Automatic control system of intelligent seeding machine

Abstract

The invention relates to the technical field of agricultural machinery automation, in particular to an intelligent seeding machinery automation control system which comprises a soil variability analysis module, a dynamic seeding mode adjustment module, a soil structure adjustment module, a seeding control and optimization module, an intelligent fault diagnosis module and a visualization module. Soil data are collected in real time through a soil variability analysis module, spatial variability and seeding suitability of soil are analyzed by utilizing a machine learning algorithm, and a dynamic seeding mode adjustment module automatically adjusts the seeding depth, the seeding speed, the seed spacing and the feeding amount according to an analysis result. The soil structure adjusting module can intelligently adjust the structure according to the compaction or loosening condition of soil, the intelligent fault diagnosis module monitors the operation state of the seeder in real time and diagnoses and repairs faults, and the visualization module provides a remote monitoring interface. According to the invention, the seeding process can be accurately controlled according to different soil conditions, the seeding uniformity and the crop germination rate are improved, and the efficiency and precision of agricultural production are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural machinery automation, and in particular to an intelligent seeding machinery automation control system. Background Art

[0002] In modern agricultural production, sowing is a key link, which has a direct impact on seed germination rate, crop growth quality and agricultural output. Traditional sowing machinery relies on fixed sowing depth, speed, seed spacing and seed delivery amount. This method is difficult to adapt to the needs of different soil environments and crop types, and it is easy to cause seed waste or poor planting results. With the development of intelligent agriculture, people hope to achieve precise sowing through intelligent sowing systems, thereby improving resource utilization efficiency and reducing the impact on the environment. The automatic control system of intelligent sowing machinery can automatically adjust the sowing parameters according to the soil conditions and terrain changes in different regions to adapt to the complex farmland environment and achieve accurate, uniform and efficient sowing effects.

[0003] However, there are still some problems that need to be solved in the existing technology. First, traditional seeding machinery has poor adaptability to the soil environment and cannot dynamically adjust the seeding parameters according to factors such as the spatial variability, humidity, and hardness of the soil, resulting in inaccurate seeding depth and spacing, which affects the growth of crops. Secondly, the existing intelligent seeding system has deficiencies in seeding machine operation status monitoring, fault diagnosis, and path correction. It cannot handle complex terrain or equipment failures in real time, resulting in instability in the seeding process. Summary of the invention

[0004] The invention provides an intelligent automatic control system for sowing machinery.

[0005] The intelligent seeding machinery automation control system includes a soil variability analysis module, a dynamic seeding mode adjustment module, a soil structure adjustment module, a seeding control and optimization module, an intelligent fault diagnosis module and a visualization module, wherein; The soil variability analysis module is used to collect soil data in real time, including soil moisture, temperature, pH value, salinity, hardness and particle size distribution, and use machine learning algorithms to model and analyze the collected soil data in spatial and temporal dimensions to predict the spatial variability and suitability of soil in real time; The dynamic sowing mode adjustment module is linked with the soil variability analysis module to automatically adjust the sowing depth, sowing speed, seed spacing and seed delivery amount according to the predicted soil spatial variability and sowing suitability; The soil structure adjustment module is used to intelligently adjust the compaction and looseness of the soil when the seeder passes through the soil; The sowing control and optimization module is used to comprehensively adjust the sowing parameters according to the output results of the soil variability analysis module and the dynamic sowing mode adjustment module. The sowing parameters include sowing depth, sowing speed, seed spacing and seed delivery amount; The intelligent fault diagnosis module is used to monitor the operating status of the planter in real time, detect the faults that occur and perform diagnosis; The visualization module is used to display the system working status and soil and sowing data in real time, including soil moisture, temperature and sowing depth, and provide it to operators in the form of a graphical interface to help make more intuitive decisions and adjustments.

[0006] Optionally, the soil variability analysis module includes: The soil variability analysis module collects soil data in real time, the soil data including soil moisture, temperature, pH value, salinity, hardness and particle size distribution, and the soil data is collected through multiple sensors, including a moisture sensor, a temperature sensor, a pH value sensor, a salinity sensor, a hardness sensor and a particle size sensor; Transmitting the collected soil data to a preset data processing unit via wireless communication; Preprocess the collected soil data, including noise removal, interpolation to fill missing values ​​and unit conversion; The preprocessed soil data were normalized to unify the dimensions and scales of different soil data items.

[0007] Optionally, the soil variability analysis module further includes: A spatial variability prediction model was established using the random forest algorithm; The spatial variability prediction model is trained through historical soil data, and combined with real-time collected soil data, the spatial variability index of different soil areas is predicted; Based on the predicted spatial variability index, multiple regression analysis was used to refine the division of soil suitability areas, identify areas suitable for sowing, and generate a soil suitability index. According to the evaluation results of the sowing suitability index, the area suitable for sowing and the sowing parameters, including sowing depth, sowing speed and seed release amount, are output and transmitted to the dynamic sowing mode adjustment module to optimize the sowing strategy.

[0008] Optionally, the dynamic seeding mode specifically includes: Receiving the sowing suitability data output by the soil variability analysis module, wherein the sowing suitability data includes a soil sowing suitability index and a spatial variability index, which are used to determine the sowing parameter adjustment requirements in different regions; Automatically adjust the sowing depth according to the soil sowing suitability index. The higher the sowing suitability index, the deeper the sowing depth is to increase the contact area between the seed and the soil. The lower the sowing suitability index, the shallower the sowing depth is to reduce the seed burial depth. Adjust the sowing speed according to the soil spatial variability index. The larger the spatial variability index, the greater the difference in soil regions, and the lower the sowing speed to ensure uniform distribution of seeds. The smaller the spatial variability index, the faster the sowing speed to improve sowing efficiency. Automatically adjust the seed spacing based on the sowing suitability index and spatial variability index. The higher the sowing suitability index and the smaller the spatial variability, the smaller the seed spacing, so as to increase the seed density and the number of germinations per unit area. If the sowing suitability index is lower or the spatial variability is greater, the seed spacing is larger to avoid over-crowding of seeds that affects growth. The seed supply is automatically adjusted to match the sowing suitability index and spatial variability index. The higher the sowing suitability, the more seed supply is required to ensure that soil resources are fully utilized. The lower the sowing suitability, the lower the seed supply is to save resources.

[0009] Optionally, the soil structure adjustment module includes: The soil hardness sensor installed on the seeder detects soil hardness data in real time, and the hardness data is used to determine the compaction or looseness of the soil; The detected soil hardness data is compared with the preset soil hardness standard value. When the soil hardness value exceeds the preset range, the system identifies the soil area as a compacted or too hard area and requires structural adjustment; When the soil hardness exceeds the preset standard, the loosening device is automatically activated, and the loosening device adjusts the loosening intensity and depth according to the actual value of the soil hardness; The soil hardness sensor continuously monitors the hardness changes of the soil, and automatically stops the loosening device when the preset hardness is reached.

[0010] Optionally, the soil structure adjustment module further includes: According to the soil hardness data detected by the soil hardness sensor, the looseness of the soil is monitored in real time to determine whether the soil is within the preset hardness range; When the soil hardness is detected to be lower than the preset range, the compaction device is automatically activated to compact the soil; The working intensity of the compaction device is dynamically adjusted through the control system, and the compaction intensity is gradually increased or decreased according to the actual detected soil hardness data until the soil hardness reaches the preset range suitable for sowing; After the compaction operation is completed, the soil hardness sensor detects the soil hardness again to ensure that the soil hardness is within the standard value range for sowing suitability. If the hardness is within the preset range, the compaction device will automatically stop and the soil conditioning work will be completed.

[0011] Optionally, the seeding control and optimization module includes: Receiving and comprehensively analyzing output data from the soil variability analysis module and the dynamic sowing mode adjustment module, the data including soil spatial variability, sowing suitability index and initial values ​​of dynamically adjusted sowing parameters; During the sowing process, the execution of the sowing operation is monitored in real time, including the actual values ​​of sowing depth, sowing speed, seed spacing and seed delivery amount, and the actual values ​​are compared with the preset target parameter values ​​to detect possible deviations; When the deviation between the actual sowing parameter value and the target parameter value exceeds the preset tolerance range, the adjustment mechanism is automatically triggered to make fine adjustments to the deviation item; Optimize the sowing path based on real-time monitoring feedback, and automatically correct the path if it detects that the seeder has deviated from the preset path due to changes in terrain or soil conditions; After sowing is completed, the actual implementation of the sowing parameters is summarized and evaluated, the deviation data is analyzed and a sowing quality report is generated. The report content includes the difference between the actual implementation value and the target value of sowing depth, sowing speed, seed spacing and release amount.

[0012] Optionally, the intelligent fault diagnosis module includes: The integrated sensor network monitors the operation status data of the planter in real time. The sensor network includes current sensors, temperature sensors, vibration sensors, pressure sensors and position sensors, which monitor the motor operation status, transmission system load, mechanical vibration, hydraulic pressure and the driving position of the planter respectively. Preprocess the collected operating status data, including data denoising, standardization and outlier detection; Based on the pre-processed operating status data, the normal range of each indicator is analyzed, and a fault diagnosis model is established based on the support vector machine algorithm; Classify faults according to the identification results of the fault diagnosis model and generate a fault diagnosis report; After the fault diagnosis is completed, the system provides corresponding repair suggestions or automatically starts the repair program based on the diagnosis results.

[0013] Optionally, the visualization module includes: Receive and integrate data from various modules in real time, including soil data provided by the soil variability analysis module, seeding depth, seeding speed, seed spacing and seed placement data provided by the dynamic seeding mode adjustment module, and operating status data and fault diagnosis reports provided by the intelligent fault diagnosis module; Process the received data, filter and classify the key parameters for display, including sowing depth, sowing speed, seed spacing, seed delivery amount and fault diagnosis report; Soil and seeding data are presented in real time through a visual interface in a variety of formats including charts, numerical values ​​and graphs.

[0014] Optionally, the visualization module further includes: Provides data query function, allowing operators to retrieve and analyze changes in soil and sowing data within any time period, to help decision-making and optimize sowing strategies; Integrated interactive function allows operators to manually adjust seeding data through a visual interface; It provides remote monitoring and operation functions, connects to remote terminals via wireless networks, and enables operators to view sowing data, soil data, and operating status data in real time in the control room or on mobile devices.

[0015] Beneficial effects of the present invention: The present invention, through the cooperation of a soil variability analysis module, a dynamic sowing mode adjustment module, and a sowing control and optimization module, can dynamically adjust the sowing depth, sowing speed, seed spacing, and seed release amount according to real-time collected soil data (such as humidity, temperature, pH value, hardness, etc.) and its spatial variability and sowing suitability. This automatic adjustment mechanism ensures that the seeder can adapt to soil conditions in different areas, thereby improving the seed germination rate and sowing efficiency, reducing seed waste, improving resource utilization, and making the entire sowing process more intelligent and precise.

[0016] In the present invention, the intelligent fault diagnosis module and the soil structure adjustment module can monitor the operation status of the seed drill in real time, including motor operation, transmission system load and sensor data, etc. When a fault or abnormality occurs, the system can timely diagnose and provide repair suggestions or automatically start the repair program. In addition, the soil structure adjustment module monitors and adjusts the soil hardness in real time to ensure that the soil compaction or looseness in the sowing area meets the sowing requirements, further ensuring the working stability of the seed drill and the adaptability of the soil environment, thereby effectively reducing the failure rate and ensuring the continuity and efficiency of sowing.

[0017] In the present invention, through the visualization module, the system displays information such as soil status, sowing parameters and equipment operation status in real time in a graphical interface, which is convenient for operators to intuitively monitor and manage the sowing process. The module also supports historical data query and remote monitoring functions. Operators can make decisions quickly based on real-time data and historical trends, and manually adjust sowing parameters when necessary. This interactive control design not only simplifies the operation, but also greatly improves the decision-making efficiency, helping operators to manage the seeder more flexibly in complex environments and achieve efficient operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention; Figure 2 The figure is a flow chart of a dynamic seeding mode adjustment module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0021] like Figure 1-Figure 2 As shown, the intelligent seeding machinery automation control system includes a soil variability analysis module, a dynamic seeding mode adjustment module, a soil structure adjustment module, a seeding control and optimization module, an intelligent fault diagnosis module and a visualization module, wherein; The soil variability analysis module is used to collect soil data in real time, including soil moisture, temperature, pH value, salinity, hardness, and particle size distribution. It also uses machine learning algorithms to model and analyze the collected soil data in spatial and temporal dimensions, and predict the spatial variability and suitability of soil in real time. The dynamic sowing pattern adjustment module is linked with the soil variability analysis module to automatically adjust the sowing depth, sowing speed, seed spacing and seed placement according to the predicted soil spatial variability and sowing suitability; The soil structure adjustment module is used to intelligently adjust the compaction and loosening of the soil when the seeder passes through the soil, ensuring that the soil structure after sowing is suitable for seed germination. The module detects the hardness of the soil through sensors, and automatically activates the loosening device to adjust the soil structure when the soil hardness exceeds the preset range, ensuring that the seeds can grow in a suitable soil environment; The sowing control and optimization module is used to comprehensively adjust the sowing parameters according to the output results of the soil variability analysis module and the dynamic sowing mode adjustment module. The sowing parameters include sowing depth, sowing speed, seed spacing and seed delivery amount; The intelligent fault diagnosis module is used to monitor the operating status of the planter in real time, detect and diagnose any faults that occur. The module monitors the system working status through an integrated sensor network, such as motor operation, transmission system load, abnormal fluctuations in sensor data, etc., and gives repair suggestions or automatically starts the repair program based on the fault diagnosis results; The visualization module is used to display the system working status and soil and sowing data in real time, including soil moisture, temperature and sowing depth, and provide it to operators in the form of a graphical interface to help make more intuitive decisions and adjustments.

[0022] The Soil Variability Analysis module includes: The soil variability analysis module collects soil data in real time. The soil data includes soil moisture, temperature, pH value, salinity, hardness and particle size distribution. The soil data is collected through multiple sensors, including humidity sensor, temperature sensor, pH value sensor, salinity sensor, hardness sensor and particle size sensor, among which; Humidity sensor: used to measure the relative humidity of the soil; Temperature sensor: used to measure soil temperature; pH sensor: used to measure the pH value of soil; Salt sensor: used to measure the salt concentration of soil; Hardness sensor: used to measure the hardness of soil (such as soil compressive strength); Particle size sensor: used to measure the particle size distribution of soil; The collected soil data is transmitted to the preset data processing unit via wireless communication. The data transmission adopts standardized data protocols, such as MQTT or LoRa, to ensure stable data transmission and real-time performance. The collected soil data are preprocessed, including denoising, interpolation to fill missing values ​​and unit conversion. The denoising method is wavelet transform, and the interpolation to fill missing values ​​is completed by Kriging interpolation or spline interpolation method. The preprocessed soil data were normalized to unify the dimensions and scales of different soil data items to ensure that the data could be compared and analyzed under a unified standard. The Z-Score standardization method was used for data standardization. By efficiently collecting soil data in real time, preprocessing and standardizing it, accurate and comparable data is provided for subsequent machine learning modeling analysis, which ensures the high quality of soil data and the accuracy of analysis.

[0023] The Soil Variability Analysis Module also includes: A spatial variability prediction model is established using the random forest algorithm, which consists of multiple decision trees. Each decision tree is trained by inputting features (such as soil moisture, temperature, pH value, salinity, hardness, particle size distribution, etc.) to generate a model with strong generalization ability. The spatial variability prediction model is trained by historical soil data and combined with real-time collected soil data to predict the spatial variability index of different soil areas, which is calculated as: ; Among them, SVI represents soil variability index, H represents soil hardness, M represents soil moisture, T represents soil temperature, P represents soil pH value, S represents salt concentration, G represents particle size distribution, function f is the spatial variability prediction model, and the tree ensemble results obtained through training are used to predict soil variability; Based on the predicted spatial variability index, multiple regression analysis was used to refine the division of soil suitability areas, identify areas suitable for sowing, and generate the soil suitability index. The suitability index was calculated as: ; Among them, AI represents the broadcastability index, , , , , , The weight coefficients assigned to each soil property (hardness, moisture, temperature, pH, salinity and particle size) are optimized and adjusted based on historical data. This formula is used to quantitatively evaluate soil suitability based on the weights of each soil attribute. According to the evaluation results of the sowing suitability index, the area suitable for sowing and sowing parameters, including sowing depth, sowing speed and seed release amount, are output and transmitted to the dynamic sowing mode adjustment module to optimize the sowing strategy; By using the random forest algorithm to model and analyze soil data, the spatial variability of soil can be effectively predicted, and combined with multiple regression analysis, the soil suitability can be quantitatively evaluated, ensuring that the spatial differences of soil are fully considered, thereby achieving accurate sowing area division and optimization of sowing parameters, significantly improving sowing efficiency and crop germination rate.

[0024] Dynamic seeding mode includes: Receive the suitability data output by the soil variability analysis module, which includes the soil suitability index and the spatial variability index, and is used to determine the adjustment requirements of sowing parameters in different regions; The sowing depth is automatically adjusted according to the soil suitability index. The higher the sowing suitability index, the deeper the sowing depth is to increase the contact area between the seed and the soil. The lower the sowing suitability index, the shallower the sowing depth is to reduce the seed burial depth and ensure the sowing effect in the unsuitable sowing area. The adjustment range of the sowing depth is based on the preset standard value and is carried out according to the following formula: ; Where D is the sowing depth, For standard sowing depth, It is an adjustment coefficient, which is determined dynamically based on the soil suitability index; The sowing speed is adjusted according to the soil spatial variability index. The larger the spatial variability index, the greater the difference in soil regions, and the lower the sowing speed to ensure uniform distribution of seeds. The smaller the spatial variability index, the faster the sowing speed to improve sowing efficiency. The adjustment range of sowing speed is calculated by the following formula; ; Where V is the actual sowing speed, is the standard sowing speed. To adjust the coefficient, it is dynamically determined based on the soil spatial variability index; The seed spacing is automatically adjusted based on the sowing suitability index and spatial variability index. The higher the sowing suitability index and the smaller the spatial variability, the smaller the seed spacing is to increase the seed density and the number of germinations per unit area. If the sowing suitability index is lower or the spatial variability is greater, the seed spacing is larger to avoid over-crowding of seeds affecting growth. The seed spacing adjustment formula is expressed as: ; Where S is the actual seed spacing, is the standard seed spacing, To adjust the coefficient, it is dynamically determined based on the soil suitability index and spatial variability index; The seed placement amount is automatically adjusted to match the sowing suitability index and spatial variability index. The higher the sowing suitability, the more seed placement is required to ensure that soil resources are fully utilized. The lower the sowing suitability, the lower the seed placement is to save resources. The adjustment of seed placement is determined by the following formula: ; Among them, Q is the actual amount of seeds put in, is the standard seed placement amount, The adjustment coefficient is calculated dynamically based on the sowing suitability index and spatial variability index; The dynamic sowing mode adjustment module achieves precise sowing control in different soil areas by automatically adjusting the sowing depth, speed, seed spacing and release amount, ensuring that the sowing parameters can adapt to the spatial differences of the soil, improving sowing uniformity and seed utilization, thereby optimizing the overall sowing effect and significantly improving agricultural production efficiency.

[0025] The soil structure conditioning module includes: The soil hardness sensor installed on the seeder detects soil hardness data in real time. The hardness data is used to determine the compaction or looseness of the soil, ensuring that the collected soil information is highly accurate and real-time. The detected soil hardness data is compared with the preset soil hardness standard value. When the soil hardness value exceeds the preset range, the system identifies the soil area as a compacted or too hard area and requires structural adjustment; When the soil hardness exceeds the preset standard, the loosening device is automatically activated. The loosening device adjusts the loosening intensity and depth according to the actual value of the soil hardness to ensure that the loosening effect meets the sowing requirements and improves the growth environment of the seeds. The soil hardness sensor continuously monitors the hardness change of the soil. When the preset hardness is reached, the loosening device will automatically stop working to prevent excessive loosening of the soil and affect the sowing effect. By detecting and adjusting soil hardness in real time, it is possible to effectively identify and improve over-compacted soil areas, thereby providing a suitable growth environment for seeds and ensuring the suitability of the soil structure after sowing.

[0026] The soil structure conditioning module also includes: According to the soil hardness data detected by the soil hardness sensor, the looseness of the soil is monitored in real time to determine whether the soil is within the preset hardness range to ensure the stability and suitability of the soil structure after sowing; When the soil hardness is detected to be lower than the preset range, the compaction device is automatically activated to compact the soil to ensure that the soil is not too loose, thereby avoiding inconsistent seed depth or soil instability caused by excessive loosening; The working intensity of the compaction device is dynamically adjusted through the control system, and the compaction intensity is gradually increased or decreased according to the actual detected soil hardness data until the soil hardness reaches the preset range suitable for sowing; After the compaction operation is completed, the soil hardness sensor detects the soil hardness again to ensure that the soil hardness is within the standard value range for sowing suitability. If the hardness meets the preset range, the compaction device will automatically stop and the soil conditioning work will be completed; By dynamically adjusting the looseness and compaction of the soil, we ensure that the soil structure after the seeder passes can meet the growth needs of the seeds. This not only improves the suitability of the soil for sowing, but also significantly improves the germination success rate and crop growth quality after sowing.

[0027] The seeding control and optimization module includes: Receive and comprehensively analyze the output data from the soil variability analysis module and the dynamic sowing mode adjustment module, including soil spatial variability, sowing suitability index and initial values ​​of dynamically adjusted sowing parameters; During the sowing process, the execution of the sowing operation is monitored in real time, including the actual values ​​of sowing depth, sowing speed, seed spacing and seed delivery amount, and the actual values ​​are compared with the preset target parameter values ​​to detect possible deviations; When the deviation between the actual sowing parameter value and the target parameter value exceeds the preset tolerance range, the adjustment mechanism is automatically triggered to make fine adjustments to the deviation items, for example: (1) If the actual sowing depth is too shallow, gradually increase the sowing depth until the target depth is reached; (2) If the seed spacing is too small, the sowing path is automatically adjusted to increase the spacing; (3) If the seed release rate is too high, reduce the release rate appropriately to ensure that the seed amount sown each time is within the target range; Based on real-time monitoring feedback, the sowing path is optimized. If the seeder is detected to deviate from the preset path due to changes in terrain or soil conditions, the path is automatically corrected to ensure that the seeder moves along the preset path, thereby achieving uniform sowing. Specifically, it includes: (1) Real-time position monitoring: The current position and attitude of the planter are monitored in real time through the high-precision GPS module and inertial navigation system (INS) installed on the planter. The system records the longitude and latitude coordinates, azimuth and tilt angle of the planter at a high frequency. At the same time, the terrain is scanned by a camera or LiDAR to obtain terrain information such as soil height difference, slope, and obstacles in front of the planter; (2) Path deviation detection: The system compares the current position and driving direction of the planter with the target point and travel direction of the preset path, and calculates the distance and angle (deviation) that the planter deviates from the preset path; When the deviation exceeds the preset allowable range (e.g., a deviation of 1 meter or an angle deviation of more than 5 degrees), the system identifies it as path deviation; (3) Path correction algorithm: When a deviation is detected, the system automatically activates the path correction algorithm. The path correction adopts a path correction method based on proportional-integral-differential (PID) control to gradually reduce the deviation by adjusting the speed and steering angle of the planter. The control model is expressed as: ; in, To correct the steering angle, , and is the gain coefficient of the PID controller, e is the deviation distance between the current position of the planter and the preset path, is the integral of the deviation (accumulated error), is the rate of change of the deviation (differential); (4) Speed ​​and steering adjustment: Based on the steering angle adjustment result output by the correction algorithm, the system dynamically adjusts the differential speed of the left and right wheels of the planter to achieve accurate steering correction. If the planter deviates from the left path, the speed of the right wheel is increased to make the planter turn in the direction of the preset path; if it deviates from the right path, the speed of the left wheel is increased to correct the path. At the same time, the system adjusts the seeder's travel speed according to the terrain slope and soil tightness. For example, it slows down on steeper downhill sections to ensure that the seeder does not slip when correcting the path. (5) Path correction confirmation: After the path is corrected, the system compares the position and posture of the planter with the preset path again. If the deviation is within the allowable range, the system confirms that the correction is successful and resumes normal driving; If the deviation is still beyond the allowable range, repeat the above correction steps until the planter returns to the preset path; (6) Real-time path update and feedback: If the terrain is complex or large-area soil differences are detected, the system will dynamically update the preset path and replan the sowing route to ensure that the seeder moves along the optimal path; The deviation data of the correction process will be recorded for subsequent path optimization and parameter adjustment of the seeding control module to improve the accuracy of the next path correction; After sowing is completed, the actual execution of sowing parameters is summarized and evaluated, the deviation data is analyzed and a sowing quality report is generated. The report includes the difference between the actual execution value and the target value of sowing depth, sowing speed, seed spacing and seeding amount, so as to optimize the parameters of subsequent sowing operations; Through real-time monitoring and fine-tuning of the sowing control and optimization module, the system can effectively ensure the stability and consistency of the sowing operation and reduce sowing errors caused by terrain changes or equipment deviations. This module provides comprehensive real-time control and optimization during the sowing process, significantly improving the accuracy and uniformity of sowing, and helping to achieve efficient and reliable agricultural production operations.

[0028] Intelligent fault diagnosis module includes: The integrated sensor network monitors the operation status data of the planter in real time. The sensor network includes current sensors, temperature sensors, vibration sensors, pressure sensors and position sensors, which monitor the motor operation status, transmission system load, mechanical vibration, hydraulic pressure and the driving position of the planter respectively. Preprocess the collected operating status data, including data denoising, standardization, and outlier detection, to ensure data accuracy and consistency. Outlier detection identifies possible abnormal fluctuations in the data by setting thresholds or using mean variance analysis. Based on the pre-processed operating status data, the normal range of various indicators is analyzed, and a fault diagnosis model is established based on the support vector machine algorithm. The fault diagnosis model is trained through historical operating status data and known fault samples, and the support vector machine algorithm is used to identify the fault mode of the equipment operating status. The process of fault mode identification is as follows: (1) When the data of a certain sensor deviates from the normal range (for example, the current or temperature exceeds the standard), the model determines that the component monitored by the sensor has a potential fault; (2) If multiple sensor data are abnormal at the same time, the system will conduct a comprehensive analysis of the abnormal signals to identify possible compound faults; The fault diagnosis model classifies the faults and generates a fault diagnosis report, which includes the fault location, fault type and possible cause. If it is a minor fault, the system provides repair suggestions; if it is a serious fault, the emergency shutdown procedure is automatically initiated to prevent further damage. After the fault diagnosis is completed, the system provides corresponding repair suggestions or automatically starts the repair program based on the diagnosis results. The repair suggestions include: reducing the speed of the motor, reducing the load of the transmission system, adjusting the sowing depth, etc. For self-repairable faults (such as minor sensor abnormalities), the system automatically calibrates the sensor parameters and tries to restore the normal operation of the equipment; The intelligent fault diagnosis module, through the integrated sensor network and support vector machine algorithm, can monitor the operating status of the seeder in real time, detect and diagnose faults, and provide repair suggestions or automatically start the repair program. This module effectively improves the operating stability and fault response speed of the seeder, ensuring the continuity of the seeding process and the reliability of the equipment.

[0029] The visualization modules include: Receive and integrate data from various modules in real time, including soil data provided by the soil variability analysis module, seeding depth, seeding speed, seed spacing and seed placement data provided by the dynamic seeding mode adjustment module, and operating status data and fault diagnosis reports provided by the intelligent fault diagnosis module; Process the received data, filter and classify the key parameters for display, including sowing depth, sowing speed, seed spacing, seed placement and fault diagnosis report. To ensure the accuracy and readability of the information, perform necessary unit conversion, value formatting and time sequence alignment on the data to ensure that the displayed content is updated in real time and meets the operational requirements; The visual interface displays soil and sowing data (sowing data includes sowing depth, sowing speed, seed spacing and seed placement) in real time in various forms including charts, numerical values ​​and graphics. The specific contents include: Soil parameters: Display current values ​​and historical trend graphs of soil moisture, temperature, pH value, salt concentration, hardness and particle size distribution to help operators understand the changing trends of soil conditions; Sowing parameters: Display the current values ​​and dynamic adjustments of sowing depth, sowing speed, seed spacing and seeding amount, ensuring that operators can monitor sowing accuracy in real time; Fault status: Displays the equipment operating status, alarm information and fault location identification provided by the intelligent fault diagnosis module, so that operators can quickly identify and handle system abnormalities.

[0030] The visualization module also includes: Provides data query function, allowing operators to retrieve and analyze changes in soil and sowing data within any time period, to help decision-making and optimize sowing strategies; Integrated interactive function allows operators to manually adjust sowing data through a visual interface. When a sowing parameter or soil condition changes suddenly, the operator can directly input the adjustment value through the interface, and the system automatically applies the updated parameter and reflects it in real time on the interface. It provides remote monitoring and operation functions, connects to remote terminals via wireless networks, and enables operators to view sowing data, soil data, and operating status data in real time in the control room or on mobile devices.

[0031] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0032] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Intelligent seeding machinery automatic control system, characterized by: It includes soil variability analysis module, dynamic seeding pattern adjustment module, soil structure adjustment module, seeding control and optimization module, intelligent fault diagnosis module and visualization module, among which; The soil variability analysis module is used to collect soil data in real time, including soil moisture, temperature, pH value, salinity, hardness and particle size distribution, and use machine learning algorithms to model and analyze the collected soil data in spatial and temporal dimensions to predict the spatial variability and suitability of soil in real time; The dynamic sowing mode adjustment module is linked with the soil variability analysis module to automatically adjust the sowing depth, sowing speed, seed spacing and seed delivery amount according to the predicted soil spatial variability and sowing suitability; The soil structure adjustment module is used to intelligently adjust the compaction and looseness of the soil when the seeder passes through the soil; The sowing control and optimization module is used to comprehensively adjust the sowing parameters according to the output results of the soil variability analysis module and the dynamic sowing mode adjustment module. The sowing parameters include sowing depth, sowing speed, seed spacing and seed delivery amount; The intelligent fault diagnosis module is used to monitor the operating status of the planter in real time, detect the faults that occur and perform diagnosis; The visualization module is used to display the system working status and soil and sowing data in real time, including soil moisture, temperature and sowing depth, and provide them to operators in the form of a graphical interface.

2. The intelligent automatic control system for sowing machinery according to claim 1 is characterized in that: The soil variability analysis module includes: The soil variability analysis module collects soil data in real time, the soil data including soil moisture, temperature, pH value, salinity, hardness and particle size distribution, and the soil data is collected through multiple sensors, including a moisture sensor, a temperature sensor, a pH value sensor, a salinity sensor, a hardness sensor, and a particle size sensor; Transmitting the collected soil data to a preset data processing unit via wireless communication; Preprocess the collected soil data, including noise removal, interpolation to fill missing values ​​and unit conversion; The preprocessed soil data were normalized to unify the dimensions and scales of different soil data items.

3. The intelligent automatic control system for sowing machinery according to claim 2 is characterized in that: The soil variability analysis module also includes: A spatial variability prediction model was established using the random forest algorithm; The spatial variability prediction model is trained through historical soil data, and combined with real-time collected soil data, the spatial variability index of different soil areas is predicted; Based on the predicted spatial variability index, multiple regression analysis was used to refine the division of soil suitability areas, identify areas suitable for sowing, and generate a soil suitability index. According to the evaluation results of the sowing suitability index, the area suitable for sowing and the sowing parameters, including sowing depth, sowing speed and seed release amount, are output and transmitted to the dynamic sowing mode adjustment module.

4. The intelligent automatic control system for sowing machinery according to claim 3 is characterized in that: The dynamic seeding mode specifically includes: Receiving the sowing suitability data output by the soil variability analysis module, wherein the sowing suitability data includes a soil sowing suitability index and a spatial variability index; Automatically adjust the sowing depth according to the soil sowing suitability index. The higher the sowing suitability index, the deeper the sowing depth is to increase the contact area between the seed and the soil. The lower the sowing suitability index, the shallower the sowing depth is to reduce the seed burial depth. Adjust the sowing speed according to the soil spatial variability index. The larger the spatial variability index, the greater the difference in soil regions, and the lower the sowing speed to ensure uniform distribution of seeds. The smaller the spatial variability index, the faster the sowing speed to improve sowing efficiency. Automatically adjust the seed spacing based on the sowing suitability index and spatial variability index. The higher the sowing suitability index and the smaller the spatial variability, the smaller the seed spacing, so as to increase the seed density and the number of germinations per unit area. If the sowing suitability index is lower or the spatial variability is greater, the seed spacing is larger to avoid over-crowding of seeds that affects growth. The seed supply is automatically adjusted to match the sowing suitability index and spatial variability index. The higher the sowing suitability, the more seed supply is required to ensure that soil resources are fully utilized. The lower the sowing suitability, the lower the seed supply is to save resources.

5. The intelligent automatic control system for sowing machinery according to claim 4 is characterized in that: The soil structure adjustment module comprises: The soil hardness sensor installed on the seeder detects soil hardness data in real time, and the hardness data is used to determine the compaction or looseness of the soil; The detected soil hardness data is compared with the preset soil hardness standard value. When the soil hardness value exceeds the preset range, the system identifies the soil area as a compacted or too hard area and requires structural adjustment; When the soil hardness exceeds the preset standard, the loosening device is automatically activated, and the loosening device adjusts the loosening intensity and depth according to the actual value of the soil hardness; The soil hardness sensor continuously monitors the hardness changes of the soil, and automatically stops the loosening device when the preset hardness is reached.

6. The intelligent automatic control system for sowing machinery according to claim 5 is characterized in that: The soil structure adjustment module also includes: According to the soil hardness data detected by the soil hardness sensor, the looseness of the soil is monitored in real time to determine whether the soil is within the preset hardness range; When the soil hardness is detected to be lower than the preset range, the compaction device is automatically activated to compact the soil; The working intensity of the compaction device is dynamically adjusted through the control system, and the compaction intensity is gradually increased or decreased according to the actual detected soil hardness data until the soil hardness reaches the preset range suitable for sowing; After the compaction operation is completed, the soil hardness sensor detects the soil hardness again to ensure that the soil hardness is within the standard value range for sowing suitability. If the hardness is within the preset range, the compaction device will automatically stop and the soil conditioning work will be completed.

7. The intelligent automatic control system for sowing machinery according to claim 6 is characterized in that: The sowing control and optimization module includes: Receiving and comprehensively analyzing output data from the soil variability analysis module and the dynamic sowing mode adjustment module, the data including soil spatial variability, sowing suitability index and initial values ​​of dynamically adjusted sowing parameters; During the sowing process, the execution of the sowing operation is monitored in real time, including the actual values ​​of sowing depth, sowing speed, seed spacing and seed delivery amount, and the actual values ​​are compared with the preset target parameter values; When the deviation between the actual sowing parameter value and the target parameter value exceeds the preset tolerance range, the adjustment mechanism is automatically triggered to make fine adjustments to the deviation item; Optimize the sowing path based on real-time monitoring feedback, and automatically correct the path if it detects that the seeder has deviated from the preset path due to changes in terrain or soil conditions; After sowing is completed, the actual implementation of the sowing parameters is summarized and evaluated, the deviation data is analyzed and a sowing quality report is generated. The report content includes the difference between the actual implementation value and the target value of sowing depth, sowing speed, seed spacing and release amount.

8. The intelligent automatic control system for sowing machinery according to claim 7 is characterized in that: The intelligent fault diagnosis module comprises: The integrated sensor network monitors the operation status data of the planter in real time. The sensor network includes current sensors, temperature sensors, vibration sensors, pressure sensors and position sensors, which monitor the motor operation status, transmission system load, mechanical vibration, hydraulic pressure and the driving position of the planter respectively. Preprocess the collected operating status data, including data denoising, standardization and outlier detection; Based on the pre-processed operating status data, the normal range of each indicator is analyzed, and a fault diagnosis model is established based on the support vector machine algorithm; Classify faults according to the identification results of the fault diagnosis model and generate a fault diagnosis report; After the fault diagnosis is completed, the system provides corresponding repair suggestions or automatically starts the repair program based on the diagnosis results.

9. The intelligent automatic control system for sowing machinery according to claim 8 is characterized in that: The visualization module comprises: Receive and integrate data from various modules in real time, including soil data provided by the soil variability analysis module, seeding depth, seeding speed, seed spacing and seed placement data provided by the dynamic seeding mode adjustment module, and operating status data and fault diagnosis reports provided by the intelligent fault diagnosis module; Process the received data, filter and classify the key parameters for display, including sowing depth, sowing speed, seed spacing, seed delivery amount and fault diagnosis report; Soil and seeding data are presented in real time through a visual interface in a variety of formats including charts, numerical values ​​and graphs.

10. The intelligent automatic control system for sowing machinery according to claim 9, characterized in that: The visualization module also includes: Provides data query function, allowing operators to retrieve and analyze changes in soil and sowing data within any time period; Integrated interactive function allows operators to manually adjust seeding data through a visual interface; It provides remote monitoring and operation functions, connects to remote terminals via wireless networks, and enables operators to view sowing data, soil data, and operating status data in real time in the control room or on mobile devices.

Images