Method for detecting deviation of cotton picking machine from row based on GNSS and mechanical sensing

Abstract

The application discloses a kind of based on GNSS and mechanical sensing's cotton picker deviation detection method, method includes: obtaining the deviation original value of current time cotton picker's alignment sensor device measurement cotton picker deviation;Obtain the alignment sensor device detection point coordinate and movement heading of current time cotton picker, and save to first-in first-out queue;Based on deviation original value and set deviation threshold, judge whether the crop row of cotton picker alignment sensor device detection point is missing row broken ridge;If not missing row broken ridge, utilize the designed Kalman filter, alignment sensor data and GNSS data are fused and handled to obtain more accurate and smooth alignment deviation estimation result;If missing row broken ridge, adopt GNSS positioning to calculate the alignment deviation of alignment sensor device detection point, until all alignment deviation detection is completed.The application makes that cotton picker can adapt to the small curvature variation of crop row when automatic alignment operation, also can guarantee stable and accurate alignment when cotton field missing plant broken ridge.

Description

Technical Field

[0001] This invention belongs to the technical field of agricultural machinery automation, specifically relating to a method for detecting row deviation in cotton harvesters based on GNSS and mechanical sensing. Background Technology

[0002] Cotton, as one of my country's key economic crops, occupies a pivotal position in domestic agriculture. In recent years, with the advancement of mechanized cotton harvesting and impurity removal technology in Xinjiang Uygur Autonomous Region and the booming development of the domestic cotton harvester industry, cotton harvesting costs have been effectively controlled, labor productivity and operational quality have significantly improved, and the scale of Xinjiang Uygur Autonomous Region's cotton industry has expanded rapidly. However, in the process of intelligent cotton harvesting, the level of intelligence and informatization of cotton harvesters in Xinjiang Uygur Autonomous Region still needs improvement. Although satellite navigation-assisted operations have been implemented in the cultivation and management stage, manual driving is still relied upon in the harvesting stage, increasing the workload of operators. At the same time, in order to meet the precision requirements of cotton planting and harvesting (sowing straight-line error and row alignment error not exceeding 3 cm, and harvesting row alignment error not exceeding 5 cm), the row alignment control of cotton harvesters poses a high technical challenge.

[0003] Shanghai University has developed an intelligent row-alignment control system based on machine vision. This system uses cameras to acquire real-time images of the cotton harvester's field and processes these images to identify the position of the cotton rows, thereby guiding the harvester to automatically align with the rows. However, when cotton enters the harvest season, the cotton field environment becomes more complex due to the leakage of fibers from the cotton bolls, affecting the recognition efficiency of the machine vision system and limiting its application.

[0004] Shaya Boshiran Intelligent Agricultural Machinery Co., Ltd. has designed a mechanical alignment structure that uses a linkage assembly and angle sensors mounted on the divider to monitor the alignment deviation of the cotton harvester. Although this method is less expensive, its alignment accuracy is not high, especially when dealing with cotton fields with missing plants or broken rows.

[0005] In addition, Shanghai University proposed a parallel trajectory navigation method. This method first requires the operator to manually drive the cotton harvester to complete the first row alignment and record the GNSS-RTK positioning data. Then, based on this data, a parallel navigation baseline is calculated for the subsequent harvesting of each row. While this method has some adaptability to handling missing plants or gaps in the rows, its adaptability decreases for non-straight crop rows or crop rows with small curvature changes.

[0006] Therefore, developing a reliable method for detecting the row alignment status of cotton harvesters has become a pressing technical problem in this field, in order to ensure efficient and accurate automatic row alignment control even in complex cotton field environments. Summary of the Invention

[0007] The main objective of this invention is to overcome the shortcomings and deficiencies of the prior art and provide a method for detecting row alignment deviation in cotton harvesters based on GNSS and mechanical sensing. This invention combines satellite positioning and row alignment sensing devices, integrating the row alignment deviation obtained by satellite positioning with that obtained by mechanical sensors. This allows the cotton harvester to adapt to small curvature changes in crop rows during automatic row alignment operations, while also ensuring stable and accurate row alignment when there are missing plants or gaps in the cotton field, thereby improving system reliability.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] In a first aspect, the present invention provides a method for detecting row deviation of a cotton harvester based on GNSS and mechanical sensing, comprising the following steps:

[0010] Obtain the original value of the cotton harvester's row alignment deviation as measured by the row alignment sensor at the current moment;

[0011] The positioning coordinates of the main antenna in the GNSS dual antenna on the cotton harvester are converted to the detection points of the row sensor device to obtain the coordinates of the detection points of the row sensor device. The heading of the cotton harvester is measured based on the GNSS dual antenna. The coordinates of the detection points of the row sensor device and the heading of the cotton harvester are saved to the first-in-first-out queue.

[0012] Based on the original deviation value and the set deviation threshold, it is determined whether there are missing rows or broken rows of crops at the detection point of the row sensor of the cotton harvester.

[0013] If there are no missing rows or gaps, the designed Kalman filter can be used to fuse the row sensor data and GNSS data to obtain a more accurate and smooth row deviation estimation result.

[0014] If there are missing rows or gaps in the rows, GNSS positioning is used to calculate the alignment deviation at the detection points of the alignment sensor until all alignment deviations are detected.

[0015] As a preferred technical solution, obtaining the original value of the cotton harvester's row deviation measured by the row sensing device at the current moment specifically involves:

[0016] During the operation of the cotton harvester along the crop row, when the cotton harvesting head deviates from the center line of the crop row, the cotton plant stalk will touch the detection rod of the mechanical row alignment sensor installed on both sides of the cotton harvesting head. The angle at which the cotton plant stalk pushes the detection rod to rotate is measured by the angle sensor and converted into the original value of the row alignment deviation.

[0017] As a preferred technical solution, the positioning coordinates of the main antenna in the GNSS dual antennas on the cotton harvester are transformed to the detection points of the row sensing device, using the following coordinate transformation formula:

[0018]

[0019] In the formula, x dn y dn To determine the coordinates of the sensor detection points in the geodetic navigation coordinate system, x gn y gn The coordinates of the GNSS main antenna in the geodetic navigation coordinate system are: x represents the heading deviation of the cotton harvester's movement. db y db To determine the positioning coordinates of the sensor detection points in the cotton harvester's body coordinate system, x gb y gb The coordinates of the GNSS main antenna in the cotton harvester's body coordinate system are generally (x db ,y db ) and (x gb ,y gb The position coordinates of the cotton harvester in the machine's coordinate system remain fixed.

[0020] As a preferred technical solution, the determination of whether there are missing rows or gaps in the crop row at the detection point of the cotton harvester's row sensor specifically involves:

[0021] If the range of N consecutive jumps in the original value of the cotton harvester's row deviation is less than the set deviation jump threshold, it is determined to be a missing row or broken row; otherwise, it is determined to be a normal crop row.

[0022] As a preferred technical solution, the designed Kalman filter is as follows:

[0023] Assume the cotton harvester moves in an approximately straight line with a gradually changing speed during operation. Define the state vector x of the Kalman filter. k for:

[0024]

[0025] In the formula, This is the estimation result of the line deviation of the line sensor; This is an estimate of the cotton harvester speed;

[0026] The state transition matrix A of the Kalman filter k for:

[0027]

[0028] In the formula, dt is the operating period of the filter. The heading deviation is the deviation of the cotton harvester from the target heading. The heading deviation is calculated as follows:

[0029] The current target heading ψ of the cotton harvester is obtained by averaging the cumulative headings of the cotton harvesters in the first-in-first-out queue. ref :

[0030]

[0031] In the formula, N is the counter for program operation, N > 0. When the cotton harvester starts, stops, or turns around, the counter and the heading accumulation value are re-initialized, and the current heading deviation of the cotton harvester is:

[0032] ψ e =ψ ref -ψ

[0033] The observation vector Z of the Kalman filter k The observation matrix H is as follows:

[0034]

[0035] In the formula, To introduce observation noise into the positional deviation observations of the line sensor; GNSS dual-antenna velocity observations to introduce observation noise.

[0036] As a preferred technical solution, if there are missing rows or gaps in the rows, GNSS positioning is used to calculate the alignment deviation at the detection point of the mechanical row alignment sensor. Specifically:

[0037] The coordinate data of the detection points of the row sensors in the first-in-first-out queue are fitted with a straight line using the least squares method. The formulas for calculating the slope and intercept of the straight line are as follows:

[0038]

[0039] In the formula, Let be the slope estimate of the linear function; n is the length of the first-in-first-out queue; x(i) and y(i) are the coordinates of the cotton harvester's trajectory points at time i; The mean of the x-coordinates; The mean of the y-coordinates; This is the intercept value of a linear function;

[0040] GNSS alignment deviation is calculated using the point-to-line method. The equation of the reference path is ax + by + c = 0, and the GNSS positioning coordinates of the detection point are (x, y). It is defined that when the detection point is to the left of the direction of travel on the reference path, d... e <0, when the detection point is on the right side of the reference path's direction of travel. e If the value is greater than 0, the positional deviation calculated using the GNSS point-to-line method is as follows:

[0041]

[0042] In the formula, y(k) represents the line deviation of the detection point calculated by GNSS at time k; x(k) represents the x-coordinate of the detection point at time k; y(k) represents the y-coordinate of the detection point at time k.

[0043] As a preferred technical solution, the designed Kalman filter is used to fuse the line sensor data and GNSS data, specifically as follows:

[0044] The state vector of the Kalman filter consists of the cotton harvester's alignment deviation and forward speed, while the measurement vector consists of the alignment deviation observations from the alignment sensor and the GNSS dual-antenna speed observations. The state transition matrix is ​​updated in real time based on the heading deviation of the cotton harvester from the target heading. The parameters of the state noise variance matrix and the measurement noise variance matrix are tuned based on the filter estimation results.

[0045] Secondly, the present invention provides a cotton harvester row deviation detection system based on GNSS and mechanical sensing, which is applied to the cotton harvester row deviation detection method based on GNSS and mechanical sensing, including a row deviation calculation module, a coordinate transformation module, a row missing and row break judgment module, a first processing module and a second processing module.

[0046] The row deviation calculation module is used to obtain the original value of the row deviation of the cotton harvester measured by the row sensing device of the cotton harvester at the current moment;

[0047] The coordinate transformation module is used to transform the positioning coordinates of the main antenna in the GNSS dual antennas on the cotton harvester to the detection point of the row sensor device, obtain the coordinates of the detection point of the row sensor device, and measure the heading of the cotton harvester based on the GNSS dual antennas, and save the coordinates of the detection point of the row sensor device and the heading of the cotton harvester to the first-in-first-out queue.

[0048] The missing row / broken row judgment module is used to determine whether the crop row at the detection point of the row sensor of the cotton harvester is missing or broken based on the original deviation value and the set deviation jump threshold.

[0049] The first processing module is used to fuse the row sensor data and GNSS data using a designed Kalman filter if there are no missing rows or gaps in the rows, in order to obtain a more accurate and smoother row deviation estimation result.

[0050] The second processing module is used to calculate the alignment deviation at the detection point of the alignment sensor device using GNSS positioning if there are missing rows or gaps in the rows, until all alignment deviations are detected.

[0051] Thirdly, the present invention provides a cotton harvester, the cotton harvester comprising:

[0052] At least one processor; and,

[0053] A memory communicatively connected to the at least one processor; wherein,

[0054] The memory stores computer program instructions that can be executed by the at least one processor, which enables the at least one processor to execute the GNSS and mechanical sensing-based cotton harvester row deviation detection method.

[0055] Fourthly, the present invention provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the method for detecting row deviation of cotton harvesters based on GNSS and mechanical sensing.

[0056] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0057] This invention combines satellite positioning with row alignment sensing devices, integrating the row alignment deviation obtained from satellite positioning with that obtained from mechanical sensors. This allows the cotton harvester to adapt to small curvature changes in crop rows during automatic row alignment operations, while also ensuring stable and accurate row alignment when cotton fields have missing plants or broken rows, thereby improving system reliability. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a flowchart of a cotton harvester row deviation detection method based on GNSS and mechanical sensing according to an embodiment of the present invention;

[0060] Figure 2 This is a schematic diagram of coordinate transformation according to an embodiment of the present invention;

[0061] Figure 3 This is a block diagram of a cotton harvester row deviation detection system based on GNSS and mechanical sensing, according to an embodiment of the present invention.

[0062] Figure 4 This is a structural diagram of a cotton harvester according to an embodiment of the present invention. Detailed Implementation

[0063] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort are within the scope of protection of the present application.

[0064] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0065] like Figure 1 As shown, this embodiment provides a method for detecting row deviation in cotton harvesters based on GNSS and mechanical sensing, including the following steps:

[0066] Step 1: Obtain the original value of the cotton harvester's row deviation measured by the row sensor at the current moment.

[0067] Furthermore, during the operation of the cotton harvester along the crop row, when the cotton harvesting head deviates from the center line of the crop row, the cotton plant stalk will touch the detection rod of the mechanical row alignment sensor installed on both sides of the cotton harvesting head. The angle at which the cotton plant stalk pushes the detection rod to rotate is measured by the angle sensor and converted into row alignment deviation.

[0068] Step 2: Obtain the coordinates of the detection points of the cotton harvester's row sensors and its heading at the current moment, and save them to the first-in-first-out queue.

[0069] like Figure 2 As shown, based on the Euler transformation principle, the positioning coordinates of the main antenna in the GNSS dual antenna installed on the roof of the cotton harvester cab are transformed to the detection points of the row sensing device, and then buffered together with the cotton harvester's heading measured by the dual-antenna GNSS into a fixed-length first-in-first-out queue.

[0070] Furthermore, the positioning coordinates of the main antenna in the GNSS dual antennas on the cotton harvester are transformed to the detection points of the row sensing device using the following coordinate transformation formula:

[0071]

[0072] In the formula, x dn y dn To determine the coordinates of the sensor detection points in the geodetic navigation coordinate system, x gn ygn The coordinates of the GNSS main antenna in the geodetic navigation coordinate system are: x represents the heading deviation of the cotton harvester's movement. db y db To determine the positioning coordinates of the sensor detection points in the cotton harvester's body coordinate system, x gb y gb The coordinates of the GNSS main antenna in the cotton harvester's body coordinate system are generally (x db ,y db ) and (x gb ,y gb The position coordinates of the cotton harvester in the machine's coordinate system remain fixed.

[0073] Step 3: Determine whether there are missing rows or gaps in the crop rows at the detection point of the cotton harvester's row sensor.

[0074] Furthermore, if the range of N consecutive jumps in the original measurement value of the row deviation of the cotton harvester is less than the set deviation jump threshold, it is determined to be a missing row or broken row; otherwise, it is determined to be a normal crop row.

[0075] For example, under conditions of missing rows and broken rows, 1000 sets of raw row deviation data were measured from the row alignment sensor. Set threshold max and min correspond to the maximum and minimum values ​​of the row deviation measurement, respectively. M is the threshold proportional coefficient. The values ​​of M and N are adjusted in the actual working environment.

[0076] Step 4: If there are no missing rows or broken rows, use the designed Kalman filter to fuse the row sensor data and GNSS data to obtain a more accurate and smooth row deviation estimation result.

[0077] Furthermore, the Kalman filter is designed as follows:

[0078] Assuming the cotton harvester moves in an approximately straight line with a gradually changing speed during operation, the state vector of the Kalman filter is defined as follows:

[0079]

[0080] In the formula, This is the estimation result of the row deviation of the row sensor; This is the estimated speed of the cotton harvester.

[0081] The state transition matrix of the filter is:

[0082]

[0083] In the formula, dt is the operating period of the filter. Since the output frequency of the positioning board is 10Hz, we take dt = 0.1s. The heading deviation of the cotton harvester from the target heading is calculated as follows:

[0084] The current target heading of the cotton harvester is obtained by averaging the cumulative headings of the cotton harvesters in the first-in-first-out queue.

[0085]

[0086] In the formula, N is the counter used for program execution, and N > 0. When the cotton harvester starts, stops, or turns around, the counter and the heading accumulation value need to be reinitialized. Therefore, the current heading deviation of the cotton harvester is:

[0087] ψ e =ψ ref -ψ

[0088] The observation vector and observation matrix of the Kalman filter are as follows:

[0089]

[0090] In the formula, To introduce observation noise into the positional deviation observations of the line sensor; GNSS dual-antenna velocity observations to introduce observation noise.

[0091] Kalman filter Q k and R k The parameters were tuned through experiments.

[0092] Furthermore, using the designed Kalman filter, the line sensor data and GNSS data are fused and processed, specifically as follows:

[0093] The state vector of the Kalman filter consists of the cotton harvester's alignment deviation and forward speed, while the measurement vector consists of the alignment deviation observations from the alignment sensor and the GNSS dual-antenna speed observations. The state transition matrix is ​​updated in real time based on the heading deviation of the cotton harvester from the target heading. The parameters of the state noise variance matrix and the measurement noise variance matrix are tuned based on the filter estimation results.

[0094] Step 5: If there are missing rows or gaps in the rows, use GNSS positioning to calculate the alignment deviation at the detection point of the mechanical alignment sensor.

[0095] Furthermore, the coordinate data in the first-in-first-out queue are fitted with a straight line using the least squares method. The formulas for calculating the slope and intercept of the straight line are as follows:

[0096]

[0097] In the formula, y(i) is the slope estimate of the linear function; n is the length of the identification data, that is, the length of the first-in-first-out queue; x(i) and y(i) are the coordinates of the cotton harvester's trajectory points at time i; Let m be the mean of the x-coordinates; Let m be the mean of the y-coordinates;

[0098] This is the intercept value of a linear function.

[0099] GNSS alignment deviation is calculated using the point-to-line method. Assume the equation of the reference path is ax + by + c = 0, and the GNSS positioning coordinates of the detection point are (x, y). It is defined that when the detection point is to the left of the direction of travel on the reference path, d... e <0, when the detection point is on the right side of the reference path's direction of travel. e If the value is greater than 0, the positional deviation calculated using the GNSS point-to-line method is as follows:

[0100]

[0101] In the formula, Let x(k) represent the line deviation of the detection point calculated by GNSS at time k, m; x(k) represent the x-coordinate of the detection point at time k, m; and y(k) represent the y-coordinate of the detection point at time k, m.

[0102] Step 6: Return to Step 1 and repeat the process until all rows have been checked.

[0103] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously.

[0104] Based on the same concept as the cotton harvester row deviation detection method based on GNSS and mechanical sensing in the above embodiments, the present invention also provides a cotton harvester row deviation detection system based on GNSS and mechanical sensing. This system can be used to execute the above-described cotton harvester row deviation detection method based on GNSS and mechanical sensing. For ease of explanation, the structural schematic diagram of the embodiment of the cotton harvester row deviation detection system based on GNSS and mechanical sensing only shows the parts related to the embodiments of the present invention. Those skilled in the art will understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0105] Please see Figure 3In another embodiment of this application, a cotton harvester row deviation detection system 100 based on GNSS and mechanical sensing is provided. The system includes a row deviation calculation module 101, a coordinate transformation module 102, a row gap / break judgment module 103, a first processing module 104, and a second processing module 105.

[0106] The row deviation calculation module 101 is used to obtain the original value of the row deviation of the cotton harvester measured by the row sensing device of the cotton harvester at the current moment.

[0107] The coordinate transformation module 102 is used to transform the positioning coordinates of the main antenna in the GNSS dual antenna on the cotton harvester to the detection point of the row sensor device, obtain the coordinates of the detection point of the row sensor device, and measure the heading of the cotton harvester based on the GNSS dual antenna, and save the coordinates of the detection point of the row sensor device and the heading of the cotton harvester to the first-in-first-out queue.

[0108] The missing row / broken row judgment module 103 is used to determine whether the crop row at the detection point of the row sensor of the cotton harvester is missing or broken based on the original deviation value and the set deviation jump threshold.

[0109] The first processing module 104 is used to fuse the row sensor data and GNSS data using a designed Kalman filter if there are no missing rows or broken rows, in order to obtain a more accurate and smooth row deviation estimation result.

[0110] The second processing module 105 is used to calculate the row alignment deviation at the detection point of the row alignment sensor using GNSS positioning if there are missing rows or broken rows, until all row alignment deviations are detected.

[0111] It should be noted that the cotton harvester row deviation detection system based on GNSS and mechanical sensing of the present invention corresponds one-to-one with the cotton harvester row deviation detection method based on GNSS and mechanical sensing of the present invention. The technical features and beneficial effects described in the embodiments of the cotton harvester row deviation detection method based on GNSS and mechanical sensing are applicable to the embodiments of cotton harvester row deviation detection based on GNSS and mechanical sensing. For details, please refer to the description in the embodiments of the method of the present invention, which will not be repeated here.

[0112] Furthermore, in the above embodiments of the cotton harvester row deviation detection system based on GNSS and mechanical sensing, the logical division of each program module is only an example. In actual applications, the above functions can be assigned to different program modules as needed, for example, for the sake of corresponding hardware configuration requirements or software implementation convenience. That is, the internal structure of the cotton harvester row deviation detection system based on GNSS and mechanical sensing is divided into different program modules to complete all or part of the functions described above.

[0113] Please see Figure 4 In one embodiment, a cotton harvester is provided that implements a cotton harvester row deviation detection method based on GNSS and mechanical sensing. The cotton harvester 200 may include a first processor 201, a first memory 202 and a bus, and may also include a computer program stored in the first memory 202 and executable on the first processor 201, such as a cotton harvester row deviation detection program 203 based on GNSS and mechanical sensing.

[0114] The first memory 202 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the first memory 202 can be an internal storage unit of the cotton harvester 200, such as the portable hard drive of the cotton harvester 200. In other embodiments, the first memory 202 can also be an external storage device of the cotton harvester 200, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the cotton harvester 200. Furthermore, the first memory 202 can include both internal storage units and external storage devices of the cotton harvester 200. The first memory 202 can be used not only to store application software and various data installed on the cotton harvester 200, such as the code of the cotton harvester row deviation detection program 203 based on GNSS and mechanical sensing, but also to temporarily store data that has been output or will be output.

[0115] In some embodiments, the first processor 201 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The first processor 201 is the control unit of the cotton harvester, connecting various components of the cotton harvester through various interfaces and lines. It executes programs or modules stored in the first memory 202 and calls data stored in the first memory 202 to perform various functions of the cotton harvester 200 and process data.

[0116] Figure 4 Only a cotton harvester with components is shown; those skilled in the art will understand that... Figure 4The structure shown does not constitute a limitation on the cotton harvester 200, and may include fewer or more parts than shown, or combine certain parts, or have different arrangements of parts.

[0117] The cotton harvester 200's first memory 202 stores a GNSS and mechanical sensing-based cotton harvester row deviation detection program 203, which is a combination of multiple instructions. When run in the first processor 201, it can achieve the following:

[0118] Obtain the original value of the cotton harvester's row alignment deviation as measured by the row alignment sensor at the current moment;

[0119] The positioning coordinates of the main antenna in the GNSS dual antenna on the cotton harvester are converted to the detection points of the row sensor device to obtain the coordinates of the detection points of the row sensor device. The heading of the cotton harvester is measured based on the GNSS dual antenna. The coordinates of the detection points of the row sensor device and the heading of the cotton harvester are saved to the first-in-first-out queue.

[0120] Based on the original deviation value and the set deviation threshold, it is determined whether there are missing rows or broken rows of crops at the detection point of the row sensor of the cotton harvester.

[0121] If there are no missing rows or gaps, the designed Kalman filter can be used to fuse the row sensor data and GNSS data to obtain a more accurate and smooth row deviation estimation result.

[0122] If there are missing rows or gaps in the rows, GNSS positioning is used to calculate the alignment deviation at the detection points of the alignment sensor until all alignment deviations are detected.

[0123] Furthermore, if the modules / units integrated into the cotton harvester 200 are implemented as software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0124] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0125] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0126] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A method for detecting row deviation in cotton harvesters based on GNSS and mechanical sensing, characterized in that, Includes the following steps: Obtain the original value of the cotton harvester's row alignment deviation as measured by the mechanical row alignment sensor at the current moment; The positioning coordinates of the main antenna in the GNSS dual antenna on the cotton harvester are converted to the detection point of the mechanical row-to-row sensor to obtain the coordinates of the detection point of the mechanical row-to-row sensor. The heading of the cotton harvester is measured based on the GNSS dual antenna. The coordinates of the detection point of the mechanical row-to-row sensor and the heading of the cotton harvester are saved to the first-in-first-out queue. Based on the original deviation value and the set deviation threshold, it is determined whether there are missing rows or broken rows of crops at the detection point of the cotton harvester's mechanical row sensor. If there are no missing rows or gaps, the data from the mechanical alignment sensor and GNSS data can be fused using the designed Kalman filter to obtain a more accurate and smoother alignment deviation estimation result. If there are missing rows or gaps in the rows, use GNSS positioning to calculate the alignment deviation at the detection points of the mechanical alignment sensor until all alignment deviations are detected. The designed Kalman filter is as follows: Assume the cotton harvester moves in an approximately straight line with a gradually changing speed during operation. Define the state vector of the Kalman filter. for: In the formula, This is the estimation result of the line deviation of the mechanical line-to-line sensing device; This is an estimate of the cotton harvester speed; Kalman filter state transition matrix for: In the formula, The filter's operating cycle, The heading deviation is the deviation of the cotton harvester from the target heading. The heading deviation is calculated as follows: The current target heading of the cotton harvester is obtained by averaging the cumulative headings of the cotton harvesters in the first-in-first-out queue. : In the formula This is a counter used during program execution. When the cotton harvester starts, stops, or turns around, the counter and heading accumulation value are reinitialized. The current heading deviation of the cotton harvester is then: The observation vector Z of the Kalman filter k The observation matrix H is as follows: In the formula, The mechanical pair position deviation observation value of the line sensor is used to introduce observation noise; GNSS dual-antenna velocity observations to introduce observation noise; The designed Kalman filter is used to fuse data from the mechanical line sensing device and GNSS data, specifically as follows: The state vector of the Kalman filter consists of the cotton harvester's row deviation and forward speed, while the measurement vector consists of the row deviation observations from the mechanical row sensor and the GNSS dual-antenna speed observations. The state transition matrix is ​​updated in real time based on the heading deviation of the cotton harvester from the target heading. The parameters of the state noise variance matrix and the measurement noise variance matrix are tuned based on the filter estimation results.

2. The method for detecting row deviation of cotton harvesters based on GNSS and mechanical sensing according to claim 1, characterized in that, The process of obtaining the original value of the cotton harvester's row alignment deviation measured by the mechanical row alignment sensor at the current moment is specifically as follows: During the operation of the cotton harvester along the crop row, when the cotton harvesting head deviates from the center line of the crop row, the cotton plant stalk will touch the detection rod of the mechanical row alignment sensor installed on both sides of the cotton harvesting head. The angle at which the cotton plant stalk pushes the detection rod to rotate is measured by the angle sensor and converted into the original value of the row alignment deviation.

3. The method for detecting row deviation of cotton harvesters based on GNSS and mechanical sensing according to claim 1, characterized in that, The coordinate transformation formula is as follows: The positioning coordinates of the main antenna in the GNSS dual antenna system on the cotton harvester are converted to the detection points of the mechanical row-to-row sensor. In the formula, , The coordinates of the detection points of the mechanical line sensing device in the geodetic navigation coordinate system. , The coordinates of the GNSS main antenna in the geodetic navigation coordinate system are: This refers to the heading deviation of the cotton harvester's movement. , The coordinates of the detection points of the mechanical line sensor device in the coordinate system of the cotton harvester. , These are the positioning coordinates of the GNSS main antenna in the cotton harvester's body coordinate system. and The position coordinates of the cotton harvester in the vehicle coordinate system remain fixed.

4. The method for detecting row deviation of cotton harvesters based on GNSS and mechanical sensing according to claim 1, characterized in that, The determination of whether there are missing rows or gaps in the crop rows at the detection point of the cotton harvester's mechanical row sensor is as follows: If the original value of the cotton harvester's row deviation is continuous If the jump range is less than the set deviation jump threshold, it is determined to be a missing row or broken row; otherwise, it is determined to be a normal crop row.

5. The method for detecting row deviation of cotton harvesters based on GNSS and mechanical sensing according to claim 1, characterized in that, If there are missing rows or gaps in the rows, the alignment deviation at the detection point of the mechanical alignment sensor is calculated using GNSS positioning. Specifically: The coordinate data of the detection points of the mechanical pairing sensors in the first-in-first-out queue are fitted using the least squares method. The formulas for calculating the slope and intercept of the line are as follows: In the formula, is the estimated slope of the linear function; n is the length of the first-in-first-out queue; , for The coordinates of the cotton harvester's travel trajectory points at all times; for The mean of the coordinates; for The mean of the coordinates; This is the intercept value of a linear function; The GNSS alignment deviation is calculated using the point-to-line method, assuming the equation of the reference path is... The GNSS positioning coordinates of the detection point are It is stipulated that when the detection point is on the left side of the reference path's direction of travel... When the detection point is on the right side of the reference path's direction of travel The positional deviation calculated using the GNSS point-to-line method is as follows: In the formula, Indicates the first The line deviation of the detection point is calculated by GNSS at any time; Indicates the first The x-coordinate of the detection point at any given time; Indicates the first The ordinate of the time-based detection point.

6. A cotton harvester row deviation detection system based on GNSS and mechanical sensing, characterized in that, The cotton harvester row deviation detection method based on GNSS and mechanical sensing, applied to any one of claims 1-5, includes a row deviation calculation module, a coordinate transformation module, a row missing / row break judgment module, a first processing module, and a second processing module. The row alignment deviation calculation module is used to obtain the original value of the cotton harvester's row alignment deviation measured by the mechanical row alignment sensor of the cotton harvester at the current moment; The coordinate transformation module is used to transform the positioning coordinates of the main antenna in the GNSS dual antenna on the cotton harvester to the detection point of the mechanical row-to-row sensor, obtain the coordinates of the detection point of the mechanical row-to-row sensor, and measure the heading of the cotton harvester based on the GNSS dual antenna, and save the coordinates of the detection point of the mechanical row-to-row sensor and the heading of the cotton harvester to the first-in-first-out queue. The missing row / broken row judgment module is used to determine whether there are missing rows / broken rows at the detection point of the cotton harvester's mechanical row sensor based on the original deviation value and the set deviation jump threshold. The first processing module is used to fuse the data from the mechanical row alignment sensor and the GNSS data using a designed Kalman filter, if there are no missing rows or broken rows, to obtain a more accurate and smooth row alignment deviation estimation result. The second processing module is used to calculate the alignment deviation at the detection point of the mechanical alignment sensor device if there is a missing row or a broken row, until all alignment deviations are detected.

7. A cotton harvester, characterized in that, The cotton harvester includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the cotton harvester row deviation detection method based on GNSS and mechanical sensing as described in any one of claims 1-5.

8. A computer-readable storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the cotton harvester row deviation detection method based on GNSS and mechanical sensing as described in any one of claims 1-5.

Images