A method and system for estimating and optimizing the dispersion stability of herbicide suspension concentrates

Abstract

The present application belongs to the field of agricultural technology and discloses a method and system for estimating and optimizing the dispersion stability of a herbicide suspension concentrate. The method accelerates the deterioration process of the suspension concentrate by simulating various environmental conditions and measures turbidity data in real time to evaluate the dispersion stability, thereby enabling rapid and accurate estimation of the dispersion stability.

Description

Technical Field

[0001] The present application relates to the field of agricultural technology, and in particular to a method and system for estimating and optimizing the dispersion stability of a herbicide suspension concentrate. Background Art

[0002] Driven by the dual imperatives of environmental protection and sustainable agricultural development, environmentally friendly herbicide suspension concentrates (SCs), such as biogenic herbicides, essential oil-based herbicides, natural organic acid-based herbicides, amino acid-based herbicides, and polysaccharide-based herbicides, have gradually become a vital component of modern agricultural production systems. Faced with the urgent market demand for environmentally friendly pesticides, many small pesticide companies are actively investing in R&D, developing new herbicide products primarily based on natural or biodegradable ingredients. These environmentally friendly SCs are formulated with a greater emphasis on environmental friendliness, striving to minimize potential adverse impacts on the ecological environment.

[0003] However, compared to traditional herbicides, environmentally friendly herbicide suspension concentrates (SCs) present particularly significant challenges in terms of dispersion stability. Dispersion stability is not only directly related to the full release of the herbicide's active ingredient and a key factor in maintaining product shelf life and ensuring product quality, but it also directly impacts the reliability and durability of field weed control. For small pesticide companies, ensuring the quality of every batch of product leaving the factory is crucial, and rigorous pre-market quality control is essential. Therefore, how to quickly and accurately assess the dispersion stability of environmentally friendly herbicide SCs under various complex environmental conditions has become a key technical challenge in product quality control. While traditional long-term storage tests are recognized as the gold standard for stability assessment, their inherent time-consuming nature severely hinders small companies' ability to quickly adjust product formulations and flexibly respond to market changes. This is particularly true when faced with complex and variable field environmental factors, such as high temperature, high humidity, and irrigation water of varying hardness. Traditional methods often struggle to provide effective stability feedback in a short period of time. The industry urgently needs a simple, rapid, and reliable dispersion stability assessment method that can effectively simulate a variety of extreme field environments under laboratory conditions. This method will provide timely and effective technical support for the formulation optimization and quality control of environmentally friendly herbicide suspension concentrates, thereby effectively safeguarding the healthy development of green agriculture and ensuring stable and reliable field weed control. However, the market still lacks a dispersion stability assessment technology that combines rapidity, accuracy, and environmental adaptability. Small pesticide companies still face the dual challenges of efficiency and cost in quality control of environmentally friendly herbicide products.

[0004] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for estimating and optimizing the dispersion stability of a herbicide suspension concentrate, which can quickly and accurately estimate the dispersion stability.

[0006] In a first aspect, the present application provides a method for estimating and optimizing the dispersion stability of a herbicide suspension concentrate, the method comprising:

[0007] A1. Dilute the suspension concentrate to be tested with simulated irrigation water of varying hardness to form multiple initial suspension concentrate samples. Divide each initial suspension concentrate sample into multiple replicates, forming multiple replicate groups; each replicate group contains replicates corresponding to the simulated irrigation water of all hardnesses.

[0008] A2. Subject each parallel sample group to different environmental stress conditions to accelerate the degradation of the suspension concentrate dispersion stability. During the degradation process, the turbidity data of each parallel sample is measured in real time. Environmental stress conditions include temperature and humidity conditions.

[0009] A3. Based on the measured turbidity data, calculate the turbidity change rate of each parallel sample to evaluate the dispersion stability performance of each parallel sample;

[0010] A4. Evaluate the comprehensive dispersion stability performance of the suspension concentrate to be tested based on the dispersion stability performance of each parallel sample;

[0011] A5. Analyze the impact of various environmental factors on the dispersion stability of the suspension concentrate under test based on the dispersion stability performance of each replicate sample and the corresponding simulated irrigation water hardness and environmental stress conditions. Environmental factors include irrigation water hardness, temperature, and humidity.

[0012] A6. Output an evaluation report that includes the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance of the suspension concentrate to be tested, and the impact level of various environmental factors on the dispersion stability of the suspension concentrate to be tested.

[0013] Furthermore, the present application also proposes that step A1 includes:

[0014] A101. Prepare simulated irrigation water of various hardness levels based on the common water quality range in the intended use area.

[0015] A102. Dilute the suspension concentrate to target concentration using simulated irrigation water of varying hardness to obtain multiple initial suspension concentrate samples.

[0016] A103. Measure each initial suspension concentrate sample and dispense it into multiple sample containers, with each sample container corresponding to a parallel sample, to form multiple parallel sample groups; each parallel sample group contains parallel samples corresponding to simulated irrigation water of all hardnesses.

[0017] Furthermore, the present application also proposes that step A2 includes:

[0018] A201. Obtain historical meteorological data for the intended area of use, including temperature and humidity data;

[0019] A202. Using a clustering algorithm, extract multiple typical environmental stress combinations from historical meteorological data; each typical environmental stress combination includes a temperature data set and a humidity data set;

[0020] A203. Set the temperature and humidity of each channel of the environmental stress acceleration device so that the environmental stress conditions of each channel correspond to a typical environmental stress combination;

[0021] A204. Place each parallel sample group in each channel of the environmental stress acceleration device to accelerate the deterioration of the suspension dispersion stability;

[0022] A205. During the degradation process, the turbidity data of each parallel sample is measured in real time.

[0023] Furthermore, the present application also proposes that step A202 includes:

[0024] B1. Perform cluster analysis on historical meteorological data using various clustering algorithms to obtain multiple clustering results; the clustering algorithms include K-means clustering algorithm, hierarchical clustering algorithm, and DBSCAN clustering algorithm;

[0025] B2. Evaluate multiple clustering results based on multiple evaluation metrics and select the optimal clustering result; the evaluation metrics include silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index;

[0026] B3. Calculate the mean temperature and mean humidity in each cluster in the optimal clustering result to obtain the typical environmental stress combination of the corresponding cluster.

[0027] Furthermore, the present application also proposes that step B1 includes:

[0028] B101. Based on historical meteorological data, standardize temperature and humidity data to eliminate dimensional differences;

[0029] B102. Use the elbow rule to determine the optimal number of clusters for the K-means clustering algorithm. Based on the determined optimal number of clusters, perform cluster analysis on the standardized historical meteorological data using the K-means clustering algorithm to generate multiple clusters and obtain the K-means clustering results.

[0030] B103. For the hierarchical clustering algorithm, use the Wardlinkage method to calculate the inter-cluster distance, construct a hierarchical clustering dendrogram, and then segment the dendrogram into multiple clusters based on the set threshold or number of clusters to obtain the clustering results of the hierarchical clustering algorithm.

[0031] B104. For the DBSCAN clustering algorithm, the grid search method is used to determine the neighborhood radius and minimum sample number parameters. Based on the determined neighborhood radius and minimum sample number parameters, the DBSCAN clustering algorithm is used to perform cluster analysis on historical meteorological data, generate multiple clusters, and obtain the DBSCAN algorithm clustering results.

[0032] Furthermore, the present application also proposes that step B2 includes:

[0033] B201. Calculate the silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index for each clustering result.

[0034] B202. For each evaluation indicator, normalize and reciprocate the value to the interval [0, 1] to obtain the normalized evaluation indicator.

[0035] B203. For each clustering result, perform a weighted summation of the normalized silhouette coefficient, normalized Calinski-Harabasz index, and normalized Davies-Bouldin index to obtain a comprehensive score.

[0036] B204. Select the clustering result with the highest comprehensive score as the optimal clustering result.

[0037] Furthermore, the present application also proposes that step A3 includes:

[0038] A301. Extract turbidity data of each parallel sample at different time points to form a turbidity time series;

[0039] A302. Calculate the turbidity change rate using the sliding window method for each turbidity time series;

[0040] A303. For each parallel sample, calculate the average turbidity change rate of the entire degradation process based on the corresponding turbidity change rate calculation result, and convert it into a dispersion stability performance evaluation index.

[0041] Furthermore, the present application also proposes that step A303 includes:

[0042] For each parallel sample, the turbidity change rate time series is extracted and divided into multiple time windows according to the time sequence;

[0043] For each time window, the average weighted value of the turbidity change rate is calculated; the farther the time window is from the initial moment of the degradation process, the smaller the corresponding weight coefficient;

[0044] For each parallel sample, the average weighted value of the turbidity change rate in each time window was accumulated as an evaluation index of the dispersion stability performance.

[0045] Furthermore, the present application also proposes that step A4 includes:

[0046] A401. Obtain historical meteorological data for the intended use area and calculate the probability of occurrence of various environmental stress conditions in the intended use area based on the historical meteorological data;

[0047] A402. Convert the probability of occurrence of each environmental stress condition in the expected use area into a weight coefficient;

[0048] A403. Calculate the weighted average dispersion stability performance of each parallel sample based on its dispersion stability performance and the corresponding weight coefficient as the comprehensive dispersion stability performance of the suspending agent to be tested.

[0049] In a second aspect, the present application also proposes a herbicide suspension dispersion stability prediction and optimization system, which includes:

[0050] An environmental stress acceleration device has multiple channels, each channel having independently adjustable environmental stress conditions, and each channel is used to accelerate the degradation of suspension dispersion stability on different parallel sample groups under different environmental stress conditions; the environmental stress conditions include temperature conditions and humidity conditions; the parallel sample groups are obtained by: diluting the suspension to be tested with simulated irrigation water of multiple different hardnesses to form multiple initial suspension samples; each initial suspension sample is divided into multiple parallel samples to form multiple parallel sample groups; each parallel sample group contains parallel samples corresponding to all simulated irrigation water hardnesses;

[0051] Turbidity detection device, used to measure the turbidity data of each parallel sample in real time during the degradation process;

[0052] The host computer is used to perform the following steps:

[0053] According to the measured turbidity data, the turbidity change rate of each parallel sample is calculated to evaluate the dispersion stability performance of each parallel sample;

[0054] Evaluate the comprehensive dispersion stability performance of the suspension concentrate to be tested based on the dispersion stability performance of each parallel sample;

[0055] Based on the dispersion stability performance of each parallel sample and the corresponding simulated irrigation water hardness and environmental stress conditions, the influence level of each environmental factor on the dispersion stability of the suspension concentrate to be tested was analyzed; environmental factors include irrigation water hardness, temperature and humidity;

[0056] The output includes an evaluation report of the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance and the impact level of each environmental factor on the dispersion stability of the suspension agent to be tested.

[0057] Beneficial effects: The present application provides a method and system for estimating and optimizing the dispersion stability of herbicide suspension concentrates. By simulating various environmental conditions to accelerate the deterioration process of the suspension concentrate and measuring turbidity data in real time to evaluate the dispersion stability, the dispersion stability can be estimated quickly and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of the method for estimating and optimizing the dispersion stability of a herbicide suspension concentrate provided in an embodiment of the present application.

[0059] Figure 2 This is a schematic diagram of the structure of the herbicide suspension dispersion stability prediction and optimization system provided in the embodiment of the present application.

[0060] Explanation of reference numerals: 1. Environmental stress acceleration device; 2. Turbidity detection device; 3. Host computer. DETAILED DESCRIPTION

[0061] The technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. The components of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application.

[0062] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0063] refer to Figure 1 , this application proposes a method for estimating and optimizing the dispersion stability of a herbicide suspension concentrate, the method comprising:

[0064] A1. Dilute the suspension concentrate to be tested with simulated irrigation water of varying hardness to form multiple initial suspension concentrate samples. Divide each initial suspension concentrate sample into multiple replicates, forming multiple replicate groups; each replicate group contains replicates corresponding to the simulated irrigation water of all hardnesses.

[0065] A2. Subject each parallel sample group to different environmental stress conditions to accelerate the degradation of the suspension concentrate dispersion stability. During the degradation process, the turbidity data of each parallel sample is measured in real time. Environmental stress conditions include temperature and humidity conditions.

[0066] A3. Based on the measured turbidity data, calculate the turbidity change rate of each parallel sample to evaluate the dispersion stability performance of each parallel sample;

[0067] A4. Evaluate the comprehensive dispersion stability performance of the suspension concentrate to be tested based on the dispersion stability performance of each parallel sample;

[0068] A5. Analyze the impact of various environmental factors on the dispersion stability of the suspension concentrate under test based on the dispersion stability performance of each replicate sample and the corresponding simulated irrigation water hardness and environmental stress conditions. Environmental factors include irrigation water hardness, temperature, and humidity.

[0069] A6. Output an evaluation report that includes the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance of the suspension concentrate to be tested, and the impact level of various environmental factors on the dispersion stability of the suspension concentrate to be tested.

[0070] Wherein, in step A1, the suspension to be tested is first diluted by a series of configured simulated irrigation waters, and the hardness gradient of the simulated irrigation water covers the common water quality range of the expected use area. For example, the hardness of the simulated irrigation water can be set to three or more grades of low hardness, medium hardness and high hardness. Each initial suspension sample is then divided into multiple equal parts and placed in different sample containers to form parallel samples in order to ensure the reliability of the experimental results. The parallel samples are grouped according to the hardness of the simulated irrigation water to form multiple parallel sample groups, so that each parallel sample group contains parallel samples under all hardness conditions, which is convenient for subsequent comparative experiments under the same environmental stress.

[0071] Wherein, in step A2, each parallel sample group is placed in a different channel of the environmental stress acceleration device. For example, the environmental stress acceleration device has a plurality of chambers separated from each other, and the environmental stress conditions of each chamber are independently controllable, so each chamber is a channel. The environmental stress conditions, i.e., temperature and humidity, are set to different combinations in different channels to simulate the meteorological conditions that may occur in the expected use area. The environmental stress acceleration device can accurately control the temperature and humidity of each channel to achieve the purpose of accelerating the degradation of the suspension sample. During the deterioration process of the suspension, the turbidity detection device measures the turbidity data of each parallel sample in real time, and the turbidity data reflects the changes in the dispersion state of the suspension. The turbidity detection device can be a non-contact optical sensor to avoid interference with the sample.

[0072] In step A3, the turbidity change rate is calculated by analyzing the real-time measured turbidity data. For example, a sliding window method can be used to calculate the change in turbidity value per unit time to characterize the dispersion stability performance of the suspension agent. A smaller turbidity change rate indicates better dispersion stability of the suspension agent.

[0073] In step A4, the comprehensive dispersion stability performance is obtained based on the dispersion stability performance evaluation of each parallel sample. For example, the probability of occurrence of various environmental stress conditions can be determined based on historical meteorological data for the intended area of use, and this probability can be used as a weighting factor to perform a weighted average of the dispersion stability performance under each environmental stress condition to obtain the comprehensive dispersion stability performance.

[0074] In step A5, the degree of impact of environmental factors on dispersion stability is determined by comparing dispersion stability performance under different environmental conditions. For example, statistical analysis methods, such as analysis of variance (ANOVA), regression analysis, or correlation analysis, can be used to assess the degree of impact of each environmental factor on dispersion stability performance. Based on the statistical analysis results, the degree of impact of each environmental factor on the dispersion stability of the suspension concentrate is then determined. Specifically, statistical analysis software, such as SPSS, SAS, or R, can be used to perform data analysis to obtain quantitative impact analysis results. The quantitative impact analysis results are then compared with a preset threshold to determine the impact level.

[0075] In step A6, an evaluation report is ultimately output. This report includes the dispersion stability performance evaluation results of each parallel sample, the comprehensive dispersion stability performance evaluation results of the suspension concentrate to be tested, and an analysis of the impact level of various environmental factors on dispersion stability, providing data support for optimizing the herbicide suspension concentrate formulation. For example, a preset evaluation report template can be retrieved from a database, and the dispersion stability performance evaluation results of each parallel sample, the comprehensive dispersion stability performance evaluation results of the suspension concentrate to be tested, and the analysis of the impact level of various environmental factors on dispersion stability can be added to the corresponding locations of the evaluation report template to generate the final evaluation report.

[0076] Specifically, this method for estimating and optimizing the dispersion stability of herbicide suspension concentrates (SCs) works by simulating various environmental factors likely to be encountered in actual applications, accelerating the degradation of the SC's dispersion stability. During this degradation process, turbidity changes are monitored in real time to rapidly assess the SC's dispersion stability under different environments. First, in step A1, SC samples are prepared by diluting them in irrigation water of varying hardness, simulating the differences in water quality encountered in actual use. Subsequently, in step A2, these samples are subjected to varying temperature and humidity conditions to accelerate SC degradation, and the degradation process is dynamically monitored through real-time turbidity measurements. Step A3 quantifies the SC's dispersion stability performance by calculating the rate of turbidity change. Step A4 comprehensively considers the dispersion stability under different environmental conditions to determine the overall dispersion stability performance of the SC under test, providing a more comprehensive picture of the product's stability in actual application. Step A5 further analyzes the impact of irrigation water hardness, temperature, and humidity on dispersion stability, providing clear guidance for formulation optimization. Finally, step A6 produces an evaluation report, providing a scientific basis for quality control and formulation improvement of the SC. This method avoids the time-consuming disadvantages of traditional long-term storage experiments and achieves rapid estimation and optimization of the dispersion stability of herbicide suspension concentrates.

[0077] In some embodiments, step A1 comprises:

[0078] A101. Prepare simulated irrigation water of various hardness levels based on the common water quality range in the intended use area.

[0079] A102. Dilute the suspension concentrate to target concentration using simulated irrigation water of varying hardness to obtain multiple initial suspension concentrate samples.

[0080] A103. Measure each initial suspension concentrate sample and dispense it into multiple sample containers, with each sample container corresponding to a parallel sample, to form multiple parallel sample groups; each parallel sample group contains parallel samples corresponding to simulated irrigation water of all hardnesses.

[0081] Among them, in step A101, the common water quality range of the expected use area can be understood as the statistical distribution of the hardness of the irrigation water in the area, for example, by collecting water quality monitoring data of the expected use area for many years and analyzing the range of water hardness. Configuring simulated irrigation water of multiple different hardnesses can be specifically implemented as follows: for example, if the water hardness range of the expected use area is mainly distributed between 50ppm and 300ppm, six types of simulated irrigation water with hardness of 50ppm, 100ppm, 150ppm, 200ppm, 250ppm and 300ppm can be configured. The preparation method of simulated irrigation water can refer to the method in "Quality Control Technology of Pesticide Suspension Concentrates" and be prepared using reagents such as calcium chloride, magnesium sulfate, and sodium bicarbonate.

[0082] In step A102, the target concentration refers to the dilution concentration of the herbicide suspension concentrate during actual field use. This concentration is typically recommended by pesticide manufacturers based on product characteristics and usage scenarios. The suspension concentrate to be tested is diluted to the target concentration to simulate the state of the herbicide during actual use.

[0083] Among them, in step A103, the purpose of packaging into multiple sample containers is to set up parallel samples. Multiple parallel samples are prepared under each hardness condition for subsequent dispersion stability testing under different environmental stress conditions to ensure the reliability of the experimental results. The parallel sample group is constructed by combining a parallel sample under all hardness conditions to form a parallel sample group, so as to facilitate testing and comparison under the same environmental stress conditions. Among them, the number of parallel samples obtained by packaging each initial suspension sample (i.e., the number of parallel sample groups) can be set according to actual needs, for example, according to the number of channels of the environmental stress acceleration device, so that all parallel sample groups can be accelerated at the same time to save time; in fact, it can also exceed the number of channels of the environmental stress acceleration device, but it is necessary to accelerate the degradation of each parallel sample group in batches.

[0084] Specifically, through step A101, the hardness setting of the simulated irrigation water can truly reflect the water quality characteristics of the expected use area, thereby allowing the subsequent dispersion stability evaluation to be more in line with actual application scenarios. Step A102 ensures that the suspension concentrate to be tested is diluted to the actual use concentration in the simulated irrigation water, further improving the authenticity of the experiment. Step A103 ensures the accuracy and repeatability of the experimental results by preparing parallel sample groups. Through the above steps, a parallel sample group can be prepared that can represent the water quality characteristics of the expected use area and simulate the actual use concentration, laying the foundation for the subsequent evaluation of the dispersion stability of the herbicide suspension concentrate, making the evaluation results more practical and guiding.

[0085] In some embodiments, step A2 comprises:

[0086] A201. Obtain historical meteorological data for the intended area of use, including temperature and humidity data;

[0087] A202. Using a clustering algorithm, extract multiple typical environmental stress combinations from historical meteorological data; each typical environmental stress combination includes a temperature data set and a humidity data set;

[0088] A203. Set the temperature and humidity of each channel of the environmental stress acceleration device so that the environmental stress conditions of each channel correspond to a typical environmental stress combination;

[0089] A204. Place each parallel sample group in each channel of the environmental stress acceleration device to accelerate the deterioration of the suspension dispersion stability;

[0090] A205. During the degradation process, the turbidity data of each parallel sample is measured in real time.

[0091] In step A201, historical meteorological data can be obtained from the public database of the Meteorological Bureau, and the time span of the data can be set to the data of the past few years or the past ten years to ensure the representativeness of the data.

[0092] In step A202, a clustering algorithm is used to analyze historical meteorological data to extract representative environmental stress combinations. Specifically, historical meteorological data is first collected, and the data includes temperature and humidity information. Subsequently, a variety of clustering algorithms, such as the K-means algorithm, the hierarchical clustering algorithm, or the DBSCAN algorithm, can be applied to identify patterns in the meteorological data and group similar meteorological conditions into several clusters. Each cluster represents a typical environmental stress state. By calculating the mean of temperature and humidity within each cluster, a typical environmental stress combination representing the cluster can be obtained, and the combination includes a temperature value and a humidity value. As a result, the setting of environmental stress conditions is no longer a random selection, but is based on a scientific analysis of historical meteorological data to ensure that the selected environmental stress conditions can represent the common climate types in the intended use area. It should be noted that when clustering, the temperature and humidity at the same time point in the historical meteorological data constitute a two-dimensional data point, and cluster analysis is performed on these two-dimensional data points. Specifically, each two-dimensional data point is equivalent to a two-dimensional coordinate, and a clustering algorithm is used to perform cluster analysis on a series of two-dimensional coordinate points.

[0093] In step A203, these typical environmental stress combinations are then used to set up different channels in the environmental stress acceleration device, with each channel simulating a typical environmental stress condition. Parallel sample groups are placed in these channels for accelerated degradation experiments, and turbidity data is measured in real time in step A205 to provide data support for subsequent dispersion stability assessment.

[0094] In step A204 , the duration of the degradation process can be set according to actual needs, such as 7 days, 10 days, etc.

[0095] In step A205, after the experiment starts, the turbidity detection device automatically collects the turbidity value of each parallel sample at a preset time interval, such as every 5 minutes, 10 minutes or 30 minutes, and the collected data can be stored in a data storage device.

[0096] Specifically, historical meteorological data of the expected use area is obtained through step A201, which ensures the relevance of the environmental stress conditions analyzed subsequently with the actual application scenarios. Step A202 is the core of the method. The application of the clustering algorithm realizes the extraction of a small number of representative typical environmental stress combinations from a large amount of historical meteorological data. Cluster analysis can identify the inherent structure in the data set, classify similar meteorological conditions, and represent each category with a typical environmental stress combination, avoiding the arbitrariness of the selection of environmental stress conditions, ensuring that the selected environmental stress conditions can represent the common climate types in the expected use area, and solving the problem of the lack of scientific basis for the setting of environmental stress conditions in traditional methods. Step A203 applies the extracted typical environmental stress combination to the channel setting of the environmental stress acceleration device, so that the experimental conditions can simulate the real environment, thereby improving the practical guiding significance of the experimental results. Steps A204 and A205 carry out suspension dispersion stability degradation experiments and turbidity data measurements under the set typical environmental stress conditions, providing a data basis for subsequent dispersion stability evaluation. Through the above steps, the scientific selection of environmental stress conditions is achieved, making the dispersion stability prediction method more suitable for the actual application environment, improving the accuracy and representativeness of the prediction, and providing more efficient technical support for the formulation optimization and quality control of herbicide suspension concentrates.

[0097] In some possible implementations, step A202 includes:

[0098] B1. Perform cluster analysis on historical meteorological data using various clustering algorithms to obtain multiple clustering results; the clustering algorithms include K-means clustering algorithm, hierarchical clustering algorithm, and DBSCAN clustering algorithm;

[0099] B2. Evaluate multiple clustering results based on multiple evaluation metrics and select the optimal clustering result; the evaluation metrics include silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index;

[0100] B3. Calculate the mean temperature and mean humidity in each cluster in the optimal clustering result to obtain the typical environmental stress combination of the corresponding cluster.

[0101] In step B1, multiple clustering algorithms are used on historical meteorological data to explore potential environmental stress patterns from different perspectives. Specifically, the K-means clustering algorithm divides clusters based on distance and is suitable for discovering spherical clusters; the hierarchical clustering algorithm forms a hierarchical structure by merging or splitting data points layer by layer, revealing nested relationships between data points; and the DBSCAN clustering algorithm identifies clusters based on density and can effectively identify clusters of arbitrary shapes and noise points. By combining these three algorithms, more comprehensive and robust clustering results can be obtained.

[0102] Among them, in step B2, after obtaining multiple clustering results, in order to select the optimal clustering result, multiple evaluation indicators are introduced to objectively evaluate the quality of the clustering results. The silhouette coefficient is used to evaluate the intra-cluster cohesion and inter-cluster separation; the Calinski-Harabasz index evaluates the clustering effect by calculating the ratio of inter-cluster dispersion and intra-cluster dispersion; the Davies-Bouldin index evaluates the clustering effect by calculating the inter-cluster similarity and intra-cluster dispersion. These indicators can measure the quality of clustering results from different aspects. By comprehensively considering these indicators, the optimal clustering result can be selected more accurately. Among them, the calculation methods of the silhouette coefficient, Calinski-Harabasz index and Davies-Bouldin index are existing technologies and will not be described in detail here.

[0103] In step B3, after determining the optimal clustering result, the mean temperature and humidity values of the data points in each cluster are calculated to obtain a representative environmental stress combination. This extracted environmental stress combination can represent the environmental characteristics of each cluster center and is used in the subsequent suspension dispersion stability assessment, thereby improving the environmental representativeness of the evaluation experiment.

[0104] Specifically, this solution aims to solve the problem of unclear clustering algorithm selection and clustering result evaluation criteria when using clustering algorithms to extract typical environmental stress combinations. Through step B1, multiple clustering algorithms such as K-means clustering algorithm, hierarchical clustering algorithm and DBSCAN clustering algorithm are used to mine different clustering patterns from historical meteorological data, thereby obtaining multiple clustering results, ensuring the comprehensiveness of clustering analysis. Then, through step B2, multiple evaluation indicators such as silhouette coefficient, Calinski-Harabasz index and Davies-Bouldin index are introduced to objectively evaluate the clustering results obtained by different clustering algorithms, and the clustering result with the best score is selected to ensure the quality of the clustering results. Finally, in step B3, based on the optimal clustering result, the temperature mean and humidity mean of each cluster are calculated to obtain a typical environmental stress combination, so that the extracted environmental stress combination can represent the typical environmental characteristics of historical meteorological data. Through the above steps, this solution solves the problems of unclear algorithm selection and result evaluation criteria in the environmental stress combination extraction process, improves the accuracy and reliability of environmental stress combination extraction, and enables subsequent suspension dispersion stability evaluation experiments to more effectively simulate real environmental conditions, thereby improving the accuracy of the evaluation results.

[0105] Preferably, step B1 may include:

[0106] B101. Based on historical meteorological data, standardize temperature and humidity data to eliminate dimensional differences;

[0107] B102. Use the elbow rule to determine the optimal number of clusters for the K-means clustering algorithm. Based on the determined optimal number of clusters, perform cluster analysis on the standardized historical meteorological data using the K-means clustering algorithm to generate multiple clusters and obtain the K-means clustering results.

[0108] B103. For the hierarchical clustering algorithm, use the Wardlinkage method to calculate the inter-cluster distance, construct a hierarchical clustering dendrogram, and then segment the dendrogram into multiple clusters based on the set threshold or number of clusters to obtain the clustering results of the hierarchical clustering algorithm.

[0109] B104. For the DBSCAN clustering algorithm, the grid search method is used to determine the neighborhood radius and minimum sample number parameters. Based on the determined neighborhood radius and minimum sample number parameters, the DBSCAN clustering algorithm is used to perform cluster analysis on historical meteorological data, generate multiple clusters, and obtain the DBSCAN algorithm clustering results.

[0110] Among them, in step B101, there is a dimension difference between the temperature data and the humidity data. Therefore, by standardizing the temperature data and the humidity data, for example, using the Z-score standardization method or the Min-Max standardization method, the cluster analysis result deviation caused by the dimension difference between the temperature and humidity data is eliminated.

[0111] Among them, in step B102, the elbow rule is used to determine the optimal number of clusters of the K-means clustering algorithm. Specifically, the elbow rule draws a relationship graph between the number of clusters and the sum of squared errors, and selects the number of clusters with a significantly slower rate of decrease of the sum of squared errors as the optimal number of clusters (the specific process is existing technology and is not described in detail here). Subsequently, based on the determined optimal number of clusters, the K-means clustering algorithm is used to perform cluster analysis on the standardized historical meteorological data to obtain the K-means algorithm clustering results.

[0112] Among them, in step B103, the Wardlinkage method is used to calculate the inter-cluster distance in the hierarchical clustering algorithm. The Wardlinkage method aims to minimize the intra-cluster variance and construct a hierarchical clustering dendrogram. The dendrogram is segmented by setting a threshold or the number of clusters, thereby obtaining the clustering result of the hierarchical clustering algorithm (the specific process is existing technology and will not be described in detail here).

[0113] Among them, in step B104, the grid search method is adopted to determine the neighborhood radius and minimum sample number parameters of the DBSCAN clustering algorithm. The grid search method traverses the set parameter combinations, evaluates the clustering effect, and selects the optimal parameter combination. Subsequently, based on the determined neighborhood radius and minimum sample number parameters, the DBSCAN clustering algorithm is used to perform cluster analysis on the historical meteorological data to obtain the DBSCAN algorithm clustering results (the specific process is existing technology and will not be described in detail here).

[0114] Specifically, step B1 first standardizes the historical meteorological data through step B101, eliminating the interference of the dimensional differences of temperature and humidity data on cluster analysis, and ensuring the accuracy of cluster analysis; then, through steps B102, B103 and B104, cluster analysis is performed on the standardized historical meteorological data using three different clustering algorithms, namely K-means clustering algorithm, hierarchical clustering algorithm and DBSCAN clustering algorithm. Since different clustering algorithms have different clustering principles and applicable scenarios, cluster analysis using multiple clustering algorithms can explore historical meteorological data from multiple angles. The potential distribution characteristics of the data are used to improve the reliability of the clustering results and avoid the problem of inaccurate clustering results due to improper selection of a single clustering algorithm. Furthermore, in step B102, the elbow rule is used to determine the optimal number of clusters for the K-means clustering algorithm. In step B104, the grid search method is used to determine the neighborhood radius and minimum sample number parameters of the DBSCAN clustering algorithm. The reasonable parameters of the clustering algorithm are determined by the parameter optimization method, which can improve the accuracy of the clustering results and enable the clustering results to more realistically reflect the distribution characteristics of historical meteorological data, thereby providing a guarantee for the accuracy of subsequent environmental stress combination extraction.

[0115] Furthermore, step B2 may include:

[0116] B201. Calculate the silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index for each clustering result.

[0117] B202. For each evaluation indicator, normalize and reciprocate the value to the interval [0, 1] to obtain the normalized evaluation indicator.

[0118] B203. For each clustering result, perform a weighted summation of the normalized silhouette coefficient, normalized Calinski-Harabasz index, and normalized Davies-Bouldin index to obtain a comprehensive score.

[0119] B204. Select the clustering result with the highest comprehensive score as the optimal clustering result.

[0120] Among them, in step B201, the silhouette coefficient, Calinski-Harabasz index and Davies-Bouldin index are calculated for multiple clustering results obtained by multiple clustering algorithms, respectively, to quantify the quality of each clustering result. The silhouette coefficient can be calculated by first calculating the average distance between each sample and other samples in its cluster, as well as the average distance between the sample and all samples in the nearest cluster, and then calculating the silhouette coefficient based on these two distances. The closer the silhouette coefficient value is to 1, the better the clustering effect. The Calinski-Harabasz index can be calculated by calculating the ratio of the inter-cluster discreteness to the intra-cluster discreteness. The higher the Calinski-Harabasz index value, the better the clustering effect. The Davies-Bouldin index can be calculated by calculating the similarity between each cluster and its most similar cluster. The lower the Davies-Bouldin index value, the better the clustering effect.

[0121] In step B202, since higher values of the silhouette coefficient and the Calinski-Harabasz index indicate better clustering effects, and lower values of the Davies-Bouldin index indicate better clustering effects, in order to unify the evaluation criteria, the Davies-Bouldin index needs to be reciprocally processed so that higher values indicate better clustering effects. At the same time, since the numerical ranges of different evaluation indicators may differ, in order to make different evaluation indicators comparable, the values of each evaluation indicator need to be normalized to the [0,1] interval. The normalization method can be, for example, using the minimum-maximum normalization method to linearly transform the original data to the [0,1] interval.

[0122] In step B203, for each clustering result, a weighted summation of the normalized silhouette coefficient, the normalized Calinski-Harabasz index, and the normalized reciprocal Davies-Bouldin index is performed to obtain a comprehensive score. The weighted summation can be performed, for example, by assigning equal or different weights to the three indicators and then adding the weighted values to obtain the comprehensive score.

[0123] In step B204 , the comprehensive scores of the clustering results are compared, and the clustering result with the highest comprehensive score is selected as the optimal clustering result, so that subsequent steps can be performed based on the optimal clustering result.

[0124] Specifically, a technical solution for selecting an optimal clustering result from a plurality of clustering results is provided herein. After obtaining a plurality of clustering results by step B1, in order to select the optimal clustering result therefrom, first the silhouette coefficient, Calinski-Harabasz index and Davies-Bouldin index of each clustering result are calculated by step B201. These indices have quantified the quality of the clustering result from different angles. Then, by step B202, these evaluation indices are normalized and processed with an inverse, so that different indices are comparable, and the evaluation direction is consistent. Then, in step B203, each evaluation indices are comprehensively considered by means of a weighted summation, and a comprehensive score for each clustering result is obtained. The higher the comprehensive score, the better the quality of the clustering result. Finally, by step B204, the clustering result with the highest comprehensive score is selected as the optimal clustering result. By the above steps, the optimal clustering result can be objectively and effectively selected from a plurality of clustering results, providing a more reliable basis for subsequent analysis, and thus improving the accuracy of the dispersion stability estimation of the suspending agent.

[0125] In some embodiments, step A3 comprises:

[0126] A301. Extract turbidity data of each parallel sample at different time points to form a turbidity time series;

[0127] A302. Calculate the turbidity change rate using the sliding window method for each turbidity time series;

[0128] A303. For each parallel sample, calculate the average turbidity change rate of the entire degradation process based on the corresponding turbidity change rate calculation result, and convert it into a dispersion stability performance evaluation index.

[0129] In step A301, turbidity data can be read from a data storage device and arranged in chronological order to form a turbidity time series. This can fully reflect the dynamic changes in the dispersion stability of the suspension agent and provide a data basis for subsequent calculation of the turbidity change rate and evaluation of dispersion stability performance.

[0130] Wherein, among the step A302, can set size and the step-length of sliding window, for example, window size is set to 10 time points, and step-length is set to 1 each time point, then from the starting moment of turbidity time series, according to step-length sliding window, in each window, calculate the turbidity rate of change.The turbidity rate of change can adopt multiple computing methods, for example, the linear regression slope of turbidity data in the calculation window, or the difference mean of turbidity data in the calculation window, or with the turbidity data difference between window end point and the window starting point divided by the window time length.Thus, can effectively smooth the fluctuation of turbidity time series, catch the trend of turbidity change, accurately reflect the suspension dispersion stability rate of change.

[0131] In step A303, the average of the turbidity change rates of all sliding windows for each parallel sample throughout the degradation process can be calculated as the average turbidity change rate of the parallel sample. The dispersion stability performance evaluation index can be the average turbidity change rate itself, or it can be a numerical value that maps the average turbidity change rate to a specific interval. For example, the average turbidity change rate is normalized to a score of 0-100, with higher values indicating better dispersion stability performance. In this way, the overall level of suspension dispersion stability during the entire degradation process can be comprehensively reflected and converted into a quantifiable evaluation index, facilitating comparison and evaluation of dispersion stability performance between different samples and under different conditions.

[0132] Specifically, this program, first, extracts the turbidity time series by step A301, realizes the comprehensive tracking and data description of the dynamic change process of the suspension dispersion stability. Then, adopts the sliding window method to calculate the turbidity change rate by step A302, effectively smoothes the data fluctuation, highlights the trend of turbidity change, and improves the accuracy of rate calculation. Finally, calculates the average turbidity change rate by step A303 and converts it into a performance evaluation index, realizes the quantitative evaluation of dispersion stability performance, is convenient for performance comparison and evaluation. Through the above steps, a clear, specific, and operable dispersion stability evaluation method is provided, making the technical scheme more practical and effective.

[0133] Through the above technical solution, the present application makes the calculation method of the turbidity change rate clearer and the evaluation method of the dispersion stability performance more specific, thereby improving the accuracy and reliability of the dispersion stability evaluation results, and providing more effective data support for the subsequent optimization of the suspending agent to be tested based on the dispersion stability performance evaluation results, as well as the analysis of the impact level of various environmental factors on the dispersion stability.

[0134] In some preferred embodiments, step A303 includes:

[0135] For each parallel sample, the turbidity change rate time series is extracted and divided into multiple time windows according to the time sequence;

[0136] For each time window, the average weighted value of the turbidity change rate is calculated; the farther the time window is from the initial moment of the degradation process, the smaller the corresponding weight coefficient;

[0137] For each parallel sample, the average weighted value of the turbidity change rate in each time window was accumulated as an evaluation index of the dispersion stability performance.

[0138] The time window refers to the multiple time periods into which the turbidity change rate time series is divided. This is different from the sliding window mentioned above. The time window can be divided into equal or unequal intervals. For example, a time window can be set every two hours. Or, based on the characteristics of the turbidity change rate, a smaller time window can be set during periods of faster turbidity change and a larger time window during periods of slower turbidity change.

[0139] The further the time window is from the initial moment of the degradation process, the smaller the corresponding weight coefficient. This is to highlight the role of early degradation information in the comprehensive assessment. Different weight coefficients are assigned to different time windows because the degradation rate is faster in the early stages. The weight coefficients can be set using linear, exponential, or step-by-step methods. For example, the weight coefficient of the first time window can be set to 1, the weight coefficient of the second time window to 0.9, and so on. The weight coefficients decrease linearly as the time window increases from the initial moment. For another example, the weight coefficient can be set to decrease exponentially as the time window increases from the initial moment, for example, the weight coefficient is 0.98 to the power of n, where n is the sequence number of the time window from the initial moment.

[0140] For each time window, an average weighted value of the turbidity change rate is calculated to obtain a value that better represents the overall level of the turbidity change rate within the time window. The average weighted value can be calculated by first calculating the average value of the turbidity change rate within the time window, and then multiplying the average value by the weight coefficient corresponding to the time window.

[0141] The average weighted value of the cumulative turbidity change rate of each time window refers to the accumulation of the average weighted values calculated from all time windows to obtain an overall evaluation index for comprehensively evaluating the dispersion stability performance of the suspension.

[0142] Specifically, this approach aims to more accurately assess dispersion stability performance. Rather than simply calculating the average turbidity change rate throughout the degradation process, it introduces the concepts of time windows and weighted averages to more accurately reflect the dynamic characteristics of dispersion stability over time.

[0143] First, the turbidity change rate time series is divided into multiple time windows according to the chronological order. This can decompose the entire degradation process into multiple stages for analysis and capture the characteristics of turbidity changes in different time periods.

[0144] Secondly, for each time window, the average weighted value of the turbidity change rate is calculated, and the weight coefficient is set so that the farther the time window is from the initial moment of the degradation process, the smaller the corresponding weight coefficient. The significance of this weighting method is that in the early stages of deterioration of the suspension dispersion stability, the turbidity change rate may be more sensitive and better reflect the potential instability factors of the dispersed system. Therefore, giving the early time window a higher weight can highlight the role of early degradation information in the comprehensive assessment. As the degradation process progresses, the turbidity change rate may tend to be flat, and the impact of the later changes on the overall stability is relatively weakened. Therefore, it is reasonable to reduce the weight of the later time window.

[0145] Finally, the weighted average values of the turbidity change rates for each parallel sample in each time window are added together to produce a comprehensive dispersion stability performance evaluation index. This index comprehensively considers the turbidity changes over different time periods and highlights the impact of early degradation. This allows for a more comprehensive and accurate assessment of the dispersion stability performance of the suspension concentrate, overcoming the shortcomings of simple averaging methods that may ignore important early degradation information. This makes the evaluation results more realistic and provides a more reliable basis for subsequent formulation optimization and quality control.

[0146] Through the above technical solution, the present application can more accurately evaluate the dispersion stability performance of the suspension concentrate, especially when the turbidity change rate tends to be flat in the later stage of the deterioration process, the impact of the early turbidity change rate on the dispersion stability is effectively highlighted, so that the evaluation results can be more in line with the actual situation and provide a more reliable basis for subsequent formula optimization and quality control.

[0147] In some embodiments, step A4 comprises:

[0148] A401. Obtain historical meteorological data for the intended use area and calculate the probability of occurrence of various environmental stress conditions in the intended use area based on the historical meteorological data;

[0149] A402. Convert the probability of occurrence of each environmental stress condition in the expected use area into a weight coefficient;

[0150] A403. Calculate the weighted average dispersion stability performance of each parallel sample based on its dispersion stability performance and the corresponding weight coefficient as the comprehensive dispersion stability performance of the suspending agent to be tested.

[0151] In step A401, the method for acquiring historical meteorological data can be referred to as step A201. Specifically, the probability of occurrence of environmental stress conditions can be calculated by statistically analyzing the frequency of occurrence of various environmental stress conditions in the historical meteorological data, and then dividing the frequency of occurrence of each environmental stress condition by the total number of observations to obtain the probability of occurrence of that environmental stress condition in the intended use area.

[0152] In step A402, the conversion of the probability of occurrence of environmental stress conditions to weight coefficients can adopt a linear mapping method, for example, the higher the probability of occurrence, the larger the weight coefficient, and vice versa; a nonlinear mapping method can also be adopted to emphasize or weaken the impact of certain specific environmental stress conditions.

[0153] Specifically, in step A403, the weighted average dispersion stability performance is calculated by multiplying the dispersion stability performance of the parallel samples under each environmental stress condition by the corresponding weight coefficient, and then adding all the products to obtain the weighted average dispersion stability performance, which is used as the comprehensive dispersion stability performance of the suspension to be tested.

[0154] Specifically, for the problem of comprehensive dispersion stability performance evaluation, a weighted average method based on the probability of occurrence of environmental stress conditions is proposed. Step A401 quantifies the possibility of different environmental stress conditions occurring in the area by analyzing the historical meteorological data of the expected use area, which provides an environmental background basis for the subsequent comprehensive evaluation. Step A402 converts these probabilities of occurrence into weight coefficients so that in the comprehensive evaluation, the environmental stress conditions that occur more frequently have a greater impact on the final result. Step A403 utilizes these weight coefficients to perform a weighted average calculation on the dispersion stability performance of each parallel sample under different environmental stress conditions to obtain the comprehensive dispersion stability performance of the suspension to be tested. Thus, the evaluation result is closer to the actual performance of the suspension to be tested in the actual application scenario, and improves the accuracy and practicality of the evaluation.

[0155] In some embodiments, in step A5, first, the dispersion stability performance of each parallel sample is used as the dependent variable, and the corresponding simulated irrigation water hardness, temperature and humidity are used as independent variables to construct a regression model; the regression model can be a multiple linear regression model or a nonlinear regression model; the regression model can introduce interaction terms, such as the interaction term between irrigation water hardness and temperature, the interaction term between temperature and humidity, etc., to analyze the impact of the interaction between environmental factors on the dispersion stability performance; regression analysis is performed based on the constructed regression model to obtain the regression coefficients of each environmental factor and the interaction term, wherein the absolute value of the regression coefficient can represent the degree of influence of the corresponding environmental factor or interaction term on the dispersion stability performance, and the larger the absolute value, the higher the influence level; finally, according to the size of the regression coefficient, the influence level of each environmental factor on the dispersion stability of the suspension to be tested is determined (for example, different influence levels are pre-set, and a corresponding regression coefficient range is set for each influence level, and the corresponding influence level is determined according to the regression coefficient range into which the calculated regression coefficient falls), and whether there is interaction and nonlinear influence between the environmental factors.

[0156] refer to Figure 2 The present application also proposes a herbicide suspension dispersion stability prediction and optimization system, which includes:

[0157] An environmental stress acceleration device 1 has multiple channels, each channel having independently adjustable environmental stress conditions, and each channel is used to accelerate the degradation of suspension dispersion stability on different parallel sample groups under different environmental stress conditions; the environmental stress conditions include temperature conditions and humidity conditions; the parallel sample groups are obtained by: diluting the suspension to be tested with simulated irrigation water of multiple different hardnesses to form multiple initial suspension samples; each initial suspension sample is divided into multiple parallel samples to form multiple parallel sample groups; each parallel sample group contains parallel samples corresponding to all simulated irrigation water hardnesses;

[0158] Turbidity detection device 2, used to measure the turbidity data of each parallel sample in real time during the degradation process;

[0159] Host computer 3 is used to perform the following steps:

[0160] According to the measured turbidity data, the turbidity change rate of each parallel sample is calculated to evaluate the dispersion stability performance of each parallel sample;

[0161] Evaluate the comprehensive dispersion stability performance of the suspension concentrate to be tested based on the dispersion stability performance of each parallel sample;

[0162] Based on the dispersion stability performance of each parallel sample and the corresponding simulated irrigation water hardness and environmental stress conditions, the influence level of each environmental factor on the dispersion stability of the suspension concentrate to be tested was analyzed; environmental factors include irrigation water hardness, temperature and humidity;

[0163] The output includes an evaluation report of the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance and the impact level of each environmental factor on the dispersion stability of the suspension agent to be tested.

[0164] Among them, the environmental stress acceleration device 1 is configured to have multiple independent channels, which can be independently adjusted in terms of temperature conditions and humidity conditions, so as to conduct accelerated degradation experiments on dispersion stability of parallel sample groups under different environmental stresses. The preparation method of the parallel sample group is as follows: first, the suspension to be tested is diluted with a variety of hardness simulated irrigation water to form a plurality of initial suspension samples; then, each initial suspension sample is divided into multiple parts and placed in different sample containers to form multiple parallel samples, and finally constitute a plurality of parallel sample groups. Each parallel sample group contains parallel samples corresponding to all hardness simulated irrigation water, so as to simulate the impact of changes in water hardness on the stability of the suspension in actual applications. The turbidity detection device 2 is configured to collect turbidity data of each parallel sample in real time during the suspension degradation experiment to monitor changes in the dispersion state of the suspension. The host computer 3 serves as a data processing and analysis center, and its functions are implemented as follows: first, based on the data collected by the turbidity detection device 2, the turbidity change rate of each parallel sample during the degradation process is calculated, and this rate is used as an indicator for evaluating the dispersion stability performance; then, the dispersion stability performance of each parallel sample is comprehensively evaluated to evaluate the overall dispersion stability of the suspension concentrate to be tested; then, based on the dispersion stability performance of each parallel sample and the experimental conditions (simulated irrigation water hardness, temperature and humidity), the degree of influence of these environmental factors on the dispersion stability of the suspension concentrate is analyzed, and the key influencing factors are determined; finally, the system generates an evaluation report, which covers the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance of the suspension concentrate to be tested, and the influence level of each environmental factor, providing data support for subsequent formula optimization.

[0165] Specifically, the system operates by simulating actual field conditions, accelerating the degradation of the dispersion stability of herbicide suspension concentrates and rapidly evaluating them. An environmental stress accelerator (1) provides a controlled temperature and humidity environment to simulate different climatic conditions. Diluting the suspension concentrate with simulated irrigation water of varying hardness simulates regional variations in water quality. During the experiment, a turbidity detection device (2) monitors the dispersion state of the suspension concentrate in real time. The rate of turbidity change reflects the dispersion stability of the suspension concentrate. A host computer (3) analyzes the turbidity data to quantify the dispersion stability performance and assess the impact of various environmental factors. This system rapidly obtains dispersion stability data for herbicide suspension concentrates under various environmental conditions, overcoming the time-consuming nature of traditional long-term storage experiments. This system provides a technical means for small pesticide companies to rapidly optimize their formulations and ensure product quality. By analyzing the impact levels of environmental factors, key factors influencing suspension concentrate stability can be identified, providing guidance for formulation improvements. The final evaluation report provides a basis for company decision-making and helps enhance product competitiveness.

[0166] The environmental stress acceleration device 1 may be a multi-channel constant temperature and humidity chamber, the turbidity detection device 2 may be an online turbidity meter, and the host computer 3 may be a personal computer, industrial computer, server or other device with computing capabilities.

[0167] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for estimating and optimizing the dispersion stability of a herbicide suspension concentrate, characterized in that: The method includes: A1. Dilute the suspension concentrate to be tested with simulated irrigation water of varying hardness to form multiple initial suspension concentrate samples. Divide each initial suspension concentrate sample into multiple replicates, forming multiple replicate groups; each replicate group contains replicates corresponding to the simulated irrigation water of all hardnesses. A2. Subject each parallel sample group to different environmental stress conditions to accelerate the degradation of the suspension concentrate dispersion stability. During the degradation process, the turbidity data of each parallel sample is measured in real time. Environmental stress conditions include temperature and humidity conditions. A3. Based on the measured turbidity data, calculate the turbidity change rate of each parallel sample to evaluate the dispersion stability performance of each parallel sample; A4. Evaluate the comprehensive dispersion stability performance of the suspension concentrate to be tested based on the dispersion stability performance of each parallel sample; A5. Analyze the impact of various environmental factors on the dispersion stability of the suspension concentrate under test based on the dispersion stability performance of each replicate sample and the corresponding simulated irrigation water hardness and environmental stress conditions. Environmental factors include irrigation water hardness, temperature, and humidity. A6. Output an evaluation report that includes the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance of the suspension concentrate to be tested, and the impact level of various environmental factors on the dispersion stability of the suspension concentrate to be tested; Step A2 includes: A201. Obtain historical meteorological data for the intended area of use, including temperature and humidity data; A202. Using a clustering algorithm, extract multiple typical environmental stress combinations from historical meteorological data; each typical environmental stress combination includes a temperature data set and a humidity data set; A203. Set the temperature and humidity of each channel of the environmental stress acceleration device so that the environmental stress conditions of each channel correspond to a typical environmental stress combination; A204. Place each parallel sample group in each channel of the environmental stress acceleration device to accelerate the deterioration of the suspension dispersion stability; A205. During the degradation process, the turbidity data of each parallel sample is measured in real time.

2. A method for estimating and optimizing the dispersion stability of a herbicide suspension according to claim 1, characterized in that: Step A1 includes: A101. Prepare simulated irrigation water of various hardness levels based on the common water quality range in the intended use area. A102. Dilute the suspension concentrate to target concentration using simulated irrigation water of varying hardness to obtain multiple initial suspension concentrate samples. A103. Measure each initial suspension concentrate sample and dispense it into multiple sample containers, with each sample container corresponding to a parallel sample, to form multiple parallel sample groups; each parallel sample group contains parallel samples corresponding to simulated irrigation water of all hardnesses.

3. A method for estimating and optimizing the dispersion stability of a herbicide suspension according to claim 1, characterized in that: Step A202 includes: B1. Perform cluster analysis on historical meteorological data using multiple clustering algorithms to obtain multiple clustering results; the clustering algorithms include K-means clustering algorithm, hierarchical clustering algorithm and DBSCAN clustering algorithm; B2. Evaluate multiple clustering results based on multiple evaluation indicators and select the optimal clustering result; the evaluation indicators include silhouette coefficient, Calinski-Harabasz index and Davies-Bouldin index; B3. Calculate the mean temperature and mean humidity in each cluster in the optimal clustering result to obtain the typical environmental stress combination of the corresponding cluster.

4. A method for estimating and optimizing the dispersion stability of a herbicide suspension concentrate according to claim 3, characterized in that: Step B1 includes: B101. Based on historical meteorological data, standardize temperature and humidity data to eliminate dimensional differences; B102. Use the elbow rule to determine the optimal number of clusters for the K-means clustering algorithm. Based on the determined optimal number of clusters, perform cluster analysis on the standardized historical meteorological data using the K-means clustering algorithm to generate multiple clusters and obtain the K-means clustering results. B103. For the hierarchical clustering algorithm, use the Wardlinkage method to calculate the inter-cluster distance, construct a hierarchical clustering dendrogram, and then segment the dendrogram into multiple clusters based on the set threshold or number of clusters to obtain the clustering results of the hierarchical clustering algorithm. B104. For the DBSCAN clustering algorithm, the grid search method is used to determine the neighborhood radius and minimum sample number parameters. Based on the determined neighborhood radius and minimum sample number parameters, the DBSCAN clustering algorithm is used to perform cluster analysis on historical meteorological data, generate multiple clusters, and obtain the DBSCAN algorithm clustering results.

5. A method for estimating and optimizing the dispersion stability of a herbicide suspension according to claim 3, characterized in that: Step B2 includes: B201. Calculate the silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index for each clustering result. B202. For each evaluation indicator, normalize and reciprocate the value to the interval [0, 1] to obtain the normalized evaluation indicator. B203. For each clustering result, perform a weighted summation of the normalized silhouette coefficient, normalized Calinski-Harabasz index, and normalized Davies-Bouldin index to obtain a comprehensive score. B204. Select the clustering result with the highest comprehensive score as the optimal clustering result.

6. A method for estimating and optimizing the dispersion stability of a herbicide suspension according to claim 1, characterized in that: Step A3 includes: A301. Extract turbidity data of each parallel sample at different time points to form a turbidity time series; A302. Calculate the turbidity change rate using the sliding window method for each turbidity time series; A303. For each parallel sample, calculate the average turbidity change rate of the entire degradation process based on the corresponding turbidity change rate calculation result, and convert it into a dispersion stability performance evaluation index.

7. A method for estimating and optimizing the dispersion stability of a herbicide suspension according to claim 6, characterized in that: Step A303 includes: For each parallel sample, the turbidity change rate time series is extracted and divided into multiple time windows according to the time sequence; For each time window, the average weighted value of the turbidity change rate is calculated; the farther the time window is from the initial moment of the degradation process, the smaller the corresponding weight coefficient; For each parallel sample, the average weighted value of the turbidity change rate in each time window was accumulated as an evaluation index of the dispersion stability performance.

8. The method for predicting and optimizing the dispersion stability of a herbicide suspension concentrate according to claim 1, wherein: Step A4 includes: A401. Obtain historical meteorological data for the intended use area and calculate the probability of occurrence of various environmental stress conditions in the intended use area based on the historical meteorological data; A402. Convert the probability of occurrence of each environmental stress condition in the expected use area into a weight coefficient; A403. Calculate the weighted average dispersion stability performance of each parallel sample based on its dispersion stability performance and the corresponding weight coefficient as the comprehensive dispersion stability performance of the suspending agent to be tested.

9. A herbicide suspension dispersion stability prediction and optimization system, characterized in that: The system includes: An environmental stress acceleration device has multiple channels, each channel having independently adjustable environmental stress conditions, each channel being used to accelerate the degradation of suspension dispersion stability on different parallel sample groups under different environmental stress conditions; the environmental stress conditions include temperature and humidity conditions; the parallel sample groups are obtained by: diluting the suspension to be tested with simulated irrigation water of multiple different hardnesses to form multiple initial suspension samples; each initial suspension sample is divided into multiple parallel samples to form multiple parallel sample groups; each parallel sample group contains parallel samples corresponding to the simulated irrigation water of all hardnesses; The environmental stress acceleration device accelerates the deterioration of the dispersion stability of the suspension agent on different parallel sample groups under different environmental stress conditions, specifically comprising: obtaining historical meteorological data of the expected use area, the historical meteorological data including temperature data and humidity data; using a clustering algorithm to extract multiple typical environmental stress combinations from the historical meteorological data; each typical environmental stress combination including a temperature data and a humidity data; setting the temperature and humidity of each channel so that the environmental stress condition of each channel corresponds to a typical environmental stress combination; and placing each parallel sample group in each channel to accelerate the deterioration of the dispersion stability of the suspension agent; Turbidity detection device, used to measure the turbidity data of each parallel sample in real time during the degradation process; The host computer is used to perform the following steps: According to the measured turbidity data, the turbidity change rate of each parallel sample is calculated to evaluate the dispersion stability performance of each parallel sample; Evaluate the comprehensive dispersion stability performance of the suspension concentrate to be tested based on the dispersion stability performance of each parallel sample; Based on the dispersion stability performance of each parallel sample and the corresponding simulated irrigation water hardness and environmental stress conditions, the influence level of each environmental factor on the dispersion stability of the suspension concentrate to be tested was analyzed; environmental factors include irrigation water hardness, temperature and humidity; The output includes an evaluation report of the dispersion stability performance of each parallel sample, the comprehensive dispersion stability performance and the impact level of each environmental factor on the dispersion stability of the suspension agent to be tested.

Images