly improving the efficiency of peanut harvesting and the level of crop protection.

[0110] Crop damage prediction includes:

[0111] Damage risk index calculation: Based on the generated comprehensive maturity index M and crop density parameter D, the probability of crops encountering breakage, shedding, squeezing, or excessive friction during harvest is quantified to generate the damage risk index R, which is expressed as:

[0112] ;

[0113] Among them, R is the injury risk index, ranging from ,The higher the R, the greater the risk of damage. represents the maturity function, which indicates the probability of crop damage due to immaturity (M is small) or overmaturity (M is close to 1). represents the density function, which indicates the possibility of crops piling up, squeezing, and getting stuck due to high density. is the maximum density allowed, 、 is the weight coefficient, which represents the influence weight of maturity and density on damage, satisfying ;

[0114] Crop damage type prediction: Based on the generated damage risk index R, the crop damage type is predicted, including rupture, shedding, squeezing, or excessive friction. Specifically,

[0115] Low risk: When R<0.3, it indicates low risk and no damage to crops;

[0116] Medium risk: When , it indicates medium risk, with crops cracking or squeezing;

[0117] High risk: When When , it indicates high risk, crops may fall off or experience excessive friction;

[0118] Through the above content, the damage risks that crops may encounter during the harvesting process, such as breakage, shedding, squeezing or excessive friction, are quantified. The graded prediction method based on the damage risk index can not only assess the degree of crop damage in real time, but also accurately identify different damage types with low, medium and high risks. It can effectively reduce crop losses, optimize the harvesting process, improve work efficiency, and at the same time protect crop quality to the greatest extent and enhance the intelligence and stability of the system.

[0119] The regulation control module includes:

[0120] Feeding parameter generation: Based on the results of crop damage type prediction and combined with operating environment data, comprehensive analysis of the current state of the crop and the operating environment is performed to generate adjustment values ​​for feeding parameters;

[0121] Dynamic instruction generation: based on the adjustment values ​​of the generated input parameters, automatic adjustment instructions are generated in real time;

[0122] Through the above content, it is possible to accurately respond to the results of crop damage type prediction, and combined with real-time operating environment data, comprehensively analyze the current state of the crop and operating conditions, and dynamically generate optimized adjustment parameters for feeding speed, force and angle, effectively reducing the accumulation, squeezing or breakage problems caused by crop damage or environmental changes, and ensuring smooth and uniform crop feeding.

[0123] Feed parameter generation includes:

[0124] Low-risk generation feeding parameters: When the crop damage type is predicted to be low risk, the feeding speed v is kept at the maximum value, the feeding force F is adjusted according to the soil moisture, and the feeding angle Adjust based on ground slope, expressed as:

[0125] ;

[0126] ;

[0127] ;

[0128] in, is the maximum operating speed of the feeding system, is the maximum value of feeding force, h is the soil moisture, is the default feeding angle, is the slope adjustment coefficient, slope is the ground slope;

[0129] Medium risk generation feeding parameters: When the crop damage type is predicted to be medium risk, the feeding speed v is adjusted according to the soil moisture, the feeding force F is adjusted according to the soil moisture and crop density parameter D, and the feeding angle is adjusted. Adjustment is made based on the ground slope and crop density parameter D, which can be expressed as:

[0130] ;

[0131] ;

[0132] ;

[0133] in, and are the slope and density adjustment factors, respectively;

[0134] High-risk generation feeding parameters: When the crop damage type is predicted to be high risk, the feeding speed v is adjusted in combination with soil moisture, the feeding force F is adjusted in combination with soil moisture and crop density parameter D, and the feeding angle is adjusted in combination with soil moisture and crop density parameter D. Adjustment is based on the crop density parameter D, which is expressed as:

[0135] ;

[0136] ;

[0137] ;

[0138] in, is the density adjustment factor;

[0139] Through the above content, combined with the predicted results of crop damage risk types and real-time collected operating environment data, the feeding speed, force and angle are dynamically optimized to ensure that the system can accurately adapt to operational needs under low, medium and high risk conditions. Data-driven intelligent adjustment is achieved to minimize crop breakage, squeezing or jamming during the feeding process, while improving operational efficiency and crop protection capabilities.

[0140] Dynamic instruction generation includes:

[0141] Speed ​​adjustment instruction generation: Generate feeding speed adjustment instruction according to feeding speed parameter v;

[0142] Force adjustment command generation: Generate feed force adjustment command based on feed force parameter F;

[0143] Angle adjustment command generation: according to the input angle parameters , generate feeding angle adjustment instructions;

[0144] Through the above content, automated and dynamic operation adjustments are achieved, ensuring that the system can quickly respond to changes in the working environment and the needs of crop status, and optimize the feeding process.

[0145] The power drive module includes:

[0146] Feeding speed control: Based on the generated feeding speed adjustment command, the motor is driven to adjust the feeder's running speed to ensure that the crops enter the subsequent processing units evenly and smoothly to avoid accumulation or jamming;

[0147] Feeding force control: Based on the generated feeding force adjustment instructions, the output pressure of the hydraulic pump is controlled and the vibration intensity of the vibration device is adjusted in real time to prevent the crops from being broken or squeezed due to excessive force, or from being poorly fed due to insufficient force;

[0148] Feeding angle adjustment: Based on the generated feeding angle adjustment command, the servo motor is controlled to adjust the tilt angle of the feeding assembly, so that the feeding device can adapt to changes in ground slope and crop density, ensuring that crops can be fed evenly under complex terrain conditions;

[0149] Through the above content, it is possible to quickly respond to the automatic adjustment instructions generated by the adjustment control module, drive the electric motor, hydraulic pump and servo motor respectively, ensure the dynamic adjustment of the feeder, vibration device and tilt angle, and realize efficient linkage from instruction to execution, ensuring that crops are fed evenly and smoothly under complex terrain and environmental conditions, while avoiding crop damage and accumulation problems caused by excessive force, excessive speed or uncomfortable angle.

[0150] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0151] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A peanut harvester adaptive feeding system, characterized in that: It includes data acquisition module, crop harvest damage prediction module, regulation and control module and power drive module, among which; The data acquisition module monitors the peanut harvester's operating environment data in real time, including ground slope and soil moisture; The crop harvest damage prediction module collects crop growth parameters in real time, including crop maturity and density, and predicts the damage to the crops during the harvest process based on the growth parameters; The adjustment control module generates automatic adjustment instructions based on the predicted crop damage results and combined with the working environment data, including adjusting the feeding speed, force and angle; The power drive module drives each unit in the adjustable feeding assembly, including the electric motor, hydraulic pump and servo motor, according to the generated automatic adjustment instructions; The crop harvest damage prediction module includes: Crop maturity collection: Real-time collection of crop maturity information, including the shape, hardness, and color of peanut shells; Crop density monitoring: real-time monitoring of crop density distribution to obtain the density of crops in different operation areas; Crop damage prediction: Based on the results of crop maturity and crop density, it predicts the damage that crops will encounter during the harvest process, including crop breakage, falling off, squeezing or excessive friction; The crop maturity collection includes: Shape acquisition: The shape data of peanut crops is collected through a camera installed on the peanut harvester. The Canny edge detection algorithm is used to extract the outline of the peanuts and generate the shape parameter S; Hardness testing: An ultrasonic sensor is used to collect the hardness of peanuts in real time. The compression test method is used to measure the deformation of the peanut shell under a predetermined pressure to generate the hardness parameter H. Color analysis: Collect the color data of peanuts and generate color parameters C using the HSV model; Maturity assessment: Based on the generated shape parameters, hardness parameters, and color parameters, the maturity of the peanuts is comprehensively assessed. The maturity assessment adopts a weighted average method to calculate a comprehensive maturity index M; The crop density monitoring includes: Depth data acquisition: Using cameras and lidar equipment installed on peanut harvesters, real-time image and depth data of crops within the operating area are acquired; Image processing and region segmentation: Use K-means clustering algorithm to process the crop image data collected by the camera, extract the crop distribution area and generate a binary image. The number of pixels N in the crop distribution area is pixels Represents the crop coverage in the unit area; Density calculation: Combined with the depth data of the LiDAR, the density of crops in each area is calculated to generate the crop density parameter D; Density distribution generation: Based on the crop density parameter D, a density distribution map of the operating area is generated, using colors or gradients to represent the crop density in different areas; The crop damage prediction includes: Damage risk index calculation: Based on the generated comprehensive maturity index M and crop density parameter D, the probability of crops encountering breakage, shedding, squeezing, or excessive friction during harvest is quantified to generate the damage risk index R; Crop damage type prediction: Based on the generated damage risk index R, the crop damage type is predicted, including cracking, shedding, squeezing, or excessive friction. Specifically, Low risk: When R<0.3, it indicates low risk and no damage to crops; Medium risk: When 0.3≤R<0.7, it indicates medium risk, and crops are cracked or squeezed; High risk: When R ≥ 0.7, it indicates high risk and crops may fall off or experience excessive friction.

2. The peanut harvester adaptive feeding system according to claim 1, characterized in that: The data acquisition module includes: Ground slope collection: Use the laser radar installed on the peanut harvester to measure the slope of the working ground in real time and obtain ground inclination angle data; Soil moisture collection: Use a soil moisture sensor to monitor the soil moisture level in real time and obtain the current soil moisture value to determine the softness or hardness of the soil.

3. The peanut harvester adaptive feeding system according to claim 2, characterized in that: The regulation control module includes: Feeding parameter generation: Based on the results of crop damage type prediction and combined with operating environment data, a comprehensive analysis of the current state of the crop and the operating environment is conducted to generate adjustment values ​​for feeding parameters; Dynamic command generation: Generates automatic adjustment commands in real time based on the generated adjustment values ​​of the input parameters.

4. The peanut harvester adaptive feeding system according to claim 3, characterized in that: The feeding parameter generation includes: Low-risk generation feeding parameters: When the crop damage type is predicted to be low risk, the feeding speed v is maintained at the maximum value, the feeding force F is adjusted according to soil moisture, and the feeding angle θ is adjusted based on the ground slope; Medium-risk feeding parameters: When the crop damage type is predicted to be medium risk, the feeding speed v is adjusted based on soil moisture, the feeding force F is adjusted based on soil moisture and crop density parameter D, and the feeding angle θ is adjusted based on ground slope and crop density parameter D; High-risk generation feeding parameters: When the crop damage type is predicted to be high risk, the feeding speed v is adjusted based on soil moisture, the feeding force F is adjusted based on soil moisture and crop density parameter D, and the feeding angle θ is adjusted based on the crop density parameter D.

5. The peanut harvester adaptive feeding system according to claim 4, characterized in that: The dynamic instruction generation includes: Speed ​​adjustment command generation: Generate feeding speed adjustment command according to feeding speed parameter v; Force adjustment command generation: Generate feed force adjustment command according to feed force parameter F; Angle adjustment instruction generation: Generate the feed angle adjustment instruction according to the feed angle parameter θ.

6. The peanut harvester adaptive feeding system according to claim 5, characterized in that: The power drive module includes: Feeding speed control: According to the generated feeding speed adjustment instruction, the motor is driven to adjust the running speed of the feeder; Feeding force control: According to the generated feeding force adjustment instruction, the output pressure of the hydraulic pump is controlled and the vibration intensity of the vibration device is adjusted in real time; Feeding angle adjustment: According to the generated feeding angle adjustment instruction, the servo motor is controlled to adjust the inclination angle of the feeding component so that the feeding device can adapt to changes in ground slope and crop density.

Images