A method and system for combine harvester feed rate detection and control

Abstract

The application discloses a combine harvester feeding amount detection and control method and system, and relates to the field of intelligent monitoring of agricultural machinery. The method comprises the following steps: collecting operation parameters of a combine harvester in real time; generating a control signal by using a variable universe fuzzy PID control algorithm according to the operation parameters and a pre-established feeding amount detection model; the feeding amount detection model is a relationship model of operation parameters and actual feeding amount; the variable universe fuzzy PID control algorithm is a universe self-adapting stretching and contracting mechanism introduced in a fuzzy PID algorithm; and the forward speed of the combine harvester is adjusted based on the control signal to control the feeding amount of the combine harvester. The application realizes real-time detection and stable control of the feeding amount of the combine harvester during operation, and thus improves the harvesting quality of the combine harvester.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring of agricultural machinery, and in particular to a method and system for detecting and controlling the feed amount of a combine harvester. Background Technology

[0002] As a key piece of equipment in the grain harvesting process, the efficiency and quality of combine harvesters directly affect the quality of the harvest. In recent years, the rate of agricultural mechanization has increased significantly, but combine harvesters still suffer from problems such as reliance on manual experience for monitoring operating parameters and unstable feed control, resulting in a high harvest loss rate.

[0003] Feeding, as the initial stage of harvesting, is affected by various factors and is closely related to the harvester's operating speed, stubble height, and crop density and height in the field. The feeding amount is also an important indicator for measuring the harvester's performance. Excessive feeding can easily cause problems such as harvester blockage, engine overload, and accelerated blade wear. Insufficient feeding will cause the harvester to idle and uneven wear of parts. Therefore, it is crucial to keep the feeding amount stably within a reasonable range to improve harvester efficiency and reduce harvester failure rate. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for detecting and controlling the feed amount of a combine harvester, which can realize real-time detection and stable control of the feed amount during the operation of the combine harvester, thereby improving the harvesting quality of the combine harvester.

[0005] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a method for detecting and controlling the feed rate of a combine harvester, including: Real-time acquisition of combine harvester operating parameters; Based on the operation parameters and the pre-established feed rate detection model, a variable universe of discourse fuzzy PID control algorithm is used to generate control signals; the feed rate detection model is a relationship model between the operation parameters and the actual feed rate; the variable universe of discourse fuzzy PID control algorithm is a fuzzy PID algorithm that introduces an adaptive universe of discourse scaling mechanism. The forward speed of the combine harvester is adjusted based on the control signal to control the feed rate of the combine harvester.

[0006] Secondly, this application provides a combine harvester feed rate detection and control system, comprising: The operation information acquisition module is used to collect the operation parameters of the combine harvester in real time; The intelligent control module is used to generate control signals using a variable universe of discourse fuzzy PID control algorithm based on the operation parameters and a pre-established feed rate detection model; the feed rate detection model is a relationship model between the operation parameters and the actual feed rate; the variable universe of discourse fuzzy PID control algorithm is a fuzzy PID algorithm that introduces an adaptive universe of discourse scaling mechanism. An adjustment module is executed to adjust the forward speed of the combine harvester based on the control signal, so as to control the feed rate of the combine harvester.

[0007] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a method and system for detecting and controlling the feed amount of a combine harvester. By collecting the operating parameters of the combine harvester in real time and determining the actual feed amount based on the feed amount detection model, the detection efficiency and accuracy of the feed amount are improved. Furthermore, a variable universe of discourse fuzzy PID control algorithm is used to adjust the forward speed of the combine harvester, thereby achieving stable control of the feed amount of the combine harvester and improving the harvesting quality of the combine harvester. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0009] Figure 1 A flowchart illustrating a method for detecting and controlling the feed amount of a combine harvester, provided as an embodiment of this application; Figure 2 This is a block diagram illustrating the principle of a variable universe of discourse fuzzy PID control algorithm in one embodiment of this application. Figure 3 A schematic diagram of the overall structure of a combine harvester feed rate detection and control system provided in an embodiment of this application; Figure 4 A schematic diagram of the hardware structure of a combine harvester feed rate detection and control system provided in an embodiment of this application; Figure 5 This is a schematic diagram of the job information collection module in one embodiment of this application. Detailed Implementation

[0010] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0012] In one exemplary embodiment, such as Figure 1 As shown, a method for detecting and controlling the feed amount of a combine harvester is provided, including the following steps 101 to 103.

[0013] Step 101: Real-time acquisition of the combine harvester's operating parameters. These parameters include the combine harvester's drive shaft torque and the pressure exerted by the undercarriage plate. As an optional implementation, the operating parameters may also include drive shaft speed, stubble height, forward speed (track wheel speed pulse signal), and operating route.

[0014] Step 102: Based on the operation parameters and the pre-established feed rate detection model, a control signal is generated using a variable universe of discourse fuzzy PID control algorithm. The feed rate detection model is a relationship model between the operation parameters and the actual feed rate. The variable universe of discourse fuzzy PID control algorithm introduces an adaptive universe of discourse scaling mechanism into the fuzzy PID algorithm; its principle is as follows... Figure 2 As shown.

[0015] In a specific application example, step 102 specifically includes steps 21 to 23.

[0016] Step 21: The job parameters are sequentially subjected to mean filtering, outlier detection, and Gaussian filtering to obtain preprocessed job parameters. Outlier detection is achieved by filtering data points exceeding the mean ± 3 standard deviations using the 3σ principle.

[0017] Step 22: Determine the actual feed amount based on the pre-processing operation parameters and the pre-established feed amount detection model.

[0018] As an optional implementation, the feed rate detection model is pre-established using the least squares method to fit the operating parameters and the corresponding actual feed rate. The feed rate detection model includes: a model showing the relationship between the drive shaft torque and the actual feed rate, a model showing the relationship between the under-bridge pressure and the actual feed rate, and a model showing the relationship between the fused data of the drive shaft torque and the under-bridge pressure and the actual feed rate.

[0019] Specifically, the steps for constructing the model of the relationship between the drive shaft torque and the actual feed amount are as follows: During the stable operation phase of the combine harvester, the speed of the header drive shaft is relatively constant. Based on this, the drive shaft torque is collected, and 50 drive shaft torques are randomly selected. The relationship between the actual feed amount and the header torque is fitted using the least squares method to establish a univariate linear regression equation.

[0020] The steps for constructing the model of the relationship between the extrusion pressure of the bridge bottom plate and the actual feed amount are as follows: randomly select 50 extrusion pressures of the bridge bottom plate, and establish a univariate linear regression equation between the extrusion pressure of the bridge bottom plate and the actual feed amount using the least squares method.

[0021] The steps for constructing the relationship model between the fused data of the drive shaft torque and the under-bridge extrusion pressure and the actual feed rate are as follows: standardize the data of the drive shaft torque and the under-bridge extrusion pressure to eliminate the difference in dimensions and make different characteristics comparable in the analysis; then calculate the weights using the correlation coefficients between the drive shaft torque and the under-bridge extrusion pressure and the actual feed rate; finally, fuse the two types of data using the weighted average method to establish the relationship model between the fused data and the actual feed rate.

[0022] In establishing the relational model, the crop unit mass area is further determined based on the stubble height (the measured crop unit mass area differs between a stubble height of 20cm and 15cm, with a higher unit mass at 15cm). The actual feed rate is calibrated by combining this with the combine harvester's forward speed. The formula is: Q= mS=mLv ;in, Q This is the actual amount fed. m Area per unit mass of crop S This refers to the area of ​​crops harvested per unit of time. L For the width of the cut, v This refers to the forward speed of the combine harvester.

[0023] Step 23: Based on the actual feed rate and the rated feed rate, a control signal is generated using a variable universe fuzzy PID control algorithm.

[0024] Specifically, step 23 includes the following steps (1) to (6): (1) Based on the actual feeding amount Q real and the rated feed rate Q set Determine the input variables and their fundamental domains.

[0025] The input variables include feed rate deviation. e and rate of change of deviation ec Specifically, the feed rate deviation is calculated based on the actual feed rate and the rated feed rate:e = Q set - Q real The rate of change of deviation is determined based on the deviation in feed volume within a set time period: ec = d e / d t ;in, de and dt It is a differential symbol. The fundamental domain for determining feed rate deviation. e ∈[− E , E The fundamental domain of the rate of change of deviation. ec ∈[− EC , EC ];in, The maximum value of the fundamental universe of discourse for the feed rate deviation. The maximum value of the fundamental universe of discourse for the rate of change of deviation. E =6, EC =6, corresponding to the fuzzy domain [−6,6].

[0026] (2) Based on the input variables and the basic universe of discourse of the input variables, dynamically calculate the scaling factor of the input universe of discourse.

[0027] The input universe of discourse scaling factor includes the feed rate deviation universe of discourse scaling factor and the deviation change rate universe of discourse scaling factor. The feed rate deviation universe of discourse scaling factor is: The scaling factor of the universe of discourse for the rate of change of deviation is: ;in, The feed rate deviation universe scaling factor. The scaling factor for the universe of discourse of the rate of change of deviation. For the deviation in feed amount, The rate of change of deviation , , All are constants greater than 0.

[0028] Specifically, the function modeling construction of the input universe scaling factor satisfies: when | e |or| ec When |increases, and Expanding the domain of discourse to enhance stability; when | e |or| ec When | decreases, and Shrinking the domain of discourse improves control accuracy.

[0029] (3) Determine the basic universe of discourse and the scaling factor of the output universe of discourse.

[0030] The output variable is the PID parameter correction amount of the fuzzy PID algorithm: , , ;in, Proportional coefficient correction amount This is the correction amount for the integral coefficient. This is the correction amount for the differential coefficients.

[0031] The fundamental universe of discourse for the output variable is: , K The maximum value of the fundamental universe of discourse for the output variable. K =0.6.

[0032] Output universe scaling factor β Divided into seven fuzzy levels, include , and , The universe of discourse scaling factor is the correction factor for the proportionality coefficient. The universe scaling factor is the correction factor for the integral coefficients. The universe of discourse scaling factor is the correction factor for the differential coefficients. Output universe of discourse scaling factor. β The design principle of fuzzy rules is: if e and ec If the sign is the same and larger, then β Output large correction amount for rapid correction; if e Close to zero but ec If it is larger, then β Reduce overshoot. Output universe of discourse scaling factor. β Adjustments can be made online using fuzzy rules.

[0033] (4) Based on the basic universe of the input variable, the scaling factor of the input universe, the basic universe of the output variable, and the scaling factor of the output universe, adjust the universe range of the input variable and the universe range of the output variable to obtain the variable universe of the input and the variable universe of the output.

[0034] The input variable universe is , .

[0035] The output variable universe of discourse is: , , .

[0036] in, To address the fuzzy feed rate deviation, The fuzzy deviation rate is... This is the correction amount for the fuzzy proportional coefficient. This is the correction amount for the fuzzy integral coefficients. This is the correction amount for the fuzzy differential coefficients.

[0037] (5) Based on the input variable universe of discourse, the output variable universe of discourse, and the fuzzy rule of the scaling factor, perform fuzzy inference to determine the PID parameter correction amount: , , .

[0038] Specifically, fuzzy rules are queried within the input and output variable domains, and the PID parameter correction is output.

[0039] (6) Generate a control signal based on the PID parameter correction amount and the input variable.

[0040] Specifically, the current PID parameters are generated based on the PID parameter correction amount and the set original PID parameters: , , ;in, This is the current scaling factor. The current integral coefficient, For the current differential coefficients, This is the original proportionality coefficient. These are the original integral coefficients. These are the original differential coefficients.

[0041] The control signal is the rotation angle command of the stepper motor. The stepper motor converts the rotation command into the angle of the HST joystick through a transmission ratio, achieving stepless adjustment of the forward speed. The specific formula used is... Generate control signals. Among them, for t The rotation angle command of the stepper motor is always in effect. for t The deviation in feed amount at any given time.

[0042] Step 103: Adjust the forward speed of the combine harvester based on the control signal to control the feed rate of the combine harvester and keep the feed rate stable within the set range.

[0043] Based on the same inventive concept, such as Figure 3 As shown in the figure, this application embodiment also provides a combine harvester feed rate detection and control system, including: an operation information acquisition module 301, an intelligent control module 302, and an execution adjustment module 303.

[0044] As an optional implementation, the combine harvester feed rate detection and control system is installed on the Kubota 4LZ-6.5A8 combine harvester.

[0045] The operation information acquisition module 301 is used to collect the operation parameters of the combine harvester in real time.

[0046] In a specific application example, the operating parameters include the combine harvester's drive shaft torque and the underbody pressure of the bridge plate. For example... Figure 4 and Figure 5 As shown, the operation information acquisition module 301 includes a torque sensor and a pressure sensor. The torque sensor is installed on the header drive shaft and is used to detect the torque of the combine harvester's drive shaft in real time. The torque sensor is a dynamic torque sensor, which is installed on the header drive shaft through a modified broken shaft, with both ends connected to the original shaft via a perforated coupling. The pressure sensor is installed on the bridge bottom plate and is used to detect the compressive pressure of the combine harvester's bridge bottom plate in real time. The pressure sensor is a spoke-type load cell, integrated into a floating detection device on the bridge bottom plate, with an upper steel plate hinged to prevent straw scratching.

[0047] As an optional implementation, the operating parameters also include drive shaft speed, stubble height, forward speed, and operating route. A torque sensor is also used to detect the combine harvester's drive shaft speed in real time. The operating information acquisition module 301 also includes an angle sensor, a speed sensor, and a BeiDou / GPS antenna module. The angle sensor is used to detect the stubble height. The angle sensor uses a SIN-type tilt sensor fixed at the height of the header above the bridge; the stubble height is further obtained by detecting the header angle. The speed sensor is used to detect the combine harvester's forward speed. The speed sensor uses an incremental encoder mounted on the end of the track drive wheel axle. The BeiDou / GPS module is placed on top of the combine harvester. The BeiDou / GPS antenna module is used to record the combine harvester's operating route, and can also be used to determine the combine harvester's forward speed.

[0048] The signal output terminals of the torque sensor, pressure sensor, angle sensor, speed sensor, and Beidou / GPS antenna module are all connected to the signal input terminal of the intelligent control module 302.

[0049] The intelligent control module 302 generates control signals using a variable universe of discourse fuzzy PID control algorithm based on the operation parameters and a pre-established feed rate detection model. The feed rate detection model is a relationship model between the operation parameters and the actual feed rate. The variable universe of discourse fuzzy PID control algorithm introduces an adaptive universe of discourse scaling mechanism into the fuzzy PID algorithm.

[0050] As an optional implementation, the intelligent control module 302 includes a PLC controller and a human-machine interface. The PLC controller has a built-in mean filtering algorithm and uses the 3σ principle for outlier detection; the backend data is processed by Gaussian filtering. The PLC controller connects to various sensors via digital / analog input interfaces. The human-machine interface is based on a software-developed display terminal and receives PLC control commands.

[0051] The adjustment module 303 is used to adjust the forward speed of the combine harvester based on the control signal in order to control the feed amount of the combine harvester.

[0052] As an optional implementation, the control module 303 includes a motor driver and a stepper motor. The motor driver controls the rotational position of the stepper motor based on control signals, driving the actuator to rotate at a certain angle, thereby controlling the forward speed of the combine harvester.

[0053] The working process of the combine harvester feeding detection and control system provided in this application is as follows: After the combine harvester starts, each sensor collects operating parameters in real time and transmits them to the PLC controller. The PLC controller calculates the actual feeding amount according to the selected relational model and generates control signals through a variable universe of discourse fuzzy PID algorithm. A stepper motor drives the HST joystick to adjust the forward speed of the combine harvester, so that the feeding amount is stabilized within the set range. Data such as feeding amount and speed are displayed through a human-machine interface, and manual intervention of control parameters is supported.

[0054] In summary, this application solves the problems of low feed rate detection accuracy and unstable control in traditional combine harvesters by using multi-sensor fusion and adaptive control algorithms, effectively improving operating efficiency and harvest quality.

[0055] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0056] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0057] 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.

[0058] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for detecting and controlling the feed rate of a combine harvester, characterized in that, The method includes: Real-time acquisition of combine harvester operating parameters; Based on the operating parameters and the pre-established feeding quantity detection model, a variable universe of discourse fuzzy PID control algorithm is used to generate control signals. The feeding quantity detection model is a relationship model between the operating parameters and the actual feeding quantity. The variable universe of discourse fuzzy PID control algorithm introduces an adaptive scaling mechanism of the universe of discourse into the fuzzy PID algorithm. The operating parameters include the combine harvester's drive shaft torque and under-bridge pressure. The feeding quantity detection model includes: a relationship model between the drive shaft torque and the actual feeding quantity, a relationship model between the under-bridge pressure and the actual feeding quantity, and a relationship model between the fused data of the drive shaft torque and the under-bridge pressure and the actual feeding quantity. The steps for constructing the relationship model between the fused data of the drive shaft torque and the under-bridge pressure and the actual feeding quantity are as follows: standardize the data of the drive shaft torque and the under-bridge pressure to eliminate dimensional differences and make different characteristics comparable in the analysis; then calculate the weights using the correlation coefficients between the drive shaft torque and the under-bridge pressure and the actual feeding quantity; finally, fuse the two types of data using a weighted average method to establish a relationship model between the fused data and the actual feeding quantity. The forward speed of the combine harvester is adjusted based on the control signal to control the feed rate of the combine harvester; Specifically, based on the operating parameters and the pre-established feed rate detection model, a variable universe fuzzy PID control algorithm is used to generate control signals, including: The job parameters are sequentially subjected to mean filtering, outlier detection, and Gaussian filtering to obtain preprocessed job parameters. The actual feed amount is determined based on the pre-processing operation parameters and the pre-established feed amount detection model; Calculate the feed rate deviation based on the actual feed rate and the rated feed rate; determine the deviation change rate based on the feed rate deviation within a set time period; determine the basic domain of the feed rate deviation and the basic domain of the deviation change rate; input variables include feed rate deviation and deviation change rate; Based on the input variables and their fundamental universes of discourse, the input universe of discourse scaling factor is dynamically calculated; the input universe of discourse scaling factor includes the feed rate deviation universe of discourse scaling factor and the deviation change rate universe of discourse scaling factor; the feed rate deviation universe of discourse scaling factor is: The scaling factor of the universe of discourse for the rate of change of deviation is: ;in, The feed rate deviation universe scaling factor. The scaling factor for the universe of discourse of the rate of change of deviation. For the deviation in feed amount, The rate of change of deviation The maximum value of the fundamental universe of discourse for the feed rate deviation. The maximum value of the fundamental universe of discourse for the rate of change of deviation. , , All are constants greater than 0; Determine the basic universe of discourse and the scaling factor of the output universe for the output variable; the output variable is the PID parameter correction amount of the fuzzy PID algorithm. Based on the basic universe of discourse of the input variable, the scaling factor of the input universe of discourse, the basic universe of discourse of the output variable, and the scaling factor of the output universe of discourse, the universe range of the input variable and the universe range of the output variable are adjusted to obtain the variable universe of discourse of the input variable and the variable universe of discourse of the output variable. Fuzzy inference is performed based on the input variable universe of discourse, the output variable universe of discourse, and the fuzzy rule of the scaling factor to determine the PID parameter correction amount; A control signal is generated based on the PID parameter correction and the input variable.

2. The method for detecting and controlling the feed rate of a combine harvester according to claim 1, characterized in that, The feeding amount detection model is established in advance by fitting the operating parameters and the corresponding actual feeding amount using the least squares method.

3. The method for detecting and controlling the feed rate of a combine harvester according to claim 1, characterized in that, The input variable universe is , ; The output variable universe of discourse is: , , ;in, To address the fuzzy feed rate deviation, The fuzzy deviation rate is... This is the correction amount for the fuzzy proportional coefficient. This is the correction amount for the fuzzy integral coefficients. This is the correction amount for the fuzzy differential coefficients. To output the universe of discourse scaling factor, This represents the maximum value of the fundamental universe of discourse for the output variable.

4. A combine harvester feed rate detection and control system, characterized in that, The system is applied to the combine harvester feed rate detection and control method according to any one of claims 1-3, and the system comprises: The operation information acquisition module is used to collect the operation parameters of the combine harvester in real time; The intelligent control module is used to generate control signals using a variable universe of discourse fuzzy PID control algorithm based on the operation parameters and a pre-established feed rate detection model; the feed rate detection model is a relationship model between the operation parameters and the actual feed rate; the variable universe of discourse fuzzy PID control algorithm is a fuzzy PID algorithm that introduces an adaptive universe of discourse scaling mechanism. An adjustment module is executed to adjust the forward speed of the combine harvester based on the control signal, so as to control the feed rate of the combine harvester.

5. The combine harvester feed rate detection and control system according to claim 4, characterized in that, The operating parameters include the combine harvester's drive shaft torque and the under-bridge pressure; the operating information acquisition module includes: Torque sensor, used to detect the torque of the combine harvester's drive shaft in real time; Pressure sensors are used to detect the compressive pressure on the underbody plate of a combine harvester in real time.

Images