Self-adaptive regulation and control method for header of harvester

Abstract

The invention provides a harvester header self-adaptive regulation and control method, relates to the technical field of agricultural machinery intellectualization, and aims to solve the problem that a header and a reel are difficult to quickly adjust in the prior art. Self-adaptive regulation and control of the header and the reel are achieved, the height of the header and the rotating speed of the reel can be accurately adjusted according to actual operation conditions such as ground fluctuation and crop density, the regulation and control accuracy and adaptability are improved, factors such as the height of the two sides of the header and the ground, the operation speed and the crop density are comprehensively considered, and the regulation and control accuracy is improved. The height of the header and the rotating speed of the reel are adjusted more accurately, so that harvesting operation is smoother, and the problems of header damage, crop omission and the like are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent agricultural machinery, and in particular to a self-adaptive control method for a harvester header. Background Art

[0002] The header is an important part of the harvester, and the coordinated operation of the various operating parts of the header directly affects the field operation efficiency of the harvester. During the operation of the grain harvester, there are great differences in the terrain and soil conditions in different regions. Meteorological conditions also cause differences in ground flatness and crop harvesting status. Even in the same plot, due to differences in planting conditions, crop height and density are uneven. This requires operators to constantly adjust the height of the harvester header, the speed of the reel, the position of the reel and other operating conditions according to the crop status, harvesting environment and machine operation speed. Otherwise, there will be blockage, missed harvesting, the header touching the ground, overloading or underloading of the machine, etc., resulting in reduced work efficiency and increased failure rate.

[0003] A Chinese patent (publication number CN118489426A, publication date 20240816) discloses a device and control method for adjusting the height of the header of an automatic harvester. The device can adjust the height of the header of the automatic harvester. The sensing device can sense the ground height in real time. The control system controls the extension of the corresponding hydraulic cylinder or the lifting of the entire harvesting device according to the ground height in front of the flexible header unit. The local header height or the overall header height can be adjusted according to actual conditions to ensure that the header blade is not damaged; however, the adjustment effect of the header of the harvester is poor. In addition to the header height and header posture, the working state of the reel will also affect the harvesting efficiency. The current control method is difficult to coordinate the header and the reel, resulting in low working efficiency and high failure rate. Summary of the invention

[0004] The purpose of the present invention is to provide a method for adaptively controlling the cutting table of a harvester in view of the defects in the prior art. By establishing corresponding relationships between the cutting table height adjustment information and the reel wheel speed adjustment information and related parameters, the coordinated adaptive control of the cutting table and the reel wheel is realized. The cutting table height and the reel wheel speed can be accurately adjusted according to actual operating conditions, such as ground undulation, crop density, etc., thereby improving the accuracy and adaptability of the control. By comprehensively considering various factors such as the distance between the two sides of the cutting table and the ground, the operating speed, and the crop density, the cutting table height and the reel wheel speed can be adjusted more accurately. By collaboratively controlling the cutting table and the reel wheel, the harvesting operation is smoother, thereby improving the harvesting efficiency and reducing the failure rate.

[0005] In order to solve the above problems, the following solutions are adopted:

[0006] A method for adaptively controlling a harvester header, comprising:

[0007] The operation speed of the header, the height information of both sides of the header and the image of the crop in front of the header are obtained, and the image is processed to obtain the crop density according to the image information of the crop in front of the header;

[0008] Based on the height information of both sides of the cutting platform, the operating speed and the preset profiling control model, the corresponding cutting platform height adjustment information is determined; based on the crop density, the operating speed and the preset reel wheel speed control model, the corresponding reel wheel speed adjustment information is determined; wherein the preset profiling control model is the corresponding relationship between the height information of both sides of the cutting platform, the operating speed and the cutting platform height adjustment information, and the preset reel wheel speed control model is the corresponding relationship between the crop density, the operating speed and the reel wheel speed adjustment information;

[0009] The height of the header is controlled according to the header height adjustment information, and the speed of the reel is controlled according to the reel speed adjustment information.

[0010] Furthermore, it also includes:

[0011] Processing the image to obtain lodging state information, and determining corresponding reel position adjustment parameters based on the lodging state information and a preset reel position control model, wherein the preset reel position control model is a correspondence between the lodging state information and the reel position adjustment parameters;

[0012] The reel position is controlled according to the reel position adjustment parameter.

[0013] Furthermore, the lodging state information includes forward lodging and reverse lodging relative to the working direction, and the reel position adjustment parameters include reel lifting information and reel front and rear extension information.

[0014] Further, controlling the position of the reel according to the reel position adjustment parameter comprises:

[0015] When lodging in the forward direction, adjust the reel to extend forward to the front end position, and adjust the reel to descend to the bottom end position;

[0016] When lodging in reverse direction, the reel is adjusted to retract to the rear end position, and the reel is adjusted to descend to the bottom end position.

[0017] Furthermore, it also includes:

[0018] Through field tests, test data at different speeds and different crop densities were obtained, and the BP neural network model was established using the test data of corresponding operation parameters;

[0019] Genetic algorithm is used to optimize the BP neural network model, and the optimal control parameter table of the vertical and horizontal two-dimensional profiling control of the header under different operating speeds and the optimal control parameter table of the reel speed control under different density conditions are established;

[0020] According to the optimal control parameter table of the longitudinal and transverse two-dimensional profiling control of the cutting platform under different operating speeds and the optimal control parameter table of the reel speed control under different density conditions, a preset profiling control model and a preset reel speed control model are established.

[0021] Furthermore, when establishing a preset profiling control model, the influencing factors of the longitudinal and transverse two-dimensional profiling control of the header include operating speed, PID control parameters, header height target value, header height measurement value, and the deviation between the header height target value and the actual value.

[0022] Furthermore, when establishing a preset reel speed control model, the reel speed control influencing factors include operating speed, crop density value, PID control parameters, reel speed measurement value, and the ratio of reel speed to operating speed.

[0023] Furthermore, the processing of the image to obtain the crop density includes:

[0024] Acquire the image of the crop in front of the header, pre-process the captured image, grid the image and extract the color and texture features of the ear of grain;

[0025] The extracted feature data is standardized, and the image spots are classified using classification learning methods to identify the outline of the ear of grain.

[0026] The contour image of the ear of grain is refined by filling holes, the total number of ears of grain in the image is calculated, the number of ears of grain per unit area is obtained, and then the crop density is obtained.

[0027] Furthermore, the operating speed is obtained through a travel speed sensor, the height information of both sides of the harvesting table is obtained through a harvesting table longitudinal and transverse profiling device, the reel speed is obtained through a reel speed sensor, and the image is obtained through an industrial camera on the harvester.

[0028] Furthermore, the height of the harvesting platform is driven and adjusted by a harvesting platform lifting hydraulic cylinder, and the speed of the reel is adjusted by a hydraulic motor.

[0029] Compared with the prior art, the present invention has the following advantages and positive effects:

[0030] In view of the problem that it is difficult to quickly adjust the harvesting table and the reel in the prior art, the corresponding relationship between the harvesting table height adjustment information and the reel speed adjustment information and related parameters is established respectively, so that the adaptive control of the harvesting table and the reel is realized, and the harvesting table height and the reel speed can be accurately adjusted according to the actual operating conditions, such as ground undulation, crop density, etc., thereby improving the accuracy and adaptability of the control. Taking into account various factors such as the height of the two sides of the harvesting table with the ground, the operating speed, the crop density, etc., the harvesting table height and the reel speed are adjusted more accurately, making the harvesting operation smoother and reducing problems such as damage to the harvesting table and crop omission. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0032] Figure 1 The figure is a schematic diagram of the installation of the harvester header in the embodiment 1 of the present invention.

[0033] Figure 2 Schematic diagram of the vertical and horizontal square device of the header in Example 1 of the present invention Figure 1 .

[0034] Figure 3 Schematic diagram of the vertical and horizontal square device of the header in Example 1 of the present invention Figure 2 .

[0035] In the figure, 1, the cutting platform body; 2, the reel wheel height detection device; 3, the reel wheel lifting hydraulic cylinder; 4, the cutting platform longitudinal and transverse profiling device; 5, the reel wheel; 6, the reel wheel speed sensor; 7, the reel wheel front and rear movement hydraulic cylinder; 8, the reel wheel front and rear position detection device; 9, the industrial camera; 10, the profiling rod; 11, the base; 12, the profiling rod connecting ball joint; 13, the hanging belt; 14, the counterweight; 15, the connecting bearing; 16, the guard plate; 17, the seed block direction adjustment hole; 18, the counterweight hanging device; 19, the base hanging device; 20, the angle detection element. DETAILED DESCRIPTION

[0036] Example 1

[0037] In a typical embodiment of the present invention, Figure 1-Figure 3 As shown, a method for adaptive control of harvester header is given.

[0038] A method for adaptively controlling a harvester header, comprising:

[0039] Obtain the operation speed of the header, the height information of both sides of the header and the image of the crop in front of the header, and process the image to obtain the crop density;

[0040] Based on the height information of both sides of the cutting platform, the operating speed and the preset profiling control model, the corresponding cutting platform height adjustment information is determined; based on the crop density, the operating speed and the preset reel wheel speed control model, the corresponding reel wheel speed adjustment information is determined; wherein the preset profiling control model is the corresponding relationship between the height information of both sides of the cutting platform, the operating speed and the cutting platform height adjustment information, and the preset reel wheel speed control model is the corresponding relationship between the crop density, the operating speed and the reel wheel speed adjustment information;

[0041] The height of the header is controlled according to the header height adjustment information, and the speed of the reel is controlled according to the reel speed adjustment information.

[0042] Among them, different operating speeds will affect the working conditions of the cutting table and the reel; the height information of the two sides of the cutting table and the working ground is used to determine the cutting table height adjustment information based on the preset profiling control model, and the crop density is obtained by processing the image of the crop in front of the cutting table, which is convenient for determining the reel speed adjustment information.

[0043] like Figure 1 As shown, the operating speed is obtained through the travel speed sensor, the height information on both sides of the header is obtained through the header longitudinal and transverse profiling device, the image is obtained through the industrial camera on the harvester, and the reel speed is obtained through the reel speed sensor. The height of the header is driven and adjusted by the header lifting hydraulic cylinder, and the reel speed is adjusted by the hydraulic motor.

[0044] Specific, combined Figure 1-Figure 3 The harvester includes an information collection device, a controller and an actuator. The information collection device includes: a header longitudinal and transverse profiling device 4, a travel speed sensor, a reel speed sensor 6, an industrial camera 9, and a reel position detection device. The information collection device is used to obtain the working state of the harvester header.

[0045] An industrial camera 8 is installed on the front top of the harvester to take real-time photos of the grains in front; the travel speed sensor is installed on the harvester walking system; the reel wheel speed sensor 6 is installed on the reel wheel bracket at the end of the reel wheel rotating shaft; the reel wheel position detection device includes a reel wheel height detection device 2 and a reel wheel front and rear position detection device 8, one end of the reel wheel height detection device 2 is installed on the harvesting table body 1, and the other end is connected to the reel wheel bracket; one end of the reel wheel front and rear position detection device 8 is installed on the reel wheel bracket, and the other end is connected to the end of the reel wheel rotating shaft.

[0046] The header longitudinal and transverse profiling device 4 is installed at the front end of the header, one on each side, including a profiling rod 10, a base 11, a profiling rod connecting ball joint 12, a hanging belt 13, a counterweight 14, a connecting bearing 15, a guard plate 16, a counterweight direction adjustment hole 17, a counterweight hanging device 18, a base hanging device 19 and an angle detection element 20. The base 13 is installed at the front end of the harvesting platform by bolts; the profiling rod 10 is connected to the rotating shaft through the ball joint 12; the rotating shaft is installed on the base through the bearing 15; the counterweight 5 is installed at the end of the profiling rod 10 by bolts, and the rotation angle of the counterweight 14 can be adjusted through the direction adjustment hole 17 on the profiling rod 10; the hanging belt 13 hangs the profiling rod 10 on the base 11 through the hanging device 18 on the base and the counterweight.

[0047] The actuator includes: a cutting platform body 1, a reel lifting hydraulic cylinder 3, a reel 5, a reel lifting hydraulic cylinder 3, a reel forward and backward hydraulic cylinder 7, and a proportional valve group; the cutting platform body is connected to the bridge; one end of the reel forward and backward hydraulic cylinder 7 is fixed to the reel bracket, and the telescopic end is installed at the reel rotating shaft end; one end of the reel lifting hydraulic cylinder 3 is fixed to the cutting platform body 1, and the telescopic end is installed on the reel bracket.

[0048] In this embodiment, the PID control parameters of the harvester header adaptive control method are optimized based on the BP neural network model and genetic algorithm.

[0049] 1. Through field tests, test data under different speeds and crop densities are obtained, and a BP neural network is established using the data set of corresponding operating parameters.

[0050] (1) The influencing factors of the two-dimensional profiling control of the header include the operating speed, PID control parameters, the target value of the header height, the measured value of the header height, and the deviation between the target value and the actual value of the header height. The data set of the parameters of each influencing factor under a certain operating speed is selected to establish a BP neural network. A three-layer network structure is adopted, which is the input layer, hidden layer and output layer. The subscripts of the input layer, hidden layer and output layer are represented by i, j, and l respectively, and the superscripts are represented by 1, 2, and 3 respectively. The number of input layer nodes is 4, the number of hidden layer nodes is 7, and the number of output nodes of the output layer is 3. The input nodes and output nodes are shown in Table 1.

[0051] Table 1

[0052]

[0053] The output of the neural network input layer is: i (1) =x(i), (i=1,2,3,4), the input layer variables x(i) are respectively the machine tool operating speed v, the target value H of the header height, the measured value h of the header height, and the deviation value Δe between the measured value and the target value of the header height. The input and output of the hidden layer of the neural network are: Among them: NET j (2) is the input of the jth neuron in the hidden layer; W ji is the weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer; is the output of the i-th neuron in the input layer; The output of the jth neuron in the hidden layer. The input and output of the output layer of the neural network are: Among them: NET l (3) is the input of the lth neuron in the output layer; W lj(k) is the weight between the jth neuron in the hidden layer and the lth neuron in the output layer; is the output of the lth neuron in the output layer.

[0054] (2) The factors affecting the reel wheel speed control include the operating speed, crop density, PID control parameters, reel wheel speed measurement value, and the ratio of reel wheel speed to operating speed. The data set of the parameters of each influencing factor under a certain crop density condition is selected to establish a BP neural network. A three-layer network structure is adopted, with 4 input layer nodes, 8 hidden layer nodes, and 3 output nodes in the output layer. The input nodes and output nodes are shown in Table 2.

[0055] Table 2

[0056]

[0057] The output of the neural network input layer is expressed as: i (1) =x(i), (i=1,2,3,4); the input and output of the hidden layer of the neural network are: The input and output of the neural network output layer are:

[0058] In the two constructed BP neural network models, the hidden layer activation function uses the Tanh function Map the variables to [-1,1]; output layer parameter K p , K i , K D Cannot be negative, the activation function uses the Sigmoid function Map the variable to the range [0,1].

[0059] 2. Use genetic algorithm to optimize BP neural network model. First, combine all weights and thresholds in the neural network into an individual in the population; use the error between the predicted output value and the actual output of the neural network to establish the fitness function of GA; use "survival of the fittest" to replace the back propagation process in the BP neural network; reproduce n generations, and select the individual with the highest fitness from the population. This individual is the optimal weight and threshold of the model; use the optimal individual as the initial solution of the BP algorithm, and then use the BP algorithm to further optimize the neural network. When the preset optimization goal is reached or enough iterations are performed, the optimal parameter combination under the conditions of the operating speed or crop density is output to obtain the optimal control parameter K p , K i , K D The value of .

[0060] The above method is used to establish the optimal control parameter table for the two-dimensional longitudinal and transverse profiling control of the cutting platform under different operating speeds and the optimal control parameter table for the reel wheel speed control under different density conditions. Among them, the optimal control parameter table for the two-dimensional longitudinal and transverse profiling control of the cutting platform is used as a preset profiling control model, which can determine the corresponding cutting platform height adjustment information based on the height information of both sides of the cutting platform and the operating speed, so as to meet the needs of cutting platform height adjustment. The optimal control parameter table for reel wheel speed control is used as a preset reel wheel speed control model, which can determine the corresponding reel wheel speed adjustment information based on the measured values ​​of crop density, operating speed and reel wheel speed, so as to meet the needs of reel wheel speed adjustment.

[0061] 3. Adjust the header height and reel speed in both vertical and horizontal directions according to the optimal parameters

[0062] (1) The two-dimensional profiling control process of the cutting platform

[0063] During the operation of the machine, the two header longitudinal and transverse profiling devices 4 on both sides of the header detect the ups and downs of the working ground in real time. When it is detected that the header height value on one side of the header deviates from the set value Δe and does not meet the set deviation value range [Δe min Δe max ], the controller calls the optimal K at this speed p , K i , K D value, output PWM signal to control the opening of electromagnetic proportional valve, adjust the action of hydraulic cylinder of cutting platform lifting on that side, and realize rapid adjustment of cutting platform height.

[0064] (2) Reel speed control process

[0065] First, we need to measure the number of grain ears per unit area, that is, the crop density ρ. In order to prevent the industrial camera 4 from overlapping or missing the shooting area, the following conditions must be met: Where T is the interval time of camera shooting, D is the length of the camera field of view, and v is the forward speed of the machine. After image acquisition, the image contrast is enhanced, the captured image is preprocessed, the image is gridded and the color and texture features of the ears are extracted, the extracted feature data is standardized, and the image spots are classified using a classification learning method to identify the outline of the ears. The ear outline image is refined by hole filling, the total number of ears in the image is calculated, and the number of ears per unit area is obtained.

[0066] When the crop density ρ changes, the ratio coefficient k of the reel speed to the vehicle speed does not meet the set deviation value range [k min k max ], the controller calls the maximum K under the crop density condition p , K i , K DThe value is set, and the PWM signal is output to control the opening of the electromagnetic proportional valve, thereby adjusting the speed of the reel wheel and realizing adaptive adjustment of the reel wheel speed and crop density.

[0067] In addition, the image is processed to obtain lodging state information, and corresponding reel position adjustment parameters are determined based on the lodging state information and a preset reel position control model, wherein the preset reel position control model is a correspondence between the lodging state information and the reel position adjustment parameters; the reel position is controlled according to the reel position adjustment parameters.

[0068] Specifically, in this embodiment, the crop lodging status information is obtained by processing the image of the crop in front of the harvesting platform, and a preset reel position control model is established, which is the corresponding relationship between the lodging status information and the reel position adjustment parameters.

[0069] When the lodging state information includes forward lodging, the reel is adjusted to extend forward to the front position according to the reel position adjustment parameters, and the reel is adjusted to drop to the bottom position. When it is reverse lodging, the reel is adjusted to retract backward to the rear position, and the reel is adjusted to drop to the bottom position. This method of accurately adjusting the reel position according to the lodging state can better adapt to the actual growth of crops, improve harvesting efficiency, and reduce crop losses.

[0070] Specifically, the method for regulating the reel wheel in the crop lodging state can determine the crop lodging state through an image recognition method based on the crop image taken by the industrial camera 9. Similarly, a BP neural network model in the crop lodging state can be constructed according to the operation data, and a parameter table can be set. According to the grain image analysis, the grain is in a lodging state. When the grain is lodged in the forward direction, the reel wheel front and rear action hydraulic cylinder 7 is adjusted to extend to the limit state, so that the reel wheel is in the frontmost working position, and the reel wheel lifting hydraulic pressure 3 is lowered to the lowest position; when the reel wheel is lodged in the reverse direction, the reel wheel front and rear action hydraulic cylinder 7 is adjusted to contract to the limit state, so that the reel wheel is in the rearmost working position, and the reel wheel lifting hydraulic pressure 3 is lowered to the lowest position. After the reel wheel position is adjusted in place, the optimal control parameters are called to adjust the reel wheel speed according to the machine speed and crop density value.

[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for adaptively controlling a harvester header, characterized in that: include: The operation speed of the header, the height information of both sides of the header and the image of the crop in front of the header are obtained, and the image is processed to obtain the crop density according to the image information of the crop in front of the header; Based on the height information of both sides of the cutting platform, the operating speed and the preset profiling control model, the corresponding cutting platform height adjustment information is determined; based on the crop density, the operating speed and the preset reel wheel speed control model, the corresponding reel wheel speed adjustment information is determined; wherein the preset profiling control model is the corresponding relationship between the height information of both sides of the cutting platform, the operating speed and the cutting platform height adjustment information, and the preset reel wheel speed control model is the corresponding relationship between the crop density, the operating speed and the reel wheel speed adjustment information; The height of the header is controlled according to the header height adjustment information, and the speed of the reel is controlled according to the reel speed adjustment information.

2. The method for adaptively controlling the harvester header according to claim 1, characterized in that: Also includes: Process the image to obtain lodging state information, determine corresponding reel position adjustment parameters based on the lodging state information and a preset reel position control model, the preset reel position control model is a correspondence between the lodging state information and the reel position adjustment parameters; and control the reel position according to the reel position adjustment parameters.

3. The method for adaptively controlling the harvester header according to claim 2, characterized in that: The lodging state information includes forward lodging and reverse lodging relative to the working direction, and the reel position adjustment parameters include reel lifting information and reel front and rear extension information.

4. The method for adaptively controlling the harvester header according to claim 3, characterized in that: The controlling the position of the reel according to the reel position adjustment parameter comprises: When lodging in the forward direction, adjust the reel to extend forward to the front end position, and adjust the reel to descend to the bottom end position; When lodging in reverse direction, the reel is adjusted to retract to the rear end position, and the reel is adjusted to descend to the bottom end position.

5. The method for adaptively controlling the harvester header according to claim 1, characterized in that: Also includes: Through field tests, test data at different speeds and different crop densities were obtained, and the BP neural network model was established using the test data of corresponding operation parameters; Genetic algorithm is used to optimize the BP neural network model, and the optimal control parameter table of the vertical and horizontal two-dimensional profiling control of the header under different operating speeds and the optimal control parameter table of the reel speed control under different density conditions are established; According to the optimal control parameter table of the longitudinal and transverse two-dimensional profiling control of the cutting platform under different operating speeds and the optimal control parameter table of the reel speed control under different density conditions, a preset profiling control model and a preset reel speed control model are established.

6. The method for adaptively controlling the harvester header according to claim 5, characterized in that: When establishing the preset profiling control model, the influencing factors of the longitudinal and transverse two-dimensional profiling control of the header include the operating speed, PID control parameters, the header height target value, the header height measurement value, and the deviation between the header height target value and the actual value.

7. The method for adaptively controlling the harvester header according to claim 6, characterized in that: When establishing a preset reel wheel speed control model, the influencing factors of reel wheel speed control include operating speed, crop density value, PID control parameters, reel wheel speed measurement value, and the ratio of reel wheel speed to operating speed.

8. The method for adaptively controlling a harvester header according to claim 1, characterized in that: The processing of the image to obtain the crop density comprises: Acquire the image of the crop in front of the header, pre-process the captured image, grid the image and extract the color and texture features of the ear of grain; The extracted feature data is standardized, and the image spots are classified using a classification learning method to identify the outline of the ears of grain. The outline image of the ears of grain is refined by filling holes, and the total number of ears of grain in the image is calculated to obtain the number of ears of grain per unit area and the crop density.

9. The method for adaptively controlling a harvester header according to claim 1, characterized in that: The operating speed is obtained through a travel speed sensor, the height information of both sides of the harvesting platform is obtained through a harvesting platform longitudinal and transverse profiling device, the reel speed is obtained through a reel speed sensor, and the image is obtained through an industrial camera on the harvester.

10. The method for adaptively controlling a harvester header according to claim 1 or 9, characterized in that: The height of the cutting platform is driven and adjusted by a cutting platform lifting hydraulic cylinder, and the reel rotation speed is adjusted by a hydraulic motor.

Images