Combine harvester crawler trafficability control method based on visual inspection

Abstract

The invention relates to the technical field of agricultural machinery intelligent control, in particular to a combine harvester track trafficability control method based on visual inspection, which comprises the following steps: S1, predicting a motion track based on the real-time traveling speed and steering angle of a harvester; s2, extracting a real-time terrain slope angle of the trajectory region; s3, determining a target grounding pressure distribution mode required by the track in the predicted track area; s4, calculating a target hydraulic flow distribution proportion used for controlling a walking motor; and S5, the hydraulic valve group is controlled to adjust the oil supply amount according to the target flow distribution proportion. Through linkage of visual perception and hydraulic control, segmented self-adaptive adjustment of the track grounding pressure is achieved, and the trafficability and operation stability of the combine harvester under complex terrains are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of agricultural machinery, and in particular to a method for controlling the passability of a combine harvester crawler track based on visual detection. Background Art

[0002] Combine harvesters, as the main agricultural harvesting equipment, are widely used in the mechanized harvesting operations of field crops. Since they usually need to travel on unpaved and uneven farmland terrain, especially when there are obvious slopes or locally soft soil areas, the ground contact state of the tracks directly affects the stability and operating efficiency of the entire machine. The existing harvester track system mainly relies on static counterweights and fixed hydraulic drive parameters to achieve passing control, and lacks the ability to respond to dynamic terrain in real time, resulting in problems such as track slippage, uneven ground contact, and drive power waste during slope operations. In severe cases, it may even cause the machine body to roll over or sink deeply, posing a safety hazard in operations.

[0003] Currently, there is a lack of a track pressure control method that combines terrain perception with an active adjustment mechanism. This method cannot intelligently adjust the ground pressure distribution of each track section according to different terrain slopes to achieve precise drive control. Traditional methods do not fully utilize visual sensors to obtain information about the terrain ahead, nor do they integrate visual information with hydraulic system control to form a closed-loop response mechanism. Therefore, a combine harvester track control method based on visual detection is urgently needed to address these issues. Summary of the Invention

[0004] Based on the above objectives, the present invention provides a combine harvester track passability control method based on visual detection to solve the problem of difficulty in accurately identifying complex farmland terrain.

[0005] A combine harvester track passability control method based on visual detection includes the following steps:

[0006] S1: Based on the harvester's real-time speed and steering angle, calculate the predicted motion trajectory of the crawler contact area within a preset time period in the future;

[0007] S2: Use the front-facing visual sensor to collect terrain images along the predicted motion trajectory, and combine them with the aircraft pitch angle data to extract the real-time terrain slope angle of the trajectory area;

[0008] S3: According to the real-time terrain slope angle, a preset slope-pressure mapping relationship table is queried to determine the target ground pressure distribution pattern required by the track in the predicted trajectory area;

[0009] S4: Calculating a target hydraulic flow distribution ratio for controlling the travel motor according to the target ground pressure distribution pattern;

[0010] S5: Control the hydraulic valve group to adjust the oil supply according to the target flow distribution ratio, so that when the crawler enters the predicted motion trajectory area, a pressure distribution that adapts to the terrain slope is formed.

[0011] Optionally, the S1 specifically includes:

[0012] S11: Establishing kinematic input parameters of the vehicle's driving trajectory by acquiring the real-time travel speed and current steering angle of the combine harvester;

[0013] S12: Set the forecast period and divide the forecast period into several equally spaced steps to form a discrete time series;

[0014] S13: Based on the uniform circular driving model, the two-dimensional position coordinates of the vehicle center of mass at each time step are calculated to form a vehicle center of mass trajectory;

[0015] S14: Based on the coordinates of each center of mass position and the fixed geometric offset parameters of the track center relative to the center of mass, the ground contact center positions of the left and right tracks are inferred, and finally a complete ground contact trajectory of the track contact area in the future prediction time period is formed.

[0016] Optionally, the S2 specifically includes:

[0017] S21: Based on the predicted motion trajectory of the crawler contact area obtained in S1, a corresponding spatial scanning area is selected within the field of view of the visual sensor, and the front visual sensor continuously captures the two-dimensional terrain image of the area to form a real-time image sequence;

[0018] S22: Using image stitching technology to perform spatial overlapping stitching processing on adjacent images in the real-time image sequence to generate a complete topographic map covering the predicted motion trajectory area;

[0019] S23: Use stereo vision technology to extract spatial three-dimensional coordinate data from the complete terrain map and build a three-dimensional terrain model of the predicted trajectory area;

[0020] S24: acquiring real-time pitch angle data of a combine harvester body attitude sensor, and using the pitch angle data to perform coordinate correction on a three-dimensional terrain model to eliminate errors in terrain slope measurement caused by the body tilt;

[0021] S25: performing point-by-point slope calculation on the corrected three-dimensional terrain model, and extracting real-time terrain slope angle data for each location point in the predicted trajectory area.

[0022] Optionally, the S24 specifically includes:

[0023] S241: Acquire pitch angle data of the combine harvester from the body attitude sensor in real time to determine the tilt angle of the vehicle body relative to the horizontal reference plane;

[0024] S242: Constructing a three-dimensional rotation transformation matrix around the vehicle's lateral axis based on the obtained pitch angle data;

[0025] S243: Using the rotation transformation matrix, transform all coordinate points of the three-dimensional terrain model to restore the terrain model to a coordinate system with a horizontal reference plane as a reference.

[0026] Optionally, the S25 specifically includes:

[0027] S251: Based on the three-dimensional terrain model corrected in S24, determine the spatial coordinate data of each position point in the predicted trajectory area according to the vehicle's forward direction, and construct a local neighborhood centered on the position point;

[0028] S252: performing least squares plane fitting on the local neighborhood of each location point to obtain a local fitting plane equation corresponding to the location point, which is used to represent the terrain surface of the location point;

[0029] S253: Calculate the terrain slope angle at the corresponding position point based on the fitted plane normal vector. The formula is:

[0030] ,in, is the terrain slope angle of the corresponding location point; are the coefficients of the fitted plane;

[0031] S254: Execute S252 and S253 point by point in a loop to complete the calculation and extraction of real-time terrain slope angle data for all position points in the predicted trajectory area.

[0032] Optionally, the S3 specifically includes:

[0033] S31: Based on the real-time terrain slope angle data of each location point in the predicted trajectory area obtained in S2, the slope angle values are discretized one by one to obtain the slope discrete level corresponding to each location point;

[0034] S32: Based on the discrete gradient levels, a pre-stored gradient-pressure mapping table is called to extract target ground contact pressure weight ratio values of the front, middle, and rear sections of the track corresponding to each discrete gradient level;

[0035] S33: constructing target ground pressure distribution pattern curves for the three track sections based on target ground pressure weight ratio values for the front, middle, and rear sections of the track corresponding to each position point in the predicted trajectory area;

[0036] S34: Determine a final pressure distribution pattern of the track suitable for terrain slope changes within the predicted trajectory area based on the smoothed front, middle, and rear target ground contact pressure distribution pattern curves.

[0037] Optionally, the S34 specifically includes:

[0038] S341: Perform sliding window smoothing on the target ground pressure distribution curves of the front, middle and rear sections of the track generated in S33 to remove local drastic changes and obtain three continuous pressure weight curve sequences, which are recorded as and ;

[0039] S342: Calculate the weighted average of the three weight curves within the entire predicted trajectory area , and , used to characterize the global pressure distribution trend;

[0040] S343: Yes , and Normalization is performed to ensure that the sum of the three is 1, which serves as the ground pressure distribution pattern for the track to finally adapt to the terrain slope change in the predicted trajectory area.

[0041] Optionally, the S4 specifically includes:

[0042] S41: Calculating the initial hydraulic flow required for each section based on the target ground pressure weight values of the front, middle and rear sections of the track determined in S3 and the rated hydraulic flow parameters of each section of the track;

[0043] S42: Calculating the proportion of the initial hydraulic flow of the front section, the middle section, and the rear section to determine the proportion of the hydraulic flow of each section in the total oil supply flow, and obtaining the corresponding target flow distribution ratio;

[0044] S43: Based on the target hydraulic flow distribution ratio of each section, the travel motor control parameters corresponding to the front section, middle section and rear section of the crawler are output.

[0045] Optionally, the target flow distribution ratio in S42 is calculated as follows:

[0046] ,in, is the target hydraulic flow corresponding to each track section; is the target ground pressure weight value corresponding to each track section; The total hydraulic flow supplying the hydraulic pump to the track drive system.

[0047] Optionally, the S5 specifically includes:

[0048] S51: Receive the target hydraulic flow corresponding to the front, middle and rear track travel motors output by S4 as the flow control target value of the hydraulic system;

[0049] S52: Based on a pre-calibrated flow-opening relationship function, convert the target hydraulic flow of each track segment into a control opening instruction of the corresponding hydraulic valve group. The expression of the relationship function is:

[0050] ,in, The target opening degree of the hydraulic valve group of each track section; is the target hydraulic flow of each track section; It is the inverse function of the hydraulic flow-opening degree calibration function, which is used to convert the target flow into the valve port control quantity;

[0051] S53: The converted opening degree instruction is sent to the corresponding track segment hydraulic valve group in real time to drive the valve group to perform dynamic adjustment.

[0052] Beneficial effects of the present invention:

[0053] The present invention constructs a predicted track motion trajectory based on travel speed and steering angle, combines terrain images and fuselage pitch angle data obtained by the front visual sensor, establishes a three-dimensional terrain model and calculates the real-time terrain slope angle, which can achieve accurate identification of complex farmland terrain and provide a forward-looking input basis for track ground contact control.

[0054] The present invention uses the slope-pressure mapping relationship to clarify the target ground pressure weight ratios of the front, middle and rear sections of the track, and realizes real-time fine adjustment of the hydraulic system through a mapping model of hydraulic flow and valve group opening, thereby ensuring that the track has a matching ground pressure distribution under different terrain conditions, significantly improving the passability, stability and operation continuity of the combine harvester. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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.

[0056] Figure 1 Schematic diagram of a method for controlling the track passability of a combine harvester according to an embodiment of the present invention;

[0057] Figure 2 2 is a schematic diagram of the process of extracting real-time terrain slope angle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] 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.

[0059] It should be noted that references in the specification to "one embodiment," "an embodiment," "exemplary embodiments," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment will include such specific features, structures, or characteristics. Furthermore, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0060] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0061] like Figure 1-Figure 2 As shown, the combine harvester track passability control method based on visual detection includes the following steps:

[0062] S1: Based on the harvester's real-time speed and steering angle, calculate the predicted motion trajectory of the crawler contact area within a preset time period in the future;

[0063] S2: Use the front-facing visual sensor to collect terrain images along the predicted motion trajectory, and combine them with the aircraft pitch angle data to extract the real-time terrain slope angle of the trajectory area;

[0064] S3: According to the real-time terrain slope angle, a preset slope-pressure mapping relationship table is queried to determine the target ground pressure distribution pattern required by the track in the predicted trajectory area;

[0065] S4: Calculating a target hydraulic flow distribution ratio for controlling the travel motor according to the target ground pressure distribution pattern;

[0066] S5: Control the hydraulic valve group to adjust the oil supply according to the target flow distribution ratio, so that when the crawler enters the predicted motion trajectory area, a pressure distribution that adapts to the terrain slope is formed.

[0067] S1 specifically includes:

[0068] S11: By obtaining the real-time travel speed and current steering angle of the combine harvester, the kinematic input parameters of the vehicle's travel trajectory are established to initialize the trajectory prediction model. The travel speed is the linear velocity at the center of mass of the vehicle, and the steering angle is the deflection angle of the track relative to the longitudinal direction of the vehicle body.

[0069] S12: Set the prediction time period and divide the prediction period into several equally spaced steps to form a discrete time series, which is convenient for subsequent point-by-point calculation of the spatial displacement trajectory of the track center. The prediction time series can be expressed as: ;

[0070] ;in, For the The time point corresponding to the time step; is the time step interval; The total length of time to be predicted; is the number of prediction steps, which is a positive integer;

[0071] S13: Based on the uniform arc driving model, the two-dimensional position coordinates of the vehicle's center of mass at each time step are calculated to form the vehicle's center of mass trajectory. The calculation formula is as follows:

[0072] ,in, The center of mass is The spatial position coordinates of the time step; is the initial position coordinate of the vehicle's center of mass at the current moment; is the speed at the vehicle's center of mass; is the vehicle's running curvature radius, and the calculation formula is: ,in, is the vehicle's wheelbase, is the current steering angle;

[0073] S14: Based on the coordinates of each center of mass position and the fixed geometric offset parameters of the track center relative to the center of mass, the ground contact center positions of the left and right tracks are inferred, and finally a complete ground contact trajectory of the track contact area within the future prediction time period is formed; the above steps introduce a curvature motion model driven by vehicle speed and steering angle, which can accurately calculate the spatial trajectory points of the track contact area within multiple time domain steps, providing a stable and continuous prediction basis for terrain slope identification and ground contact pressure distribution optimization, thereby improving the foresight and accuracy of track passability control.

[0074] S2 specifically includes:

[0075] S21: Based on the predicted motion trajectory of the crawler contact area obtained in S1, a corresponding spatial scanning area is selected within the field of view of the visual sensor, and the front visual sensor continuously captures the two-dimensional terrain image of the area to form a real-time image sequence;

[0076] S22: Using image stitching technology to perform spatial overlapping stitching processing on adjacent images in the real-time image sequence to generate a high-resolution complete terrain map covering the predicted motion trajectory area;

[0077] S23: Use stereo vision technology to extract spatial three-dimensional coordinate data from the complete terrain map and build a three-dimensional terrain model of the predicted trajectory area;

[0078] S24: acquiring real-time pitch angle data of a combine harvester body attitude sensor, and using the pitch angle data to perform coordinate correction on a three-dimensional terrain model to eliminate errors in terrain slope measurement caused by the body tilt;

[0079] S25: Calculate the slope of the corrected three-dimensional terrain model point by point, and extract the real-time terrain slope angle data of each position point in the predicted trajectory area as input for the subsequent control of the track ground pressure; the above steps achieve high-precision three-dimensional reconstruction of the terrain in the trajectory area through stereo vision and image stitching technology, and combine the real-time correction of the terrain model with the fuselage pitch angle, effectively improving the accuracy and reliability of terrain slope measurement, and providing accurate data support for the dynamic control of the track passability.

[0080] S24 specifically includes:

[0081] S241: Acquire pitch angle data of the combine harvester from the body attitude sensor in real time to determine the tilt angle of the vehicle body relative to the horizontal reference plane;

[0082] S242: constructing a three-dimensional rotation transformation matrix around the vehicle's lateral axis based on the obtained pitch angle data to achieve coordinate correction of the three-dimensional terrain model;

[0083] S243: transforming all coordinate points of the three-dimensional terrain model using a rotation transformation matrix to restore the terrain model to a coordinate system with a horizontal reference plane as a reference;

[0084] Among them, the expression of the three-dimensional rotation transformation matrix is as follows:

[0085] ;in, Represents the rotation transformation matrix around the vehicle's lateral axis; is the real-time pitch angle of the fuselage; the above steps perform three-dimensional rotation matrix correction through the real-time pitch angle of the fuselage, effectively eliminating the measurement error caused by the tilt state of the vehicle body, ensuring the consistency of the three-dimensional terrain model with the actual ground conditions, thereby improving the accuracy and reliability of the terrain slope angle data, and providing high-precision data basis for the subsequent track ground pressure distribution.

[0086] S25 specifically includes:

[0087] S251: Based on the three-dimensional terrain model corrected in S24, determine the spatial coordinate data of each position point in the predicted trajectory area according to the vehicle's forward direction, and construct a local neighborhood centered on the position point;

[0088] S252: Perform least squares plane fitting on the local neighborhood of each location point to obtain the local fitting plane equation corresponding to the location point, which is used to represent the terrain surface of the location point. The least squares plane fitting calculation formula is: ; In the formula, each parameter satisfies the following minimization objectives:

[0089] ,in, They are the first The three-dimensional coordinates of a point; is the coefficient of the fitted plane equation; is the total number of points in the neighborhood used for fitting; is the sum of squared errors of the fitted plane equation;

[0090] S253: Calculate the terrain slope angle at the corresponding position point based on the fitted plane normal vector. The formula is:

[0091] ,in, is the terrain slope angle of the corresponding location point; are the coefficients of the fitted plane;

[0092] S254: Execute S252 and S253 in a loop point by point to complete the calculation and extraction of real-time terrain slope angle data for all position points within the predicted trajectory area; the above steps accurately calculate the real-time terrain slope angle of each position point in the predicted area through local plane fitting and normal vector analysis, ensuring high precision and detail capture capability of terrain analysis, providing accurate and continuous terrain input data for the combine harvester track pressure control, and effectively enhancing adaptability to complex terrain.

[0093] S3 specifically includes:

[0094] S31: Based on the real-time terrain slope angle data of each location point in the predicted trajectory area obtained in S2, the slope angle values are discretized one by one to obtain the slope discrete level corresponding to each location point;

[0095] S32: Based on the discrete gradient levels, a pre-stored gradient-pressure mapping table is called to extract target ground contact pressure weight ratio values of the front, middle, and rear sections of the track corresponding to each discrete gradient level;

[0096] Table 1 Slope-pressure mapping relationship table

[0097]

[0098] In Table 1 above, the slope angle range represents the terrain slope angle range where the track is predicted to be in contact with the ground, in degrees, and is divided into several discrete levels based on the calculation results of S2 and S25; the front section pressure weight represents the proportion of the target ground pressure that the front section of the track should bear under the corresponding slope angle; the middle section pressure weight represents the proportion of the target ground pressure that the middle section of the track should bear under the corresponding slope angle; and the rear section pressure weight represents the proportion of the target ground pressure that the rear section of the track should bear under the corresponding slope angle.

[0099] S33: Based on the target ground contact pressure weight ratio values of the front, middle and rear sections of the track corresponding to each position point in the predicted trajectory area, target ground contact pressure distribution pattern curves of the three sections of the track are constructed respectively to eliminate pressure mutations between adjacent points;

[0100] S34: Based on the smoothed target ground contact pressure distribution pattern curves of the front, middle and rear sections, determine the pressure distribution pattern of the track that is ultimately suitable for the terrain slope change within the predicted trajectory area, wherein the pressure distribution pattern is clearly given in the form of a pressure weight ratio of the front, middle and rear sections of the track, which serves as the input basis for subsequent travel motor flow control.

[0101] S34 specifically includes:

[0102] S341: Perform sliding window smoothing on the target ground pressure distribution curves of the front, middle and rear sections of the track generated in S33 to remove local drastic changes and obtain three continuous pressure weight curve sequences, which are recorded as and ,in represents the position index along the predicted trajectory;

[0103] S342: Calculate the weighted average of the three weight curves within the entire predicted trajectory area , and , which is used to characterize the global pressure distribution trend, is calculated as follows:

[0104] ;

[0105] ;

[0106] ,in, are the final pressure weight values of the front, middle and rear sections of the track respectively; Respectively The corresponding segment pressure weight value at each trajectory position; is the total number of position points on the trajectory;

[0107] S343: Yes Normalization is performed to ensure that the sum of the three is 1, which serves as the ground pressure distribution pattern for the track to finally adapt to the terrain slope change in the predicted trajectory area, and is used to drive the subsequent travel motor flow ratio control; the above steps can extract a stable pressure distribution strategy under the overall slope change trend through weighted averaging and normalization processing of the three-segment pressure curve, avoid allergic response to local abnormal slopes, and improve the stability and energy consumption control ability of the track control system during long-distance travel.

[0108] S4 specifically includes:

[0109] S41: Calculating the initial hydraulic flow required for each section based on the target ground pressure weight values of the front, middle and rear sections of the track determined in S3 and the rated hydraulic flow parameters of each section of the track;

[0110] The initial hydraulic flow calculation formula is: ,in, is the initial hydraulic flow of each track section; is the target ground pressure weight value corresponding to each track section, and the front section pressure weight is , mid-section pressure weight , rear pressure weight ; is the rated hydraulic flow parameter of each track section, that is, the hydraulic flow required by each track section under rated working conditions;

[0111] S42: Calculating the proportion of the initial hydraulic flow of the front section, the middle section, and the rear section to determine the proportion of the hydraulic flow of each section in the total oil supply flow, and obtaining the corresponding target flow distribution ratio;

[0112] S43: Based on the target hydraulic flow distribution ratio of each section, the travel motor control parameters corresponding to the front, middle and rear sections of the track are output for precise adjustment of the subsequent hydraulic valve group; the above steps accurately determine the target flow distribution ratio of each section of the track through direct correlation calculation between the pressure weight value and the hydraulic flow parameter, ensure that the track ground pressure is effectively matched with the actual hydraulic driving force, realize active and precise control of the contact between the track and the terrain, and improve the driving stability and energy utilization efficiency of the combine harvester in complex terrain.

[0113] The calculation formula for the target flow distribution ratio in S42 is:

[0114] ,in, is the target hydraulic flow corresponding to each track section, in liters per minute; is the target ground pressure weight value corresponding to each track section; The total hydraulic flow, in liters per minute, supplying the track drive system to the hydraulic pump.

[0115] S5 specifically includes:

[0116] S51: Receive the target hydraulic flow corresponding to the front, middle and rear track travel motors output by S4 as the flow control target value of the hydraulic system;

[0117] S52: Based on a pre-calibrated flow-opening relationship function, the target hydraulic flow of each track segment is converted into a control opening instruction of the corresponding hydraulic valve group. The expression of the relationship function is:

[0118] ,in, The target opening degree of the hydraulic valve group of each track section; is the target hydraulic flow of each track section; It is the inverse function of the hydraulic flow-opening calibration function, used to convert the target flow into the valve port control quantity;

[0119] S53: The converted opening degree instruction is sent in real time to the hydraulic valve group of the corresponding track segment, driving the valve group for dynamic adjustment so that each track segment has a hydraulic driving force that matches the target ground pressure when entering the predicted trajectory area; the above steps improve the real-time and accuracy of the track hydraulic adjustment by using the obtained target hydraulic flow to execute the valve group opening conversion control, and enhance the equipment's ability to respond immediately to changes in complex terrain slope.

[0120] 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.

[0121] 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 combine harvester track passability control method based on visual detection, characterized in that: The following steps are involved: S1: Based on the harvester's real-time speed and steering angle, calculate the predicted motion trajectory of the crawler contact area within a preset time period in the future; S2: Use the front-facing visual sensor to collect terrain images along the predicted motion trajectory, and combine them with the aircraft pitch angle data to extract the real-time terrain slope angle of the trajectory area; S3: According to the real-time terrain slope angle, a preset slope-pressure mapping relationship table is queried to determine the target ground pressure distribution pattern required by the track in the predicted trajectory area; S4: Calculating a target hydraulic flow distribution ratio for controlling the travel motor according to the target ground pressure distribution pattern; S5: Control the hydraulic valve group to adjust the oil supply according to the target flow distribution ratio, so that when the crawler enters the predicted motion trajectory area, a pressure distribution that adapts to the terrain slope is formed.

2. The combine harvester crawler passability control method based on visual detection according to claim 1, characterized in that: Said S1 specifically includes: S11: Establishing kinematic input parameters of the vehicle's driving trajectory by acquiring the real-time travel speed and current steering angle of the combine harvester; S12: Set the forecast period and divide the forecast period into several equally spaced steps to form a discrete time series; S13: Based on the uniform circular driving model, the two-dimensional position coordinates of the vehicle center of mass at each time step are calculated to form a vehicle center of mass trajectory; S14: Based on the coordinates of each center of mass position and the fixed geometric offset parameters of the track center relative to the center of mass, the ground contact center positions of the left and right tracks are inferred, and finally a complete ground contact trajectory of the track contact area in the future prediction time period is formed.

3. The combine harvester crawler passability control method based on visual detection according to claim 1, characterized in that: The S2 specifically includes: S21: Based on the predicted motion trajectory of the crawler contact area obtained in S1, a corresponding spatial scanning area is selected within the field of view of the visual sensor, and the front visual sensor continuously captures the two-dimensional terrain image of the area to form a real-time image sequence; S22: Using image stitching technology to perform spatial overlapping stitching processing on adjacent images in the real-time image sequence to generate a complete topographic map covering the predicted motion trajectory area; S23: Use stereo vision technology to extract spatial three-dimensional coordinate data from the complete terrain map and build a three-dimensional terrain model of the predicted trajectory area; S24: acquiring real-time pitch angle data of a combine harvester body attitude sensor, and using the pitch angle data to perform coordinate correction on a three-dimensional terrain model to eliminate errors in terrain slope measurement caused by the body tilt; S25: performing point-by-point slope calculation on the corrected three-dimensional terrain model, and extracting real-time terrain slope angle data for each location point in the predicted trajectory area.

4. The method for controlling the track passability of a combine harvester based on visual detection according to claim 3, characterized in that: The S24 specifically includes: S241: Acquire pitch angle data of the combine harvester from the body attitude sensor in real time to determine the tilt angle of the vehicle body relative to the horizontal reference plane; S242: Constructing a three-dimensional rotation transformation matrix around the vehicle's lateral axis based on the obtained pitch angle data; S243: Using the rotation transformation matrix, transform all coordinate points of the three-dimensional terrain model to restore the terrain model to a coordinate system with a horizontal reference plane as a reference.

5. The combine harvester crawler passability control method based on visual detection according to claim 4, characterized in that: The S25 specifically includes: S251: Based on the three-dimensional terrain model corrected in S24, determine the spatial coordinate data of each position point in the predicted trajectory area according to the vehicle's forward direction, and construct a local neighborhood centered on the position point; S252: performing least squares plane fitting on the local neighborhood of each location point to obtain a local fitting plane equation corresponding to the location point, which is used to represent the terrain surface of the location point; S253: Calculate the terrain slope angle at the corresponding position point based on the fitted plane normal vector. The formula is: ,in, is the terrain slope angle of the corresponding location point; are the coefficients of the fitted plane; S254: Execute S252 and S253 point by point in a loop to complete the calculation and extraction of real-time terrain slope angle data for all position points in the predicted trajectory area.

6. The combine harvester crawler passability control method based on visual detection according to claim 5, characterized in that: The S3 specifically includes: S31: Based on the real-time terrain slope angle data of each location point in the predicted trajectory area obtained in S2, the slope angle values are discretized one by one to obtain the slope discrete level corresponding to each location point; S32: Based on the discrete gradient levels, a pre-stored gradient-pressure mapping table is called to extract target ground contact pressure weight ratio values of the front, middle, and rear sections of the track corresponding to each discrete gradient level; S33: constructing target ground pressure distribution pattern curves for the three track sections based on target ground pressure weight ratio values for the front, middle, and rear sections of the track corresponding to each position point in the predicted trajectory area; S34: Determine a final pressure distribution pattern of the track suitable for terrain slope changes within the predicted trajectory area based on the smoothed front, middle, and rear target ground contact pressure distribution pattern curves.

7. The combine harvester crawler passability control method based on visual detection according to claim 6, characterized in that: The S34 specifically includes: S341: Perform sliding window smoothing on the target ground pressure distribution curves of the front, middle and rear sections of the track generated in S33 to remove local drastic changes and obtain three continuous pressure weight curve sequences, which are recorded as and ; S342: Calculate the weighted average of the three weight curves within the entire predicted trajectory area , and , used to characterize the global pressure distribution trend; S343: Yes , and Normalization is performed to ensure that the sum of the three is 1, which serves as the ground pressure distribution pattern for the track to finally adapt to the terrain slope change in the predicted trajectory area.

8. The combine harvester crawler passability control method based on visual detection according to claim 1, characterized in that: The S4 specifically includes: S41: Calculating the initial hydraulic flow required for each section based on the target ground pressure weight values of the front, middle and rear sections of the track determined in S3 and the rated hydraulic flow parameters of each section of the track; S42: Calculating the proportion of the initial hydraulic flow of the front section, the middle section, and the rear section to determine the proportion of the hydraulic flow of each section in the total oil supply flow, and obtaining the corresponding target flow distribution ratio; S43: Based on the target hydraulic flow distribution ratio of each section, the travel motor control parameters corresponding to the front section, middle section and rear section of the crawler are output.

9. The method for controlling the track passability of a combine harvester based on visual detection according to claim 8, characterized in that: The calculation formula of the target flow distribution ratio in S42 is: ,in, is the target hydraulic flow corresponding to each track section; is the target ground pressure weight value corresponding to each track section; The total hydraulic flow supplying the hydraulic pump to the track drive system.

10. The combine harvester crawler passability control method based on visual detection according to claim 9, characterized in that: The S5 specifically includes: S51: Receive the target hydraulic flow corresponding to the front, middle and rear track travel motors output by S4 as the flow control target value of the hydraulic system; S52: Based on a pre-calibrated flow-opening relationship function, convert the target hydraulic flow of each track segment into a control opening instruction of the corresponding hydraulic valve group. The expression of the relationship function is: ,in, The target opening degree of the hydraulic valve group of each track section; is the target hydraulic flow of each track section; It is the inverse function of the hydraulic flow-opening calibration function, used to convert the target flow into the valve port control quantity; S53: The converted opening degree instruction is sent to the corresponding track segment hydraulic valve group in real time to drive the valve group to perform dynamic adjustment.

Images