Water absorption rate detection method and system for polymer water absorption material

Abstract

The invention discloses a water absorption rate detection method and system for a macromolecular water absorption material, and relates to the technical field of macromolecular water absorption materials.The water absorption rate detection method for the macromolecular water absorption material comprises the following steps that the initial weight of a to-be-tested macromolecular water absorption material sample is weighed; dropwise adding test liquid to the surface of the polymer water-absorbing material sample by using a burette; obtaining test feature data; factors influencing the water absorption performance of the polymer water absorption material are obtained; predicting key factors influencing the water absorption rate of the polymer water absorption material; and judging whether the water absorbing material meets a preset performance standard or not. Conditions of each experiment can be ensured to be consistent, so that repeatability and reliability of results are improved, the water absorption process can be accurately controlled by dropwise adding test liquid through a burette, the water absorption behavior of the material can be better understood, key factors are adjusted through an optimization algorithm, then the performance of the material can be improved, and the test accuracy is improved. And the preset performance standard is met.

Description

Technical Field

[0001] The present invention relates to the technical field of polymer water-absorbing materials, and in particular to a method and system for detecting water absorption rate of polymer water-absorbing materials. Background Art

[0002] Polymer absorbent materials, also known as super absorbent polymers (SAP), are a class of polymer materials with extremely high water absorption capacity. This material can absorb and retain water several times or even hundreds of times its own weight, but it will not dissolve in water. Polymer absorbent materials are mainly composed of polymers such as sodium polyacrylate, which form a three-dimensional network structure through cross-linking of the network structure, so that it quickly expands and forms a gel when it encounters water.

[0003] The applications of polymer water-absorbent materials are very wide. In the agricultural field, they are used to retain moisture in the soil, which can effectively reduce the frequency of irrigation and improve the drought resistance of crops. In personal hygiene products, such as diapers and sanitary napkins, the water-absorbent properties of these materials can quickly absorb and lock in liquids, keeping them dry and comfortable. In addition, they are widely used in the medical field, such as wound dressings, and as part of flood control and protection measures. A key feature of this type of material is the volume expansion after absorbing water. This means not only that they can hold a large amount of water, but also that they can maintain their original shape and structure to a certain extent. This property makes them very valuable in applications that require rapid absorption of liquids and long periods of time.

[0004] During the production process, it is necessary to test the speed and efficiency of polymer water-absorbing materials to absorb water under specific conditions, so as to evaluate their applicability and performance. Water absorption rate detection is particularly important for polymer water-absorbing materials used in personal hygiene products, medical supplies, agriculture, environmental protection and other fields. However, the existing water absorption rate detection method for polymer water-absorbing materials is not convenient for processing experimental data during the detection process, which increases the error and reduces the accuracy of experimental data. It is also not convenient to conduct in-depth analysis of test data, making it difficult to judge the factors affecting the water absorption performance of the material, and further, it is not convenient to accurately judge and adjust the key factors affecting the water absorption performance, which will severely limit the performance optimization of the material, resulting in quality fluctuations in the final product and inability to guarantee consistent performance.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes a method and system for detecting the water absorption rate of a polymer water-absorbing material, which solves the problem that the existing method for detecting the water absorption rate of a polymer water-absorbing material proposed in the above background technology is not convenient for processing experimental data during the detection process, which increases the probability of errors and reduces the accuracy of the experimental data, and is not convenient for in-depth analysis of the test data, making it difficult to judge the key factors affecting the water absorption performance of the material, and further making it difficult to accurately judge and adjust the key factors affecting the water absorption performance, so that the performance optimization of the material will be severely restricted, resulting in quality fluctuations in the final product and the problem that consistent performance cannot be guaranteed.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: According to one aspect of the present invention, a method for detecting the water absorption rate of a polymer water-absorbing material is provided, and the method for detecting the water absorption rate of a polymer water-absorbing material comprises the following steps: S1. Prepare a preset amount of test liquid and weigh the initial weight of the polymer water-absorbing material sample to be tested; S2. placing the polymer water-absorbing material sample on the support structure, and using a burette to drip a test liquid onto the surface of the polymer water-absorbing material sample; S3. Use automated tools to record test data during the experiment and pre-process the test data to obtain test feature data; S4. Analyze the obtained test characteristic data through an analysis algorithm to obtain factors that affect the water absorption performance of the polymer water-absorbing material; S5. Based on the factors affecting water absorption performance, a prediction model for water absorption rate is constructed, and key factors affecting the water absorption rate of polymer water-absorbing materials are predicted; S6. Optimize the key factors of water absorption rate through optimization algorithm to determine whether the water-absorbing material meets the preset performance standards.

[0008] Furthermore, the use of an automated tool to record the test data during the experiment and preprocessing the test data to obtain the test feature data includes the following steps: S31, obtaining test data during the experiment through sensors; S32, obtaining repeated data corresponding to the test data, and performing denoising, filtering and smoothing on the repeated data; S33, connecting the unprocessed data rows in the test data to generate a new data table, associating different data tables through external key values, generating a complete data table, and obtaining an accurate data set; S34. Extract features from the accurate data set and obtain test feature data.

[0009] Furthermore, the method of analyzing the obtained test characteristic data by an analysis algorithm to obtain the factors affecting the water absorption performance of the polymer water-absorbing material comprises the following steps: S41, mapping the obtained test feature data to a feature space using a spectral clustering method, and selecting a number of feature vectors to form a feature point set to be analyzed; S42, taking N cluster centers as initial solutions, setting a number of particle numbers and an optimal number of iterations, and randomly generating a number of initial solutions; S43, according to the current cluster center position, the fitness value of each particle is calculated by the fitness function, and the current fitness value is updated as the individual optimal value and the current position is updated as the individual optimal position, and the global optimal value and the global optimal position are found through the individual optimal values ​​of all particles; S44, judging whether the optimal number of iteration steps is reached, if reached, going to step S48, if not reached, continuing to update the speed and position of the particle; S45, according to the updated particle positions, each sample of the feature point set is assigned to N cluster centers according to the minimum distance principle; S46, recalculating the fitness value of the particle. If the fitness value of the particle is less than the individual best fitness value of the particle, then updating the individual best fitness value of the particle to the fitness value of the particle, and updating the individual best position of the particle to the current position; S47, compare the best fitness values ​​of all individual particles, find the minimum value as the global extreme value, and update the position of the global extreme value, and go to step S44; S48. After completing the iteration, the final clustering division is used as the factor affecting the water absorption performance of the polymer absorbent material.

[0010] Furthermore, the calculation formula of the fitness function is: ; in, M Expressed as the fitness value of the particle; fitness Expressed as fitness function; N pl For the p The cluster centers and l The distance between sample points; G is the feature point set; N Represents the cluster center.

[0011] Furthermore, the method of constructing a prediction model of water absorption rate based on the obtained factors affecting water absorption performance, and predicting the key factors affecting the water absorption rate of the polymer water-absorbing material comprises the following steps: S51, inputting an initial sample set including test characteristic data of polymer water-absorbing materials under different conditions; S52, classifying all test feature data in the initial sample set to obtain a number of sample subsets containing different key features; S53, performing a loop process on each sample subset, and obtaining a principal component coefficient matrix through principal component analysis; S54, rearranging the principal component coefficient matrix, and transforming the initial sample set based on the principal component coefficient matrix to generate a new test feature data sample; S55, training the prediction model based on the new test feature data sample to obtain a sub-model for predicting the water absorption performance of the polymer water-absorbing material, returning to step S52, and looping a preset number of times to obtain an integrated prediction model; S56, using the integrated prediction model to predict the new test sample set, and obtaining several prediction results; S57. Voting or weighting all prediction results to obtain key factors affecting the water absorption rate of the polymer water-absorbing material.

[0012] Furthermore, the loop processing is performed on each sample subset to obtain a principal component coefficient matrix through principal component analysis, which includes the following steps: S531, re-sampling the test feature data sample subset of the polymer water-absorbing material by using a self-help method to generate a new test feature data sample subset; S532, performing principal component analysis on the new test feature data sample subset, and obtaining a principal component coefficient vector related to water absorption performance; S533, repeatedly executing step S531 to step S532, processing different test feature data sample subsets, obtaining several groups of principal component coefficient vectors, and merging the principal component coefficient vectors into a principal component coefficient matrix.

[0013] Furthermore, the optimization of the key factors of the water absorption rate by the optimization algorithm and determining whether the water-absorbing material meets the preset performance standards include the following steps: S61, determining adjustable key factor parameters of the polymer water-absorbing material and setting an initial search range; S62, preset an initial value of the time counter, and preset the number of iterations as a termination condition of the optimization process; S63, continuously adjusting the key factor parameters affecting the water absorption rate through internal circulation, and updating the parameters according to a preset optimization strategy; S64. Use k-fold cross validation to evaluate the water absorption rate after each adjustment of the key factor parameters; S65. Calculate the fitness score of each iteration based on the evaluation result of the water absorption rate; S66, comparing the fitness score after each iteration with the score of the previous iteration, and selecting a better set of key factor parameters as the current best solution; S67, increasing the value of the time counter, and if the preset maximum number of iterations has been reached, terminating the optimization process; S68. Analyze the water absorption rate of the polymer water-absorbing material after the optimization process is completed, and compare it with the preset performance requirements of the water-absorbing material to determine whether the water-absorbing material meets the preset performance standards. If so, the water-absorbing material meets the standards, otherwise, continue to adjust or improve.

[0014] Further, the use of k-fold cross validation to evaluate the water absorption rate after each adjustment of the key factor parameters includes the following steps: S641, initializing the verification round number to the first round; S642, dividing the data set of polymer water-absorbing materials into several subsets, and in each round, selecting one subset as a test set, and the union of all the remaining subsets as a training set; S643, training the SVM model using the adjusted key factor parameters on the training set, and testing the performance of the SVM model on the test set; S644. Calculate the generalization error of the SVM model based on the actual performance of the polymer water-absorbing material on the test set; S645, looping step S641 to step S644 until each subset has been used as a test set; S646. Obtain an average value of the generalization errors calculated in all rounds as an overall evaluation of the water absorption rate of the polymer water-absorbing material under the adjusted key factor parameters.

[0015] Furthermore, the formula for calculating the generalization error of the SVM model is: ; in, e j Expressed as j The generalization error of the subsets; S j It is represented by the SVM model for the j The predicted values ​​of the subsets; Expressed as j The true value of the subset.

[0016] According to another aspect of the present invention, a water absorption rate detection system for a polymer water-absorbing material is provided. The water absorption rate detection system for a polymer water-absorbing material comprises: An experiment preparation module, used to prepare a preset amount of test liquid and weigh the initial weight of the polymer water-absorbing material sample to be tested; An experimental operation module, used for placing a polymer water-absorbing material sample on a supporting structure, and using a burette to drip a test liquid onto the surface of the polymer water-absorbing material sample; The data acquisition and processing module is used to use automated tools to record the test data during the experiment and pre-process the test data to obtain test feature data; A data analysis module is used to analyze the obtained test characteristic data through an analysis algorithm to obtain factors that affect the water absorption performance of the polymer water-absorbing material; A prediction model building module is used to build a prediction model of water absorption rate based on the factors affecting water absorption performance, and predict key factors affecting the water absorption rate of polymer water-absorbing materials; Data analysis and optimization module, used to optimize the key factors of water absorption rate through optimization algorithms to determine whether the water absorption material meets the preset performance standards; Among them, the experiment preparation module is connected with the data acquisition and processing module through the experiment operation module, the data acquisition and processing module is connected with the prediction model construction module through the data analysis module, and the prediction model construction module is connected with the data analysis and optimization module.

[0017] The beneficial effects of the present invention are: 1. The present invention can ensure that the conditions of each experiment are consistent by preparing a preset amount of test liquid and accurately weighing the sample, thereby improving the repeatability and reliability of the results, and using a burette to add the test liquid drop by drop, the water absorption process can be accurately controlled, so that the water absorption behavior of the material can be better understood. By preprocessing the experimental data, not only human errors are reduced, but also the efficiency and accuracy of data processing are improved. By applying an analysis algorithm to conduct an in-depth analysis of the test characteristic data, the factors affecting the water absorption performance of the material can be obtained, providing a scientific basis for material design and improvement. At the same time, a water absorption rate prediction model constructed based on the factors affecting the water absorption performance can predict key factors, avoid limiting the performance optimization of the material, resulting in quality fluctuations in the final product, and unable to guarantee consistent performance. By adjusting the key factors through the optimization algorithm, the performance of the material can be improved and ensured to meet the preset performance standards.

[0018] 2. This invention analyzes the obtained test feature data through an analysis algorithm, so that by using the spectral clustering method to map the test data to the feature space and selecting key feature vectors, the patterns and trends in the data can be captured more accurately, and the cluster centers can be optimized, which not only improves the quality of clustering, but also ensures more effective data segmentation. Through the use of the fitness function, the algorithm can be dynamically adjusted according to the characteristics of the data, thereby improving the flexibility and adaptability of the algorithm.

[0019] 3. This invention constructs a prediction model for water absorption rate, which makes it possible to effectively process and analyze a large amount of test data obtained under different conditions, so as to fully understand the water absorption performance of the material. Through classification and principal component analysis, the key features that affect the water absorption performance are accurately identified, thereby improving the accuracy of the prediction. In addition, the ensemble learning method combining multiple sub-models improves the prediction performance, reduces the deviation and variance of a single model, and further accurately predicts and identifies the key factors that affect the water absorption rate.

[0020] 4. The invention optimizes the key factors of water absorption rate through an optimization algorithm, so that by determining the adjustable key factor parameters and setting the search range, the factors affecting the water absorption rate can be accurately optimized to seek the best material performance, and the water absorption rate is evaluated after each parameter adjustment by using k-fold cross validation, so that the effect of each adjustment can be fed back in time, and the reliability and stability of the evaluation results are guaranteed. By calculating the generalization error of the SVM model and taking the average value, the model performance after parameter adjustment can be comprehensively evaluated, ensuring the reliability and generalization ability of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 is a flow chart of a method for detecting water absorption rate of a polymer water-absorbing material according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a water absorption rate detection system for polymer water-absorbing materials according to an embodiment of the present invention.

[0023] In the figure: 1. Experimental preparation module; 2. Experimental operation module; 3. Data acquisition and processing module; 4. Data analysis module; 5. Prediction model construction module; 6. Data analysis and optimization module. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0025] In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0026] According to an embodiment of the present invention, a method and system for detecting the water absorption rate of a polymer water-absorbing material are provided.

[0027] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the water absorption rate detection method for polymer water-absorbing materials according to an embodiment of the present invention, the water absorption rate detection method for polymer water-absorbing materials comprises the following steps: S1. Prepare a preset amount of test liquid (e.g., distilled water or a specific chemical solution, etc.), and weigh the initial weight of the polymer water-absorbing material sample to be tested; S2. placing the polymer water-absorbing material sample on the support structure, and using a burette to drip a test liquid onto the surface of the polymer water-absorbing material sample; Specifically, the support structure refers to a device or platform for placing a sample of a polymer water-absorbing material for testing.

[0028] S3. Use automated tools (such as sensors or data recording software) to record test data during the experiment and pre-process the test data to obtain test feature data; Specifically, the test data includes time series data (recorded data changing over time, for example, when testing polymer water-absorbing materials, the amount of water absorbed by the material changing over time will be recorded), sensor readings (data collected by various sensors, such as temperature sensors, humidity sensors, pressure sensors, etc.), measurements of physical or chemical properties (such as weight, volume, concentration, pH value, etc., the data are usually obtained through special experimental instruments), image or video data (in some experiments, image capture or video recording is used to capture the experimental process, such as changes in the morphology and color of the material), operating parameters (various parameters set during the experiment, such as experimental temperature, drip acceleration rate, stirring speed, etc.), environmental data (relevant data of the environment during the experiment, such as ambient temperature, humidity, air pressure, etc.) and equipment status information (status data of experimental equipment, such as the switch status and operating status of the equipment), etc.

[0029] Specifically, the test feature data includes key indicators (for example, for chemical experiments, it may include reaction rate, changes in substance concentration, changes in pH value, etc.), statistical characteristics (such as mean, median, variance, standard deviation, etc.), time series characteristics (in time-dependent experiments, it may include peak time, time to reach steady state, periodic characteristics of time series, etc.), frequency characteristics (if the data contains periodic changes or repetitive patterns, such as vibration frequency, waveform characteristics, etc.), etc.

[0030] S4. Analyze the obtained test characteristic data through an analysis algorithm to obtain factors that affect the water absorption performance of the polymer water-absorbing material; Specifically, water absorption performance refers to dimensions such as water absorption amount, water absorption rate, and stability after water absorption.

[0031] Specifically, the factors affecting the water absorption performance of polymer water-absorbing materials include the degree of cross-linking (although similar to the cross-linking density in the key factor of water absorption rate, in terms of water absorption performance, the degree of cross-linking mainly affects the expansion capacity and stability of the material, not just the rate), the type and number of hydrophilic groups (the type and number of hydrophilic groups in the material will directly affect its water absorption, because the interaction between these groups and water molecules determines the water absorption capacity), chemical stability (the chemical stability of the material when exposed to water for a long time, including whether it is prone to hydrolysis or chemical degradation, directly affects the durability of its water absorption performance), thermal stability (the stability of the material at different temperatures, especially under high temperature conditions, may affect its water absorption capacity, especially for those materials used in high temperature applications), compression resistance and resilience (after absorbing water, the compression resistance and resilience of the material determine its performance under load), biodegradability (such as agricultural and medical applications, the biodegradability of the material is an important consideration because it affects the environmental impact and service life of the material), hydrophilic / hydrophobic balance (the overall hydrophilicity or hydrophobicity balance of the material, which affects its ability to absorb and retain water), etc.

[0032] S5. Based on the factors affecting water absorption performance, a prediction model for water absorption rate is constructed, and key factors affecting the water absorption rate of polymer water-absorbing materials are predicted; Specifically, the key factors include chemical composition and cross-linking density (the basic chemical structure of the material, such as the type of monomers used, the proportion and type of copolymers, and the cross-linking density, all directly affect its water absorption rate), physical structure characteristics (including porosity, pore size and distribution, and surface area. The pore structure is particularly critical because it determines the penetration and diffusion rate of water molecules in the material), environmental factors (environmental factors such as temperature, pH value, and ion concentration in the solution can significantly affect the water absorption rate. For example, different pH values ​​may change the hydrophilicity or hydrophobicity of the polymer material, thereby affecting the water absorption rate), preparation process (synthesis method, curing conditions, such as temperature and time, etc., the preparation process will affect the microstructure and water absorption characteristics of the final product, thereby affecting the water absorption rate), mechanical properties (the mechanical properties of the material such as strength and elasticity may affect its behavior during water absorption, such as volume expansion or contraction), external stress or pressure (in some cases, changes in external stress or pressure may also affect the water absorption performance of the material) and aging or stability (the long-term stability and anti-aging properties of the material are also important factors, and long-term use may affect its water absorption performance).

[0033] S6. Optimize the key factors of water absorption rate through optimization algorithm to determine whether the water-absorbing material meets the preset performance standards.

[0034] Specifically, performance standards refer to a series of predefined indicators or criteria used to evaluate and confirm whether the absorbent material meets specific performance requirements.

[0035] Specifically, the performance standards include water absorption rate (this is an indicator of how much water a material can absorb in a certain period of time), maximum water absorption (the maximum amount of water a material can absorb, usually measured by weight or volume ratio), water retention capacity (that is, the ability of a material to retain water under certain conditions), reusability (if the material is expected to be reused, its ability to recover during multiple water absorption and release processes is an important criterion), biocompatibility and environmental impact (the biocompatibility of the material and its impact on the environment are also important performance indicators), mechanical strength (the strength and durability of the material in the absorbed state), etc.

[0036] Preferably, the method of using an automated tool to record the test data during the experiment and preprocessing the test data to obtain the test characteristic data comprises the following steps: S31, obtaining test data during the experiment through sensors; S32, obtaining repeated data corresponding to the test data, and performing denoising, filtering and smoothing on the repeated data; S33, connecting the unprocessed data rows in the test data to generate a new data table, associating different data tables through external key values, generating a complete data table, and obtaining an accurate data set; S34. Extract features from the accurate data set and obtain test feature data.

[0037] Preferably, the step of analyzing the obtained test characteristic data by an analysis algorithm to obtain the factors affecting the water absorption performance of the polymer water-absorbing material comprises the following steps: S41, mapping the obtained test feature data to a feature space using a spectral clustering method, and selecting a number of feature vectors to form a feature point set to be analyzed; Specifically, Spectral Clustering is a clustering algorithm based on graph theory, which performs well in dealing with complex and nonlinearly separable data sets. The basic idea of ​​spectral clustering is to use the similarity of data to construct a graph, and then perform clustering based on the eigendecomposition of the graph. The core idea of ​​spectral clustering is to use the global structural information of the data for clustering. In some cases, traditional clustering methods (such as k-means) cannot correctly divide complex or nonlinearly separable data sets. Spectral clustering solves this problem by considering the relationship between data points (rather than just the distance between them), so that groups can be effectively identified even in complex data structures.

[0038] S42, taking N cluster centers as initial solutions, setting a number of particle numbers and an optimal number of iterations, and randomly generating a number of initial solutions; S43, according to the current cluster center position, the fitness value of each particle is calculated by the fitness function, and the current fitness value is updated as the individual optimal value and the current position is updated as the individual optimal position, and the global optimal value and the global optimal position are found through the individual optimal values ​​of all particles; S44, judging whether the optimal number of iteration steps is reached, if reached, going to step S48, if not reached, continuing to update the speed and position of the particle; S45, according to the updated particle positions, each sample of the feature point set is assigned to N cluster centers according to the minimum distance principle; Specifically, the working principle of the minimum distance principle is: Define the distance metric: First decide on the method used to calculate the distance, usually Euclidean distance, but it could be Manhattan distance, cosine similarity, or another suitable metric.

[0039] Determine cluster centers: At the beginning of the clustering process, determine a set of initial cluster centers.

[0040] Calculate distance and assign data points: For each sample point in the feature point set, calculate its distance from all cluster centers and assign it to the nearest cluster center.

[0041] Update cluster centers: After all data points have been assigned, update the center position of each cluster based on the average position of the data points to which they belong (or other criteria).

[0042] Repeated iteration: Repeat the process of calculating distance and updating cluster centers until certain convergence conditions are met.

[0043] S46, recalculating the fitness value of the particle. If the fitness value of the particle is less than the individual best fitness value of the particle, then updating the individual best fitness value of the particle to the fitness value of the particle, and updating the individual best position of the particle to the current position; S47, compare the best fitness values ​​of all individual particles, find the minimum value as the global extreme value, and update the position of the global extreme value, and go to step S44; S48. After completing the iteration, the final clustering division is used as the factor affecting the water absorption performance of the polymer absorbent material.

[0044] Specifically, clustering refers to identifying and classifying various factors that affect the water absorption properties of polymer absorbent materials.

[0045] Preferably, the calculation formula of the fitness function is: ; in, M Expressed as the fitness value of the particle; fitness Expressed as fitness function; N pl For the p The cluster centers and l The distance between sample points; G is the feature point set; N Represents the cluster center.

[0046] Specifically, the analysis algorithm is a particle swarm optimization clustering algorithm based on feature analysis. The algorithm is mainly divided into two steps: first, the sample points to be divided are mapped to the feature space using the spectral clustering method to form a feature point set, and then the PSO algorithm is used to cluster in the feature space.

[0047] Preferably, the method of constructing a prediction model of water absorption rate based on the obtained factors affecting water absorption performance, and predicting key factors affecting the water absorption rate of the polymer water-absorbing material comprises the following steps: S51, inputting an initial sample set including test characteristic data of polymer water-absorbing materials under different conditions; S52, classifying all test feature data in the initial sample set to obtain a number of sample subsets containing different key features; S53, performing a loop process on each sample subset, and obtaining a principal component coefficient matrix through principal component analysis; S54, rearranging the principal component coefficient matrix, and transforming the initial sample set based on the principal component coefficient matrix to generate a new test feature data sample; S55, training the prediction model based on the new test feature data sample to obtain a sub-model for predicting the water absorption performance of the polymer water-absorbing material, returning to step S52, and looping a preset number of times to obtain an integrated prediction model; S56, using the integrated prediction model to predict the new test sample set, and obtaining several prediction results; S57. Voting or weighting all prediction results to obtain key factors affecting the water absorption rate of the polymer water-absorbing material.

[0048] Specifically, the analysis algorithm is a heterogeneous multi-classifier integration algorithm. First, the rotating forest is used to transform and divide the original sample set to obtain a new sample set. Then, a support vector machine with high classification accuracy or a kernel matching pursuit with fast classification speed is selected as the basic integrated individual classifier through a specific proportion, and the new sample set is classified to obtain its prediction label. Finally, the prediction labels under the two models are combined. By combining two different classifier models, the algorithm achieves the complementarity of accuracy and speed, and improves the generalization error of the integrated system after the mixed integration of the two.

[0049] Preferably, performing a loop process on each sample subset to obtain a principal component coefficient matrix by principal component analysis comprises the following steps: S531, re-sampling the test feature data sample subset of the polymer water-absorbing material by using a self-help method to generate a new test feature data sample subset; Specifically, the bootstrap method resampling the sample subset means: randomly extracting some samples with replacement from the optimized motor drive performance parameter sample set to form a new sample subset. On this sample subset, continue to randomly extract samples with replacement to form a second sample subset. This resampling process is repeated several times to obtain multiple new sample subsets. On these newly generated sample subsets, search for test feature data combinations. These test feature data constitute a new test feature data sample subset.

[0050] S532, performing principal component analysis on the new test feature data sample subset, and obtaining a principal component coefficient vector related to water absorption performance; S533, repeatedly executing step S531 to step S532, processing different test feature data sample subsets, obtaining several groups of principal component coefficient vectors, and merging the principal component coefficient vectors into a principal component coefficient matrix.

[0051] Preferably, the optimization of the key factors of the water absorption rate by an optimization algorithm and determining whether the water-absorbing material meets the preset performance standards include the following steps: S61, determining adjustable key factor parameters of the polymer water-absorbing material and setting an initial search range; Specifically, the adjustable key factor parameters include the cross-linking density of the polymer chain (the cross-linking density affects the mechanical strength and water absorption capacity of the material. Too high a cross-linking density may limit the water absorption, while too low a cross-linking density may cause an unstable material structure), monomer composition (different monomers may affect the water absorption rate and the maximum water absorption amount. For example, monomers containing hydrophilic groups usually increase the water absorption capacity), surface modification (surface properties, such as hydrophilicity or hydrophobicity, can be adjusted by chemical modification to affect the interaction between the material and water), thickness and shape (physical parameters will affect the water absorption capacity and performance of the material), type and proportion of additives (certain additives, such as plasticizers and stabilizers, can change the physical and chemical properties of the material, thereby affecting its water absorption), temperature and pH sensitivity (certain polymer materials can be designed to change their water absorption capacity at specific temperatures or pH values), etc.

[0052] S62, preset an initial value of the time counter (usually 0 or 1), and preset the number of iterations as a termination condition of the optimization process; Specifically, a time counter is a counting variable used to track the iteration process in an algorithm or program. In optimization and computational tasks, a time counter is used to monitor the number of iterations that an algorithm has executed and decide when to stop the iteration process.

[0053] Specifically, the termination conditions include that the time recorded by the time counter reaches a preset maximum value and the number of iterations of the optimization algorithm reaches a preset maximum number.

[0054] S63, continuously adjusting the key factor parameters affecting the water absorption rate through internal circulation, and updating the parameters according to a preset optimization strategy; Specifically, the inner loop: adjust the performance parameters according to a certain strategy, calculate the objective function, and determine whether the parameters need to be updated. This cyclic process is called the inner loop.

[0055] S64. Use k-fold cross validation to evaluate the water absorption rate after each adjustment of the key factor parameters; Specifically, k-fold cross validation is a machine learning model evaluation method, which refers to dividing the collected motor drive performance data into k subsets, one of which is used as a validation set and the remaining k-1 subsets are used as training sets.

[0056] S65. Calculate the fitness score of each iteration based on the evaluation result of the water absorption rate; S66, comparing the fitness score after each iteration with the score of the previous iteration, and selecting a better set of key factor parameters as the current best solution; S67, increasing the value of the time counter, and if the preset maximum number of iterations has been reached, terminating the optimization process; S68. Analyze the water absorption rate of the polymer water-absorbing material after the optimization process is completed, and compare it with the preset performance requirements of the water-absorbing material to determine whether the water-absorbing material meets the preset performance standards. If so, the water-absorbing material meets the standards, otherwise, continue to adjust or improve.

[0057] Preferably, the use of k-fold cross validation to evaluate the water absorption rate after each adjustment of the key factor parameters comprises the following steps: S641, initializing the verification round number to the first round; S642, dividing the data set of polymer water-absorbing materials into several subsets, and in each round, selecting one subset as a test set, and the union of all the remaining subsets as a training set; S643, training the SVM model using the adjusted key factor parameters on the training set, and testing the performance of the SVM model on the test set; S644. Calculate the generalization error of the SVM model based on the actual performance of the polymer water-absorbing material on the test set; Specifically, generalization error is an important indicator for evaluating the generalization ability of machine learning models. It reflects the prediction error of the model on new data that has not been seen.

[0058] Specifically, calculating the generalization error of the SVM model refers to calculating the prediction error of the SVM model on the test set.

[0059] S645, looping step S641 to step S644 until each subset has been used as a test set; S646. Obtain an average value of the generalization errors calculated in all rounds as an overall evaluation of the water absorption rate of the polymer water-absorbing material under the adjusted key factor parameters.

[0060] Preferably, the formula for calculating the generalization error of the SVM model is: ; in, e j Expressed as j The generalization error of the subsets; S j It is represented by the SVM model for the j The predicted values ​​of the subsets; Expressed as j The true value of the subset.

[0061] Specifically, the optimization algorithm is an SVM parameter selection method based on an improved bird flock optimization algorithm, which is a strategy for applying a nature-inspired algorithm to machine learning parameter optimization. In this method, an improved bird flock optimization algorithm is used to select or optimize the parameters of the SVM to improve the performance of the model.

[0062] Specifically, SVM is a supervised learning algorithm based on the principle of structural risk minimization. It uses expected risk minimization as the evaluation criterion and aims to obtain a decision function with high generalization ability through finite sample training, that is, to find an optimal hyperplane to completely separate the samples under the condition of linear separability.

[0063] Specifically, the improved bird flock optimization algorithm refers to the improvement and variant of the traditional particle swarm optimization algorithm (Particle Swarm Optimization, PSO). The particle swarm optimization algorithm is an optimization technology based on swarm intelligence, which simulates the social behavior of bird flocks or fish schools to solve optimization problems.

[0064] Specifically, the improved bird flock optimization algorithm includes the following improvements: Improvements in speed and position update rules: In standard PSO, the movement of particles is based on their best historical position and the best position of the entire group. Improved algorithms may use different rules to adjust the speed and position of particles to improve convergence speed and avoid falling into local optimality.

[0065] Parameter adjustment and control: Improved algorithms may include dynamic adjustment mechanisms for PSO parameters such as inertia weight, individual best and group best learning factors to balance exploration (global search) and exploitation (local search) during the search process.

[0066] Customization to adapt to specific problems: For specific types of problems (such as nonlinear problems, multi-objective problems, etc.), the improved bird flock optimization algorithm may be specially designed to solve these problems more effectively.

[0067] According to another embodiment of the present invention, Figure 2As shown, a water absorption rate detection system for a polymer water-absorbing material is also provided, and the water absorption rate detection system for a polymer water-absorbing material comprises: Experiment preparation module 1, used to prepare a preset amount of test liquid and weigh the initial weight of the polymer water-absorbing material sample to be tested; Experimental operation module 2 is used to place the polymer water-absorbing material sample on the support structure, and use a burette to drip a test liquid onto the surface of the polymer water-absorbing material sample; The data acquisition and processing module 3 is used to use an automated tool to record the test data during the experiment and pre-process the test data to obtain test feature data; The data analysis module 4 is used to analyze the obtained test characteristic data through an analysis algorithm to obtain factors affecting the water absorption performance of the polymer water-absorbing material; A prediction model building module 5 is used to build a prediction model of water absorption rate based on the factors affecting water absorption performance, and predict key factors affecting the water absorption rate of the polymer water-absorbing material; Data analysis and optimization module 6, used to optimize the key factors of water absorption rate through optimization algorithm, and determine whether the water absorption material meets the preset performance standards; Among them, the experiment preparation module 1 is connected with the data acquisition and processing module 3 through the experiment operation module 2, the data acquisition and processing module 3 is connected with the prediction model construction module 5 through the data analysis module 4, and the prediction model construction module 5 is connected with the data analysis and optimization module 6.

[0068] In summary, with the aid of the above technical solution of the present invention, the present invention analyzes the obtained test feature data through an analysis algorithm, so that by using the spectral clustering method to map the test data to the feature space and selecting the key feature vector, the patterns and trends in the data can be captured more accurately, and the cluster centers are optimized, which not only improves the quality of clustering, but also ensures more effective data segmentation. Through the use of the fitness function, the algorithm can be dynamically adjusted according to the characteristics of the data, thereby improving the flexibility and adaptability of the algorithm. The present invention constructs a prediction model for water absorption rate, so that a large amount of test data obtained under different conditions can be effectively processed and analyzed, so as to fully understand the water absorption performance of the material, and through grade division and principal component analysis, the key features that affect the water absorption performance are accurately identified, the accuracy of the prediction is improved, and the integrated learning method combined with multiple sub-models improves the prediction performance, reduces the deviation and variance of a single model, and then accurately predicts and identifies the key factors that affect the water absorption rate. The invention optimizes the key factors of water absorption rate through an optimization algorithm, so that by determining the adjustable key factor parameters and setting the search range, the factors affecting the water absorption rate can be accurately optimized to seek the best material performance, and the water absorption rate is evaluated after each parameter adjustment by using k-fold cross validation, so that the effect of each adjustment can be fed back in time, and the reliability and stability of the evaluation results are guaranteed. By calculating the generalization error of the SVM model and taking the average value, the model performance after parameter adjustment can be comprehensively evaluated, ensuring the reliability and generalization ability of the prediction results.

[0069] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting the water absorption rate of a polymer water-absorbing material, characterized in that: The water absorption rate detection method for polymer water-absorbing materials comprises the following steps: S1. Prepare a preset amount of test liquid and weigh the initial weight of the polymer water-absorbing material sample to be tested; S2. placing the polymer water-absorbing material sample on the support structure, and using a burette to drip a test liquid onto the surface of the polymer water-absorbing material sample; S3. Use automated tools to record test data during the experiment and pre-process the test data to obtain test feature data; S4. Analyze the obtained test characteristic data through an analysis algorithm to obtain factors that affect the water absorption performance of the polymer water-absorbing material; S5. Based on the factors affecting water absorption performance, a prediction model for water absorption rate is constructed, and key factors affecting the water absorption rate of polymer water-absorbing materials are predicted; S6. Optimize the key factors of water absorption rate through optimization algorithm to determine whether the water-absorbing material meets the preset performance standards.

2. A method for detecting water absorption rate of a polymer water-absorbing material according to claim 1, characterized in that: The method of using an automated tool to record the test data during the experiment and preprocessing the test data to obtain the test feature data includes the following steps: S31, obtaining test data during the experiment through sensors; S32, obtaining repeated data corresponding to the test data, and performing denoising, filtering and smoothing on the repeated data; S33, connecting the unprocessed data rows in the test data to generate a new data table, associating different data tables through external key values, generating a complete data table, and obtaining an accurate data set; S34. Extract features from the accurate data set and obtain test feature data.

3. A method for detecting water absorption rate of a polymer water-absorbing material according to claim 1, characterized in that: The method of analyzing the obtained test characteristic data by an analysis algorithm to obtain the factors affecting the water absorption performance of the polymer water-absorbing material comprises the following steps: S41, mapping the obtained test feature data to a feature space using a spectral clustering method, and selecting a number of feature vectors to form a feature point set to be analyzed; S42, taking N cluster centers as initial solutions, setting a number of particle numbers and an optimal number of iterations, and randomly generating a number of initial solutions; S43, according to the current cluster center position, the fitness value of each particle is calculated by the fitness function, and the current fitness value is updated as the individual optimal value and the current position is updated as the individual optimal position, and the global optimal value and the global optimal position are found through the individual optimal values ​​of all particles; S44, judging whether the optimal number of iteration steps is reached, if reached, going to step S48, if not reached, continuing to update the speed and position of the particle; S45, according to the updated particle positions, each sample of the feature point set is assigned to N cluster centers according to the minimum distance principle; S46, recalculating the fitness value of the particle. If the fitness value of the particle is less than the individual best fitness value of the particle, then updating the individual best fitness value of the particle to the fitness value of the particle, and updating the individual best position of the particle to the current position; S47, compare the best fitness values ​​of all individual particles, find the minimum value as the global extreme value, and update the position of the global extreme value, and go to step S44; S48. After completing the iteration, the final clustering division is used as the factor affecting the water absorption performance of the polymer absorbent material.

4. A method for detecting water absorption rate of polymer water-absorbing materials according to claim 3, characterized in that: The calculation formula of the fitness function is: ； in, M Expressed as the fitness value of the particle; fitness Expressed as fitness function; N pl For the p The cluster centers and l The distance between sample points; G is the feature point set; N Represents the cluster center.

5. A method for detecting water absorption rate of polymer water-absorbing materials according to claim 1, characterized in that: The method of constructing a prediction model of water absorption rate based on the factors affecting water absorption performance and predicting the key factors affecting the water absorption rate of the polymer water-absorbing material comprises the following steps: S51, inputting an initial sample set including test characteristic data of polymer water-absorbing materials under different conditions; S52, classifying all test feature data in the initial sample set to obtain a number of sample subsets containing different key features; S53, performing a loop process on each sample subset, and obtaining a principal component coefficient matrix through principal component analysis; S54, rearranging the principal component coefficient matrix, and transforming the initial sample set based on the principal component coefficient matrix to generate a new test feature data sample; S55, training the prediction model based on the new test feature data sample to obtain a sub-model for predicting the water absorption performance of the polymer water-absorbing material, returning to step S52, and looping a preset number of times to obtain an integrated prediction model; S56, using the integrated prediction model to predict the new test sample set, and obtaining several prediction results; S57. Voting or weighting all prediction results to obtain key factors affecting the water absorption rate of the polymer water-absorbing material.

6. A method for detecting water absorption rate of a polymer water-absorbing material according to claim 5, characterized in that: The loop processing is performed on each sample subset to obtain a principal component coefficient matrix through principal component analysis, comprising the following steps: S531, re-sampling the test feature data sample subset of the polymer water-absorbing material by using a self-help method to generate a new test feature data sample subset; S532, performing principal component analysis on the new test feature data sample subset, and obtaining a principal component coefficient vector related to water absorption performance; S533, repeatedly executing step S531 to step S532, processing different test feature data sample subsets, obtaining several groups of principal component coefficient vectors, and merging the principal component coefficient vectors into a principal component coefficient matrix.

7. A method for detecting water absorption rate of polymer water-absorbing materials according to claim 1, characterized in that: The optimization algorithm is used to optimize the key factors of the water absorption rate, and judging whether the water-absorbing material meets the preset performance standards includes the following steps: S61, determining adjustable key factor parameters of the polymer water-absorbing material and setting an initial search range; S62, preset an initial value of the time counter, and preset the number of iterations as a termination condition of the optimization process; S63, continuously adjusting the key factor parameters affecting the water absorption rate through internal circulation, and updating the parameters according to a preset optimization strategy; S64. Use k-fold cross validation to evaluate the water absorption rate after each adjustment of the key factor parameters; S65. Calculate the fitness score of each iteration based on the evaluation result of the water absorption rate; S66, comparing the fitness score after each iteration with the score of the previous iteration, and selecting a better set of key factor parameters as the current best solution; S67, increasing the value of the time counter, and if the preset maximum number of iterations has been reached, terminating the optimization process; S68. Analyze the water absorption rate of the polymer water-absorbing material after the optimization process is completed, and compare it with the preset performance requirements of the water-absorbing material to determine whether the water-absorbing material meets the preset performance standards. If so, the water-absorbing material meets the standards, otherwise, continue to adjust or improve.

8. A method for detecting water absorption rate of polymer water-absorbing materials according to claim 7, characterized in that: The k-fold cross validation is used to evaluate the water absorption rate after each adjustment of the key factor parameters, including the following steps: S641, initializing the verification round number to the first round; S642, dividing the data set of polymer water-absorbing materials into several subsets, and in each round, selecting one subset as a test set, and the union of all the remaining subsets as a training set; S643, training the SVM model using the adjusted key factor parameters on the training set, and testing the performance of the SVM model on the test set; S644. Calculate the generalization error of the SVM model based on the actual performance of the polymer water-absorbing material on the test set; S645, looping step S641 to step S644 until each subset has been used as a test set; S646. Obtain an average value of the generalization errors calculated in all rounds as an overall evaluation of the water absorption rate of the polymer water-absorbing material under the adjusted key factor parameters.

9. A method for detecting water absorption rate of polymer water-absorbing materials according to claim 8, characterized in that: The formula for calculating the generalization error of the SVM model is: ； in, e j Expressed as j The generalization error of the subsets; S j It is represented by the SVM model for the j The predicted values ​​of the subsets; Expressed as j The true value of the subset.

10. A water absorption rate detection system for polymer water-absorbing materials, used to implement the water absorption rate detection method for polymer water-absorbing materials according to any one of claims 1 to 9, characterized in that: The water absorption rate detection system for polymer water-absorbing materials comprises: An experiment preparation module, used to prepare a preset amount of test liquid and weigh the initial weight of the polymer water-absorbing material sample to be tested; An experimental operation module, used for placing a polymer water-absorbing material sample on a supporting structure, and using a burette to drip a test liquid onto the surface of the polymer water-absorbing material sample; The data acquisition and processing module is used to use automated tools to record the test data during the experiment and pre-process the test data to obtain test feature data; A data analysis module is used to analyze the obtained test characteristic data through an analysis algorithm to obtain factors that affect the water absorption performance of the polymer water-absorbing material; A prediction model building module is used to build a prediction model of water absorption rate based on the factors affecting water absorption performance, and predict key factors affecting the water absorption rate of polymer water-absorbing materials; Data analysis and optimization module, used to optimize the key factors of water absorption rate through optimization algorithms to determine whether the water absorption material meets the preset performance standards; Among them, the experiment preparation module is connected with the data acquisition and processing module through the experiment operation module, the data acquisition and processing module is connected with the prediction model construction module through the data analysis module, and the prediction model construction module is connected with the data analysis and optimization module.

Images