Intelligent multifunctional grain threshing method and system

Abstract

The invention relates to the technical field of intelligent agriculture, in particular to an intelligent multifunctional grain threshing method and system. The method comprises the following steps that a conveying belt device is controlled to evenly convey grains to be threshed to an inlet of a threshing device, a photoelectric sensor is controlled to detect the number and speed of the conveyed grains, and grain conveying data are generated; generating threshing strength and speed parameters according to the grain conveying data, and respectively obtaining threshing strength parameter data and threshing speed parameter data; performing threshing operation of the thresher according to the threshing strength parameter data and the threshing speed parameter data, and monitoring the pressure of the cavity of the thresher to obtain threshing pressure data; and performing threshing effect evaluation according to the threshing pressure data to obtain threshing effect evaluation data, and performing optimization adjustment on the threshing strength parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain real-time threshing optimization parameter data. The threshing efficiency can be improved, and the grain quality can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent agricultural technology, and in particular to an intelligent multifunctional grain threshing method and system. Background Art

[0002] With the rapid development of agricultural automation and intelligence, traditional grain threshing systems can no longer meet the needs of modern agricultural production. In the traditional grain threshing process, equipment usually relies on preset fixed parameters for threshing operations, lacks intelligent monitoring and real-time adjustment mechanisms, and often leads to low threshing efficiency, high grain damage rate, high energy consumption and severe equipment wear. These problems make it difficult for traditional threshing equipment to maintain efficient and stable operation when processing different types of grains or under different production conditions, increasing production costs and waste of resources. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes an intelligent multifunctional grain threshing method and system to solve at least one of the above technical problems.

[0004] The present application provides an intelligent multifunctional grain threshing method, the method comprising:

[0005] S1, controlling the conveyor belt device to evenly convey the grains to be threshed to the entrance of the threshing device, and controlling the photoelectric sensor to detect the quantity and speed of the conveyed grains to generate grain conveying data;

[0006] S2. Generate threshing force and speed parameters according to the grain transportation data, and obtain threshing force parameter data and threshing speed parameter data respectively;

[0007] S3, performing threshing operation of the thresher according to the threshing force parameter data and the threshing speed parameter data, and monitoring the cavity pressure of the thresher to obtain threshing pressure data;

[0008] S4. Evaluate the threshing effect according to the threshing pressure data to obtain threshing effect evaluation data, and optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain real-time threshing optimization parameter data to perform auxiliary operations for adjusting grain threshing parameters.

[0009] The present invention ensures uniform distribution of grains in the threshing device by precisely controlling the speed of the conveyor belt and the conveying amount of grains, reduces pauses and bottlenecks in the threshing process, and thus greatly improves the overall threshing efficiency. Based on the grain conveying data collected in real time, the threshing force parameters and threshing speed parameters are dynamically generated and adjusted to ensure that the force and speed in the threshing process are always in the best state, avoiding excessive or insufficient threshing. By monitoring the pressure in the thresher cavity, the threshing pressure data is obtained in real time, and the threshing effect is evaluated to achieve closed-loop control, which can immediately detect and correct abnormalities in the threshing process and ensure the threshing quality. Accurate force and speed control effectively reduces the mechanical damage of grains in the threshing process, maintains the integrity and quality of grains, and improves the market competitiveness of products. According to the threshing effect evaluation data, the threshing force parameters and threshing speed parameters are automatically optimized and adjusted to achieve self-learning and optimization of the threshing process, thereby improving the intelligence level and adaptability of the system.

[0010] Optionally, S1 includes:

[0011] Remotely initialize and configure the conveyor belt device through the grain threshing IoT platform to obtain the initial parameter data of the conveyor belt;

[0012] The conveyor belt is transported according to the initial parameter data of the conveyor belt, and the grain image is collected by a visual device installed on the conveyor belt device to obtain the grain image data;

[0013] Extract grain distribution according to grain image data to obtain grain distribution data;

[0014] Generate conveyor belt vibration frequency parameters and conveyor belt transmission rate data according to grain distribution data, and obtain conveyor belt vibration frequency parameter data and conveyor belt transmission rate data respectively;

[0015] Optimize conveyor belt transportation according to conveyor belt vibration frequency parameter data and conveyor belt transmission rate data;

[0016] The photoelectric sensor is controlled to detect the quantity and speed of the conveyed grains and generate grain conveying data.

[0017] In the present invention, the conveyor belt device is remotely initialized and configured through the grain threshing Internet of Things platform, and the initial parameters of the conveyor belt can be quickly set and adjusted without on-site operation. The remote control capability reduces manual intervention and improves the convenience and flexibility of operation. The visual device placed on the conveyor belt device is used to collect grain images to realize real-time monitoring of grain distribution during transportation. By extracting the distribution of the collected grain image data, accurate grain distribution data is generated, and the distribution of grains on the conveyor belt can be described in detail, providing a reliable basis for parameter generation. According to the accurate grain distribution data, the vibration frequency parameters and transmission rate parameters of the conveyor belt are automatically generated. Based on the data-driven parameter generation method, the uniformity of grain distribution during transportation is ensured, congestion and damage are reduced, and transportation efficiency is improved. The generated vibration frequency parameters and transmission rate parameters are used to optimize the conveying operation of the conveyor belt. The running state of the conveyor belt is dynamically adjusted so that it can respond to changes in grain distribution in real time and maintain the stability and efficiency of the transportation process. The photoelectric sensor is used to detect the quantity and speed of the conveyed grain in real time, which is not only used for real-time monitoring of the transportation state, but also provides an important reference for the generation of threshing force and speed parameters, forming a data-driven closed-loop control system.

[0018] Optionally, wherein the grain distribution extraction comprises:

[0019] Extracting grain image features according to the grain image data to obtain grain image feature data;

[0020] Perform grain region segmentation according to grain image feature data to obtain grain region segmentation data;

[0021] Optimize the segmented area according to the grain area segmentation data to obtain grain area optimization data;

[0022] Generate a grain distribution map based on grain area optimization data to obtain grain spatial distribution map data;

[0023] The spatial distribution data of the grains is analyzed spatially to obtain the grain distribution data.

[0024] In the present invention, by extracting features from grain image data, it is possible to accurately capture multidimensional features such as grain morphology, color and texture, and improve the quality of basic data for analysis. Based on the extracted image feature data, image segmentation (such as U-Net, Mask R-CNN) is used to achieve accurate segmentation of grain areas and distinguish grains from background or impurities. By optimizing the segmented areas (such as morphological operations, edge smoothing), small noise areas are removed and the clarity of grain area boundaries is enhanced. Based on the optimized regional data, a detailed grain spatial distribution map is generated using spatial mapping (such as Voronoi diagram, KDE) to intuitively display the distribution of grains on the conveyor belt. Spatial data analysis (such as spatial autocorrelation analysis, cluster analysis) is performed on the generated spatial distribution map data to deeply understand the distribution pattern and trend of grains, providing a scientific basis for the optimization of threshing parameters. Based on the grain distribution data, the vibration frequency parameters and transmission rate parameters of the conveyor belt are automatically generated and dynamically adjusted to ensure uniform distribution and efficient transportation of grains during the threshing process.

[0025] Optionally, the distribution data spatial analysis includes:

[0026] Extracting multidimensional spatial features from the grain spatial distribution map data to obtain multidimensional spatial feature data of grains;

[0027] According to the multi-dimensional spatial characteristic data of grains, global spatial autocorrelation analysis and local spatial autocorrelation analysis are performed to obtain the global spatial autocorrelation data of grains and the local spatial autocorrelation data of grains respectively;

[0028] According to the global spatial autocorrelation data of grains and the local spatial autocorrelation data of grains, the spatial relationship coupling processing of grains is carried out to obtain the full local relationship coupling data of grains;

[0029] Density estimation is performed based on the grain full-local relationship coupling data to obtain grain distribution density map data;

[0030] Spatial cluster analysis was performed on the grain distribution density map data to obtain the grain distribution data.

[0031] In the present invention, by extracting multidimensional spatial features from the spatial distribution map data of grains, various spatial features of grains during transportation, such as morphology, density, distribution pattern, etc., can be captured. A dual understanding of the global and local characteristics of grain distribution is provided, which helps to identify the overall distribution trend and local anomalies, and improves the level of detail of the analysis. By coupling the spatial relationship of global spatial autocorrelation data with local spatial autocorrelation data, spatial relationship information at different levels is integrated to form a more comprehensive and coordinated data model. A grain distribution density map is generated by a density estimation method (such as kernel density estimation KDE) to intuitively display the density and distribution characteristics of grains in space. The density map data is clustered by spatial clustering analysis (such as DBSCAN, K-means), and the clustered and dispersed areas of grain distribution are automatically identified, so as to achieve accurate classification and management of grain areas.

[0032] Optionally, the multidimensional space feature extraction includes:

[0033] The grain spatial distribution map data is converted into three dimensions to obtain grain spatial three-dimensional map data;

[0034] Feature extraction is performed based on the grain spatial three-dimensional map data and the grain spatial distribution map data to obtain the grain spatial three-dimensional map feature data and the grain spatial distribution map feature data respectively;

[0035] Performing local feature extraction on the grain spatial three-dimensional map feature data and the grain spatial distribution map feature data to obtain grain three-dimensional local feature data and grain spatial local feature data respectively;

[0036] Extracting high-order features from the three-dimensional local feature data of the grain and the spatial local feature data of the grain, and obtaining the three-dimensional high-order feature data of the grain and the spatial high-order feature data of the grain respectively;

[0037] The three-dimensional high-order feature data of grains and the spatial high-order feature data of grains are fused to obtain the multi-dimensional spatial feature data of grains.

[0038] In the present invention, the spatial distribution map data of grains is converted into three dimensions to obtain three-dimensional spatial map data of grains, thereby enriching the spatial dimension information of the data. Feature extraction is performed separately according to the three-dimensional spatial map data of grains and the two-dimensional distribution map data to capture the characteristic information of grains in different dimensions, thereby improving the depth and breadth of data analysis and providing a solid foundation for more complex spatial relationship analysis and optimization. In-depth mining of detailed information in grain distribution, such as local dense areas, sparse areas and abnormal distribution points, significantly improves the ability to recognize grain distribution details and supports more accurate threshing parameter adjustment. Through high-order feature extraction, the complex patterns and deep relationships in grain distribution are revealed, the descriptive ability and analysis depth of the data are enhanced, and more comprehensive and detailed feature support is provided for intelligent optimization. Through feature fusion, feature information from different dimensions is integrated, the integrity and consistency of data analysis are improved, and more efficient spatial distribution analysis and optimization control are supported.

[0039] Optionally, S2 includes:

[0040] Extract grain features according to grain transportation data to obtain grain feature data;

[0041] The threshing force is generated according to the grain characteristic data to obtain the threshing force parameter data;

[0042] The threshing speed parameters are generated according to the grain characteristic data to obtain the threshing speed parameter data.

[0043] The present invention can fully capture the multi-dimensional features of grains, such as morphology, color, density, flow rate, etc., by extracting features from grain transport data. Ensure that the threshing force is highly matched with the grain characteristics, avoid excessive or insufficient threshing, reduce grain damage, and improve threshing quality and efficiency. Dynamically adjust the threshing speed to ensure the stability and efficiency of the threshing process, improve overall production efficiency, and reduce energy consumption. Through the precise generation of threshing force and speed parameters, ensure that the force and speed during the threshing process are in the optimal state, and ensure the integrity and quality of the grain. Based on the real-time collected grain characteristic data, the threshing parameters are dynamically generated and adjusted, so that the system can adapt to changes in different grain types and production environments.

[0044] Optionally, the grain feature extraction comprises:

[0045] Extract dynamic features based on grain transportation data to obtain dynamic feature data of grain transportation;

[0046] Conducting velocity and density analysis on the dynamic characteristic data of grain transportation, and obtaining the velocity characteristic data of grain transportation and the density characteristic data of grain transportation respectively;

[0047] Perform morphological feature extraction and reflection feature extraction according to the grain transportation data to obtain grain transportation morphological feature data and grain transportation reflection feature data respectively;

[0048] The grain conveying velocity characteristic data, the grain conveying density characteristic data, the grain conveying morphology characteristic data and the grain conveying reflection characteristic data are subjected to feature generation to obtain the grain characteristic data.

[0049] In the present invention, dynamic feature extraction is performed on grain transportation data to obtain dynamic change characteristics of grains during transportation, such as flow rate fluctuations, transportation stability, etc. Accurately understand the flow and density changes of grains during transportation, and optimize the operating parameters of the conveyor belt (such as speed, vibration frequency) according to the flow rate and density characteristic data, improve transportation efficiency, and reduce grain congestion and damage. Accurately identify the morphological characteristics of different types of grains to ensure that the threshing force and speed parameters can be adjusted according to the specific morphology of the grains, reduce damage to the grains during the threshing process, and improve product quality. By reflecting characteristic data, grains of different varieties and maturity can be accurately distinguished, supporting intelligent adjustment of threshing parameters, ensuring the optimal treatment of different varieties of grains during the threshing process, and improving product consistency and market competitiveness.

[0050] Optionally, S3 includes:

[0051] The threshing force parameter data and the detachment speed parameter data are loaded into the thresher control system through the industrial Internet interface to obtain the thresher parameter loading data;

[0052] The threshing operation is started according to the thresher parameter loading data to perform the threshing operation of the thresher;

[0053] The pressure sensor installed in the thresher is used to collect the pressure in the thresher cavity to obtain the threshing pressure data.

[0054] In the present invention, the threshing force parameter data and the threshing speed parameter data are loaded into the thresher control system through the industrial Internet interface to realize the automatic transmission and configuration of the parameters. According to the loaded thresher parameter loading data, the thresher is automatically started to perform the threshing operation to realize fully automated operation. Real-time monitoring of the threshing process is realized to ensure that the threshing pressure is maintained within the set range to prevent equipment overload or grain damage. High-precision pressure data supports real-time adjustment and optimization of the threshing process to ensure threshing quality and equipment safety. Accurate control and optimization of threshing parameters are realized to ensure that the threshing process runs in the best state, improve threshing efficiency, reduce grain damage, and ensure stable threshing quality.

[0055] Optionally, S4 includes:

[0056] The threshing image data is obtained by collecting threshing images through an image sensor arranged on the threshing machine;

[0057] According to the threshing image data, threshing efficiency and grain damage rate are extracted to obtain threshing efficiency data and grain damage rate data;

[0058] The threshing effect is evaluated according to the threshing pressure data, the threshing efficiency data and the grain damage rate data to obtain the threshing effect evaluation data;

[0059] According to the threshing effect evaluation data, the threshing force parameter data and the threshing speed parameter data are optimized and adjusted to obtain real-time threshing optimization parameter data for auxiliary operations of grain threshing parameter adjustment.

[0060] In the present invention, threshing efficiency is extracted through threshing image data, and the efficiency index of threshing operation, such as the number of grains threshed per unit time, can be accurately quantified. Grain damage rate is extracted through threshing image data, and the degree of grain damage during threshing can be monitored and evaluated in real time. Combining threshing pressure data, threshing efficiency data and grain damage rate data, a comprehensive evaluation of the threshing process is provided to ensure that the threshing operation achieves the best balance between efficiency and quality, and supports scientific decision-making and continuous improvement. Dynamic optimization of threshing parameters is achieved to ensure that the threshing process is always in the best working state, improve threshing efficiency, reduce grain damage rate, and improve overall production quality.

[0061] Optionally, the present application further provides an intelligent multifunctional grain threshing system for executing the intelligent multifunctional grain threshing method as described above, wherein the intelligent multifunctional grain threshing system comprises:

[0062] A grain conveying module is used to control the conveyor belt device to evenly convey the grains to be threshed to the entrance of the threshing device, and to control the photoelectric sensor to detect the quantity and speed of the conveyed grains to generate grain conveying data;

[0063] A grain threshing parameter generation module is used to generate threshing force and speed parameters according to grain conveying data, and obtain threshing force parameter data and threshing speed parameter data respectively;

[0064] The threshing operation module of the thresher is used to perform the threshing operation of the thresher according to the threshing force parameter data and the threshing speed parameter data, and to monitor the pressure of the thresher cavity to obtain the threshing pressure data;

[0065] The real-time threshing optimization module is used to evaluate the threshing effect according to the threshing pressure data, obtain the threshing effect evaluation data, and optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain the real-time threshing optimization parameter data for auxiliary operations of grain threshing parameter adjustment.

[0066] The purpose of the present invention is to remotely initialize and configure the conveyor belt device through the Internet of Things platform, and combine the photoelectric sensor to monitor the quantity and speed of conveyed grains in real time to achieve full automation control of the conveying process. Comprehensive monitoring of the threshing process is achieved to ensure the real-time and accuracy of the data, and provide a reliable data basis for subsequent parameter generation and optimization. Through multidimensional spatial feature extraction technology, the grain spatial distribution map data is converted into multidimensional spatial feature data, and combined with global and local spatial autocorrelation analysis, the deep spatial relationship of grain distribution is revealed. Ensure that the threshing force and speed are highly matched with the grain characteristics, optimize the efficiency and quality of the threshing process, reduce grain damage, and improve the consistency and market competitiveness of the product after threshing. Real-time monitoring and dynamic adjustment of the threshing process are achieved to ensure that the threshing pressure is always maintained within the optimal range, prevent equipment overload or grain damage, and improve the stability and reliability of the threshing process. The present invention forms a data-driven continuous optimization mechanism to ensure that the threshing process is always in the best state, improve the overall threshing efficiency and grain quality, and reduce production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings:

[0068] Figure 1 A flowchart showing the steps of an intelligent multifunctional grain threshing method according to an embodiment is shown;

[0069] Figure 2 A flowchart showing the steps of an intelligent grain conveying method according to an embodiment is shown;

[0070] Figure 3 A flowchart showing the steps of a method for generating grain threshing parameters according to an embodiment is shown;

[0071] Figure 4 A flowchart showing a threshing method of a thresher according to an embodiment of the present invention is provided;

[0072] Figure 5 A flowchart of the steps of a real-time threshing optimization method according to an embodiment is shown;

[0073] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0074] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0076] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0077] See also Figures 1 to 5 The present application provides an intelligent multifunctional grain threshing method, the method comprising:

[0078] S1, controlling the conveyor belt device to evenly convey the grains to be threshed to the entrance of the threshing device, and controlling the photoelectric sensor to detect the quantity and speed of the conveyed grains to generate grain conveying data;

[0079] Specifically, the control system first controls the conveyor belt device so that the grains to be threshed can be evenly conveyed to the entrance of the threshing device. A series of guide devices, such as guide rollers and diverter devices, are pre-installed on the conveyor belt to ensure that the grains are not piled up or excessively dispersed and are conveyed to the threshing area. In addition, a photoelectric sensor is installed on the conveyor belt, which can detect the amount and speed of the conveyed grains. The sensor detects the number and density of grain particles by emitting a light beam and receiving the reflected light signal, and judges the flow rate and speed of the grain by the duration of the signal and the transmission speed. The sensor then transmits this data to the control system to form grain transportation data. For example, the photoelectric sensor detects that 500 grams of grain pass through the grain conveyor belt every minute, and the conveying speed is 0.5 m / s.

[0080] S2. Generate threshing force and speed parameters according to the grain transportation data, and obtain threshing force parameter data and threshing speed parameter data respectively;

[0081] Specifically, the system will use internal control logic to generate initial parameters for threshing force and speed. Specifically, the control system will analyze data such as the amount of grains and flow rate to determine whether the current threshing device needs to increase or decrease force and speed. The system sets preset force and speed levels. For example, according to the number density of grains, the threshing force is divided into different levels such as low, medium and high. At the same time, the control system will adjust the speed of the thresher according to the speed of the grains on the conveyor belt to ensure the consistency of the threshing effect. The generated threshing force and speed parameters are input into the execution module of the threshing device in the form of data to provide basic parameters for the threshing operation. For example, the control system determines the required threshing force and speed based on the weight and speed of the grains. Generally speaking, the more grains there are, the more threshing force should be appropriately increased to ensure effective threshing. The system is designed with three force levels (low, medium and high) and three speed levels (low, medium and high). The system determines that 500 grams / minute and a conveying speed of 0.5 meters / second are suitable for the "medium" force and "medium" speed levels.

[0082] S3, performing threshing operation of the thresher according to the threshing force parameter data and the threshing speed parameter data, and monitoring the cavity pressure of the thresher to obtain threshing pressure data;

[0083] Specifically, the thresher performs threshing operations according to the generated force and speed parameters. During the threshing process, in order to monitor the pressure in the threshing chamber in real time, a pressure sensor is installed in the chamber wall of the thresher. The sensor can sense slight changes in the pressure in the chamber to ensure that the threshing operation is carried out within a safe and efficient range. The sensor transmits the pressure data to the control system and generates threshing pressure data in real time. When the control system detects abnormal pressure (such as too large or too small), it automatically adjusts the threshing force or reminds the operator. In addition, the system will determine whether the threshing operation is going smoothly by monitoring the feedback signal in the threshing chamber to optimize the efficiency of the threshing process. For example, the thresher starts threshing according to the input 50 units of force and 40 rpm speed. The pressure sensor monitors the pressure in the chamber in real time. For example, if the pressure is maintained below 200 kPa, it indicates that the threshing is smooth. If it exceeds 200 kPa, it may indicate blockage or other problems, and the force needs to be reduced or the delivery rate needs to be adjusted.

[0084] S4. Evaluate the threshing effect according to the threshing pressure data to obtain threshing effect evaluation data, and optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain real-time threshing optimization parameter data to perform auxiliary operations for adjusting grain threshing parameters.

[0085] Specifically, the control system will conduct a real-time evaluation of the threshing effect based on the threshing pressure data, which is achieved by analyzing the relationship between the threshing pressure and the grain breakage rate, that is, the system compares the pressure data with the preset effect evaluation standard to judge the quality of the current threshing effect. The system will compare the pressure data with the evaluation model of the threshing effect to obtain the threshing effect evaluation data. If the current effect is lower than expected, the system will automatically adjust the parameters of the threshing force and speed, and generate real-time optimized threshing parameter data, which will be transmitted to the execution module for adjustment. The adjustment mechanism can continuously optimize the operating state of the thresher through the feedback control model, thereby improving the efficiency and quality of grain threshing and avoiding damage or threshing leakage. For example, the system compares the threshing pressure data of 180 kPa with the preset target threshing pressure (such as 160-200 kPa) to judge the current state. If the pressure is low or high, the system will adjust the threshing force and speed parameters according to the threshing effect. For example, if the pressure is high, the threshing force is reduced by 5 units and the speed is reduced by 5 rpm; if it is low, the force and speed are increased on the contrary.

[0086] Optionally, S1 includes:

[0087] S11. Remotely initialize and configure the conveyor belt device through the grain threshing Internet of Things platform to obtain initial parameter data of the conveyor belt;

[0088] Specifically, the system remotely initializes and configures the conveyor belt device through the grain threshing IoT platform to obtain the initial parameter data of the conveyor belt. The initial parameter data includes the length, width, material properties (such as friction coefficient) and power configuration of the motor of the conveyor belt. The system first sends an initialization command through the platform, receives basic information data feedback from the conveyor belt, such as the physical properties of the conveyor belt, and confirms on the platform interface whether each parameter meets the preset standards. If a parameter is abnormal or exceeds the allowable range, the IoT platform will issue a warning to prompt you to check the status of the conveyor belt.

[0089] S12, performing conveyor belt transportation operation according to the initial parameter data of the conveyor belt, and collecting grain images through a visual device installed on the conveyor belt device to obtain grain image data;

[0090] Specifically, based on the data of the initial configuration, the system starts the conveyor belt transportation operation and starts to transport grains. In order to monitor the grains in real time, a visual device (such as a high-resolution camera) is installed on the conveyor belt device, which collects image data of the grains in real time. When the camera shoots the grains, a specific sampling frequency is set (for example, 5 frames of images are collected per second) to ensure that the collected images can accurately reflect the flow of the grains. The image data is transmitted to the data processing unit through the interface and saved in the system database. The visual device can capture the distribution, density and particle size of the grains to extract and provide raw image data.

[0091] S13, extracting grain distribution according to the grain image data to obtain grain distribution data;

[0092] Specifically, after receiving the grain image data, the system starts to extract the grain distribution. By analyzing the grain distribution in the image, the density and uniformity of the grain are obtained. Specifically, the system first grayscales the image to reduce data complexity. Then, the edge detection method is used to separate the grain area from the background to form a clear grain outline. By calculating the proportion of grain pixels in the entire image, the distribution density of the grain on the conveyor belt can be obtained. In addition, the system will also detect the shape and size of the grain to determine whether there is accumulation or uneven distribution. The generated grain distribution data will be used to adjust the vibration frequency and transmission rate of the conveyor belt.

[0093] S14, generating conveyor belt vibration frequency parameters and conveyor belt transmission rate data according to the grain distribution data, and obtaining conveyor belt vibration frequency parameter data and conveyor belt transmission rate data respectively;

[0094] Specifically, based on the obtained grain distribution data, the system analyzes whether the grain is evenly distributed on the conveyor belt. If uneven distribution is detected (for example, more accumulation at one end), the vibration frequency of the conveyor belt will be increased to help disperse the grains on the entire conveyor belt. The system first inputs the grain distribution data into the control module (through a preset parameter matching table or calculation engine) to calculate a suitable vibration frequency to ensure the uniform distribution of grains on the conveyor belt. For the generation of the transmission rate, the system sets different rates according to the density of the grain (through a preset parameter matching table or calculation engine) to ensure that the grain is not transported too fast or too slow. The vibration frequency parameters and transmission rate data are transmitted to the control module of the conveyor belt for real-time control of the operation of the conveyor belt. If the image data shows that the grain distribution is uneven, mainly concentrated on the left side of the conveyor belt, the system sets the vibration frequency to 10 Hz and the transmission rate to 0.6 m / s to optimize the grain distribution.

[0095] S15, performing conveyor belt transportation optimization operation according to the conveyor belt vibration frequency parameter data and the conveyor belt transmission rate data;

[0096] Specifically, according to the generated vibration frequency parameters and transmission rate, the conveyor belt enters the optimized operation state, adjusts the vibration and speed of the conveyor belt, and evenly distributes the grain on the entire belt surface. The system will make real-time feedback adjustments during this process. If the distribution after adjustment is still not ideal, the system will further optimize the vibration frequency and rate until the target distribution state is reached. Through such adaptive adjustments, the system ensures the uniformity of grain flow and provides a stable prerequisite for the threshing process.

[0097] S16, controlling the photoelectric sensor to detect the quantity and speed of conveyed grains, and generating grain conveying data.

[0098] Specifically, after the conveyor belt is running stably, the photoelectric sensor installed at the end of the conveyor belt begins to detect the amount and speed of grain passing through. The photoelectric sensor calculates the number of grain particles passing through by emitting light and detecting the reflected signal. The system transmits the detected grain data to the control center, generates grain transportation data, and provides data support for threshing parameters. The system also stores this data in the database for future analysis and tuning.

[0099] Optionally, wherein the grain distribution extraction comprises:

[0100] Extracting grain image features according to the grain image data to obtain grain image feature data;

[0101] Specifically, the system extracts image features from grain image data to identify and locate the basic features of grains (such as shape, texture, color, etc.) and obtain grain image feature data. The system first preprocesses the image (including denoising, grayscale, and normalization) to extract more accurate feature data. Next, the edge features of the grains are identified through edge detection and morphological operations to obtain the outline of each grain particle. In addition, the system can also extract texture features in the image based on texture analysis methods to identify the size, density, and morphological distribution of the grains.

[0102] Perform grain region segmentation according to grain image feature data to obtain grain region segmentation data;

[0103] Specifically, based on the extracted image feature data, the system segments the grain area in the image. The goal of this step is to distinguish the grain area from the background area in order to better analyze the spatial distribution of the grain. The system uses a threshold segmentation method to first perform a preliminary segmentation of the grain area and the background area in the image based on image brightness and features. Then, for further optimization, the system applies morphological operations (such as dilation and erosion operations) to remove noise and ensure that the segmented grain area is coherent and complete. Through this processing, the system generates clear grain area segmentation data, which clearly separates the grain area from the background.

[0104] Optimize the segmented area according to the grain area segmentation data to obtain grain area optimization data;

[0105] Specifically, after completing the preliminary region segmentation, the system further optimizes the segmented regions to ensure that the boundaries of each grain region are more accurate and to reduce the number of erroneous segmentations. This process uses contour detection and shape analysis techniques to check the shape of each segmented region. If a region does not match the morphology of a typical grain grain (such as aspect ratio, area range), the system marks it as abnormal and corrects it. For example, for regions that are too small or too large, the system will automatically merge or segment them so that each segmented region is as close to the size of the actual grain grain as possible. The output is grain region optimization data that reflects the accurate boundaries and positions of each grain grain.

[0106] Generate a grain distribution map based on grain area optimization data to obtain grain spatial distribution map data;

[0107] Specifically, the system generates a grain distribution map based on the optimized grain area data to visualize the spatial distribution of grains on the conveyor belt. Specifically, the system maps the coordinates and size of each grain area to the spatial distribution map, so that the location, density and morphological characteristics of each grain are clearly visible in the map. The generated grain distribution map shows the overall layout of grains, including concentrated and dispersed areas of grains. The distribution map data structure contains the location information and spatial distribution attributes of each grain, providing data support for the next step of spatial analysis.

[0108] The spatial distribution data of the grains is analyzed spatially to obtain the grain distribution data.

[0109] Specifically, the system performs spatial analysis on the generated grain spatial distribution map data to extract the overall distribution pattern of grains on the conveyor belt. The system uses statistical methods to calculate the grain density area, uniformity and distribution trend. For example, the system calculates the density of grains in different areas, compares dense and sparse areas, and determines the fluidity and accumulation of grains. If the density in a certain area is too high, it means that the grains are piled up, and the vibration frequency of the conveyor belt needs to be adjusted to redistribute the grains. The generated grain distribution data contains information such as the density and distribution trend of the grains.

[0110] Optionally, the distribution data spatial analysis includes:

[0111] Extracting multidimensional spatial features from the grain spatial distribution map data to obtain multidimensional spatial feature data of grains;

[0112] Specifically, the system performs multidimensional spatial feature extraction on the grain spatial distribution map data to extract the characteristic data of grains in multiple spatial dimensions. Multidimensional spatial features include the position coordinates of each grain particle (such as x, y position), particle density, geometric characteristics of particles (such as area, shape factor) and distribution trend. First, the system extracts these attributes from the distribution map and generates a feature vector for each grain particle. These feature vectors represent the distribution characteristics of grains in different spatial dimensions.

[0113] According to the multi-dimensional spatial characteristic data of grains, global spatial autocorrelation analysis and local spatial autocorrelation analysis are performed to obtain the global spatial autocorrelation data of grains and the local spatial autocorrelation data of grains respectively;

[0114] Specifically, based on the extracted multidimensional spatial feature data, the system performs global and local spatial autocorrelation analysis to evaluate the aggregation and spatial relationship of grain distribution. Global spatial autocorrelation analysis is used to measure the grain distribution pattern in the entire space, such as whether there is obvious aggregation or discrete distribution. The system first calculates the spatial average density of all grain particles, and then calculates the density difference between each particle and its neighboring particles. By analyzing the distribution of these differences, it can be determined whether the grains are aggregated or dispersed as a whole. Local spatial autocorrelation analysis further focuses on the local aggregation of grains. The system selects a local window (such as a few adjacent centimeters), calculates the density distribution of each grain particle in the area, determines the distribution characteristics of the local area, and identifies dense or sparse areas.

[0115] According to the global spatial autocorrelation data of grains and the local spatial autocorrelation data of grains, the spatial relationship coupling processing of grains is carried out to obtain the full local relationship coupling data of grains;

[0116] Specifically, the system couples the global and local spatial autocorrelation data to analyze the distribution relationship of grains at different spatial scales. The coupling process is to integrate global and local characteristics to establish the spatial distribution relationship of grains. For example, if the global analysis shows that the distribution of grains is relatively clustered, but the local analysis shows that the density of some areas is low, the system will couple these inconsistent information to obtain a spatial distribution relationship with global and local corresponding spatial coupling relationships. Through matrix operations, the system integrates the global and local autocorrelation values ​​into a coupled data matrix to analyze the distribution correlation of each region.

[0117] Density estimation is performed based on the grain full-local relationship coupling data to obtain grain distribution density map data;

[0118] Specifically, using the coupled data, the system further estimates the distribution density of grains and generates a grain distribution density map. Density estimation is based on the spatial distribution of each particle and the number density of neighboring particles. The system uses a spatial density estimation method to calculate the density value based on the number of neighboring particles and the area of ​​each particle. The density map shows the density of grains in different areas and helps identify high-density and low-density areas. The density distribution of each area can be intuitively displayed through color coding or other visualization methods. In the density estimation, the system concluded that the density in the upper left corner area is 4 particles per square centimeter, while the density in the lower right corner area is 1 particle per square centimeter. The generated density map uses different shades of color to represent different densities.

[0119] Spatial cluster analysis was performed on the grain distribution density map data to obtain the grain distribution data.

[0120] Specifically, the system performs spatial cluster analysis on the generated grain distribution density map data to identify the grain clustering areas. The system identifies a series of cluster points on the density map and classifies the grain clustering areas into different clusters based on density, proximity, and spatial continuity. For example, the system will treat continuous high-density areas as the same cluster, and low-density areas as sparse clusters. The cluster analysis results provide an overall pattern of grain distribution, which is used to further optimize the conveyor belt or threshing parameters.

[0121] Optionally, the multidimensional space feature extraction includes:

[0122] The grain spatial distribution map data is converted into three dimensions to obtain grain spatial three-dimensional map data;

[0123] Specifically, the system performs a three-dimensional conversion on the spatial distribution map data of the grains in order to obtain the three-dimensional distribution of the grains in space. First, the grain image data collected by the camera or sensor is generally a two-dimensional plane distribution map. The system combines these two-dimensional image data with depth information (such as through a binocular camera or a depth sensor) to map the plane position of the grains into a three-dimensional coordinate system to form a three-dimensional distribution model. The three-dimensional coordinates (x, y, z) of each grain particle can describe its specific position in space.

[0124] Feature extraction is performed based on the grain spatial three-dimensional map data and the grain spatial distribution map data to obtain the grain spatial three-dimensional map feature data and the grain spatial distribution map feature data respectively;

[0125] Specifically, after completing the three-dimensional conversion, the system extracts the basic features of each grain particle based on the three-dimensional graph data and the spatial distribution graph data. For the three-dimensional graph data, the system can extract the three-dimensional shape, size (volume), spatial position and other information of the particles; for the spatial distribution graph data, the two-dimensional density, distribution position, geometric shape (area, boundary features) and so on of each particle are extracted. By extracting these features, the basic features used to describe each particle in three-dimensional space can be generated. For example, the system extracts that the three-dimensional volume of a grain particle is 0.5 cubic millimeters, the spatial position is (x=10, y=15, z=8), the corresponding plane area is 3 square millimeters, and the density is 5 particles per square centimeter.

[0126] Performing local feature extraction on the grain spatial three-dimensional map feature data and the grain spatial distribution map feature data to obtain grain three-dimensional local feature data and grain spatial local feature data respectively;

[0127] Specifically, the system further extracts local features from the three-dimensional map feature data and the spatial distribution map feature data, focusing on the detailed features of the grain particles in the local area. Local feature extraction includes identifying the relative position relationship between particles, local density, and details such as the surface roughness and boundary curvature of the particles. Local features can reveal the spatial relationship of grains in a specific area and provide a basis for the extraction of high-order features. The system analyzed a local area and found that three grain particles formed a local dense area with a density of 10 particles per cubic centimeter. At the same time, it was detected that the surface roughness of these particles was similar and the boundary curvature was high, indicating that they came from the same source or were affected by the same external force.

[0128] Extracting high-order features from the three-dimensional local feature data of the grain and the spatial local feature data of the grain, and obtaining the three-dimensional high-order feature data of the grain and the spatial high-order feature data of the grain respectively;

[0129] Specifically, after completing the local feature extraction, the system further extracts high-order features from the local feature data. High-order features contain more complex spatial relationship features, such as the spatial arrangement pattern of particles, the structural continuity of local areas, the symmetry of overall geometric shapes, etc. These features can reflect the complex spatial relationship between grain particles and reveal certain specific patterns or trends. For example, the system can analyze whether the arrangement direction of the particles is consistent and whether there is an obvious spatial hierarchy or hierarchical structure. The system detected a group of grain particles in a local area that are arranged linearly with consistent arrangement directions and high spatial structural continuity. These high-order features indicate that these particles may have been affected by external forces in a consistent direction, forming a specific distribution pattern.

[0130] The three-dimensional high-order feature data of grains and the spatial high-order feature data of grains are fused to obtain the multi-dimensional spatial feature data of grains.

[0131] Specifically, after extracting the high-order feature data, the system fuses the three-dimensional and spatial high-order feature data to form comprehensive multi-dimensional spatial feature data. The feature fusion process integrates the three-dimensional and two-dimensional spatial features, and combines important features (such as high-density areas, specific arrangement patterns, etc.) through feature weight analysis to generate a unified feature description. The fused feature data can express the spatial distribution pattern of grain particles at a high level and provide multi-dimensional feature support for spatial analysis and autocorrelation processing. During the fusion process, the system combines the features of high density and linear arrangement, marks these areas as high-importance areas, and generates multi-dimensional spatial feature data containing information such as the volume, density, arrangement direction, and position of each particle, comprehensively displaying the overall spatial distribution characteristics of the grain.

[0132] Optionally, S2 includes:

[0133] S21, extracting grain features according to the grain transportation data to obtain grain feature data;

[0134] Specifically, the system extracts key characteristic data related to threshing from the grain conveying data. The conveying data includes information such as the weight, flow rate, particle density, shape and size of the grain. The system first processes these raw data and removes abnormal data points through data screening and preprocessing to ensure data accuracy. Then, the system calculates characteristics such as the average particle size, distribution density, and weight of the grain. For example, the particle density is inferred using the weight and flow rate data of the grain, and then the characteristics such as the average particle volume and number are calculated.

[0135] Using the grain velocity and the conveyor belt geometry, calculate the volume flow rate of the grain, which is the volume of grain that passes through per unit time. This is calculated as follows:

[0136] V(Q)=V×W b ×H;

[0137] V(Q) is the volume flow rate of grain on the conveyor belt per unit time, in cubic meters per second, V is the flow velocity of grain (meters per second), W b is the conveyor belt width (m), and H is the thickness of the grain layer on the conveyor belt (m).

[0138] The average density of the grain particles is estimated using the measured total grain weight W and volume flow rate V(Q) and the conveying time T, as follows:

[0139]

[0140] ρ ais the average density of grain particles, in kilograms per cubic meter (note the consistency of units, if W is grams, it needs to be converted to kilograms), W is the total weight of grains passing through in a period of time, V(Q) is the volume flow rate of grains on the conveyor belt per unit time, and T is the conveying time.

[0141] To calculate the average volume of grains, obtain the typical density of grains or infer the average volume of a single grain through the formula. a , the average volume of a single particle can be calculated by the following formula:

[0142]

[0143] V 粒 is the average volume of each particle, m 粒 is the average mass of a single grain (which can be obtained by weighing multiple grains and taking the average value), ρ a is the average density of grain particles.

[0144] If the average grain volume V of the grain is known 粒 , the total number of particles N passing through the conveyor belt can be calculated: The number of grains is calculated using the following formula:

[0145]

[0146] N is the total number of particles passing through the conveyor belt, V(Q) is the volume flow rate of grains on the conveyor belt per unit time, T is the conveying time, V 粒 is the average volume of each particle.

[0147] S22, generating threshing force according to the grain characteristic data to obtain threshing force parameter data;

[0148] Specifically, based on the extracted grain characteristic data, the system generates threshing force parameters through a preset parameter rule engine. The magnitude of the threshing force is closely related to the hardness, grain density and size of the grain. Grains with larger grains and higher density require higher threshing forces to effectively separate the grain husks. The system estimates the required threshing force based on the density and grain size data of the grains, combined with the existing standard force parameter range. By comparing with the standard threshing force values ​​in the database, the system generates appropriate threshing force parameters to achieve efficient and safe threshing effects. Based on the previously extracted characteristic data (grain density 700 grains / cubic centimeter, average size 5 mm), the force parameter generated by the system is 75 units, ensuring that it is suitable for threshing the husks of this type of grain.

[0149] S23. Generate threshing speed parameters according to the grain characteristic data to obtain threshing speed parameter data.

[0150] Specifically, the system generates threshing speed parameters based on the grain characteristic data through a preset parameter rule engine to ensure threshing efficiency and effect. The choice of threshing speed depends on the density, hardness, shape and flow rate of the grain particles. Grains with smaller particles and lower density can be set at a higher threshing speed to increase the processing speed; while harder and larger particles need to reduce the speed to reduce damage. Based on these characteristic data, the system generates parameters in combination with the safe speed range of the equipment to ensure that the threshing speed is moderate and the shelling effect is good. If the system recognizes that the current grain density is 700 grains per cubic centimeter and the grain size is 5 mm, in order to ensure the threshing quality, the system sets the threshing speed parameter to 35 rpm.

[0151] Optionally, the grain feature extraction comprises:

[0152] Extract dynamic features based on grain transportation data to obtain dynamic feature data of grain transportation;

[0153] Specifically, the system uses grain conveying data to extract dynamic features, including real-time changes in the weight, flow rate, and density of grains on the conveyor belt. The goal of dynamic feature extraction is to determine whether a stable flow state is maintained during grain conveying, and to identify whether there are abnormal fluctuations in flow rate or density. The system performs a time series analysis of the flow rate and density, calculates the average, maximum, and minimum values, and identifies the range and frequency of fluctuations. If large fluctuations are detected in a short period of time (such as high and low flow rates), the system records these changing characteristics to analyze the stability of transportation. For example, the average flow rate recorded by the system over a period of time is 0.6 m / s, the average density is 300 particles per cubic centimeter, the flow rate fluctuation amplitude is 10%, and the fluctuation frequency is 0.5 Hz.

[0154] Conducting velocity and density analysis on the dynamic characteristic data of grain transportation, and obtaining the velocity characteristic data of grain transportation and the density characteristic data of grain transportation respectively;

[0155] Specifically, after obtaining the dynamic characteristic data, the system will further analyze the detailed characteristics of the flow rate and density. The purpose of the flow rate characteristic analysis is to understand whether the flow rate of grains on the conveyor belt is stable; the density characteristic analysis evaluates the distribution density of grains during transportation. The system performs variance analysis on the flow rate, calculates the amplitude of the flow rate change, and determines whether there are abnormal fluctuations. For the density data, the system will count the number of particles per unit conveyor belt area to ensure the consistency of density. If the density fluctuates greatly, the system will record the abnormal changes. In the analysis, the system obtained an average flow rate of 0.6 m / s and a flow rate variance of 0.03; the density per unit area is 300 particles / cubic centimeter, and the density fluctuation amplitude is 8%.

[0156] Perform morphological feature extraction and reflection feature extraction according to the grain transportation data to obtain grain transportation morphological feature data and grain transportation reflection feature data respectively;

[0157] Specifically, the system further extracts the morphological characteristics and reflection characteristics of the grains from the conveying data. The morphological feature extraction includes the geometric shape, size and surface roughness of the particles. The grain image is processed by a camera, and edge detection is used to identify the shape (such as round, oval) and size (such as diameter, area) of each particle. Reflection feature extraction is based on the reflection data of infrared or laser sensors (based on infrared or laser sensors preset on the conveyor belt), analyzing the light reflectivity of the grain surface, reflecting the roughness and humidity of the particles. Grains with higher humidity will show lower reflectivity, so the system will record this characteristic data. The system detects that the shape of the grain particles is oval, the average size is 5 mm, and the reflectivity is 70%.

[0158] The grain conveying velocity characteristic data, the grain conveying density characteristic data, the grain conveying morphology characteristic data and the grain conveying reflection characteristic data are subjected to feature generation to obtain the grain characteristic data.

[0159] Specifically, after completing the extraction of various features, the system integrates the velocity feature, density feature, morphology feature and reflection feature data to generate comprehensive grain feature data. The system standardizes these data to ensure the dimensional consistency between different features. Then, the feature data are combined into a feature vector to form a specific description of the grain during the transportation process, including its flow state, density, morphology and reflection characteristics.

[0160] Optionally, S3 includes:

[0161] S31, loading the threshing force parameter data and the detachment speed parameter data into the thresher control system through the industrial Internet interface to obtain the thresher parameter loading data;

[0162] Specifically, the system needs to transmit the previously generated threshing force and speed parameter data to the control system of the thresher through the industrial Internet interface. The industrial Internet interface usually uses standard industrial communication protocols (such as Modbus, OPC UA, etc.) to ensure stable data transmission and real-time performance. The system will first format the parameter data to make it conform to the acceptance format of the thresher control system. Then, the formatted data packet is sent to the controller of the thresher through the interface. The controller will parse the data packet and load the threshing force and speed parameters into the specified control variables for threshing operations. The transmission process involves verification steps to ensure the security and accuracy of the data. After receiving the data, the thresher controller parses it, assigns the force and speed parameters to the relevant variables of the control system, generates thresher parameter loading data, and ensures that the parameters are successfully loaded into the control system.

[0163] Specifically, the system transmits the threshing force and speed parameter data to the control system of the thresher through the industrial Internet interface. This process uses industrial communication protocols (such as Modbus and OPC UA) to ensure data stability and real-time performance. First, the system formats the force and speed parameter data to meet the input format required by the control system (such as JSON or XML format), and adds a checksum to ensure that no errors occur during data transmission. The formatted data packet is sent to the controller of the thresher control system through the industrial interface. The controller parses the data and loads the parsed data into the operating parameters of the thresher. For example, the threshing force parameter is 70 units and the threshing speed parameter is 40 rpm. The system packages the data into the format of {"force":70,"speed":40,"checksum":"abc123"}, transmits it to the control system, and successfully parses and loads it.

[0164] S32, starting the threshing operation according to the thresher parameter loading data, so as to perform the threshing operation of the thresher;

[0165] Specifically, after the thresher parameter loading data is confirmed to be correct, the system issues a start command to start the threshing operation. The thresher control system will first verify whether the currently loaded parameters (such as force and speed) are within the safe operating range of the equipment. If the parameters are out of range, the system will trigger an alarm and refuse to start. After confirmation, the system starts the motor, starts the working operation of the thresher, and sets the threshing force and speed. The thresher controller adjusts the operating parameters in real time to ensure that the actual force and speed match the set values. At the same time, it will start the monitoring module to record key status information, such as motor power, temperature, etc., to ensure the stability of the threshing process. If the thresher parameters are set to 70 units of force and 40 rpm of speed, the system will check and confirm that the parameters are within the safe range (such as the upper limit of force is 80 units and the upper limit of speed is 50 rpm), and start smoothly.

[0166] S33, collecting the pressure of the thresher cavity through a pressure sensor installed in the thresher to obtain threshing pressure data.

[0167] Specifically, during the threshing operation, the system collects the pressure data in the cavity in real time through the pressure sensor installed in the thresher cavity. The pressure sensor is usually installed in the key part of the threshing cavity, which can detect the pressure fluctuations generated during the threshing process in real time. The system sets the acquisition frequency, such as 5 times per second, to ensure that all key pressure changes are captured. The pressure sensor transmits the collected data to the thresher control system through the signal conversion module (such as analog signal to digital signal). The system analyzes the data in real time to determine whether the threshing force is stable at the target value to avoid grain damage or incomplete threshing due to excessive or insufficient pressure. In addition, the system sets a pressure threshold. Once the pressure exceeds the safe range, an alarm will be triggered to remind the operator to make adjustments. If the system analyzes the pressure data in real time and checks whether the pressure is within the preset safety range (for example, 100-200 kPa), once the pressure exceeds the set threshold, the system will immediately issue an alarm and record abnormal data. If the normal threshing pressure is 150 kPa, the system records the average pressure fluctuation between 145-155 kPa. At a certain moment, the pressure rose to 210 kPa, exceeding the set upper limit of 200 kPa. The system immediately triggered an alarm and stored the abnormal data point.

[0168] Optionally, S4 includes:

[0169] S41, collecting threshing images by an image sensor installed in the thresher to obtain threshing image data;

[0170] Specifically, the system collects image data of the threshing process in real time through a high-resolution image sensor installed in the thresher. The image sensor is usually installed in a key position in the threshing chamber and can capture the state of the grain during the threshing process. The system sets the frequency of image acquisition (such as 5 images per second) to ensure that the detailed changes in the threshing process can be monitored. The collected image data is transmitted to the control system through the data interface for subsequent analysis. The system formats and compresses the image data so that it can be stored in the database in real time. If the image sensor collects 5 images per second, and the resolution of each image is 1920x1080, the system compresses and stores the image data to save space and improve transmission efficiency.

[0171] S42, extracting threshing efficiency and grain damage rate according to the threshing image data to obtain threshing efficiency data and grain damage rate data;

[0172] Specifically, the system uses the collected image data to calculate the threshing efficiency and grain damage rate. The threshing efficiency reflects the degree of separation between the grain husk and the grain during the threshing process, while the grain damage rate indicates whether the grain is damaged during the threshing process. The calculation of the threshing efficiency uses image processing methods (such as deep neural network algorithms) to identify the proportion of hulled grain grains and unhulled grain grains. The system segments the image, distinguishes the area ratio of hulled and unhulled grains, and calculates the threshing efficiency. For the grain damage rate, the system detects the integrity of the grains through morphological analysis, identifies damaged or deformed grain grains, and calculates the damage ratio. Finally, the threshing efficiency data and grain damage rate data are generated. If the image analysis shows that 80% of the grains are hulled and 20% of the grains are unhulled, the threshing efficiency is 80%; at the same time, the system identifies that 5% of the grain grains are damaged, then the grain damage rate is 5%.

[0173] S43, performing threshing effect evaluation according to the threshing pressure data, the threshing efficiency data and the grain damage rate data to obtain threshing effect evaluation data;

[0174] Specifically, the system analyzes the real-time monitored threshing pressure data, threshing efficiency data, and grain damage rate data to evaluate the threshing effect. The threshing effect evaluation includes analyzing whether the threshing efficiency meets the standard, whether the damage rate is within the allowable range, and whether the pressure data remains within the ideal range. The system first compares these data with the preset standard values: for example, whether the threshing efficiency is greater than 75%, whether the damage rate is less than 10%, and whether the pressure is stable within the set range (such as 150-200 kPa). If the data exceeds the set threshold, the system will judge that the threshing effect is not ideal, record the abnormality and enter the parameter optimization stage. If the threshing efficiency is 80% (greater than the 75% standard), the damage rate is 5% (less than the 10% standard), and the pressure is within the range of 150-200 kPa, the system evaluates that the threshing effect is good.

[0175] S44. Optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain real-time threshing optimization parameter data to perform auxiliary operations for adjusting grain threshing parameters.

[0176] Specifically, according to the threshing effect evaluation data, the system optimizes and adjusts the threshing force and speed parameters. If the evaluation shows that the threshing efficiency is low or the damage rate is high, the system will increase the threshing force or reduce the speed accordingly; if the pressure is too high or the damage rate exceeds the standard, the system will reduce the force or increase the speed appropriately. The optimization process calculates the adjusted parameters to ensure that the new parameters are within the safety range of the equipment. The system loads the optimized parameter data into the control system, adjusts the threshing force and speed in real time, and realizes adaptive control. If the evaluation shows that the threshing efficiency is 70% (lower than the standard), the system increases the threshing force to 75 units and reduces the speed to 35 rpm to improve efficiency.

[0177] Optionally, the present application further provides an intelligent multifunctional grain threshing system for executing the intelligent multifunctional grain threshing method as described above, wherein the intelligent multifunctional grain threshing system comprises:

[0178] A grain conveying module is used to control the conveyor belt device to evenly convey the grains to be threshed to the entrance of the threshing device, and to control the photoelectric sensor to detect the quantity and speed of the conveyed grains to generate grain conveying data;

[0179] A grain threshing parameter generation module is used to generate threshing force and speed parameters according to grain conveying data, and obtain threshing force parameter data and threshing speed parameter data respectively;

[0180] The threshing operation module of the thresher is used to perform the threshing operation of the thresher according to the threshing force parameter data and the threshing speed parameter data, and to monitor the pressure of the thresher cavity to obtain the threshing pressure data;

[0181] The real-time threshing optimization module is used to evaluate the threshing effect according to the threshing pressure data, obtain the threshing effect evaluation data, and optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain the real-time threshing optimization parameter data for auxiliary operations of grain threshing parameter adjustment.

[0182] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0183] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent multifunctional grain threshing method, characterized in that: The method comprises: S1, controlling the conveyor belt device to evenly convey the grains to be threshed to the entrance of the threshing device, and controlling the photoelectric sensor to detect the quantity and speed of the conveyed grains to generate grain conveying data; S2. Generate threshing force and speed parameters according to the grain transportation data, and obtain threshing force parameter data and threshing speed parameter data respectively; S3, performing threshing operation of the thresher according to the threshing force parameter data and the threshing speed parameter data, and monitoring the pressure of the thresher cavity to obtain threshing pressure data; S4. Evaluate the threshing effect according to the threshing pressure data to obtain threshing effect evaluation data, and optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain real-time threshing optimization parameter data to perform auxiliary operations for adjusting grain threshing parameters.

2. The method according to claim 1, characterized in that S1 includes: Remotely initialize and configure the conveyor belt device through the grain threshing IoT platform to obtain the initial parameter data of the conveyor belt; The conveyor belt is transported according to the initial parameter data of the conveyor belt, and the grain image is collected by a visual device installed on the conveyor belt device to obtain the grain image data; Extract grain distribution according to grain image data to obtain grain distribution data; Generate conveyor belt vibration frequency parameters and conveyor belt transmission rate data according to grain distribution data, and obtain conveyor belt vibration frequency parameter data and conveyor belt transmission rate data respectively; Optimize conveyor belt transportation according to conveyor belt vibration frequency parameter data and conveyor belt transmission rate data; The photoelectric sensor is controlled to detect the quantity and speed of the conveyed grains and generate grain conveying data.

3. The method according to claim 2, characterized in that The grain distribution extraction includes: Extracting grain image features according to the grain image data to obtain grain image feature data; Perform grain region segmentation according to grain image feature data to obtain grain region segmentation data; Optimize the segmented area according to the grain area segmentation data to obtain grain area optimization data; Generate a grain distribution map based on grain area optimization data to obtain grain spatial distribution map data; The spatial distribution data of the grains is analyzed spatially to obtain the grain distribution data.

4. The method according to claim 3, characterized in that The spatial analysis of distribution data includes: Extracting multidimensional spatial features from the grain spatial distribution map data to obtain multidimensional spatial feature data of grains; According to the multi-dimensional spatial characteristic data of grains, global spatial autocorrelation analysis and local spatial autocorrelation analysis are performed to obtain the global spatial autocorrelation data of grains and the local spatial autocorrelation data of grains respectively; According to the global spatial autocorrelation data of grains and the local spatial autocorrelation data of grains, the spatial relationship coupling processing of grains is carried out to obtain the full local relationship coupling data of grains; Density estimation is performed based on the grain full-local relationship coupling data to obtain grain distribution density map data; Spatial cluster analysis was performed on the grain distribution density map data to obtain the grain distribution data.

5. The method according to claim 4, characterized in that The multidimensional space feature extraction includes: The grain spatial distribution map data is converted into three dimensions to obtain grain spatial three-dimensional map data; Feature extraction is performed based on the grain spatial three-dimensional map data and the grain spatial distribution map data to obtain the grain spatial three-dimensional map feature data and the grain spatial distribution map feature data respectively; Performing local feature extraction on the grain spatial three-dimensional map feature data and the grain spatial distribution map feature data to obtain grain three-dimensional local feature data and grain spatial local feature data respectively; Extracting high-order features from the three-dimensional local feature data of the grain and the spatial local feature data of the grain, and obtaining the three-dimensional high-order feature data of the grain and the spatial high-order feature data of the grain respectively; The three-dimensional high-order feature data of grains and the spatial high-order feature data of grains are fused to obtain the multi-dimensional spatial feature data of grains.

6. The method according to claim 1, characterized in that S2 include: Extract grain features according to grain transportation data to obtain grain feature data; The threshing force is generated according to the grain characteristic data to obtain the threshing force parameter data; The threshing speed parameters are generated according to the grain characteristic data to obtain the threshing speed parameter data.

7. The method according to claim 6, characterized in that The grain feature extraction includes: Extract dynamic features based on grain transportation data to obtain dynamic feature data of grain transportation; Conducting velocity and density analysis on the dynamic characteristic data of grain transportation, and obtaining the velocity characteristic data of grain transportation and the density characteristic data of grain transportation respectively; Perform morphological feature extraction and reflection feature extraction according to the grain transportation data to obtain grain transportation morphological feature data and grain transportation reflection feature data respectively; The grain conveying velocity characteristic data, the grain conveying density characteristic data, the grain conveying morphology characteristic data and the grain conveying reflection characteristic data are subjected to feature generation to obtain the grain characteristic data.

8. The method according to claim 1, characterized in that S3 includes: The threshing force parameter data and the detachment speed parameter data are loaded into the thresher control system through the industrial Internet interface to obtain the thresher parameter loading data; The threshing operation is started according to the thresher parameter loading data to perform the threshing operation of the thresher; The pressure sensor installed in the thresher is used to collect the pressure in the thresher cavity to obtain the threshing pressure data.

9. The method according to claim 1, characterized in that: S4 includes: The threshing image data is obtained by collecting threshing images through an image sensor arranged on the threshing machine; According to the threshing image data, threshing efficiency and grain damage rate are extracted to obtain threshing efficiency data and grain damage rate data; The threshing effect is evaluated according to the threshing pressure data, the threshing efficiency data and the grain damage rate data to obtain the threshing effect evaluation data; According to the threshing effect evaluation data, the threshing force parameter data and the threshing speed parameter data are optimized and adjusted to obtain real-time threshing optimization parameter data for auxiliary operations of grain threshing parameter adjustment.

10. An intelligent multifunctional grain threshing system, characterized in that: Used to perform the intelligent multifunctional grain threshing method according to claim 1, the intelligent multifunctional grain threshing system comprises: A grain conveying module is used to control the conveyor belt device to evenly convey the grains to be threshed to the entrance of the threshing device, and to control the photoelectric sensor to detect the quantity and speed of the conveyed grains to generate grain conveying data; A grain threshing parameter generation module is used to generate threshing force and speed parameters according to grain conveying data, and obtain threshing force parameter data and threshing speed parameter data respectively; The threshing operation module of the thresher is used to perform the threshing operation of the thresher according to the threshing force parameter data and the threshing speed parameter data, and to monitor the pressure of the thresher cavity to obtain the threshing pressure data; The real-time threshing optimization module is used to evaluate the threshing effect according to the threshing pressure data, obtain the threshing effect evaluation data, and optimize and adjust the threshing force parameter data and the threshing speed parameter data according to the threshing effect evaluation data to obtain the real-time threshing optimization parameter data for auxiliary operations of grain threshing parameter adjustment.

Images