A statistical model and parameter identification method and system for seed flow detection and planting machinery performance testing

Abstract

This invention discloses a statistical model and parameter identification method and system for seed flow detection in agricultural machinery performance testing, belonging to the field of agricultural machinery testing. The method first measures the mechanical and morphological parameters of crop materials to construct a digital model of the crop; then, it collects material flow data using seed flow detection, derives the probability distribution, and builds an M / D / I / K queuing statistical model to analyze quantitative characteristics and preliminarily identify performance parameters; it analyzes the material motion law through discrete element simulation to assist in identifying motion-related parameters; it builds a multi-channel synchronous camera test platform to conduct actual measurements and calculate operational indicators; finally, it verifies the model accuracy, comprehensively identifies core mechanical parameters, and completes structural and parameter optimization. This invention can accurately complete statistical modeling and full-dimensional parameter identification of planting machinery, effectively solving problems such as missed sowing, seed jamming, and uneven seed distribution, and is applicable to the performance testing and optimization of various planting machinery, especially seed distribution devices.

Description

Technical Field

[0001] This invention relates to the field of agricultural machinery testing technology, and in particular to a statistical model and parameter identification method and system for seed flow detection and planting machinery performance testing. Background Technology

[0002] Planting machinery is the core equipment for large-scale modern agricultural production, and the seed metering device is a key component of planting machinery. Currently, various types of planting machinery generally suffer from problems such as uneven seeding, blockages, missed seeding, and poor consistency in row operation. They also have low single-seeding rates and high rates of double seeding and missed seeding, which seriously affect the efficiency and quality of planting operations.

[0003] Currently, there are many shortcomings in the performance testing and analysis methods for planting machinery: First, the seeding, queuing, and sowing processes of crop materials are stochastic processes, and traditional deterministic analysis models cannot accurately characterize the random distribution characteristics of material flow, making it difficult to establish effective statistical models; Second, traditional manual testing methods are inefficient and prone to errors, and cannot continuously collect dynamic material flow data, nor can they complete multi-dimensional statistical analysis and probability distribution derivation; Third, existing technologies cannot systematically identify multiple core performance parameters such as single-sowing rate, reseeding rate, uniformity index, and transmission slip coefficient; Fourth, simulation analysis and bench testing are disconnected, failing to form a complete technical system of "modeling-statistical analysis-simulation-experimentation-parameter identification-optimization," resulting in a lack of sufficient theoretical and data support for machinery improvement.

[0004] In summary, existing technologies cannot accurately complete the statistical modeling, performance parameter identification, and fault tracing of planting machinery. There is an urgent need to combine seed flow detection, stochastic statistical models, and discrete element simulation technology to build a complete performance testing and parameter identification scheme for planting machinery. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, the purpose of this invention is to provide a statistical model and parameter identification method and system for seed flow detection and planting machinery performance testing.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: This invention provides a statistical model and parameter identification method for seed flow detection and planting machinery performance testing, comprising the following steps: S1. Material Parameter Acquisition and Digital Model Construction: Select crop samples corresponding to planting machinery operations, measure the physical and mechanical parameters of the crop body and crop population, as well as friction and collision mechanical parameters, statistically analyze the parameter distribution patterns, and construct a crop digital model that integrates mechanical parameters and distribution characteristics by combining discrete element modeling. S2. Construct a statistical model based on seed flow detection and analyze quantity characteristics: Use seed flow detection to collect video data of crop material flow during the operation of planting machinery, statistically analyze the material quantity sequence within a unit interval and derive the corresponding probability distribution, screen the optimal random model that is suitable for the material conveying process, build an M / D / 1 / K queuing statistical model based on the optimal random model, simulate and generate multiple material quantity sequences based on the queuing statistical model, analyze the material flow pattern and preliminarily identify the basic performance parameters of the machinery, and analyze the causes of operation failures. S3. Discrete Element Simulation Analysis of Material Motion Characteristics: A three-dimensional structural model of planting machinery is built. The three-dimensional structural model of planting machinery and the digital model of crops are imported into the discrete element simulation system to simulate the motion state of crop materials throughout the entire process. Multi-dimensional field feature quantities are extracted and their distribution patterns are statistically analyzed. Material motion characteristics, equipment blockage and jamming and material orientation and arrangement mechanisms are analyzed to help identify mechanical motion performance parameters. S4. Build an experimental platform to conduct actual tests and data collection: Build an experimental testing platform for planting machinery with adjustable structure and operating parameters and integrated multi-channel synchronous camera function. Combine simulation and statistical model analysis conclusions to design multi-factor experimental schemes. Collect measured material flow characteristic data through seed flow detection, statistically analyze the distribution pattern of data and calculate various operating performance indicators of the machinery. S5. Model Validation, Precise Parameter Identification and Mechanical Optimization: Compare measured data with simulation and statistical model output data to verify the accuracy of statistical and simulation models. Combine multi-dimensional analysis results to comprehensively identify various performance parameters of planting machinery. Based on the parameter analysis results, formulate optimization schemes for mechanical structure and operating parameters and complete the optimization.

[0007] Furthermore, step S1 specifically includes: S101. Select multiple crop varieties and sampling areas, design sampling combinations based on response surface methodology, collect crop samples under different sampling conditions, measure the sample dimensions, moisture content, mass and various mechanical strength parameters, statistically analyze the frequency distribution of dimensions and derive the corresponding probability distribution. S102. Based on response surface methodology, collect individual crop samples, measure the bulk density, density, friction angle, and angle of repose of the crop population particles, as well as the friction coefficient and collision coefficient between crops and between crops and mechanical parts, and statistically analyze the frequency distribution of the external dimensions of individual crops and derive the corresponding probability distribution. S103. Based on the discrete element sphere construction method, establish a crop discrete element model, integrate all measured parameters and distribution patterns, and construct a crop digital model with parameter query and working condition prediction functions.

[0008] Furthermore, step S2 specifically includes: S201. Set up multiple sets of different statistical unit intervals, use camera equipment to collect video of the entire process of planting machinery seeding, queuing and planting, extract the material quantity sequence corresponding to each unit interval through image detection technology, statistically analyze the quantity frequency distribution and draw a histogram, derive the probability distribution, and simultaneously calculate the leakage rate, single material rate and heavy material rate indicators. S202. Select multiple random models, calibrate the parameters of each model using the measured material quantity sequence, conduct simulation calculations to obtain simulation sequences, and screen the random model with the best fitting effect through goodness-of-fit test. S203. With the optimization goals of no jamming, low leakage rate, and high single-material rate, the optimal statistical unit interval and model parameters are determined by combining the optimal stochastic model, and the speed range for stable operation of planting machinery is defined. S204. Based on the optimal stochastic model, build an M / D / 1 / K queuing statistical model. For multi-row operation machinery, establish a multi-path independent queuing model to simulate and generate queuing length and material quantity sequence, statistically analyze the sequence distribution law, identify performance parameters such as single-sowing rate, re-sowing rate, missed sowing rate, and seeding uniformity, and analyze the causes of jamming, missed sowing, and broken strip failures.

[0009] Furthermore, step S3 specifically includes: S301. Use 3D modeling software to draw a 3D structural model of the entire planting machinery and key working components, and import the 3D structural model of the planting machinery and the crop digital model obtained in step S1 into the discrete element simulation system. S302. Set the operating parameters of the planting machinery, simulate the entire process of crop material encapsulation, queuing, and seeding within a complete working cycle, and extract the position field, attitude field, trajectory field, velocity field, internal force field, and external load field characteristic quantities of the material flow. S303. Statistically analyze the frequency and probability distribution of characteristic quantities of each field, analyze the influence mechanism of mechanical structure and operating parameters on the material motion state, analyze the generation mechanism of blockage, material collision and leakage, as well as the material orientation and arrangement mechanism, and identify motion performance parameters such as transmission slip coefficient and cavity distance.

[0010] Furthermore, step S4 specifically includes: S401. Construct a testing platform for planting machinery. The testing platform can adjust the operating speed, mechanical tilt angle, key structural dimensions, motion parameters, and statistical unit intervals for each stage, and is equipped with multi-channel synchronous high-speed camera equipment. S402. Based on the analysis conclusions of statistical models and discrete element simulations, a multi-factor optimal design method is adopted to formulate an experimental plan. The experimental plan is used to control the platform parameters and carry out the actual test. The material flow video of the complete working cycle is collected. S403. Extract the measured sequence of seed quantity, queue length, material axis azimuth angle, and seed quantity using image detection technology, statistically analyze the distribution patterns of each characteristic quantity, calculate performance indicators such as seed uniformity index and sowing uniformity index, and evaluate the material orientation arrangement efficiency.

[0011] Furthermore, step S5 specifically includes: S501. Compare the measured feature sequences, distribution patterns, and various performance indicators with the output results of the statistical model and discrete element simulation, respectively, quantify and analyze the model error, and complete the model accuracy verification. S502, combining statistical analysis, motion simulation, and experimental results, comprehensively identifies core performance parameters of planting machinery such as single-sowing rate, re-sowing rate, missed sowing rate, seeding rate, uniformity index, hole spacing, and transmission slip coefficient; S503, with the optimization goals of no blockages, minimum missed sowing rate, and maximum single sowing rate, identifies mechanical structural defects and unreasonable parameters, formulates structural modification and operating parameter matching schemes, and completes the overall optimization of planting machinery.

[0012] Furthermore, the planting machinery is sugarcane planting machinery, and the corresponding core working component is a stepped rotary track type single-bud sugarcane seed metering device.

[0013] Furthermore, the seed flow detection image detection, sequence extraction, and simulation calculation are implemented using MATLAB software; the response surface design, frequency statistics, probability distribution derivation, and goodness-of-fit test are implemented using SAS statistical software; the discrete element simulation is implemented using EDEM software; and the three-dimensional modeling of the planting machinery is implemented using SolidWorks software.

[0014] This invention also provides a statistical model and parameter identification system for seed flow detection and planting machinery performance testing, comprising the following modules: Material parameter acquisition and digital model construction module: used to select crop samples corresponding to planting machinery operations, measure the physical and mechanical parameters of the crop body and crop population, as well as friction and collision mechanical parameters, statistically analyze the parameter distribution law, and construct a crop digital model that integrates mechanical parameters and distribution characteristics by combining discrete element modeling method; The module for constructing a statistical model and analyzing quantity characteristics based on seed flow detection is used to collect video data of crop material flow during the operation of planting machinery using seed flow detection, statistically analyze the material quantity sequence within a unit interval and derive the corresponding probability distribution, screen the optimal random model that is suitable for the material conveying process, build an M / D / 1 / K queuing statistical model based on the optimal random model, simulate and generate multiple material quantity sequences based on the queuing statistical model, analyze the material flow pattern and preliminarily identify the basic performance parameters of the machinery, and analyze the causes of operational failures. Discrete Element Simulation Module for Analyzing Material Motion Characteristics: This module is used to build a three-dimensional structural model of planting machinery. It imports the three-dimensional structural model of planting machinery and the digital model of crops into the discrete element simulation system to simulate the motion state of crop materials throughout the entire process. It extracts multi-dimensional field features and statistically analyzes their distribution patterns. It analyzes the motion characteristics of materials, equipment blockage and jamming, and the material orientation and arrangement mechanism, and helps to identify mechanical motion performance parameters. The experimental platform is used to conduct field tests and data acquisition: It is used to build a planting machinery experimental test platform with adjustable structure and operating parameters and integrated multi-channel synchronous camera function. It combines the analysis conclusions of simulation and statistical models to design multi-factor experimental schemes, collects measured material flow characteristic data through seed flow detection, statistically analyzes the distribution patterns of data, and calculates various operating performance indicators of the machinery. Model validation, precise parameter identification, and mechanical optimization module: This module compares measured data with simulation and statistical model output data to verify the accuracy of the statistical and simulation models. It comprehensively identifies various performance parameters of planting machinery based on multi-dimensional analysis results, and formulates and completes optimization schemes for mechanical structure and operating parameters based on parameter analysis results.

[0015] Compared with the prior art, the technical solution disclosed in this invention has the following beneficial effects: Constructing a professional statistical model to accurately characterize the characteristics of random operations: Step S2 of this invention relies on seed flow detection and data collection, combined with probability distribution and M / D / 1 / K queuing statistical model to analyze the random flow of materials, breaking through the limitations of traditional deterministic models, and can accurately quantify phenomena such as missed seeding, re-seeding, and stagnation, providing statistical theoretical support for performance parameter identification; Multi-dimensional identification of core performance parameters: Combining statistical models, discrete element simulation, and physical experiments, it can comprehensively identify various key parameters such as single-sowing rate, re-sowing rate, missed sowing rate, uniformity index, hole spacing, and transmission slip coefficient. The parameter identification dimensions are complete and the results are accurate. Seed stream detection empowers detection and improves data quality: The entire process uses seed stream detection and image detection technology to collect dynamic data, replacing manual detection. This greatly improves data continuity, accuracy and efficiency, and ensures that the results of statistical modeling and parameter analysis are true and reliable. Simulation and experiment are linked to form a complete technical closed loop: material modeling, statistical modeling, motion simulation, platform testing, model verification, parameter identification and equipment optimization are completed in sequence. Simulation guides the experiment, and the experiment verifies the model. The logical closed loop and the parameter identification and optimization scheme have sufficient basis. Addressing operational malfunctions at their root: By combining statistical analysis and kinetic mechanism analysis, problems such as seed jamming, missed sowing, and uneven seeding are traced back to their source. Targeted optimization of mechanical structure and parameters is then performed to effectively improve the overall operational performance of planting machinery. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A schematic diagram of the statistical model and parameter identification method for seed flow detection and planting machinery performance testing provided in an embodiment of the present invention; Figure 2 A schematic diagram of a method for constructing spherical elements of non-spherical particles according to an embodiment of the present invention; Figure 3 The discrete element model of single-bud sugarcane provided in this embodiment of the invention is shown in Figure a, where a is the sugarcane segment model and b is the sugarcane leaf model. Figure 4 This is a schematic diagram illustrating the construction of the M / D / 1 / K queuing model provided in an embodiment of the present invention; Figure 5 This is a detailed technical roadmap for the statistical model and parameter identification method for seed flow detection and planting machinery performance testing provided in this embodiment of the invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] This embodiment uses sugarcane planting machinery and its matching stepped rotary track single-bud sugarcane seed metering device as the application object. Those skilled in the art can adjust the parameters and experimental schemes according to actual working conditions. Figure 1 and 5 As shown, this embodiment of the invention provides a statistical model and parameter identification method for seed flow detection and planting machinery performance testing, specifically including: Step S1: Material Parameter Acquisition and Digital Model Construction This step is used to obtain the basic physical and mechanical parameters of the crop and build a discrete element digital model. Figures 2-3 The schematic diagram of constructing a model for the discrete element sphere of crops is the core result of this step.

[0021] Sample collection: Select the mainstream sugarcane varieties and corresponding planting areas in the local area, complete the response surface experimental design using SAS software, set three major influencing factors: variety, root diameter, and sampling height, and collect sugarcane stalk samples from the ground to the stalk tip, as well as single-bud sugarcane variety samples on the corresponding stalks according to the design scheme.

[0022] Parameter determination: A universal testing machine was used to determine the tensile, shear, bending, compression, and impact strength, elastic modulus, and Poisson's ratio of the stalks; a moisture content meter was used to detect the moisture content of the stalks, and the triaxial dimensions and unit weight of the stalks were measured simultaneously. For single-bud sugarcane varieties, a dedicated bulk material testing device was used to determine the bulk density, sliding friction angle, angle of repose, and internal friction angle; a collision test device was used to determine the friction coefficient and collision recovery coefficient between sugarcane varieties and between sugarcane varieties and seed metering device components.

[0023] Statistical analysis: SAS software was used to conduct frequency statistics and draw histograms on the triaxial dimensions of stalks and sugarcane seeds, and to deduce their probability distribution type and distribution parameters.

[0024] Digital model building: Reference Figures 2-3 The discrete element method shown employs a staggered arrangement of multiple spherical particles to construct non-spherical discrete element models of sugarcane segments and leaves. It integrates all measured mechanical parameters, friction and collision parameters, and size distribution patterns to build a visualized digital model of sugarcane. This model supports parameter querying and material parameter prediction under different working conditions, providing a foundational model for subsequent simulations.

[0025] This allows for the acquisition of accurate and comprehensive basic parameters of sugarcane materials, providing precise material boundary conditions for subsequent queuing models and discrete element simulations, ensuring that the simulation model closely matches actual working conditions; the digital model enables integrated parameter management, improving the convenience of testing and simulation.

[0026] Step S2: Construct a statistical model based on seed flow detection and analyze quantitative features. This step relies on seed flow detection data to build a stochastic statistical model and a queuing model. Figure 4 This is a schematic diagram of the M / D / 1 / K queuing statistical model structure, which is the core model structure of this step.

[0027] Sugarcane variety data acquisition: Multiple statistical unit intervals were set, and under normal operating conditions of the seed metering device, high-speed cameras were used to continuously capture video of the entire process of seeding, queuing, and seeding for multiple complete working cycles; an image detection algorithm was written using MATLAB to identify and count the number of sugarcane varieties in each unit interval frame by frame, generating a time series of sugarcane variety counts.

[0028] Distribution statistics and index calculation: Using SAS software, the frequency distribution of the number of cyst types is statistically analyzed, histograms are plotted and probability distribution functions are fitted, and the rate of missed cysts, single cysts, and multiple cysts are calculated simultaneously.

[0029] Random model selection: Several commonly used random models such as Poisson distribution and normal distribution were selected. The parameters of each model were calibrated based on the measured number of cyst species, and the number of cyst species was generated by simulation. The goodness-of-fit test was used to compare the simulated sequence and the measured sequence, and the model with the highest coefficient of determination was selected as the optimal random model for the cyst species process.

[0030] Parameter optimization: With "no jamming, minimum leakage rate, and maximum single-cell rate" as the optimization objectives, the optimal unit interval and random model parameters are determined by relying on the MATLAB optimization algorithm, and the high-speed range in which the seed metering device can operate stably is defined.

[0031] Queue Model Construction and Simulation: Reference Figure 4 The M / D / 1 / K queuing statistical model structure shown uses the optimal random model as the material arrival process and combines it with the fixed operation rhythm of the seed metering device to complete the model construction. For multi-row sugarcane planters, multiple independent queuing models are established in parallel for synchronous simulation, and the queuing length and seeding sequence are output. SAS is used to analyze the sequence distribution pattern, calculate the missed seeding rate, duplicate seeding rate, and consistency index of each row, analyze the quantitative causes of seed jamming, missed seeding, and broken strips, and preliminarily identify the basic performance parameters of the equipment.

[0032] To accurately characterize the random quantitative features of sugarcane seed flow and select a random model suitable for the seed metering device's operating patterns; through Figure 4 The queuing model shown reproduces the quantity changes of the entire process of seeding, queuing, and seeding, and locates the causes of seeding failure from a random statistical perspective, providing data support for optimizing the operating parameters of the seeding machine.

[0033] Step S3: Discrete Element Simulation Analysis of Material Motion Characteristics 3D Modeling and Model Import: Using SolidWorks software, draw 3D models of the entire stepped rotary track seed metering device, including key components such as the rotary track, hopper, and partition, according to actual dimensions, and complete assembly and interference checks; import the seed metering device 3D model and the sugarcane digital model constructed in step S1 into the EDEM discrete element simulation software.

[0034] Simulation settings: In EDEM, set the working parameters such as the rotation speed, tilt angle, and working direction of the seed metering device to match the actual field working conditions, set the simulation duration to cover multiple complete work cycles, and start the simulation calculation.

[0035] Field feature extraction and statistics: After the simulation is completed, the position field, attitude field, motion trajectory, velocity, inter-particle internal force, and equipment external load of sugarcane seed are extracted in the three stages of seeding, queuing and planting. MATLAB and SAS are used to perform frequency statistics and probability distribution derivation on the feature data.

[0036] Mechanism Analysis: The influence of the structural dimensions and motion parameters of the seed metering device on the speed, posture, and collision state of the sugarcane seeds is analyzed; phenomena such as seed jamming, accumulation, and jumping out are observed during the simulation process, and the motion mechanisms of seed jamming, seed collision, and missed seeding are analyzed; the changes in the posture of the sugarcane seeds are tracked, and the directional queuing and directional seeding mechanisms with the seed axis parallel to the seed furrow direction are summarized, and motion performance parameters such as transmission slip coefficient and hole spacing are identified.

[0037] This research aims to analyze the movement patterns of sugarcane seed flow from a kinematic and dynamic perspective, clarify the correlation between structural parameters and operational failures and the effectiveness of directional seeding, overcome the limitations of quantitative statistics in analyzing movement mechanisms, and provide a theoretical basis for the structural modification of seed metering devices.

[0038] Step S4: Set up the experimental platform to conduct experimental tests and collect data. This step involves building a physical testing platform and conducting actual measurements, clearly demonstrating the platform structure, adjustable components, and multi-camera layout.

[0039] Experimental platform construction: A dedicated seed metering device test platform is built based on existing frames or sugarcane planters. The platform supports stepless adjustment of operating speed, seed metering device tilt angle, rotary track structure dimensions, motion parameters, and statistical unit intervals for each stage. The platform is equipped with three synchronous high-speed cameras, corresponding to the seeding area, queuing area, and seed metering area, respectively, which can simultaneously collect video data of the entire process.

[0040] Experimental design: Based on the simulation results of S2 and S3, a multi-factor optimal experimental design was carried out using SAS software. The core structural parameters and operating parameters that affect seeding performance were selected as experimental factors, and the number of experimental groups and parameter levels were determined.

[0041] Video acquisition and data extraction: The platform parameters were adjusted sequentially according to the experimental plan, and multiple working cycles of video were captured for each group of experiments; the measured feature sequences such as the number of seed pods, queue length, sugarcane seed axis azimuth angle, and number of seed pods were extracted using the MATLAB image detection algorithm.

[0042] Performance analysis: Statistically analyze the distribution patterns of various characteristic quantities, calculate the uniformity of planting, single-row rate, duplicate-row rate, and missed-row rate, and evaluate the actual effectiveness of directional queuing and directional planting based on the sugarcane seed axis azimuth data.

[0043] This allows us to obtain seeding performance data under real-world working conditions, complete performance analysis under the coupling effect of multiple factors, and provide experimental evidence for model verification and final optimization scheme formulation; relying on Figure 4 The multi-channel synchronous camera layout shown ensures complete and synchronized data acquisition throughout the entire process.

[0044] Step S5: Model Validation, Precise Parameter Identification, and Mechanical Optimization Model accuracy verification: The measured feature sequences, probability distributions, and various queuing performance indicators of S4 are compared item by item with the simulation results of the S2 queuing model and the S3 discrete element simulation. The relative error is calculated to verify the reliability and accuracy of the two types of simulation models.

[0045] Defect identification and parameter identification: Combining simulation analysis conclusions and experimental data, identify existing structural defects and unreasonable operating parameters of the seed metering device; integrate statistical analysis, motion simulation, and experimental data to comprehensively identify all core performance parameters such as single-sowing rate, re-sowing rate, missed sowing rate, seeding volume, uniformity index, hole spacing, and transmission slip coefficient.

[0046] Optimization plan formulation and implementation: With "no blockages or jams, minimal missed seeding rate, and maximum single-seeding rate" as the core objectives, the structural dimensions and component shapes of the seed metering device were modified in a targeted manner to match the optimal operating parameters; the structural transformation and parameter tuning were completed to achieve overall optimization of the planting machinery.

[0047] Complete the engineering verification of the simulation model to ensure that the simulation conclusions can be applied in practice; complete the systematic optimization of the seed metering device from two dimensions: structure and parameters, effectively solve the original problems of missed seeding, seed jamming, and uneven seeding, and improve the overall operation performance of the machine.

[0048] It should be noted that the method of this invention is not only applicable to sugarcane planting machinery and stepped rotary track single-bud sugarcane seed metering devices, but also, after slight parameter adaptation, can be applied to performance testing, statistical modeling and parameter identification of other types of planting machinery and seeding devices such as grooved wheel type, disc type, and chain spoon type. The MATLAB, SAS, EDEM and SolidWorks used in this invention are all industry-standard software, and the algorithms and models can be implemented through conventional programming and software operation, and the solution has strong engineering feasibility.

[0049] Based on the same idea, this invention also provides a statistical model and parameter identification system for seed flow detection and planting machinery performance testing, comprising the following modules: Material parameter acquisition and digital model construction module: used to select crop samples corresponding to planting machinery operations, measure the physical and mechanical parameters of the crop body and crop population, as well as friction and collision mechanical parameters, statistically analyze the parameter distribution law, and construct a crop digital model that integrates mechanical parameters and distribution characteristics by combining discrete element modeling method; The module for constructing a statistical model and analyzing quantity characteristics based on seed flow detection is used to collect video data of crop material flow during the operation of planting machinery using seed flow detection, statistically analyze the material quantity sequence within a unit interval and derive the corresponding probability distribution, screen the optimal random model that is suitable for the material conveying process, build an M / D / 1 / K queuing statistical model based on the optimal random model, simulate and generate multiple material quantity sequences based on the queuing statistical model, analyze the material flow pattern and preliminarily identify the basic performance parameters of the machinery, and analyze the causes of operational failures. Discrete Element Simulation Module for Analyzing Material Motion Characteristics: This module is used to build a three-dimensional structural model of planting machinery. It imports the three-dimensional structural model of planting machinery and the digital model of crops into the discrete element simulation system to simulate the motion state of crop materials throughout the entire process. It extracts multi-dimensional field features and statistically analyzes their distribution patterns. It analyzes the motion characteristics of materials, equipment blockage and jamming, and the material orientation and arrangement mechanism, and helps to identify mechanical motion performance parameters. The experimental platform is used to conduct field tests and data acquisition: It is used to build a planting machinery experimental test platform with adjustable structure and operating parameters and integrated multi-channel synchronous camera function. It combines the analysis conclusions of simulation and statistical models to design multi-factor experimental schemes, collects measured material flow characteristic data through seed flow detection, statistically analyzes the distribution patterns of data, and calculates various operating performance indicators of the machinery. Model validation, precise parameter identification, and mechanical optimization module: This module compares measured data with simulation and statistical model output data to verify the accuracy of the statistical and simulation models. It comprehensively identifies various performance parameters of planting machinery based on multi-dimensional analysis results, and formulates and completes optimization schemes for mechanical structure and operating parameters based on parameter analysis results.

[0050] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0051] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0052] It should also be noted that in the apparatus, device, and method of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of the present invention.

[0053] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0054] It should be understood that the qualifying terms "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly illustrate the technical solutions and are not intended to limit the scope of protection of the present invention.

[0055] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A statistical model and parameter identification method for seed flow detection and planting machinery performance testing, characterized in that, Includes the following steps: S1. Material Parameter Acquisition and Digital Model Construction: Select crop samples corresponding to planting machinery operations, measure the physical and mechanical parameters of the crop body and crop population, as well as friction and collision mechanical parameters, statistically analyze the parameter distribution patterns, and construct a crop digital model that integrates mechanical parameters and distribution characteristics by combining discrete element modeling. S2. Construct a statistical model based on seed flow detection and analyze quantity characteristics: Use seed flow detection to collect video data of crop material flow during the operation of planting machinery, statistically analyze the material quantity sequence within a unit interval and derive the corresponding probability distribution, screen the optimal random model that is suitable for the material conveying process, build an M / D / 1 / K queuing statistical model based on the optimal random model, simulate and generate multiple material quantity sequences based on the queuing statistical model, analyze the material flow pattern and preliminarily identify the basic performance parameters of the machinery, and analyze the causes of operation failures. S3. Discrete Element Simulation Analysis of Material Motion Characteristics: A three-dimensional structural model of planting machinery is built. The three-dimensional structural model of planting machinery and the digital model of crops are imported into the discrete element simulation system to simulate the motion state of crop materials throughout the entire process. Multi-dimensional field feature quantities are extracted and their distribution patterns are statistically analyzed. Material motion characteristics, equipment blockage and jamming and material orientation and arrangement mechanisms are analyzed to help identify mechanical motion performance parameters. S4. Build an experimental platform to conduct actual tests and data collection: Build an experimental testing platform for planting machinery with adjustable structure and operating parameters and integrated multi-channel synchronous camera function. Combine simulation and statistical model analysis conclusions to design multi-factor experimental schemes. Collect measured material flow characteristic data through seed flow detection, statistically analyze the distribution pattern of data and calculate various operating performance indicators of the machinery. S5. Model Validation, Precise Parameter Identification and Mechanical Optimization: Compare measured data with simulation and statistical model output data to verify the accuracy of statistical and simulation models. Combine multi-dimensional analysis results to comprehensively identify various performance parameters of planting machinery. Based on the parameter analysis results, formulate optimization schemes for mechanical structure and operating parameters and complete the optimization.

2. The method according to claim 1, characterized in that, Step S1 specifically includes: S101. Select multiple crop varieties and sampling areas, design sampling combinations based on response surface methodology, collect crop samples under different sampling conditions, measure the sample dimensions, moisture content, mass and various mechanical strength parameters, statistically analyze the frequency distribution of dimensions and derive the corresponding probability distribution. S102. Based on response surface methodology, collect individual crop samples, measure the bulk density, density, friction angle, and angle of repose of the crop population particles, as well as the friction coefficient and collision coefficient between crops and between crops and mechanical parts, and statistically analyze the frequency distribution of the external dimensions of individual crops and derive the corresponding probability distribution. S103. Based on the discrete element sphere construction method, establish a crop discrete element model, integrate all measured parameters and distribution patterns, and construct a crop digital model with parameter query and working condition prediction functions.

3. The method according to claim 1, characterized in that, Step S2 specifically includes: S201. Set up multiple sets of different statistical unit intervals, use camera equipment to collect video of the entire process of planting machinery seeding, queuing and planting, extract the material quantity sequence corresponding to each unit interval through image detection technology, statistically analyze the quantity frequency distribution and draw a histogram, derive the probability distribution, and simultaneously calculate the leakage rate, single material rate and heavy material rate indicators. S202. Select multiple random models, calibrate the parameters of each model using the measured material quantity sequence, conduct simulation calculations to obtain simulation sequences, and screen the random model with the best fitting effect through goodness-of-fit test. S203. With the optimization goals of no jamming, low leakage rate, and high single-material rate, the optimal statistical unit interval and model parameters are determined by combining the optimal stochastic model, and the speed range for stable operation of planting machinery is defined. S204. Based on the optimal stochastic model, build an M / D / 1 / K queuing statistical model. For multi-row operation machinery, establish a multi-path independent queuing model to simulate and generate queuing length and material quantity sequence, statistically analyze the sequence distribution law, identify performance parameters such as single-sowing rate, re-sowing rate, missed sowing rate, and seeding uniformity, and analyze the causes of jamming, missed sowing, and broken strip failures.

4. The method according to claim 1, characterized in that, Step S3 specifically includes: S301. Use 3D modeling software to draw a 3D structural model of the entire planting machinery and key working components, and import the 3D structural model of the planting machinery and the crop digital model obtained in step S1 into the discrete element simulation system. S302. Set the operating parameters of the planting machinery, simulate the entire process of crop material encapsulation, queuing, and seeding within a complete working cycle, and extract the position field, attitude field, trajectory field, velocity field, internal force field, and external load field characteristic quantities of the material flow. S303. Statistically analyze the frequency and probability distribution of characteristic quantities of each field, analyze the influence mechanism of mechanical structure and operating parameters on the material motion state, analyze the generation mechanism of blockage, material collision and leakage, as well as the material orientation and arrangement mechanism, and identify motion performance parameters such as transmission slip coefficient and cavity distance.

5. The method according to claim 1, characterized in that, Step S4 specifically includes: S401. Construct a testing platform for planting machinery. The testing platform can adjust the operating speed, mechanical tilt angle, key structural dimensions, motion parameters, and statistical unit intervals for each stage, and is equipped with multi-channel synchronous high-speed camera equipment. S402. Based on the analysis conclusions of statistical models and discrete element simulations, a multi-factor optimal design method is adopted to formulate an experimental plan. The experimental plan is used to control the platform parameters and carry out the actual test. The material flow video of the complete working cycle is collected. S403. Extract the measured sequence of seed quantity, queue length, material axis azimuth angle, and seed quantity using image detection technology, statistically analyze the distribution patterns of each characteristic quantity, calculate performance indicators such as seed uniformity index and sowing uniformity index, and evaluate the material orientation arrangement efficiency.

6. The method according to claim 1, characterized in that, Step S5 specifically includes: S501. Compare the measured feature sequences, distribution patterns, and various performance indicators with the output results of the statistical model and discrete element simulation, respectively, quantify and analyze the model error, and complete the model accuracy verification. S502, combining statistical analysis, motion simulation, and experimental results, comprehensively identifies core performance parameters of planting machinery such as single-sowing rate, re-sowing rate, missed sowing rate, seeding rate, uniformity index, hole spacing, and transmission slip coefficient; S503, with the optimization goals of no blockages, minimum missed sowing rate, and maximum single sowing rate, identifies mechanical structural defects and unreasonable parameters, formulates structural modification and operating parameter matching schemes, and completes the overall optimization of planting machinery.

7. The method according to any one of claims 1-6, characterized in that, The planting machinery is sugarcane planting machinery, and the corresponding core working component is a stepped rotary track type single-bud sugarcane seed metering device.

8. The method according to claim 1, characterized in that, The seed flow detection image detection, sequence extraction, and simulation calculation are implemented using MATLAB software; the response surface design, frequency statistics, probability distribution derivation, and goodness-of-fit test are implemented using SAS statistical software; the discrete element simulation is implemented using EDEM software; and the 3D modeling of the planting machinery is implemented using SolidWorks software.

9. A statistical model and parameter identification system for seed flow detection and planting machinery performance testing, characterized in that, Includes the following modules: Material parameter acquisition and digital model construction module: used to select crop samples corresponding to planting machinery operations, measure the physical and mechanical parameters of the crop body and crop population, as well as friction and collision mechanical parameters, statistically analyze the parameter distribution law, and construct a crop digital model that integrates mechanical parameters and distribution characteristics by combining discrete element modeling method; The module for constructing a statistical model and analyzing quantity characteristics based on seed flow detection is used to collect video data of crop material flow during the operation of planting machinery using seed flow detection, statistically analyze the material quantity sequence within a unit interval and derive the corresponding probability distribution, screen the optimal random model that is suitable for the material conveying process, build an M / D / 1 / K queuing statistical model based on the optimal random model, simulate and generate multiple material quantity sequences based on the queuing statistical model, analyze the material flow pattern and preliminarily identify the basic performance parameters of the machinery, and analyze the causes of operational failures. Discrete Element Simulation Module for Analyzing Material Motion Characteristics: This module is used to build a three-dimensional structural model of planting machinery. It imports the three-dimensional structural model of planting machinery and the digital model of crops into the discrete element simulation system to simulate the motion state of crop materials throughout the entire process. It extracts multi-dimensional field features and statistically analyzes their distribution patterns. It analyzes the motion characteristics of materials, equipment blockage and jamming, and the material orientation and arrangement mechanism, and helps to identify mechanical motion performance parameters. The experimental platform is used to conduct field tests and data acquisition: It is used to build a planting machinery experimental test platform with adjustable structure and operating parameters and integrated multi-channel synchronous camera function. It combines the analysis conclusions of simulation and statistical models to design multi-factor experimental schemes, collects measured material flow characteristic data through seed flow detection, statistically analyzes the distribution patterns of data, and calculates various operating performance indicators of the machinery. Model validation, precise parameter identification, and mechanical optimization module: This module compares measured data with simulation and statistical model output data to verify the accuracy of the statistical and simulation models. It comprehensively identifies various performance parameters of planting machinery based on multi-dimensional analysis results, and formulates and completes optimization schemes for mechanical structure and operating parameters based on parameter analysis results.

Images