Intelligent fertilizer distribution control system based on Beidou positioning

Abstract

The invention discloses an intelligent fertilizer distribution control system based on Beidou positioning, and relates to the technical field of agricultural automation, and the system comprises the steps: building a fertilization simulation model, and obtaining the relation data of the disc opening size and the fertilization amount of a fertilizer distributor through an experiment; soil analysis data and remote sensing image data are collected and preprocessed; generating a fertilization prescription map by using a multi-objective optimization model based on the preprocessed soil analysis data and remote sensing image data according to the soil characteristics and crop requirements of the field; high-precision positioning data are obtained through a Beidou positioning system, and the fertilization prescription map and the high-precision positioning data are fused to complete field space calibration; based on the field space calibration result and the high-precision positioning data, adopting a Dijkstra algorithm to generate an optimal fertilizer spreading path; in combination with the real-time speed of the tractor and the fertilization simulation model, the disc opening size of the fertilizer spreader is dynamically regulated and controlled, and the fertilization amount is accurately controlled by using a control algorithm; the tractor corner and the field boundary are monitored in real time, and the fertilizer distributor is automatically closed.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural automation, and in particular to an intelligent fertilizer spreading control system based on Beidou positioning. Background Art

[0002] With the rapid growth of the global population, agricultural production is facing increasing pressure. Improving agricultural production efficiency, reducing resource waste and protecting the environment have become important development directions of modern agriculture. Traditional fertilization methods lack precise control, resulting in fertilizer waste and uneven fertilization, which not only affects crop growth, but may also have adverse effects on the soil and the environment.

[0003] At present, existing agricultural technologies are developing in the direction of intelligence and automation, and intelligent agricultural machinery and drone technology are gradually being applied in field management. For example, automated seeders, precision fertilizer applicators and other equipment are playing an increasingly important role in farmland operations. However, most of these devices rely on manual control or preset parameters, cannot dynamically adapt to the actual conditions of the field, lack flexible control methods, and are difficult to achieve precise control according to speed, terrain and soil conditions, especially during the fertilization process.

[0004] As a global navigation and positioning system independently developed by China, the Beidou satellite navigation system has significant advantages such as high precision and high coverage, and has gradually been widely used in agriculture. The intelligent fertilizer spreading system combined with Beidou positioning technology can effectively improve the automation and intelligence level of agricultural machinery and equipment, reduce resource waste in the fertilization process, and improve agricultural production efficiency. Therefore, it is urgent to develop an intelligent fertilizer spreading control system based on Beidou positioning technology to solve the shortcomings of traditional fertilizer spreading methods and achieve efficient management of field operations. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides an intelligent fertilizer spreading control system based on Beidou positioning to solve the problem of being unable to dynamically adapt to the actual conditions of the field, lacking flexible control means, and especially difficult to achieve precise control according to speed, terrain and soil conditions during the fertilizer spreading process.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: The present invention provides an intelligent fertilizer spreading control system based on Beidou positioning, which comprises: The model building module is used to establish a fertilization simulation model and obtain the relationship data between the opening size of the fertilizer spreader and the amount of fertilizer applied through experiments. The data acquisition module is used to collect soil analysis data and remote sensing image data and perform preprocessing. The prescription map generation module is used to generate a fertilization prescription map based on the preprocessed soil analysis data and remote sensing image data according to the soil characteristics of the field and crop requirements. The spatial calibration module is used to obtain high-precision positioning data through the Beidou positioning system, merge the fertilization prescription map with the high-precision positioning data, and complete the field spatial calibration. The path generation module is used to generate the optimal fertilizer spreading path based on the field spatial calibration results and high-precision positioning data using the Dijkstra algorithm. The opening control module is used to dynamically adjust the opening size of the fertilizer spreader in combination with the real-time speed of the tractor and the fertilization simulation model, and use the control algorithm to accurately control the amount of fertilizer applied. The state detection module is used to monitor the tractor corners and field boundaries in real time and automatically shut down the fertilizer spreader.

[0008] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, a fertilization simulation model is established, and the relationship data between the opening size of the fertilizer spreader and the amount of fertilizer applied is obtained through experiments, including the following steps: Establish an accurate physical model of the fertilizer spreader through the existing fertilizer spreader, and import the physical model of the fertilizer spreader into the EDEM software for simulation; Determine the different types of fertilizers suitable for the fertilizer spreader, and set the parameters of different types of fertilizers and the opening size of the fertilizer spreader in the simulation software; Under each opening size setting, multiple simulation experiments were conducted, and finite element simulation analysis was performed each time by changing the parameters of different fertilizer types to obtain comprehensive simulation results; Record the total mass of fertilizer spread per unit time for each opening size, and calculate the corresponding fertilizer application amount; Repeat the simulation experiment, take the average value of fertilizer application as the final data, and record the corresponding opening size; The parameters during the simulation experiment were recorded, the simulation experiment data were organized into tables, MATLAB was used to draw a graph between the opening size and the amount of fertilizer applied, the preliminary trend and linear or nonlinear relationship were determined, and different mathematical models were selected for fitting.

[0009] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, soil analysis data and remote sensing image data are collected and pre-processed, including the following steps: Conduct soil sampling in selected areas and analyze soil samples; Use satellite remote sensing technology to obtain high-resolution remote sensing image data; For the collected remote sensing image data, MATLAB software is used to perform geometric correction, atmospheric correction and radiation correction; Soil analysis data were cleaned and standardized.

[0010] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, according to the soil characteristics of the field and the crop requirements, based on the pre-processed soil analysis data and remote sensing image data, a fertilization prescription map is generated using a multi-objective optimization model, including the following steps: The soil analysis data and remote sensing image data were spatially registered, and the soil analysis data and remote sensing image data were loaded using QGIS3 software for spatial analysis to determine the soil characteristics and vegetation index indicators of the field; The K-means clustering method is used to partition the fields, and the soil partition map of the fields is generated based on the clustering results; Determine fertilization accuracy, fertilization cost, and fertilizer loss risk as optimization goals; Set constraints to meet crop demand, total fertilizer application limit, and fertilizer application limit in high slope areas; The particle swarm optimization algorithm is used as the optimization algorithm for the multi-objective optimization model; Generate a swarm of particles randomly and assign initial velocity and position to each particle; Calculate the comprehensive objective function value of each particle and record the individual optimal solution and the global optimal solution; Update the particle position and speed according to the particle's current speed and position update formula; Repeatedly update particles until the maximum number of iterations is reached or the change in the objective function value is less than the set threshold, and then output the optimal solution; After the optimization is completed, the fertilizer application results of each grid cell are converted into a gridded fertilizer prescription map, and the field map is superimposed to output the final fertilizer prescription map.

[0011] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, wherein: high-precision positioning data is obtained through the Beidou positioning system, and the fertilization prescription map is integrated with the high-precision positioning data to complete the field space calibration, including the following steps: Use the Beidou positioning system to obtain high-precision coordinates of the field boundaries and record the longitude and latitude information of the boundary points; obtain the center point coordinates and boundary area of ​​the field; The pixel coordinates of the fertilization prescription map are converted into geographic coordinates through the coordinate conversion formula; Overlay the field boundaries and partition coordinates onto the field map in the BeiDou system to check the spatial match between the fertilization prescription map and the actual field.

[0012] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, the Dijkstra algorithm is used to generate the optimal fertilizer spreading path based on the field spatial calibration results and high-precision positioning data, including the following steps: Through the Beidou positioning system, high-precision positioning data in the field is obtained to record the boundaries and feature points of the farmland; Use Dijkstra algorithm for fertilizer spreading path planning, use high-precision location data to provide the starting point and end point for the fertilizer spreading path planning algorithm, regard each point in the field as a node in the graph, and the boundary as an obstacle; Use Bezier curve or spline curve to smooth the fertilizer spreading path, and verify the smoothed fertilizer spreading path; Monitor the tractor's position in real time, correct the path through high-precision positioning, and recalculate the path based on environmental changes.

[0013] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, the following steps are included: combining the real-time speed of the tractor and the fertilization simulation model, dynamically adjusting the opening size of the fertilizer spreader, and using the control algorithm to accurately control the amount of fertilizer applied. The fertilizer spreader opening size controller based on the steering gear rotation and connecting rod system is adopted. The steering gear is precisely controlled by the lower computer, and the upper computer receives and processes the opening size data sent. The lower computer adds an environmental sensor to detect environmental parameters during operation and transmit them to the upper computer to ensure that the upper computer has enough data to accurately predict the size of the fertilizer spreader and plan the path. The host computer obtains the real-time speed of the tractor through the Beidou positioning system and calculates the target opening size, target angle and speed according to the simulation model; The tractor adds an absolute encoder to the front wheel and an incremental encoder to the rear wheel to ensure that the tractor is accurately controlled to run according to the expected requirements after receiving the data; The tractor angle and speed are controlled by adjusting the PID control algorithm.

[0014] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, the calculation formula of the PID control algorithm is:

[0015] in, To control the output, is the error value of the current angle or speed, is the proportionality coefficient, is the integration coefficient, is the differential coefficient.

[0016] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, it also includes a status monitoring module, which is used to monitor the tractor corners and field boundaries in real time and automatically shut down the fertilizer spreader.

[0017] As a preferred solution of the intelligent fertilizer spreading control system based on Beidou positioning described in the present invention, the method includes: real-time monitoring of the tractor turning angle and the field boundary, and automatically shutting down the fertilizer spreader, including the following steps: Use Beidou positioning system to obtain the real-time position and driving status of the tractor; Set the turning angle threshold to determine whether the tractor turning angle exceeds a certain angle; When the turning angle of the tractor is greater than the turning angle threshold, the fertilizer spreader is triggered to suspend operation. When the turning angle of the tractor is less than or equal to the turning angle and the direction is stable, the fertilizer spreading operation is resumed; Monitor the tractor's position in real time to determine if it is close to the field boundary and decide whether to shut down the fertilizer spreader based on the distance.

[0018] The beneficial effects of the present invention are as follows: high-precision positioning data of tractors and fields is obtained through the Beidou positioning system, and the fertilization prescription map is integrated with the positioning data to perform spatial calibration of the field, and the geographical location of the field boundary and the fertilization area is clarified. By combining the fertilization prescription map with the Beidou positioning data, the fertilization demand points in the prescription map can be accurately mapped to the actual geographical location of the field, ensuring that the fertilizer spreader can fertilize at the right time and in the right place. Through the Dijkstra algorithm, the optimal path covering all fertilization areas of the field can be planned to avoid repeated operations or missed areas, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 This is a module diagram of the intelligent fertilizer spreading control system based on Beidou positioning in Example 1. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides an intelligent fertilizer spreading control system based on Beidou positioning, comprising the following steps: The model building module is used to build a fertilization simulation model and obtain the relationship data between the opening size of the fertilizer spreader and the amount of fertilizer applied through experiments; Establish an accurate physical model of the fertilizer spreader through the existing fertilizer spreader, and import the physical model of the fertilizer spreader into the EDEM software for simulation; Determine the different types of fertilizers suitable for the fertilizer spreader, and set the parameters of different types of fertilizers and the opening size of the fertilizer spreader in the simulation software; Furthermore, according to the actual application of the fertilizer spreader, common granular fertilizers such as urea, diammonium phosphate, compound fertilizer, etc. are preferred, and the physical properties of particle size distribution, density, shape and fluidity are recorded for each fertilizer. Different types of fertilizer granules are created in EDEM and the above physical property parameters are entered. For example, for urea, the particle size distribution is set to 0.5-2mm, the density is 1330 kg / m³, the shape is regular particles, and the angle of repose is 30°.

[0025] According to the physical properties of the fertilizer, adjust the particle properties in the simulation (such as friction coefficient, elastic modulus, adhesion, etc.) to ensure the authenticity and reliability of the simulation results. For example, the friction coefficient of urea can be set to 0.2 and the elastic modulus to 1 GPa. Consider the different environmental conditions (such as humidity and temperature) that may be encountered during actual operations, and set the corresponding environmental parameters in the simulation. For example, the humidity can vary between 40%-80%, and the temperature can vary between 10°C-30°C.

[0026] According to different types of fertilizers, set different fertilizer data, and conduct multiple groups of experiments according to different types of fertilizers. Conduct simulation experiments in steps, set the opening size and chassis speed in sequence, for example: set the opening size to K1, change the chassis speed to U1, U2, U3 to conduct different simulation experiments to obtain simulation data; set the chassis speed to U1, change different opening sizes to K1, K2, K3 to conduct different simulation experiments to obtain simulation data.

[0027] Furthermore, determine the setting of the fertilizer spreader opening size (e.g., 20%, 30%, 50%, etc.), give priority to granular fertilizers (e.g., urea, diammonium phosphate, compound fertilizer, etc.); record the physical properties of the fertilizer, including particle size distribution (unit: mm), density (unit: kg / m³), shape (regular particles or irregular particles) and fluidity; based on the physical properties of the fertilizer, ensure that the fertilizer spreader can work normally and spread the fertilizer evenly.

[0028] Under each opening size setting, conduct multiple fertilizer spreading tests, record the total mass of fertilizer spread per unit time under each opening size, and calculate the corresponding fertilizer application amount; also record the environmental parameters (such as speed, environmental conditions, etc.) during the fertilization process.

[0029] Repeat the simulation experiment, take the average value of the fertilizer application amount as the final data, and record the corresponding opening size; in the actual operation process, select different opening sizes and chassis speeds based on the obtained simulation experiment data.

[0030] The parameters during the simulation experiment were recorded, the simulation experiment data were organized into tables, MATLAB was used to draw a graph between the opening size and the amount of fertilizer applied, the preliminary trend and linear or nonlinear relationship were determined, and different mathematical models were selected for fitting.

[0031] Furthermore, if the data presents a nonlinear relationship, a polynomial regression model is used for fitting, and if the data presents a linear trend, a linear regression model is used for fitting; Polynomial regression:

[0032] Linear Regression:

[0033] in, is the amount of fertilizer applied (unit: kg / s), is the opening size of the fertilizer spreader (unit: cm2), , ,…, is the regression coefficient, determined by experimental data, For the fitting order, the optimal value is determined according to the simulation experimental data. is the linear correlation coefficient, which indicates the influence of the opening size on the amount of fertilizer applied. is the intercept, which represents the base fertilizer rate when the spreader is at zero opening (usually zero).

[0034] It should be noted that the relationship between the rotation speed of the chassis of the fertilizer spreader and the size of the opening of the fertilizer spreader and the area and mass per unit time of the fertilizer spreader when spreading different types of fertilizers is obtained through simulation experiments. The rotation speed of the chassis of the fertilizer spreader is related to the speed of the vehicle. The faster the speed, the faster the chassis rotates, and the slower the speed, the slower the chassis rotates. However, no matter how slow the speed is, there will be a certain initial velocity. Through simulation, we can accurately know the trend and linear or nonlinear relationship between the chassis speed and the opening size and the amount of fertilizer spread and the area of ​​fertilizer spread (the speed is obtained according to the actual transmission ratio, without simulation). And select different mathematical models for fitting.

[0035] By establishing an accurate fertilization simulation model, not only can the working condition of the fertilizer spreader be monitored in real time, but also the fertilizer spreader can be precisely controlled, thus significantly improving the accuracy of the system's fertilization amount. By using the simulation model to predict the amount of fertilizer applied under different parameter combinations, agricultural workers can choose the optimal fertilizer spreader settings according to actual needs to ensure that each field receives the right amount of fertilizer. Accurate fertilizer amount control can avoid over-fertilization, reduce agricultural production costs, and reduce negative impacts on the environment, meeting the requirements of sustainable development.

[0036] Data acquisition module, used to collect soil analysis data and remote sensing image data, and perform preprocessing; Soil sampling is carried out in selected areas to analyze the soil's nutrient content, pH, moisture, etc. It is recommended to conduct multiple samplings at different locations.

[0037] Use satellite remote sensing technology to obtain high-resolution farmland images and data. Before flying, set key parameters such as flight altitude, shooting angle, shooting time, etc. to obtain the best image quality. Record weather conditions, crop growth stage and other factors that may affect fertilization.

[0038] For the collected remote sensing image data, MATLAB software is used to perform geometric correction to eliminate geometric distortion caused by factors such as the earth's curvature and sensor imaging angle; radiation correction and atmospheric correction are performed to eliminate the impact of environmental factors such as light intensity and cloud cover on the image, ensuring that the image reflects the true characteristics of the ground objects.

[0039] Soil analysis data were cleaned and standardized to ensure data consistency.

[0040] It should be noted that by analyzing the main nutrients in the soil, the system can determine the specific fertilizer needs of each area to avoid excessive or insufficient application of a certain type of fertilizer. Based on soil data, the system can generate personalized fertilization plans to ensure that each field receives the most suitable fertilizer, avoiding resource waste and environmental pollution.

[0041] The prescription map generation module is used to generate a fertilization prescription map based on the soil characteristics of the field and the crop requirements, based on the pre-processed soil analysis data and remote sensing image data, and using a multi-objective optimization model; The soil analysis data and remote sensing image data were spatially registered, and the soil analysis data and remote sensing image data were loaded using QGIS3 software for spatial analysis to determine the soil properties and vegetation index (NDVI) of the field; The Normalized Difference Vegetation Index (NDVI) is calculated through remote sensing images. The growth status of crops in the field is determined based on the distribution of NDVI values, and regional differences are marked.

[0042] The soil data and remote sensing image data are spatially registered to ensure the coordinates of the two are consistent; soil characteristic data and NDVI data are imported into MATLAB software to form a unified spatial data set The K-means clustering method was used to partition the fields, and a soil partition map of the fields was generated based on the clustering results. The fertilization requirements (fertilizer amount and fertilizer type) were marked for each partition.

[0043] Determine fertilization accuracy, fertilization cost, and fertilizer loss risk as optimization goals; Specifically, the goal of the optimization model is to comprehensively consider the following three aspects: Fertilization accuracy ( ): Quantify the deviation between actual fertilizer application and crop demand, with the goal of minimizing the deviation, ensuring that fertilizer application matches crop demand and reducing waste or insufficiency.

[0044] Fertilizer cost ( ): The total cost of fertilization, the goal is to minimize it and reduce the cost of fertilizer use while meeting crop needs.

[0045] Fertilizer loss risk ( ): The risk of fertilizer loss is related to the slope and the amount of fertilizer applied. The goal is to control the loss risk within an acceptable range, control fertilizer loss in high-slope areas, and reduce the impact on the environment.

[0046] The comprehensive objective function is:

[0047] in, is the comprehensive objective function, , , It is the target weight coefficient, which is used to adjust the priority among accuracy, economy and environmental protection.

[0048] Set constraints to meet crop demand, total fertilizer application limit, and fertilizer application limit in high slope areas; Specifically, meet the needs of crops and ensure that the amount of fertilizer applied to each grid unit is not less than the minimum requirement of the crops. Ensure that the total amount of fertilizer applied to each grid unit is less than or equal to the total fertilizer resource limit. Limit the fertilization of high slope areas to no more than the maximum amount of fertilizer applied.

[0049] After building the model, in order to solve the optimal value of the objective function, the particle swarm optimization algorithm (PSO) is used for iterative calculation. It should be noted that PSO is an optimization algorithm that simulates swarm intelligence. Each particle represents a possible fertilization scheme, and by updating the particle position and velocity, it gradually approaches the global optimal solution.

[0050] Specifically, a swarm of particles is randomly generated, each particle represents a fertilization scheme, and an initial velocity and position are assigned to each particle; Calculate the comprehensive objective function value of each particle , record the individual optimal solution and the global optimal solution; Update the particle position and speed according to the particle's current speed and position update formula. The expression is: ; ; in, For the The particle in The speed in the dimension is updated to The value of the iteration, For the The particle in The speed in the dimension is The value of the iteration, For the The particle in The individual best historical position in the dimension (i.e., the best solution obtained by the particle in the historical iteration), is the inertia weight, , is the learning factor, , is a random number, For the The particle in The position on the dimension is The value of the iteration (i.e. the current solution of the particle), For the The global optimal position in the dimension (i.e. the best historical solution of the entire particle swarm in this dimension), For the The particle in The position on the dimension is updated to The value of the iteration (i.e. the next solution of the particle).

[0051] Repeatedly update particles until the maximum number of iterations is reached or the change in the objective function value is less than the set threshold, and then output the optimal solution; After the optimization is completed, the fertilizer application results of each grid cell are converted into a gridded fertilizer prescription map, and the field map is superimposed to generate a visualization result, and the final fertilizer prescription map is output.

[0052] It should be noted that the output format is a grid fertilization map, and each grid is marked with the amount and type of fertilizer of each type of fertilizer (such as nitrogen, phosphorus, potassium, etc.). The fertilization prescription map can be directly input into agricultural machinery to guide precise fertilization. The optimization model comprehensively considers soil characteristics, crop needs and terrain characteristics, and fertilization is more scientific and reasonable. Through cost optimization, fertilizer waste is reduced, production costs are reduced, and the amount of fertilizer application is adjusted in combination with slope data to reduce fertilizer loss and environmental pollution. The output grid fertilization map is highly visualized and practical, which is convenient for direct execution by agricultural machinery and improves fertilization efficiency.

[0053] The spatial calibration module is used to obtain high-precision positioning data through the Beidou positioning system, integrate the fertilization prescription map with the high-precision positioning data, and complete the field spatial calibration; Use the Beidou positioning system to obtain high-precision coordinates of the field boundaries and record the longitude and latitude information of the boundary points; obtain the center point coordinates and boundary area of ​​the field; The pixel coordinates of the fertilization prescription map are converted into geographic coordinates through the coordinate conversion formula; Overlay the field boundaries and partition coordinates onto the field map in the Beidou system, check the spatial matching between the fertilization prescription map and the actual field, and ensure there is no misalignment or offset.

[0054] It should be noted that the Beidou high-precision positioning solves the problem of ambiguous field positions in traditional fertilization, ensuring that the amount of fertilizer applied matches the location of the fertilizer. It provides a geographic reference for subsequent path planning and intelligent control of the fertilizer spreader, making the fertilizer spreading operation more intelligent. By accurately calibrating the boundaries of the field, the fertilizer spreader is prevented from operating in non-target areas (such as outside the field or in areas where fertilizer is not required), saving fertilizer resources. Compared with other existing technologies, it has precise spatial calibration and preprocessing of the fertilizer prescription map, which can improve the accuracy of fertilization and the utilization rate of fertilizers.

[0055] The path generation module is used to generate the optimal fertilizer spreading path based on the field spatial calibration results and high-precision positioning data using the Dijkstra algorithm; Through the Beidou positioning system, the coordinates of the field boundary points are collected, the boundary point set is recorded, and the characteristic points of the field are determined, including the starting point, the end point and the coordinates of the obstacle area (such as the crop growth area) in the field; Define the working width of the fertiliser spreader (Unit: m) and the distance between spreading paths Satisfies the following formula:

[0056] in, is the overlap coefficient, which is usually in the range of 0.8 to 1.0 (adjusted according to the requirements for fertilizer spreading uniformity).

[0057] The area within the field boundary is divided into several parallel paths perpendicular to the fertilizer spreading direction; according to the operating width of the fertilizer spreader and the path spacing, a fertilizer spreading path grid is generated and a grid point set is recorded; each point in the field is regarded as a node in the graph, and the boundary is regarded as an obstacle; the grid points in the obstacle area are marked as inaccessible points to avoid the path passing through the obstacle area; the point set after the path gridding is constructed as a weighted graph.

[0058] Set the starting point of fertilizer spreading as the starting point of the weighted graph and the ending point as the end point; use the Dijkstra algorithm to calculate the shortest path from the starting point to the end point, while covering all passable points in the grid to ensure that the path is not missed; output the generated path point set, in which each point is connected in sequence to form a fertilizer spreading path.

[0059] Use Bezier curves or spline curves to smooth the fertilizer spreading path to ensure the stability of the fertilizer spreader when moving, and verify the smoothed fertilizer spreading path to check whether the path completely covers all the fertilizer spreading areas in the field; if the path is found to be missing or overlapping, readjust the path grid spacing or fertilizer spreading direction to ensure that there is no duplication or omission in the path; The tractor's position is monitored in real time, and the deviation between the tractor's current position and the planned path point is calculated. If the deviation exceeds the set threshold (for example, 0.5 meters), the path correction is triggered. Based on the current position and the planned path point, the tractor's deviation direction and correction angle are calculated, and the tractor's driving direction is adjusted to bring it back to the planned path.

[0060] Monitor field environment changes (such as obstacles, wetlands, etc.) in real time. If new inaccessible areas are found, dynamically update the path grid point set and path point set; recalculate the optimal path to adapt to the dynamic environment and ensure that the fertilizer spreader runs along the updated path.

[0061] It should be noted that the optimal path planning reduces the ineffective driving distance of the tractor, shortens the fertilizer spreading operation time, and improves the operation efficiency. By optimizing the path, the fuel consumption of the tractor and the waste of fertilizer are reduced, and the agricultural production cost is reduced. Through path optimization, it is ensured that all fertilization areas in the field can be accurately covered without missing or over-fertilization.

[0062] The opening control module is used to dynamically adjust the opening size of the fertilizer spreader by combining the real-time speed of the tractor and the fertilization simulation model, and use the control algorithm to accurately control the amount of fertilizer applied, including the following steps: The fertilizer spreader opening size controller based on the steering gear rotation and connecting rod system is adopted, and the rotation angle range of the steering gear should cover the adjustment range of the opening size; The servo is precisely controlled by the lower computer. The control signal of the servo is sent by the lower computer, and the upper computer receives and processes the opening size data sent. The lower computer adds an environmental sensor to detect environmental parameters during operation and transmit them to the upper computer to ensure that the upper computer has enough data to accurately predict the size of the fertilizer spreader and plan its path; The host computer obtains the real-time speed of the tractor through the Beidou positioning system and calculates the target opening size, target angle and speed according to the simulation model; The tractor adds an absolute encoder to the front wheel and an incremental encoder to the rear wheel to ensure that the tractor can be accurately controlled to run according to the expected requirements after receiving the data.

[0063] The tractor angle and speed are controlled by adjusting the PID control algorithm. The calculation formula is:

[0064] in, To control the output, is the error value of the current angle or speed, indicating the difference between the current state (angle or speed) and the target angle or speed. is the proportionality coefficient, reflecting the direct impact of the error on the opening adjustment. is the integral coefficient, reflecting the influence of the cumulative error on the regulation, is the differential coefficient, reflecting the influence of the error change rate on the regulation; Furthermore, the tractor speed is acquired in real time, and the target opening size is dynamically updated according to the speed change; the real-time state is compared with the target angle or speed, the error is calculated, and the tractor angle and speed are dynamically adjusted according to the error through the PID control algorithm; if the speed changes greatly (for example, the tractor speed suddenly decreases or increases by more than 10%), the controller response time should be less than 1 second, and the opening size should be quickly adjusted to adapt to the speed change. Optimize PID parameters based on historical error data , , , further improving control accuracy.

[0065] It should be noted that the use of high-precision steering gear control can quickly respond to the judgment made by the system, respond to the opening size according to the speed of the vehicle and the data of fertilizer spreading, have a good response to real-time control, and improve the accuracy of fertilizer spreading. PID control can adjust the direction and speed of the tractor in real time to ensure that it strictly follows the predetermined path, reduce deviations, and improve the accuracy and precision of fertilizer spreading.

[0066] The status monitoring module is used to monitor the tractor corners and field boundaries in real time and automatically shut down the fertilizer spreader; Use the Beidou positioning system to obtain the real-time position and driving status of the tractor. These data provide the basis for determining the turning angle and boundary of the tractor; Set a turning angle threshold to determine whether the tractor's turning angle exceeds a certain angle (such as 15°). If the turning angle exceeds the threshold, it may cause uneven fertilization by the fertilizer spreader. When the turning angle of the tractor is greater than the turning angle threshold, the fertilizer spreader is triggered to pause. When the turning angle of the tractor is less than or equal to the turning angle and the direction is stable, the fertilizer spreading operation is resumed. During the suspension of the fertilizer spreader, the movement state of the tractor is continuously monitored, and its real-time position and turning angle are recorded. When it is detected that the tractor has completed steering (that is, the turning angle of the tractor is less than or equal to the turning angle threshold and the turning angle changes approach zero for several consecutive moments), a start signal is sent to the fertilizer spreader controller to resume the fertilization operation. The operating status of the fertilizer spreader is updated to ensure that no area is missed.

[0067] Monitor the tractor's position in real time to determine if it is close to the field boundary and decide whether to shut down the fertilizer spreader based on the distance; Furthermore, the polygonal range of the field boundary is defined according to the field boundary point set, and the boundary points are provided by the field space calibration result; the point-to-polygon distance formula is used to calculate the shortest distance from the current position of the tractor to the field boundary; Set the distance threshold Y = 1m to determine whether the distance between the tractor and the boundary is less than or equal to the distance threshold Y. When the condition is met, the fertilizer spreader shutdown operation is triggered; otherwise, the fertilizer spreader remains in operation.

[0068] When the distance between the tractor and the boundary is less than or equal to the distance threshold Y, a shutdown signal is sent to the fertilizer spreader controller to immediately stop releasing fertilizer; the time when the fertilizer spreader is shut down and the tractor position are recorded for subsequent analysis and optimization of the operation process; when the tractor is far away from the boundary (that is, the distance between the tractor and the boundary is greater than the distance threshold Y), the fertilizer spreader is reopened to resume fertilization operations.

[0069] In summary, the present invention is as follows: by establishing a fertilization simulation model, the fertilizer spreader can accurately calculate the real-time fertilizer amount according to the opening size in actual operation. By collecting soil analysis data and remote sensing image data of the field, and pre-processing these data, accurate input data is provided for generating a fertilization prescription map. By combining multi-dimensional data, it is ensured that the generation of the fertilization prescription map is more in line with the actual needs of the field. By comprehensively analyzing the soil nutrient distribution, crop growth and terrain characteristics, the fertilization prescription map can guide the fertilizer spreader to apply the right amount of fertilizer in different areas. The fertilization prescription map is the core data output of precision fertilization, indicating the amount of fertilizer required in different areas of the field, and realizing "fertilization on demand". The high-precision positioning data of the tractor and the field is obtained through the Beidou positioning system, and the fertilization prescription map is integrated with the positioning data to perform spatial calibration on the field, and the geographical location of the field boundary and the fertilization area is clarified. By combining the fertilization prescription map with the Beidou positioning data, the fertilization demand points in the prescription map can be accurately mapped to the actual geographical location of the field, ensuring that the fertilizer spreader can fertilize at the right time and in the right place. Through the Dijkstra algorithm, the optimal path covering all fertilization areas of the field can be planned to avoid repeated operations or missed areas, thereby improving work efficiency.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent fertilizer spreading control system based on Beidou positioning, characterized in that: include, The model building module is used to build a fertilization simulation model and obtain the relationship data between the opening size of the fertilizer spreader and the amount of fertilizer applied through experiments; Data acquisition module, used to collect soil analysis data and remote sensing image data, and perform preprocessing; A prescription map generation module is used to generate a fertilization prescription map based on the soil characteristics of the field and the crop requirements, based on the pre-processed soil analysis data and remote sensing image data; The spatial calibration module is used to obtain high-precision positioning data through the Beidou positioning system, integrate the fertilization prescription map with the high-precision positioning data, and complete the field spatial calibration; The path generation module is used to generate the optimal fertilizer spreading path based on the field spatial calibration results and high-precision positioning data using the Dijkstra algorithm; The opening control module is used to dynamically adjust the opening size of the fertilizer spreader by combining the real-time speed of the tractor and the fertilization simulation model, and use the control algorithm to accurately control the amount of fertilizer applied.

2. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 1, characterized in that: Establish a fertilization simulation model and obtain the relationship data between the opening size of the fertilizer spreader and the amount of fertilizer applied through simulation experiments, including the following steps: Establish an accurate physical model of the fertilizer spreader through the existing fertilizer spreader, and import the physical model of the fertilizer spreader into the EDEM software for simulation; Determine the different types of fertilizers suitable for the fertilizer spreader, and set the parameters of different types of fertilizers and the opening size of the fertilizer spreader in the simulation software; Under each opening size setting, multiple simulation experiments were conducted, and finite element simulation analysis was performed each time by changing the parameters of different fertilizer types to obtain comprehensive simulation results; Record the total mass of fertilizer spread per unit time under each opening size, and calculate the corresponding fertilizer application amount; Repeat the simulation experiment, take the average value of fertilizer application as the final data, and record the corresponding opening size; The parameters during the simulation experiment were recorded, the simulation experiment data were organized into tables, MATLAB was used to draw a graph between the opening size and the amount of fertilizer applied, the preliminary trend and linear or nonlinear relationship were determined, and different mathematical models were selected for fitting.

3. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 2, characterized in that: Collect soil analysis data and remote sensing image data and perform preprocessing, including the following steps: Conduct soil sampling in selected areas and analyze soil samples; Use satellite remote sensing technology to obtain high-resolution remote sensing image data; For the collected remote sensing image data, MATLAB software is used to perform geometric correction, atmospheric correction and radiation correction; Soil analysis data were cleaned and standardized.

4. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 3, characterized in that: According to the soil characteristics of the field and the needs of crops, a fertilization prescription map is generated based on the pre-processed soil analysis data and remote sensing image data using a multi-objective optimization model, including the following steps: The soil analysis data and remote sensing image data were spatially registered, and the soil analysis data and remote sensing image data were loaded using QGIS3 software for spatial analysis to determine the soil characteristics and vegetation index indicators of the field; The K-means clustering method is used to partition the fields, and the soil partition map of the fields is generated based on the clustering results; Determine fertilization accuracy, fertilization cost, and fertilizer loss risk as optimization goals; Set constraints to meet crop demand, total fertilizer application limit, and fertilizer application limit in high slope areas; The particle swarm optimization algorithm is used as the optimization algorithm for the multi-objective optimization model; Generate a swarm of particles randomly and assign initial velocity and position to each particle; Calculate the comprehensive objective function value of each particle and record the individual optimal solution and the global optimal solution; Update the particle position and speed according to the particle's current speed and position update formula; Repeatedly update particles until the maximum number of iterations is reached or the change in the objective function value is less than the set threshold, and then output the optimal solution; After the optimization is completed, the fertilizer application results of each grid cell are converted into a gridded fertilizer prescription map, and the field map is superimposed to output the final fertilizer prescription map.

5. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 4, characterized in that: The high-precision positioning data is obtained through the Beidou positioning system, and the fertilization prescription map is integrated with the high-precision positioning data to complete the field space calibration, including the following steps: Use the Beidou positioning system to obtain high-precision coordinates of the field boundaries and record the longitude and latitude information of the boundary points; obtain the center point coordinates and boundary area of ​​the field; The pixel coordinates of the fertilization prescription map are converted into geographic coordinates through the coordinate conversion formula; Overlay the field boundaries and partition coordinates onto the field map in the BeiDou system to check the spatial match between the fertilization prescription map and the actual field.

6. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 5, characterized in that: Based on the field spatial calibration results and high-precision positioning data, the Dijkstra algorithm is used to generate the optimal fertilizer spreading path, which includes the following steps: Through the Beidou positioning system, high-precision positioning data in the field is obtained to record the boundaries and feature points of the farmland; Use Dijkstra algorithm for fertilizer spreading path planning, use high-precision location data to provide the starting point and end point for the fertilizer spreading path planning algorithm, regard each point in the field as a node in the graph, and the boundary as an obstacle; Use Bezier curve or spline curve to smooth the fertilizer spreading path, and verify the smoothed fertilizer spreading path; Monitor the tractor's position in real time, correct the path through high-precision positioning, and recalculate the path based on environmental changes.

7. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 6, characterized in that: Combined with the real-time speed of the tractor and the fertilization simulation model, the opening size of the fertilizer spreader is dynamically adjusted, and the control algorithm is used to accurately control the amount of fertilizer applied, including the following steps: The fertilizer spreader opening size controller based on the steering gear rotation and connecting rod system is adopted. The steering gear is precisely controlled by the lower computer, and the upper computer receives and processes the opening size data sent. The lower computer adds an environmental sensor to detect environmental parameters during operation and transmit them to the upper computer to ensure that the upper computer has enough data to accurately predict the size of the fertilizer spreader and plan its path; The host computer obtains the real-time speed of the tractor through the Beidou positioning system and calculates the target opening size, target angle and speed according to the simulation model; The tractor adds an absolute encoder to the front wheel and an incremental encoder to the rear wheel to ensure that the tractor is accurately controlled to run according to the expected requirements after receiving the data; The tractor angle and speed are controlled by adjusting the PID control algorithm.

8. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 7, characterized in that: The calculation formula of the PID control algorithm is: in, To control the output, is the error value of the current angle or speed, is the proportionality coefficient, is the integration coefficient, is the differential coefficient.

9. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 8, characterized in that: It also includes a status monitoring module, which is used to monitor the tractor corners and field boundaries in real time and automatically shut down the fertilizer spreader.

10. The intelligent fertilizer spreading control system based on Beidou positioning as claimed in claim 9, characterized in that: Real-time monitoring of the tractor corners and field boundaries, and automatic shut-off of the fertilizer spreader, includes the following steps: Use Beidou positioning system to obtain the real-time position and driving status of the tractor; Set the turning angle threshold to determine whether the tractor turning angle exceeds a certain angle; When the turning angle of the tractor is greater than the turning angle threshold, the fertilizer spreader is triggered to suspend operation. When the turning angle of the tractor is less than or equal to the turning angle and the direction is stable, the fertilizer spreading operation is resumed; Monitor the tractor's position in real time to determine if it is close to the field boundary and decide whether to shut down the fertilizer spreader based on the distance.

Images