Method and system for evaluating performance data of rubber material

Abstract

The invention relates to the technical field of data evaluation processing, in particular to a rubber material performance data evaluation method and system. The method comprises the following steps: acquiring original data of a rubber material; performing data preprocessing on the rubber material original data to obtain standard rubber material data; performing physicochemical characteristic identification on the standard rubber material data to obtain material physicochemical characteristic data; and performing rubber working condition scene matching on the standard rubber material data to obtain rubber working condition scene data. Through a data processing technology, an analogue simulation technology and a data evaluation technology, physicochemical feature recognition is carried out on standard rubber material data, material multi-factor coupling simulation is carried out, and a rubber material performance evaluation model is constructed so as to carry out performance evaluation on a rubber material; therefore, the performance of the rubber material in the multi-working-condition scene can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of data evaluation and processing, and in particular to a method and system for evaluating performance data of a rubber material. Background Art

[0002] In the early days, the evaluation of rubber material performance mainly relied on static tests in the laboratory, such as conventional mechanical property tests such as hardness. Although these test methods can provide certain performance data, they cannot simulate the dynamic changes in actual use scenarios. With the improvement of the performance requirements for rubber materials, researchers began to try to simulate actual use scenarios for performance evaluation, such as by constructing a sole-road stress environment model to simulate the stress conditions of sports shoe soles in actual use. However, there are obvious deficiencies in simulating complex working conditions in actual use. Rubber is often faced with the combined effects of multiple factors in actual use, such as dynamic impact, temperature changes, humidity effects, chemical corrosion and mechanical vibrations. However, most of the existing evaluation methods can only simulate a single factor and lack effective integration and comprehensive evaluation of multi-dimensional performance data, resulting in the inability to fully reflect the overall performance of rubber and it is difficult to accurately judge the comprehensive performance of rubber in actual use. In addition, the existing technology has difficulties in evaluating the performance changes of rubber under multi-factor coupling, such as temperature, humidity and mechanical stress conditions, making it difficult to accurately predict its performance in actual use. Summary of the invention

[0003] Based on this, it is necessary to provide a performance data evaluation method and system for rubber materials to solve at least one of the above technical problems.

[0004] To achieve the above object, a performance data evaluation method for a rubber material is provided, the method comprising the following steps:

[0005] Step S1: obtaining original data of rubber material; performing data preprocessing on the original data of rubber material to obtain standard rubber material data; performing physical and chemical feature recognition on the standard rubber material data to obtain material physical and chemical feature data;

[0006] Step S2: performing rubber working condition scenario matching on standard rubber material data to obtain rubber working condition scenario data; performing material physical and chemical simulation parameter mapping on material physical and chemical characteristic data according to the rubber working condition scenario data to obtain material physical and chemical simulation parameters; performing material multi-factor coupling simulation on the material physical and chemical simulation parameters to obtain material coupling simulation data; performing material performance evaluation on the material coupling simulation data to generate material coupling performance data;

[0007] Step S3: performing a performance change trend detection on the material coupling performance data to obtain performance change trend data; performing a performance evolution detection on the performance change trend data to obtain material performance evolution data; constructing a performance evaluation model based on the material coupling performance data and the material performance evolution data to obtain a rubber material performance evaluation model;

[0008] Step S4: performing rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain a rubber material performance evaluation result; visually displaying the rubber material performance evaluation result to generate a rubber material performance data evaluation report.

[0009] The present invention performs data preprocessing on the original data of rubber materials, and can convert complex and disordered original data into standard rubber material data, ensuring that the data basis for subsequent analysis and processing is unified, standardized and accurate. On this basis, the physical and chemical characteristics of the standard rubber material data are identified, and the physical and chemical characteristic data of the material can be accurately extracted, which completely covers the key physical and chemical properties of the rubber material, provides a comprehensive and accurate feature basis for the subsequent performance evaluation, avoids the evaluation deviation caused by data quality problems or inaccurate feature extraction, and ensures the scientificity and reliability of the entire performance evaluation process. The standard rubber material data is matched with rubber working conditions, and the rubber material can be accurately matched with various working conditions in actual applications, and rubber working condition scene data can be generated to ensure the pertinence and practicality of subsequent simulation and evaluation. Based on the rubber working condition scene data, the material physical and chemical characteristic data is simulated by multi-factor coupling, which fully considers the complexity of the interaction of multiple factors of the rubber material under actual working conditions, and the obtained material coupling simulation data can truly reflect the performance of the rubber material in actual use. The material coupling performance data generated by the material coupling simulation data provides an accurate and practical evaluation benchmark for subsequent performance evolution detection and model construction, making the entire evaluation process more in line with the actual application scenarios of rubber materials and improving the guiding value of the evaluation results for actual production and application. Performance evolution detection of material coupling performance data can monitor the changing trend of rubber material performance in real time and dynamically, and obtain material performance evolution data, which provides an important basis for evaluating the long-term stability and reliability of rubber materials. The performance evaluation model is constructed based on material coupling performance data and material performance evolution data. The rubber material performance evaluation model comprehensively considers the immediate performance of rubber materials under different working conditions and the long-term laws of performance evolution. The model construction process is rigorous and scientific. The evaluation model obtained can accurately reflect the overall performance of rubber materials, providing a highly reliable and practical evaluation tool for subsequent performance evaluation based on the model, effectively improving the accuracy and comprehensiveness of rubber material performance evaluation, and helping to optimize the production and application process of rubber materials. Based on the rubber material performance evaluation model, the rubber material performance evaluation of the original data of the rubber material can make full use of the accuracy and comprehensiveness of the model, directly generate the rubber material performance evaluation results for the original data, ensure the accuracy and objectivity of the evaluation results, and truly reflect the actual performance level of the rubber material. Visually display the rubber material performance evaluation results and generate a rubber material performance data evaluation report, which can present complex evaluation results in an intuitive and easy-to-understand way, making it easier for relevant technicians, production managers, etc. to quickly understand the pros and cons of the rubber material performance, and provide strong support for the optimization of the rubber material production process, quality control, and product application decisions, effectively improving the scientificity and efficiency of rubber material production and application.Therefore, the present invention realizes the physical and chemical feature recognition of standard rubber material data through data processing technology, simulation technology and data evaluation technology, and performs multi-factor coupling simulation of materials to construct a rubber material performance evaluation model to evaluate the performance of rubber materials, thereby accurately evaluating the performance of rubber materials under multiple working conditions.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire original data of rubber material;

[0012] Step S12: performing data cleaning processing on the original data of the rubber material to obtain the cleaned data of the rubber material; performing data outlier detection on the cleaned data of the rubber material to generate material data outliers;

[0013] Step S13: dividing the material data abnormal values ​​into missing values ​​and error values, filling the missing values, and removing the error values ​​to obtain abnormal value processing data;

[0014] Step S14: normalizing the abnormal value processed data to obtain material normalized data; standardizing the material normalized data to generate standard rubber material data;

[0015] Step S15: Identify the material physical properties of the standard rubber material data to generate material physical property data; identify the material chemical properties of the standard rubber material data to generate material chemical property data; and perform physicochemical feature marking on the material physical property data and the material chemical property data to obtain material physicochemical feature data.

[0016] The present invention obtains the original data of rubber material, provides a basic data source for subsequent data processing and performance evaluation, and ensures that the evaluation process has a basis; performs data cleaning processing on the original data of rubber material to obtain rubber material cleaning data, and effectively removes redundant and irrelevant information. At the same time, data outlier detection is performed on the rubber material cleaning data to generate material data outliers, which can accurately identify abnormal situations in the data and provide clear abnormal identification for subsequent data processing; the material data outliers are divided into missing values ​​and error values, the missing values ​​are filled, and the error values ​​are eliminated to obtain outlier processing data. This step can effectively repair data integrity, eliminate error interference, ensure data quality, and provide a reliable data basis for subsequent analysis; the outlier processing data is normalized to obtain material normalized data, eliminate data dimension and order of magnitude differences, and facilitate subsequent analysis and processing. The material normalized data is standardized to generate standard rubber material data, further standardize data distribution, ensure that the data has a unified statistical characteristic, and provide standardized data support for subsequent feature identification; the material physical property identification is performed on the standard rubber material data to generate material physical property data, and the physical property information of the rubber material is accurately extracted. At the same time, the standard rubber material data is used to identify the material chemical properties, generate material chemical property data, and comprehensively extract the chemical property information of the rubber material. The material physical property data and material chemical property data are physicochemically marked to obtain material physicochemical characteristic data, realizing the integration of physical and chemical property information, and providing comprehensive and accurate characteristic data for subsequent performance evaluation.

[0017] Preferably, step S2 comprises the following steps:

[0018] Step S21: extracting working condition characteristics from standard rubber material data to obtain rubber working condition characteristic data; performing working condition parameter mapping on the rubber working condition characteristic data to generate working condition parameter mapping data;

[0019] Step S22: performing scene determination on the working condition parameter mapping data to obtain preliminary working condition scene data; performing similarity detection on the preliminary working condition scene data to obtain scene similarity data;

[0020] Step S23: performing rubber working condition scene matching on the preliminary working condition scene data according to the scene similarity data to obtain rubber working condition scene data;

[0021] Step S24: performing material multi-factor coupling simulation on the material physical and chemical characteristic data according to the rubber working condition scene data to obtain material coupling simulation data;

[0022] Step S25: performing material performance evaluation on the material coupling simulation data to generate material coupling performance data.

[0023] The present invention extracts working condition characteristics from standard rubber material data to obtain rubber working condition characteristic data, which can accurately identify key characteristics of rubber materials under different working conditions. Working condition parameter mapping is performed on the rubber working condition characteristic data to generate working condition parameter mapping data, so as to achieve accurate correspondence between working condition characteristics and actual parameters, and provide a basis for subsequent working condition scene determination; scene determination is performed on the working condition parameter mapping data to obtain preliminary working condition scene data, and preliminary working condition application scenes of rubber materials are constructed. A similarity test is performed on the preliminary working condition scenario data to obtain scene similarity data, which can quantify the similarity between different working condition scenarios and provide a basis for subsequent precise matching; the preliminary working condition scenario data is matched with the rubber working condition scenario according to the scene similarity data to obtain rubber working condition scenario data, ensuring that the working condition scenario of the rubber material is highly consistent with the actual application conditions, providing an accurate working condition background for subsequent performance simulation; a material multi-factor coupling simulation is performed on the material physicochemical characteristic data according to the rubber working condition scenario data to obtain material coupling simulation data, which can comprehensively consider the multi-factor interaction of the rubber material under specific working conditions, and the simulation results are more in line with actual applications, providing accurate data support for performance evaluation; material performance evaluation is performed on the material coupling simulation data to generate material coupling performance data, which can accurately quantify the performance of the rubber material under multi-factor coupling conditions.

[0024] Preferably, step S24 includes the following steps:

[0025] Step S241: recording the stress impact degree of the rubber working condition scene data to obtain the scene stress impact degree; performing rubber deformation influence detection on the rubber working condition scene data according to the scene stress impact degree to generate deformation influence data;

[0026] Step S242: recording the temperature and humidity parameters of the rubber working condition scene data to obtain the scene temperature and humidity parameters; performing rubber chemical corrosion impact detection on the rubber working condition scene data according to the scene temperature and humidity parameters to generate chemical corrosion impact data;

[0027] Step S243: performing material physical influence simulation on the material physicochemical characteristic data according to the deformation influence data to obtain material physical influence simulation data; performing material chemical influence simulation on the material physicochemical characteristic data according to the chemical corrosion influence data to obtain material chemical influence simulation data;

[0028] Step S244: perform feature influence weight assignment on the material physical influence simulation data and the material chemical influence simulation data to obtain simulation weight assignment data; perform material multi-factor coupling simulation on the material physicochemical feature data based on the simulation weight assignment data to obtain material coupling simulation data.

[0029] The present invention records the degree of stress impact on the rubber working condition scenario data to obtain the degree of scene stress impact, which can quantify the stress impact that the rubber is subjected to in actual working conditions. According to the degree of scene stress impact, the rubber deformation impact detection is performed on the rubber working condition scenario data to generate deformation impact data, accurately reflecting the actual impact of stress impact on rubber deformation, and providing an accurate basis for subsequent physical performance simulation; the temperature and humidity parameters are recorded on the rubber working condition scenario data to obtain scene temperature and humidity parameters, and comprehensively recording the temperature and humidity environmental conditions of the rubber in actual working conditions. According to the scene temperature and humidity parameters, the rubber chemical corrosion impact detection is performed on the rubber working condition scenario data to generate chemical corrosion impact data, which can accurately identify the actual effect of temperature and humidity on rubber chemical corrosion, and provide reliable data for subsequent chemical performance simulation; according to the deformation impact data, the material physical impact simulation is performed on the material physicochemical characteristic data to obtain material physical impact simulation data, which can accurately simulate the impact of stress impact on the physical properties of rubber. According to the chemical corrosion influence data, the material chemical influence simulation is performed on the material physical and chemical characteristic data to obtain the material chemical influence simulation data, which can accurately simulate the influence of temperature and humidity on the chemical properties of rubber and provide sub-item simulation results for subsequent multi-factor coupling simulation; the material physical influence simulation data and the material chemical influence simulation data are assigned characteristic influence weights to obtain simulation weight distribution data, which can assign weights according to the importance of each factor in the actual working conditions to ensure the scientific nature of the simulation results. Based on the simulation weight distribution data, the material physical and chemical characteristic data is simulated by multi-factor coupling to obtain material coupling simulation data, which can fully consider the comprehensive influence of physical and chemical factors, and the simulation results are more in line with the actual working conditions.

[0030] Preferably, step S25 includes the following steps:

[0031] Step S251: performing a tensile strength test on the material coupling simulation data to obtain material tensile strength data; performing a material elastic state test on the material tensile strength data to generate material elastic state data;

[0032] Step S252: performing a material toughness state detection on the material elastic state data to obtain material toughness state data; performing a material deformation critical state judgment based on the material elastic state data and the material toughness state data to obtain deformation state critical data;

[0033] Step S253: recording the material fixed form duration of the deformation state critical data to generate the fixed form duration; dividing the fixed form duration into time levels to obtain form time level data;

[0034] Step S254: Map the morphological time level data to the material physical deformation level to obtain material physical deformation level data; evaluate the material physical properties based on the material physical deformation level data to generate material physical property data.

[0035] The present invention performs a tensile strength test on the material coupling simulation data to obtain the material tensile strength data, which can quantify the tensile bearing capacity of the rubber material under the coupling working condition. The material elastic state detection is performed on the material tensile strength data to generate the material elastic state data, accurately identify the elastic performance of the rubber in the stretching process, and provide basic data for subsequent performance detection; the material toughness state detection is performed on the material elastic state data to obtain the material toughness state data, which can further evaluate the anti-deformation ability of the rubber based on elasticity. According to the material elastic state data and the material toughness state data, the material deformation critical state is judged to obtain the deformation state critical data, and the deformation critical point of the rubber under the coupling working condition is clarified to provide key parameters for subsequent performance evaluation; the material fixed form duration is recorded for the deformation state critical data to generate the fixed form duration, which can quantify the stability of the rubber under the critical deformation state. The fixed form duration is divided into time grades to obtain the form time grade data, and the stability is presented in the form of grades, which is convenient for subsequent evaluation and comparison; the form time grade data is mapped to the material physical deformation grade to obtain the material physical deformation grade data, and a direct association from time stability to physical deformation performance is realized. The physical properties of the material are evaluated based on the material physical deformation grade data, and the material physical properties data are generated, which ultimately forms a quantitative evaluation result of the physical properties of the rubber material.

[0036] Preferably, step S25 further comprises the following steps:

[0037] Step S255: performing a chemical reaction test on the material coupling simulation data to obtain material chemical reaction data; performing a chemical stability test on the material chemical reaction data to generate material chemical stability data;

[0038] Step S256: judging the acid resistance of the material based on the material chemical stability data to obtain the acid resistance of the material; judging the alkali resistance of the material based on the material chemical stability data to obtain the alkali resistance of the material;

[0039] Step S257: Correlate the chemical resistance of the material according to the acid resistance and alkali resistance of the material to generate material chemical resistance data;

[0040] Step S258: mapping the material chemical resistance data to the material chemical corrosion resistance level to obtain the material chemical corrosion resistance level data; evaluating the material chemical performance of the material chemical corrosion resistance level data to generate the material chemical performance data;

[0041] Step S259: Perform material performance evaluation on the material physical performance data and the material chemical performance data to generate material coupling performance data.

[0042] The present invention performs chemical reaction tests on material coupling simulation data to obtain material chemical reaction data, which can quantify the chemical reaction characteristics of rubber materials under coupling conditions. Chemical stability testing is performed on material chemical reaction data to generate material chemical stability data, accurately evaluate the chemical stability of rubber under complex working conditions, and provide basic data for subsequent resistance analysis; the material acid resistance is judged on the material chemical stability data to obtain the material acid resistance and clarify the tolerance of rubber in acidic environments. The material alkali resistance is judged on the material chemical stability data to obtain the material alkali resistance and clarify the tolerance of rubber in alkaline environments, providing specific indicators for subsequent chemical resistance association; material chemical resistance association is performed based on the material acid resistance and material alkali resistance to generate material chemical resistance data, comprehensively evaluate the overall resistance performance of rubber in acidic and alkaline environments, and provide associated data for subsequent chemical corrosion resistance level mapping; material chemical resistance data is mapped to material chemical corrosion resistance level to obtain material chemical corrosion resistance level data, and chemical resistance is presented in the form of level for easy evaluation and comparison. The chemical properties of the materials are evaluated on the chemical corrosion resistance grade data, and the material chemical properties data are generated to form a quantitative evaluation result of the chemical properties of the rubber material; the material physical properties data and material chemical properties data are comprehensively evaluated to generate material coupling performance data to fully reflect the comprehensive performance of the rubber material under physical and chemical coupling conditions.

[0043] Preferably, step S3 comprises the following steps:

[0044] Step S31: performing a performance change trend detection on the material coupling performance data to obtain performance change trend data; performing a performance evolution detection on the performance change trend data to obtain material performance evolution data;

[0045] Step S32: merging the material coupling performance data and the material performance evolution data to obtain a material performance characteristic data set;

[0046] Step S33: dividing the material performance characteristic data set into a training set and a test set according to a ratio of 8:2 to obtain a material performance characteristic training set and a material performance characteristic test set;

[0047] Step S34: constructing a performance evaluation pre-model according to the material performance characteristic training set, and setting initial parameters to obtain a rubber material performance evaluation pre-model; training the rubber material performance evaluation pre-model through the material performance characteristic test set to obtain a rubber material performance evaluation training model;

[0048] Step S35: performing a model cross-validation evaluation on the rubber material performance evaluation training model through the material performance feature training set, specifically calculating the model accuracy, recall rate and F1 score index, and obtaining the training model evaluation data;

[0049] Step S36: adjusting the model parameters of the rubber material performance evaluation training model according to the training model evaluation data to obtain the rubber material performance evaluation model.

[0050] The present invention performs a performance change trend detection on the material coupling performance data to obtain the performance change trend data, and can identify the change law of the rubber material performance over time or working conditions. The performance change trend data is subjected to a performance evolution detection to obtain the material performance evolution data, and the dynamic change process of the performance is further quantified to provide the evolution characteristic data for the subsequent model construction; the material coupling performance data and the material performance evolution data are merged to obtain the material performance characteristic data set, which integrates the static performance and dynamic evolution characteristics of the rubber material, and provides a comprehensive data basis for the model construction; the material performance characteristic data set is divided into a training set and a test set according to a ratio of 8:2 to obtain a material performance characteristic training set and a material performance characteristic test set, and the data is reasonably allocated for model training and verification to ensure the scientificity and reliability of the model evaluation; the performance evaluation pre-model is constructed according to the material performance characteristic training set, and the initial parameters are set to obtain the rubber material performance evaluation pre-model, and provide an initial framework for model training. The rubber material performance evaluation pre-model is trained through the material performance feature test set to obtain the rubber material performance evaluation training model, and the model parameters are optimized using the test set data to improve the model's fitting and generalization capabilities; the rubber material performance evaluation training model is cross-validated and evaluated through the material performance feature training set, and the model accuracy, recall rate and F1 score indicators are specifically calculated to obtain the training model evaluation data, and the performance indicators of the model are comprehensively quantified to provide an objective basis for subsequent model optimization; the model parameters of the rubber material performance evaluation training model are adjusted according to the training model evaluation data to obtain the rubber material performance evaluation model, and the model parameters are optimized based on the evaluation indicators to ensure the accuracy and reliability of the model in practical applications, providing an efficient and accurate tool for rubber material performance evaluation.

[0051] Preferably, step S31 includes the following steps:

[0052] Step S311: extracting the performance test time of the material coupling performance data to obtain the material performance test time;

[0053] Step S312: Perform material physical strength time variation detection on the material coupling performance data according to the performance test time to generate a physical performance time variation feature; perform material chemical strength time variation detection on the material coupling performance data according to the performance test time to generate a chemical performance time variation feature;

[0054] Step S313: identifying performance change trends based on the time-varying characteristics of the physical properties and the time-varying characteristics of the chemical properties, and obtaining performance change trend data;

[0055] Step S314: determining the time series of the performance change trend data to obtain performance time series data; dividing the performance time series data into time stages to generate performance time stage data;

[0056] Step S315: Calculate the performance evolution rate of the performance time stage data to obtain the performance evolution rate; identify the performance evolution state of the performance change trend data according to the performance evolution rate to generate material performance evolution data.

[0057] The present invention extracts the performance test time of the material coupling performance data to obtain the material performance test time, which can clarify the specific time node of the rubber material performance test and provide a time benchmark for the subsequent performance change analysis; the material physical strength time change detection is performed on the material coupling performance data according to the performance test time to generate the physical performance time change characteristics; the material chemical strength time change detection is performed on the material coupling performance data according to the performance test time to generate the chemical performance time change characteristics, which can quantify the changes of the physical strength and chemical strength of the rubber material over time, respectively, and provide sub-item characteristics for the performance change trend identification; the performance change trend is identified based on the physical performance time change characteristics and the chemical performance time change characteristics, and the performance change trend data is obtained. By comprehensively analyzing the time change characteristics of physical and chemical properties, the overall change trend of the rubber material performance can be identified, providing data support for the subsequent performance evolution analysis; the performance change trend data is determined in time series to obtain performance time series data; the performance time series data is segmented into time stages to generate performance time stage data. This step can organize the performance change trend data in chronological order and divide it into different stages, so as to facilitate the subsequent calculation of the performance evolution rate of different stages; the performance evolution rate is calculated for the performance time stage data to obtain the performance evolution rate; the performance evolution state of the performance change trend data is identified according to the performance evolution rate to generate material performance evolution data. By calculating the performance evolution rate of different stages and identifying the evolution state, the dynamic evolution process of rubber material performance can be accurately quantified, providing evolution characteristic data for the construction of performance evaluation model.

[0058] Preferably, step S4 comprises the following steps:

[0059] Step S41: inputting the original data of the rubber material into the rubber material performance evaluation model to perform performance index mapping processing to obtain performance index mapping data;

[0060] Step S42: Performing a working condition scenario indicator evaluation on the performance indicator mapping data to generate working condition scenario indicator data; performing a material physicochemical characteristic evaluation on the working condition scenario indicator data to obtain physicochemical characteristic performance evaluation data;

[0061] Step S43: marking the performance level of the physical and chemical characteristic performance evaluation data to obtain the rubber material performance evaluation result;

[0062] Step S44: Graphically process the rubber material performance evaluation results to obtain performance evaluation graphical results; compile a visual report of the performance evaluation graphical results to generate a rubber material performance data evaluation report.

[0063] The present invention inputs the original data of the rubber material into the rubber material performance evaluation model for performance index mapping processing to obtain performance index mapping data. This step can convert the original data into specific performance indicators to provide a quantitative basis for subsequent evaluation; the performance index mapping data is evaluated for working condition scenario indicators to generate working condition scenario indicator data; the working condition scenario indicator data is evaluated for the physicochemical characteristics of the material to obtain physicochemical characteristic performance evaluation data. This step can combine the performance indicators with the actual working condition scenario to further evaluate the physicochemical characteristics of the rubber material under different working conditions; the physicochemical characteristic performance evaluation data is marked with performance grades to obtain rubber material performance evaluation results. This step converts complex evaluation data into intuitive grade results through performance grade marking, which is convenient for subsequent analysis and application; the rubber material performance evaluation results are graphically processed to obtain performance evaluation graphical results; and the performance evaluation graphical results are visualized and reported.

[0064] In the present specification, a performance data evaluation system for a rubber material is also provided, which is used to execute the performance data evaluation method for the rubber material. The performance data evaluation system for a rubber material comprises:

[0065] The rubber material data processing module is used to obtain the original data of the rubber material; perform data preprocessing on the original data of the rubber material to obtain the standard rubber material data; perform physical and chemical feature recognition on the standard rubber material data to obtain the material physical and chemical feature data;

[0066] The material coupling performance simulation module is used to match the standard rubber material data with the rubber working condition scenario to obtain the rubber working condition scenario data; to map the material physical and chemical simulation parameters to the material physical and chemical characteristic data according to the rubber working condition scenario data to obtain the material physical and chemical simulation parameters; to perform material multi-factor coupling simulation on the material physical and chemical simulation parameters to obtain the material coupling simulation data; to perform material performance evaluation on the material coupling simulation data to generate the material coupling performance data;

[0067] The material performance evaluation model construction module is used to detect the performance change trend of the material coupling performance data to obtain the performance change trend data; perform performance evolution detection on the performance change trend data to obtain the material performance evolution data; and construct a performance evaluation model based on the material coupling performance data and the material performance evolution data to obtain the rubber material performance evaluation model;

[0068] The material performance evaluation and display module is used to perform rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain the rubber material performance evaluation results; the rubber material performance evaluation results are visually displayed to generate a rubber material performance data evaluation report.

[0069] The present invention performs data preprocessing on the original data of rubber materials through the rubber material data processing module, and can convert complex and disordered original data into standard rubber material data, ensuring that the data basis for subsequent analysis and processing is unified, standardized and accurate. On this basis, the physical and chemical characteristics of the standard rubber material data are identified, and the physical and chemical characteristic data of the material can be accurately extracted, which completely covers the key physical and chemical properties of the rubber material, provides a comprehensive and accurate feature basis for the subsequent performance evaluation, avoids the evaluation deviation caused by data quality problems or inaccurate feature extraction, and ensures the scientificity and reliability of the entire performance evaluation process. Through the material coupling performance simulation module, the standard rubber material data is matched with the rubber working condition scene, and the rubber material can be accurately matched with various working condition scenes in actual applications, and rubber working condition scene data can be generated to ensure the pertinence and practicality of subsequent simulation and evaluation. Based on the rubber working condition scene data, the material physical and chemical characteristic data is simulated by multi-factor coupling, which fully considers the complexity of the interaction of multiple factors of the rubber material under actual working conditions, and the obtained material coupling simulation data can truly reflect the performance of the rubber material in actual use. The material coupling performance data generated by the material coupling simulation data provides an accurate and practical evaluation benchmark for subsequent performance evolution detection and model construction, making the entire evaluation process more in line with the actual application scenarios of rubber materials and improving the guiding value of the evaluation results for actual production and application. Through the material performance evaluation model construction module, the performance evolution detection of the material coupling performance data can monitor the changing trend of the rubber material performance in real time and dynamically, and obtain the material performance evolution data, which provides an important basis for evaluating the long-term stability and reliability of the rubber material. The performance evaluation model is constructed based on the material coupling performance data and the material performance evolution data. The rubber material performance evaluation model comprehensively considers the immediate performance of the rubber material under different working conditions and the long-term law of performance evolution. The model construction process is rigorous and scientific. The evaluation model obtained can accurately reflect the overall performance of the rubber material, providing a highly reliable and practical evaluation tool for the subsequent performance evaluation based on the model, effectively improving the accuracy and comprehensiveness of the rubber material performance evaluation, and helping to optimize the production and application process of rubber materials. Performing rubber material performance evaluation on the original data of rubber materials based on the rubber material performance evaluation model can make full use of the accuracy and comprehensiveness of the model, directly generate rubber material performance evaluation results for the original data, ensure the accuracy and objectivity of the evaluation results, and truly reflect the actual performance level of the rubber material.Through the material performance evaluation display module, the rubber material performance evaluation results are visualized and a rubber material performance data evaluation report is generated, which can present complex evaluation results in an intuitive and easy-to-understand manner, making it easy for relevant technical personnel, production management personnel, etc. to quickly understand the pros and cons of rubber material performance, and provide strong support for the production process optimization, quality control and product application decision-making of rubber materials, effectively improving the scientificity and efficiency of rubber material production and application. Therefore, the present invention realizes the physical and chemical feature identification of standard rubber material data through data processing technology, simulation technology and data evaluation technology, and performs multi-factor coupling simulation of materials, constructs a rubber material performance evaluation model, and performs performance evaluation on rubber materials, thereby accurately evaluating the performance of rubber materials in multiple working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of the steps of a method for evaluating performance data of a rubber material;

[0071] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0072] Figure 3 for Figure 2 Detailed implementation steps of step S31 in FIG.

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

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

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

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

[0077] To achieve this, please refer to Figures 1 to 3 , a performance data evaluation method for a rubber material, the method comprising the following steps:

[0078] Step S1: obtaining original data of rubber material; performing data preprocessing on the original data of rubber material to obtain standard rubber material data; performing physical and chemical feature recognition on the standard rubber material data to obtain material physical and chemical feature data;

[0079] Step S2: performing rubber working condition scenario matching on standard rubber material data to obtain rubber working condition scenario data; performing material physical and chemical simulation parameter mapping on material physical and chemical characteristic data according to the rubber working condition scenario data to obtain material physical and chemical simulation parameters; performing material multi-factor coupling simulation on the material physical and chemical simulation parameters to obtain material coupling simulation data; performing material performance evaluation on the material coupling simulation data to generate material coupling performance data;

[0080] Step S3: performing a performance change trend detection on the material coupling performance data to obtain performance change trend data; performing a performance evolution detection on the performance change trend data to obtain material performance evolution data; constructing a performance evaluation model based on the material coupling performance data and the material performance evolution data to obtain a rubber material performance evaluation model;

[0081] Step S4: performing rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain a rubber material performance evaluation result; visually displaying the rubber material performance evaluation result to generate a rubber material performance data evaluation report.

[0082] The present invention performs data preprocessing on the original data of rubber materials, and can convert complex and disordered original data into standard rubber material data, ensuring that the data basis for subsequent analysis and processing is unified, standardized and accurate. On this basis, the physical and chemical characteristics of the standard rubber material data are identified, and the physical and chemical characteristic data of the material can be accurately extracted, which completely covers the key physical and chemical properties of the rubber material, provides a comprehensive and accurate feature basis for the subsequent performance evaluation, avoids the evaluation deviation caused by data quality problems or inaccurate feature extraction, and ensures the scientificity and reliability of the entire performance evaluation process. The standard rubber material data is matched with rubber working conditions, and the rubber material can be accurately matched with various working conditions in actual applications, and rubber working condition scene data can be generated to ensure the pertinence and practicality of subsequent simulation and evaluation. Based on the rubber working condition scene data, the material physical and chemical characteristic data is simulated by multi-factor coupling, which fully considers the complexity of the interaction of multiple factors of the rubber material under actual working conditions, and the obtained material coupling simulation data can truly reflect the performance of the rubber material in actual use. The material coupling performance data generated by the material coupling simulation data provides an accurate and practical evaluation benchmark for subsequent performance evolution detection and model construction, making the entire evaluation process more in line with the actual application scenarios of rubber materials and improving the guiding value of the evaluation results for actual production and application. Performance evolution detection of material coupling performance data can monitor the changing trend of rubber material performance in real time and dynamically, and obtain material performance evolution data, which provides an important basis for evaluating the long-term stability and reliability of rubber materials. The performance evaluation model is constructed based on material coupling performance data and material performance evolution data. The rubber material performance evaluation model comprehensively considers the immediate performance of rubber materials under different working conditions and the long-term laws of performance evolution. The model construction process is rigorous and scientific. The evaluation model obtained can accurately reflect the overall performance of rubber materials, providing a highly reliable and practical evaluation tool for subsequent performance evaluation based on the model, effectively improving the accuracy and comprehensiveness of rubber material performance evaluation, and helping to optimize the production and application process of rubber materials. Based on the rubber material performance evaluation model, the rubber material performance evaluation of the original data of the rubber material can make full use of the accuracy and comprehensiveness of the model, directly generate the rubber material performance evaluation results for the original data, ensure the accuracy and objectivity of the evaluation results, and truly reflect the actual performance level of the rubber material. Visually display the rubber material performance evaluation results and generate a rubber material performance data evaluation report, which can present complex evaluation results in an intuitive and easy-to-understand way, making it easier for relevant technicians, production managers, etc. to quickly understand the pros and cons of the rubber material performance, and provide strong support for the optimization of the rubber material production process, quality control, and product application decisions, effectively improving the scientificity and efficiency of rubber material production and application.Therefore, the present invention realizes the physical and chemical feature recognition of standard rubber material data through data processing technology, simulation technology and data evaluation technology, and performs multi-factor coupling simulation of materials to construct a rubber material performance evaluation model to evaluate the performance of rubber materials, thereby accurately evaluating the performance of rubber materials under multiple working conditions.

[0083] In the embodiment of the present invention, reference Figure 1 As shown, the performance data evaluation method of the rubber material includes the following steps:

[0084] Step S1: obtaining original data of rubber material; performing data preprocessing on the original data of rubber material to obtain standard rubber material data; performing physical and chemical feature recognition on the standard rubber material data to obtain material physical and chemical feature data;

[0085] In the embodiment of the present invention, a high-precision mechanical property testing device is used to perform a tensile test on a rubber sample, and the stress and strain data during the tensile process are recorded to obtain mechanical property indicators such as tensile strength and elongation at break of the rubber. At the same time, a hardness tester is used to measure the hardness value of the rubber, and a thermal analyzer is used to measure the thermal conductivity of the rubber. In addition, a dielectric property tester is used to measure electrical property parameters such as the dielectric constant of the rubber. For the microstructure data of the rubber, an optical microscope and a scanning electron microscope (SEM) are used to observe the rubber sample, and microscopic images of the surface and internal structure of the rubber are taken to record its microscopic morphological characteristics; the collected raw data is filtered. A low-pass filtering technique is used, and the cutoff frequency of the filter is set to 100 Hz to remove high-frequency noise signals in the data and retain the main effective signal components. Next, the data is normalized, and all data values ​​are scaled to a range of 0 to 1; the specific operation is to calculate the maximum and minimum values ​​of each group of data, and then the value of each data point is subtracted from the minimum value, and then divided by the difference between the maximum and minimum values. After that, outlier detection and elimination are performed. Statistical methods are used to treat data points that exceed the range of the data mean plus or minus 3 times the standard deviation as outliers and are eliminated. Finally, the data is interpolated to fill in the missing points in the data. The linear interpolation method is used to calculate the values ​​of the missing data points based on the linear relationship between the known data points, thereby ensuring the integrity and continuity of the data, and finally obtaining the standard rubber material data; the chemical composition of the rubber is analyzed using Fourier transform infrared spectroscopy (FTIR) technology; the rubber sample is scanned by an infrared spectrometer to identify the characteristic absorption peaks of different functional groups in the rubber, such as CH stretching vibration peak, C=C stretching vibration peak, etc. The chemical composition and structural characteristics of the rubber are determined based on the position, intensity and shape of the absorption peak. At the same time, differential scanning calorimetry (DSC) is used to analyze the thermal properties of the rubber. The thermal effect of the rubber during heating or cooling is measured by DSC equipment, and the endothermic and exothermic peaks in the DSC curve are analyzed to obtain the thermophysical property parameters of the rubber, such as the glass transition temperature, melting point, and crystallinity. In addition, the crystal structure of the rubber is analyzed using X-ray diffraction (XRD) technology. The rubber sample is subjected to diffraction scanning by XRD equipment to determine information such as the crystal form, grain size and crystallinity of the rubber.

[0086] Step S2: performing rubber working condition scenario matching on the standard rubber material data to obtain rubber working condition scenario data; performing material multi-factor coupling simulation on the material physicochemical characteristic data according to the rubber working condition scenario data to obtain material coupling simulation data; performing material performance evaluation on the material coupling simulation data to generate material coupling performance data;

[0087] In an embodiment of the present invention, a rubber working condition scenario model is constructed using multi-parameter simulation technology. By setting different parameters such as temperature, humidity, and mechanical stress, the working condition environment of rubber in actual use is simulated. For example, for the rubber material of the sole, the stress environment model under different road conditions can be simulated. Then, the standard rubber material data is parameter-mapped with the working condition scenario model, that is, the performance data of the rubber material is matched with various parameters in the working condition scenario, so as to obtain the rubber working condition scenario data; the multi-factor coupling simulation technology is adopted to consider the interaction of multiple factors such as temperature, humidity, and mechanical stress. By simulating the physical and chemical changes of the rubber material under different working conditions, such as oxidation reaction, cross-linking reaction, etc., the influence of these factors on the performance of the rubber material is analyzed. In the specific operation, the performance data evaluation method of the rubber material of the sole can be referred to, and the rubber material can be analyzed by X-ray diffraction to obtain a microstructure change diagram, and the material performance degradation modeling is performed based on this. By simulating the microstructure changes of rubber under different working conditions, material coupling simulation data is generated; and the performance evaluation technology is used to analyze the various performance indicators in the material coupling simulation data. Through quantitative evaluation methods, such as calculating the mechanical property attenuation rate and thermal property change rate of the material, the performance of the rubber material under different working conditions can be determined. In specific operations, the degree of freedom stress response test of the rubber material can be carried out to obtain extreme environment adaptability data, and stress-strain characteristics analysis can be performed based on this. According to the evaluation results, material coupling performance data is generated to provide a basis for the performance optimization and application of rubber materials.

[0088] Step S3: performing performance evolution detection on the material coupling performance data to obtain material performance evolution data; constructing a performance evaluation model based on the material coupling performance data and the material performance evolution data to obtain a rubber material performance evaluation model;

[0089] In the embodiment of the present invention, key performance indicators including tensile strength, elongation at break, hardness, thermal conductivity and dielectric constant are extracted from the multi-factor coupling simulation data of the rubber material. At the same time, combined with the rubber working condition scenario data, the performance under different working conditions (such as temperature, humidity, mechanical stress) is recorded; the rubber sample is placed in an aging box, and the temperature is set to 100°C, 120°C, and 140°C, respectively, for 72 hours and 168 hours. After each time point, the sample is taken out, and its tensile strength and elongation at break are measured using a universal material testing machine, and the hardness is measured using a hardness tester, and the changes in performance indicators are recorded; the aged rubber sample is subjected to X-ray diffraction (XRD) analysis to observe its microstructural changes, including changes in grain size and crystallinity. At the same time, a scanning electron microscope (SEM) is used to take microscopic images of the rubber surface and internal structure, and the changes in micromorphology are recorded; the results of the aging test and microstructural analysis are organized into performance evolution data, including performance index change curves over time, microstructural change diagrams, etc. These data reflect the performance evolution trend of the rubber material under different working conditions. The material coupling performance data and material performance evolution data are integrated into a complete data set, including performance indicators such as tensile strength, elongation at break, hardness, thermal conductivity, dielectric constant, grain size, crystallinity, and corresponding working conditions (temperature, humidity, mechanical stress); the integrated data is normalized and the values ​​of all performance indicators are scaled to the range of 0 to 1. The specific operation is: calculate the maximum and minimum values ​​of each set of data, then subtract the minimum value from the value of each data point, and then divide it by the difference between the maximum and minimum values; select the random forest regression model as the performance evaluation model. Set the model parameters, including the number of trees (n_estimators) to 100, the maximum number of features (max_features) to "sqrt", and the random seed (random_state) to 42; use the stratified sampling method to divide the data set into a training set and a test set, with the test set ratio being 20%. Ensure the consistency of the distribution of performance indicators between the training set and the test set; use the training set data to train the random forest regression model. The input features are performance indicators such as tensile strength, elongation at break, hardness, thermal conductivity, dielectric constant, grain size, crystallinity, and corresponding operating conditions (temperature, humidity, and mechanical stress). The target variable is the service life or performance degradation rate of the material; the trained model is evaluated using the test set data to calculate the mean square error (MSE) and determination coefficient (R 2 Score); according to the evaluation results, the model parameters are further optimized to ensure that the model has high prediction accuracy and generalization ability. The final rubber material performance evaluation model can evaluate the performance of rubber materials under different working conditions based on the input performance data.

[0090] Step S4: performing rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain a rubber material performance evaluation result; visually displaying the rubber material performance evaluation result to generate a rubber material performance data evaluation report.

[0091] In an embodiment of the present invention, the original data of the rubber material is input into the rubber material performance evaluation model. The model processes and analyzes the original data based on the preset algorithm and parameters, thereby obtaining the rubber material performance evaluation results. Specifically, the model will quantitatively analyze the original data according to the key performance indicators of the rubber material such as elastic modulus, hardness, and wear resistance. For example, for the evaluation of the elastic modulus, the model will calculate the specific value of the elastic modulus based on the deformation of the rubber under stress conditions, combined with physical formulas such as Hooke's law. For the evaluation of hardness, the model will refer to the measurement principle of the Shore hardness tester and obtain the hardness value by analyzing the data such as the indentation depth on the rubber surface. For the evaluation of wear resistance, the model will simulate the wear of the rubber during the friction process, and obtain the wear resistance index by calculating the relationship between the wear amount and the number of frictions. After the generation of the rubber material performance evaluation results is completed, the results are visualized using a data visualization tool. The specific operation is to import the performance indicator data in the evaluation results into the visualization software, select a suitable chart type, such as a bar chart, a line chart or a radar chart, etc., and visualize the data. Taking a bar chart as an example, different performance indicators are used as the horizontal axis and the corresponding evaluation values ​​are used as the vertical axis to generate an intuitive bar chart, which can clearly show the level of each performance indicator. Finally, a rubber material performance data evaluation report is generated. The report records in detail the process of rubber material performance evaluation, the evaluation model and parameters used, the evaluation results, and the visual display content. The format of the report usually includes a cover, a table of contents, an abstract, a main text, and a conclusion. In the main text, the evaluation method, evaluation results, and comparative analysis of each performance indicator are described in detail.

[0092] Preferably, step S1 comprises the following steps:

[0093] Step S11: Acquire original data of rubber material;

[0094] Step S12: performing data cleaning processing on the original data of the rubber material to obtain the cleaned data of the rubber material; performing data outlier detection on the cleaned data of the rubber material to generate material data outliers;

[0095] Step S13: dividing the material data abnormal values ​​into missing values ​​and error values, filling the missing values, and removing the error values ​​to obtain abnormal value processing data;

[0096] Step S14: normalizing the abnormal value processed data to obtain material normalized data; standardizing the material normalized data to generate standard rubber material data;

[0097] Step S15: Identify the material physical properties of the standard rubber material data to generate material physical property data; identify the material chemical properties of the standard rubber material data to generate material chemical property data; and perform physicochemical feature marking on the material physical property data and the material chemical property data to obtain material physicochemical feature data.

[0098] In an embodiment of the present invention, the original data of rubber material is read from the database and imported into the data cleaning tool. First, the data is processed in a unified format, and all data are converted into a unified numerical format, for example, the chemical composition content in percentage form is converted into decimal form. Next, check whether there are duplicate records in the data, and identify and delete the duplicate data rows that are exactly the same by comparing the batch number, production date and various performance index values ​​of the samples. For data records with missing fields, they are marked as data to be processed; and outlier detection is performed on the cleaned data. Taking the hardness value as an example, the mean and standard deviation of all hardness values ​​are calculated, and the threshold is set to the mean plus or minus 3 times the standard deviation. The hardness values ​​that exceed the threshold range are marked as outliers. For the elastic modulus values, the box plot method is used for outlier detection, and the first quartile (Q1), the third quartile (Q3) and the interquartile range (IQR = Q3-Q1) are calculated, and the elastic modulus values ​​less than Q1-1.5IQR or greater than Q3+1.5IQR are marked as outliers. All detected outliers are summarized to generate a list of material data outliers; outliers are classified according to the list of material data outliers. For missing values, such as the missing tensile strength data of a rubber sample, by analyzing the other performance index values ​​of the sample and the tensile strength data of other samples in the same batch, it is determined whether the missing value can be filled by the interpolation method. For erroneous values ​​that obviously do not conform to the law of rubber performance, such as abnormally low or high hardness values, they are directly determined as erroneous values; for missing values, the mean filling method is used. Taking the chemical component content as an example, the average value of the chemical component content in the same batch of samples is calculated, and the average value is filled to the position of the missing data. For erroneous values, the corresponding records are directly removed from the data set. After the processing is completed, the outlier processing data is obtained; the outlier processing data is normalized. Taking the hardness value as an example, find the maximum and minimum hardness values ​​in the data set, subtract the minimum value from each hardness value and divide it by the difference between the maximum and minimum values ​​to obtain the normalized hardness value so that it ranges between 0 and 1. The same method is used to normalize other performance index data such as elastic modulus values ​​to obtain material normalized data; the material normalized data is standardized. Taking the tensile strength data as an example, the average value and standard deviation of the normalized tensile strength data are calculated, and each normalized tensile strength value is subtracted from the average value and divided by the standard deviation to obtain the standardized tensile strength value, so that the mean is 0 and the standard deviation is 1. The same method is used to standardize other performance index data to generate standard rubber material data; the physical properties of the standard rubber material data are identified. Taking the elastic modulus as an example, according to the standardized elastic modulus value, combined with the physical performance standard specifications of rubber, it is judged whether the elastic modulus of the rubber meets the performance requirements of a specific type of rubber, such as whether it belongs to the high elastic rubber range.Similar analysis is performed on other physical performance index data such as hardness value and tensile strength to generate material physical property data; chemical property identification is performed on standard rubber material data. Taking chemical component content as an example, based on the standardized chemical component content value and combined with the chemical composition standard specification of rubber, it is judged whether the chemical composition of the rubber meets the composition requirements of a specific type of rubber, such as whether it contains a specific proportion of natural rubber components. Similar analysis is performed on other chemical performance index data to generate material chemical property data; the generated material physical property data and material chemical property data are marked with physicochemical characteristics. Taking rubber samples as an example, the physical property data and chemical property data of each sample are assigned corresponding marking labels, such as marking samples that meet the physical properties of high elastic rubber as "high elasticity", and marking samples containing a specific proportion of natural rubber components as "containing natural rubber", and the marked data are integrated into material physicochemical characteristic data.

[0099] Preferably, step S2 comprises the following steps:

[0100] Step S21: extracting working condition characteristics from standard rubber material data to obtain rubber working condition characteristic data; performing working condition parameter mapping on the rubber working condition characteristic data to generate working condition parameter mapping data;

[0101] Step S22: performing scene determination on the working condition parameter mapping data to obtain preliminary working condition scene data; performing similarity detection on the preliminary working condition scene data to obtain scene similarity data;

[0102] Step S23: performing rubber working condition scene matching on the preliminary working condition scene data according to the scene similarity data to obtain rubber working condition scene data;

[0103] Step S24: performing material multi-factor coupling simulation on the material physical and chemical characteristic data according to the rubber working condition scene data to obtain material coupling simulation data;

[0104] Step S25: performing material performance evaluation on the material coupling simulation data to generate material coupling performance data.

[0105] In the embodiment of the present invention, standard rubber material data is read from the database. These data have been processed in advance and have a unified format and a standardized value range. The standard rubber material data is subjected to working condition feature extraction using a feature extraction algorithm. Taking the performance data of rubber under different temperature and pressure conditions as an example, feature vectors related to working conditions are extracted through multidimensional feature extraction technology. These feature vectors include key parameters such as temperature, pressure, and hardness change rate. Subsequently, the extracted working condition feature data is subjected to working condition parameter mapping; each parameter in the feature vector is mapped to the corresponding working condition parameter space according to a preset mapping rule to generate working condition parameter mapping data. For example, the temperature parameter is mapped to three intervals of low temperature, normal temperature, and high temperature, and the pressure parameter is mapped to three intervals of low pressure, medium pressure, and high pressure; and the working condition parameter mapping data is subjected to scenario determination. Based on the mapped parameters, combined with the actual application scenarios of rubber, such as automobile tires, industrial seals, etc., the data is divided into different working condition scenarios. For example, for automobile tire rubber, it is divided into preliminary scenarios such as urban driving, high-speed driving, and extreme weather according to temperature and pressure parameters. Subsequently, the preliminary working condition scenario data is subjected to similarity detection. The cosine similarity algorithm is used to calculate the similarity between different scene data. Taking the urban driving scene as an example, the similarity between each data point in the scene is calculated to obtain the scene similarity data; based on the scene similarity data, the preliminary scene data of the working condition is matched with the rubber working condition scene. A similarity threshold is set, such as 0.85, and data points with similarity higher than the threshold are classified as the same working condition scene. For data points below the threshold, their characteristic parameters are further analyzed, and manual verification is performed in combination with the expert knowledge base to finally determine the rubber working condition scene data. For example, if the similarity of a data point in the urban driving scene is lower than the threshold, but its temperature and pressure parameters are close to those of the urban driving scene, it is classified into the urban driving scene; based on the rubber working condition scene data, the material physical and chemical characteristic data is simulated by material multi-factor coupling. Taking automobile tire rubber as an example, in the urban driving scene, the coupling effects of multiple factors such as temperature, pressure, hardness, and elastic modulus are considered. Using finite element analysis software, combined with the physical and chemical properties of rubber, corresponding boundary conditions and loads are set for coupling simulation. Through simulation, the stress-strain distribution, energy loss and other data of the material under different working conditions are obtained, and the material coupling simulation data is generated; the material performance is evaluated based on the material coupling simulation data. Based on the simulated stress-strain distribution, energy loss and other data, combined with the performance standards of rubber and application scenario requirements, performance evaluation is performed. For example, in urban driving scenarios, the wear resistance performance index of tire rubber is evaluated, and the material coupling performance data is generated by calculating the performance index score.

[0106] Preferably, step S24 includes the following steps:

[0107] Step S241: recording the stress impact degree of the rubber working condition scene data to obtain the scene stress impact degree; performing rubber deformation influence detection on the rubber working condition scene data according to the scene stress impact degree to generate deformation influence data;

[0108] Step S242: recording the temperature and humidity parameters of the rubber working condition scene data to obtain the scene temperature and humidity parameters; performing rubber chemical corrosion impact detection on the rubber working condition scene data according to the scene temperature and humidity parameters to generate chemical corrosion impact data;

[0109] Step S243: performing material physical influence simulation on the material physicochemical characteristic data according to the deformation influence data to obtain material physical influence simulation data; performing material chemical influence simulation on the material physicochemical characteristic data according to the chemical corrosion influence data to obtain material chemical influence simulation data;

[0110] Step S244: perform feature influence weight assignment on the material physical influence simulation data and the material chemical influence simulation data to obtain simulation weight assignment data; perform material multi-factor coupling simulation on the material physicochemical feature data based on the simulation weight assignment data to obtain material coupling simulation data.

[0111] In an embodiment of the present invention, the rubber working condition scenario data is read from the database, and these data include information such as stress, strain, temperature, humidity, etc. of the rubber under different working conditions. First, the stress impact degree of the rubber working condition scenario data is recorded. The stress distribution of the rubber under different working conditions is simulated by using finite element analysis software. During the simulation process, different stress loading conditions are set, such as applying a dynamic load under compression conditions, the boundary condition is a fixed constraint on the lower end face of the truncated cone, and a sinusoidal wave displacement is applied to the upper surface node. Through simulation, the maximum stress value, the minimum stress value, and the stress change rate of the rubber at different time points are recorded to obtain the scene stress impact degree data; then, the rubber deformation influence detection is performed on the rubber working condition scenario data according to the scene stress impact degree. A deformation detection device, such as a compression permanent deformation tester, is used to perform a deformation test on the rubber sample. The rubber sample is placed in the test device, a preset stress impact condition is applied, and the deformation of the rubber under stress is recorded, including deformation parameters such as compression permanent deformation rate and elongation at break. These deformation parameters are correlated with the stress impact degree data to generate deformation influence data; and the temperature and humidity parameters of the rubber working condition scenario data are recorded. In the rubber working condition scenario data, parameters related to temperature and humidity are extracted, such as ambient temperature, relative humidity, etc. The temperature and humidity sensors are used to monitor the temperature and humidity changes of rubber under different working conditions in real time, record the temperature and humidity data, and obtain the scene temperature and humidity parameters; then, the rubber working condition scenario data is tested for the influence of rubber chemical corrosion according to the scene temperature and humidity parameters. Rubber samples are immersed in specific corrosive media, such as acid, alkali, and salt solutions, to simulate the chemical corrosion environment under actual working conditions. Under different temperature and humidity conditions, rubber samples are taken out regularly to detect chemical corrosion parameters such as hardness changes, tensile strength changes, and volume expansion. Chemical corrosion influence data are generated by comparing the changes in corrosion parameters under different temperature and humidity conditions; material physical influence simulation is performed on material physicochemical characteristic data according to deformation influence data. Finite element analysis software is used to set boundary conditions and loads corresponding to deformation influence data in combination with the physical properties of rubber (such as elastic modulus, Poisson's ratio, etc.). For example, the stress relaxation characteristics of rubber under long-term compression load are simulated according to the compression permanent deformation rate. Through simulation, the changes in the physical properties of rubber under different deformation conditions are obtained, and material physical impact simulation data is generated; the material chemical impact simulation is performed on the material physicochemical characteristic data according to the chemical corrosion impact data. Chemical analysis software is used to simulate the chemical reaction process of rubber in different corrosive media in combination with the chemical composition and structure of rubber. For example, the chemical corrosion process of rubber in an acidic environment is simulated based on the changes in hardness and tensile strength. Through simulation, the changes in the chemical properties of rubber under different chemical corrosion conditions are obtained, and material chemical impact simulation data is generated; the material physical impact simulation data and the material chemical impact simulation data are assigned feature impact weights. The weight coefficients of physical and chemical impacts are set according to the actual application scenarios and performance requirements of rubber.For example, for automobile tire rubber, the physical influence weight coefficient is set to 0.6, and the chemical influence weight coefficient is set to 0.4. Multiply the weight coefficients by the corresponding simulation data to obtain the simulation weight distribution data. Based on the simulation weight distribution data, perform a multi-factor coupling simulation of the material physicochemical characteristic data. Use multi-physics field coupling analysis software to comprehensively analyze the simulation results of physical and chemical influences. During the simulation process, consider the interaction of multiple factors such as stress, strain, temperature and humidity, and chemical corrosion, and set corresponding coupling conditions and boundary conditions. Through simulation, the comprehensive performance changes of rubber under the coupling of multiple factors are obtained, and material coupling simulation data is generated.

[0112] Preferably, step S25 comprises the following steps:

[0113] Step S251: performing a tensile strength test on the material coupling simulation data to obtain material tensile strength data; performing a material elastic state test on the material tensile strength data to generate material elastic state data;

[0114] Step S252: performing a material toughness state detection on the material elastic state data to obtain material toughness state data; performing a material deformation critical state judgment based on the material elastic state data and the material toughness state data to obtain deformation state critical data;

[0115] Step S253: recording the material fixed form duration of the deformation state critical data to generate the fixed form duration; dividing the fixed form duration into time levels to obtain form time level data;

[0116] Step S254: Map the morphological time level data to the material physical deformation level to obtain material physical deformation level data; evaluate the material physical properties based on the material physical deformation level data to generate material physical property data.

[0117] In an embodiment of the present invention, material coupling simulation data are read from a database, and these data contain information such as stress, strain, temperature and humidity of rubber under multi-factor coupling conditions. First, the material coupling simulation data is subjected to a tensile strength test. According to the requirements of international standard ISO 37, a rubber tensile specimen of standard size is prepared. The shape of the specimen is usually rectangular, with a width between 6.4mm and 12.7mm, a length between 25.4mm and 76.2mm, and a thickness between 2.0mm and 6.4mm. The surface of the specimen should be flat and smooth, without surface defects such as scratches, bubbles, and cracks. The specimen is mounted on the fixture of a universal material testing machine to ensure that the connection between the specimen and the fixture is firm and reliable. Set a suitable stretching speed, which is usually determined according to the test standard or material properties, and then start to apply the tensile force. During the test, the deformation of the specimen during the stretching process is recorded, including the load when stretched to the specified elongation, the rated load when the rubber is broken, and the elongation at break. Through these data, the material tensile strength data is obtained; then, the material elastic state of the material tensile strength data is tested. The stress-strain curve recorded during the tensile test is used to analyze the initial linear part of the curve to determine the elastic modulus of the material. According to the size of the elastic modulus and the shape of the stress-strain curve, the elastic state of the rubber material during the stretching process is judged to generate the elastic state data of the material; the material toughness state is detected for the elastic state data of the material. The stress-strain curve in the tensile test is used to analyze the yield point, elongation at break and other parameters of the curve. The toughness state of the rubber material is evaluated by calculating the elongation at break and the fracture energy to obtain the material toughness state data. According to the elastic state data of the material and the toughness state data of the material, the critical state of material deformation is judged, and the thresholds of the critical elongation at break and the critical fracture energy are set. When the elongation at break and the fracture energy of the rubber material exceed these thresholds, it is judged that the material enters the critical state of deformation. These critical state data are summarized to obtain the critical data of the deformation state; the fixed shape duration of the material is recorded for the critical data of the deformation state. After the rubber material reaches the critical state of deformation, the tensile force is continued to be applied to record the time from the critical state to the final fracture of the material. Through repeated tests, the duration of different rubber samples in the critical state is counted to generate the fixed shape duration data. Subsequently, the duration of the fixed form is divided into time levels. According to the length of the duration, the data is divided into different time levels. For example, the duration less than 10 seconds is divided into a short time level, 10 seconds to 60 seconds is divided into a medium time level, and more than 60 seconds is divided into a long time level. These time level data are aggregated to obtain the morphological time level data; the morphological time level data is mapped to the material physical deformation level. According to the correspondence between the time level and the degree of physical deformation, the morphological time level data is mapped to the material physical deformation level data. For example, the short time level corresponds to the high deformation level, the medium time level corresponds to the medium deformation level, and the long time level corresponds to the low deformation level.The physical properties of the material are evaluated based on the material's physical deformation grade data. Combined with the rubber material's tensile strength, elastic modulus, toughness state, deformation grade and other data, the physical properties of the rubber material are comprehensively evaluated according to the preset evaluation criteria.

[0118] Preferably, step S25 further comprises the following steps:

[0119] Step S255: performing a chemical reaction test on the material coupling simulation data to obtain material chemical reaction data; performing a chemical stability test on the material chemical reaction data to generate material chemical stability data;

[0120] Step S256: judging the acid resistance of the material based on the material chemical stability data to obtain the acid resistance of the material; judging the alkali resistance of the material based on the material chemical stability data to obtain the alkali resistance of the material;

[0121] Step S257: Correlate the chemical resistance of the material according to the acid resistance and alkali resistance of the material to generate material chemical resistance data;

[0122] Step S258: mapping the material chemical resistance data to the material chemical corrosion resistance level to obtain the material chemical corrosion resistance level data; evaluating the material chemical performance of the material chemical corrosion resistance level data to generate the material chemical performance data;

[0123] Step S259: Perform material performance evaluation on the material physical performance data and the material chemical performance data to generate material coupling performance data.

[0124] In an embodiment of the present invention, material coupling simulation data are read from a database, and these data include the performance of rubber under multi-factor coupling conditions. First, a chemical reaction test is performed on the material coupling simulation data. A chemical analysis instrument, such as a Fourier transform infrared spectrometer (FTIR), is used to analyze the chemical composition of the rubber sample. According to the requirements of the national standard GB / T7764-2017, a classification standard is established for different rubber materials, and the chemical composition of the rubber is identified by the characteristic peaks in the infrared spectrum. During the test, the rubber sample is exposed to different chemical environments, such as acidic and alkaline solutions, and the changes in its chemical composition are recorded to obtain material chemical reaction data; then, the material chemical reaction data is tested for chemical stability. By analyzing the changes in the characteristic peaks in the chemical reaction data, the stability of the rubber in different chemical environments is evaluated. For example, observe whether the chemical composition of the rubber sample changes significantly after being immersed in an acidic or alkaline solution, and the degree of change. According to the changes in the chemical composition, the material chemical stability data is generated; the material acid resistance is judged on the material chemical stability data. The evaluation criteria for acid resistance are set. For example, the chemical composition change rate of the rubber sample after being immersed in an acidic solution for a certain period of time is used as an evaluation index. If the change rate is lower than a certain threshold (such as 5%), the rubber is judged to have good acid resistance, and the material acid resistance data is obtained; then, the material alkali resistance is judged on the material chemical stability data. A similar method is used to use the chemical composition change rate of the rubber sample after being immersed in an alkaline solution as an evaluation index. If the change rate is lower than the set threshold (such as 5%), the rubber is judged to have good alkali resistance, and the material alkali resistance data is obtained. According to the material acid resistance and material alkali resistance data, the material chemical resistance is associated. The acid resistance and alkali resistance data are comprehensively analyzed to evaluate the chemical resistance of the rubber in an acid-base alternating environment. For example, the weighted average of the acid resistance and alkali resistance is calculated to generate the material chemical resistance data. The weight can be adjusted according to the actual application scenario of the rubber. For example, for rubber that needs to be used in a strong acid environment, the weight of the acid resistance can be higher; the material chemical resistance data is mapped to the material chemical corrosion resistance level. According to the preset chemical corrosion resistance classification standard, the material chemical resistance data is mapped to different chemical corrosion resistance levels. For example, the chemical resistance data is divided into three levels: high, medium and low, corresponding to different chemical corrosion resistance capabilities. According to the mapping results, the material chemical corrosion resistance level data is generated; then, the material chemical performance evaluation is performed on the material chemical corrosion resistance level data. Combined with the chemical composition, chemical stability and chemical corrosion resistance level data of the rubber, the chemical properties of the rubber are evaluated, and the evaluation results are output in the form of data to generate material chemical performance data for subsequent performance analysis and application decisions; the material physical performance data and material chemical performance data are comprehensively evaluated. By comparing the evaluation results of physical and chemical properties, material coupling performance data is generated.For example, comprehensive analysis is conducted on physical performance data such as tensile strength and elastic modulus and chemical performance data such as acid resistance and alkali resistance to evaluate the comprehensive performance of rubber in practical applications.

[0125] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes:

[0126] Step S31: performing a performance change trend detection on the material coupling performance data to obtain performance change trend data; performing a performance evolution detection on the performance change trend data to obtain material performance evolution data;

[0127] Step S32: merging the material coupling performance data and the material performance evolution data to obtain a material performance characteristic data set;

[0128] Step S33: dividing the material performance characteristic data set into a training set and a test set according to a ratio of 8:2 to obtain a material performance characteristic training set and a material performance characteristic test set;

[0129] Step S34: constructing a performance evaluation pre-model according to the material performance characteristic training set, and setting initial parameters to obtain a rubber material performance evaluation pre-model; training the rubber material performance evaluation pre-model through the material performance characteristic test set to obtain a rubber material performance evaluation training model;

[0130] Step S35: performing a model cross-validation evaluation on the rubber material performance evaluation training model through the material performance feature training set, specifically calculating the model accuracy, recall rate and F1 score index, and obtaining the training model evaluation data;

[0131] Step S36: adjusting the model parameters of the rubber material performance evaluation training model according to the training model evaluation data to obtain the rubber material performance evaluation model.

[0132] In an embodiment of the present invention, material coupling performance data are read from a database. These data include performance indicators such as tensile strength, elastic modulus, acid resistance and alkali resistance of rubber, and performance change trend detection is performed on the material coupling performance data. A data analysis tool, such as the Pandas library in Python, is used to perform time series analysis on each performance indicator. By calculating the rate of change of the performance indicator over time, the rising, falling or stable trend of the performance is identified. For example, for the tensile strength data, the difference between adjacent time points is calculated to obtain the performance change trend data; then, the performance change trend data is subjected to performance evolution detection. The polynomial fitting method is used to fit the curve of the performance indicator changing over time. For example, the numpy.polyfit function in Python is used to perform quadratic polynomial fitting on the change of tensile strength over time, predict the performance evolution at future time points, and generate material performance evolution data; the material coupling performance data and the material performance evolution data are merged. Using the Pandas library, the two sets of data are merged according to the timestamp and sample number. For example, the measured values ​​in the coupling performance data are merged with the predicted values ​​in the performance evolution data to form a complete material performance characteristic data set. The material performance characteristic data set is divided into a training set and a test set in a ratio of 8:2. Using the train_test_split function in Python, 80% of the data are randomly selected as the material performance characteristic training set, and the remaining 20% ​​of the data are used as the material performance characteristic test set. The performance evaluation pre-model is constructed based on the material performance characteristic training set. The support vector machine (SVM) is selected as the evaluation model, and the sklearn.svm.SVC class in Python is used. The initial parameters are set, the kernel function is selected as the radial basis function (RBF), the penalty parameter C is set to 1, and the kernel function parameter γ is set to 0.1; then, the rubber material performance evaluation pre-model is trained using the material performance characteristic test set. The fit method is used to fit the training set data, and the model parameters are adjusted to optimize the performance. For example, the C and γ parameters of SVM are adjusted by the grid search method to find the optimal parameter combination and obtain the rubber material performance evaluation training model; the rubber material performance evaluation training model is cross-validated and evaluated through the material performance feature training set. The 5-fold cross-validation method is used to divide the training set into 5 subsets, 4 subsets are used for training each time, and the remaining 1 subset is used for verification. The accuracy, recall rate and F1 score indicators of the model on the verification set are calculated; the model parameters of the rubber material performance evaluation training model are adjusted according to the training model evaluation data. According to the cross-validation results, the model parameters are fine-tuned. If the recall rate of the model is low, the penalty parameter C is appropriately increased to reduce the model deviation; if the F1 score is low, the kernel function parameter γ is adjusted to optimize the generalization ability of the model. After multiple adjustments and verifications, the optimized rubber material performance evaluation model is finally obtained.

[0133] As an example of the present invention, refer to Figure 3 As shown, in this example, step S31 includes:

[0134] Step S311: extracting the performance test time of the material coupling performance data to obtain the material performance test time;

[0135] Step S312: Perform material physical strength time variation detection on the material coupling performance data according to the performance test time to generate a physical performance time variation feature; perform material chemical strength time variation detection on the material coupling performance data according to the performance test time to generate a chemical performance time variation feature;

[0136] Step S313: identifying performance change trends based on the time-varying characteristics of the physical properties and the time-varying characteristics of the chemical properties, and obtaining performance change trend data;

[0137] Step S314: determining the time series of the performance change trend data to obtain performance time series data; dividing the performance time series data into time stages to generate performance time stage data;

[0138] Step S315: Calculate the performance evolution rate of the performance time stage data to obtain the performance evolution rate; identify the performance evolution state of the performance change trend data according to the performance evolution rate to generate material performance evolution data.

[0139] In an embodiment of the present invention, material coupling performance data are read from a database, and these data include performance indicators such as tensile strength, elastic modulus, acid resistance and alkali resistance of rubber, and corresponding test timestamps. Using Python's Pandas library, the test time field of each data is extracted and formatted into a unified time format (such as YYYY-MM-DDHH:MM:SS). For example, for a record, its test time field test_time is extracted and converted into the datetime type of Pandas to obtain the material performance test time; according to the performance test time, the material coupling performance data is subjected to time change detection of physical and chemical properties. For physical properties (such as tensile strength and elastic modulus), the difference method is used to calculate the performance change amount of adjacent time points. For example, for tensile strength data, the difference between adjacent time points is calculated to obtain the time change characteristics of physical properties. For chemical properties (such as acid resistance and alkali resistance), the percentage change rate calculation method is used to calculate the performance change rate of adjacent time points to obtain the time change characteristics of chemical properties; based on the time change characteristics of physical properties and the time change characteristics of chemical properties, the performance change trend is identified. Use the moving average method to smooth the time-varying characteristics to eliminate the impact of short-term fluctuations. For example, a 30-day moving average window is applied to the physical performance time-varying characteristic data to calculate the moving average at each time point. According to the direction of change of the moving average (increasing, decreasing, or stable), the performance change trend is identified to obtain the performance change trend data; the performance change trend data is determined as a time series. Use time series analysis tools, such as Python's statsmodels library, to model the performance change trend data. For example, the ARIMA model is used to fit the performance change trend data to determine its time series characteristics. Subsequently, the performance time series data is segmented into time stages. According to the significant points of performance change (such as trend turning points), the time series is segmented into different stages. For example, the dynamic time warping (DTW) method is used to identify the key turning points in the time series, the time series is segmented into multiple stages, and performance time stage data is generated; the performance evolution rate is calculated for the performance time stage data. In each time stage, the rate of change of the performance indicator is calculated. For example, for the tensile strength data, its slope is calculated in each stage as the performance evolution rate. According to the performance evolution rate, the performance change trend data is used to identify the performance evolution state. Thresholds are set, such as an evolution rate greater than 0.1 indicates a rapid increase, less than -0.1 indicates a rapid decrease, and between the two indicates stability. Based on these thresholds, the performance evolution rate is classified into states such as rapid increase, stability, or rapid decrease, and material performance evolution data is generated.

[0140] Preferably, step S4 comprises the following steps:

[0141] Step S41: inputting the original data of the rubber material into the rubber material performance evaluation model to perform performance index mapping processing to obtain performance index mapping data;

[0142] Step S42: Performing a working condition scenario indicator evaluation on the performance indicator mapping data to generate working condition scenario indicator data; performing a material physicochemical characteristic evaluation on the working condition scenario indicator data to obtain physicochemical characteristic performance evaluation data;

[0143] Step S43: marking the performance level of the physical and chemical characteristic performance evaluation data to obtain the rubber material performance evaluation result;

[0144] Step S44: Graphically process the rubber material performance evaluation results to obtain performance evaluation graphical results; compile a visual report of the performance evaluation graphical results to generate a rubber material performance data evaluation report.

[0145] In an embodiment of the present invention, the original data of the rubber material is input into the rubber material performance evaluation model for performance index mapping processing. The model is constructed based on a machine learning algorithm, such as a support vector machine (SVM) or a random forest (RF), and is implemented using the scikit-learn library of Python. The input parameters of the model include performance indicators such as tensile strength, elastic modulus, hardness, acid resistance and alkali resistance of the rubber, as well as the corresponding test timestamp. The initial parameters of the model are set as follows: the kernel function of the SVM is a radial basis function (RBF), the penalty parameter C is 1, and the kernel function parameter γ is 0.1; the performance index mapping data is evaluated for the working condition scenario index. Using a cluster analysis method, such as the K-Means algorithm, the performance index mapping data is divided into different working condition scenarios. For example, according to the combined characteristics of tensile strength and elastic modulus, the rubber material is divided into three working condition scenarios of high elasticity, medium elasticity and low elasticity. Subsequently, the material physicochemical characteristics of the working condition scenario index data are evaluated. The principal component analysis (PCA) method is used to extract the main physicochemical characteristics under each working condition, such as the combined characteristics of hardness and acid resistance, to generate physicochemical characteristic performance evaluation data; the physicochemical characteristic performance evaluation data is marked with performance grades. According to the preset performance grade classification standard, the physicochemical characteristic performance evaluation data is divided into four grades: excellent, good, medium, and poor. For example, if the hardness and acid resistance of a rubber material are both higher than the set threshold, it is marked as "excellent"; if only one indicator is higher than the threshold, it is marked as "good". In this way, the performance evaluation results of the rubber material are obtained; the performance evaluation results of the rubber material are graphically processed. Using Python's matplotlib and seaborn libraries, the performance evaluation results are displayed in the form of bar charts, line charts, etc. For example, a bar chart of the performance grade distribution under different working conditions and a line chart of the performance indicators changing over time are drawn. Subsequently, a visual report is compiled for the graphical results of the performance evaluation. The report includes a cover, a table of contents, an abstract, a main text, and a conclusion. In the main text, the performance evaluation process, evaluation results and graphical display content of the rubber material are described in detail, and the final rubber material performance data evaluation report is output in PDF format.

[0146] In the present specification, a performance data evaluation system for a rubber material is also provided, which is used to execute the performance data evaluation method for the rubber material. The performance data evaluation system for a rubber material comprises:

[0147] The rubber material data processing module is used to obtain the original data of the rubber material; perform data preprocessing on the original data of the rubber material to obtain the standard rubber material data; perform physical and chemical feature recognition on the standard rubber material data to obtain the material physical and chemical feature data;

[0148] The material coupling performance simulation module is used to match the standard rubber material data with the rubber working condition scenario to obtain the rubber working condition scenario data; to map the material physical and chemical simulation parameters to the material physical and chemical characteristic data according to the rubber working condition scenario data to obtain the material physical and chemical simulation parameters; to perform material multi-factor coupling simulation on the material physical and chemical simulation parameters to obtain the material coupling simulation data; to perform material performance evaluation on the material coupling simulation data to generate the material coupling performance data;

[0149] The material performance evaluation model construction module is used to detect the performance change trend of the material coupling performance data to obtain the performance change trend data; perform performance evolution detection on the performance change trend data to obtain the material performance evolution data; and construct a performance evaluation model based on the material coupling performance data and the material performance evolution data to obtain the rubber material performance evaluation model;

[0150] The material performance evaluation and display module is used to perform rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain the rubber material performance evaluation results; the rubber material performance evaluation results are visually displayed to generate a rubber material performance data evaluation report.

[0151] The present invention performs data preprocessing on the original data of rubber materials through the rubber material data processing module, and can convert complex and disordered original data into standard rubber material data, ensuring that the data basis for subsequent analysis and processing is unified, standardized and accurate. On this basis, the physical and chemical characteristics of the standard rubber material data are identified, and the physical and chemical characteristic data of the material can be accurately extracted, which completely covers the key physical and chemical properties of the rubber material, provides a comprehensive and accurate feature basis for the subsequent performance evaluation, avoids the evaluation deviation caused by data quality problems or inaccurate feature extraction, and ensures the scientificity and reliability of the entire performance evaluation process. Through the material coupling performance simulation module, the standard rubber material data is matched with the rubber working condition scene, and the rubber material can be accurately matched with various working condition scenes in actual applications, and rubber working condition scene data can be generated to ensure the pertinence and practicality of subsequent simulation and evaluation. Based on the rubber working condition scene data, the material physical and chemical characteristic data is simulated by multi-factor coupling, which fully considers the complexity of the interaction of multiple factors of the rubber material under actual working conditions, and the obtained material coupling simulation data can truly reflect the performance of the rubber material in actual use. The material coupling performance data generated by the material coupling simulation data provides an accurate and practical evaluation benchmark for subsequent performance evolution detection and model construction, making the entire evaluation process more in line with the actual application scenarios of rubber materials and improving the guiding value of the evaluation results for actual production and application. Through the material performance evaluation model construction module, the performance evolution detection of the material coupling performance data can monitor the changing trend of the rubber material performance in real time and dynamically, and obtain the material performance evolution data, which provides an important basis for evaluating the long-term stability and reliability of the rubber material. The performance evaluation model is constructed based on the material coupling performance data and the material performance evolution data. The rubber material performance evaluation model comprehensively considers the immediate performance of the rubber material under different working conditions and the long-term law of performance evolution. The model construction process is rigorous and scientific. The evaluation model obtained can accurately reflect the overall performance of the rubber material, providing a highly reliable and practical evaluation tool for the subsequent performance evaluation based on the model, effectively improving the accuracy and comprehensiveness of the rubber material performance evaluation, and helping to optimize the production and application process of rubber materials. Performing rubber material performance evaluation on the original data of rubber materials based on the rubber material performance evaluation model can make full use of the accuracy and comprehensiveness of the model, directly generate rubber material performance evaluation results for the original data, ensure the accuracy and objectivity of the evaluation results, and truly reflect the actual performance level of the rubber material.Through the material performance evaluation display module, the rubber material performance evaluation results are visualized and a rubber material performance data evaluation report is generated, which can present complex evaluation results in an intuitive and easy-to-understand manner, making it easy for relevant technical personnel, production management personnel, etc. to quickly understand the pros and cons of rubber material performance, and provide strong support for the production process optimization, quality control and product application decision-making of rubber materials, effectively improving the scientificity and efficiency of rubber material production and application. Therefore, the present invention realizes the physical and chemical feature identification of standard rubber material data through data processing technology, simulation technology and data evaluation technology, and performs multi-factor coupling simulation of materials, constructs a rubber material performance evaluation model, and performs performance evaluation on rubber materials, thereby accurately evaluating the performance of rubber materials in multiple working conditions.

[0152] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0153] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for evaluating performance data of a rubber material, characterized in that: The following steps are involved: Step S1: obtaining original data of rubber material; performing data preprocessing on the original data of rubber material to obtain standard rubber material data; performing physical and chemical feature recognition on the standard rubber material data to obtain material physical and chemical feature data; Step S2: performing rubber working condition scenario matching on standard rubber material data to obtain rubber working condition scenario data; performing material physical and chemical simulation parameter mapping on material physical and chemical characteristic data according to the rubber working condition scenario data to obtain material physical and chemical simulation parameters; performing material multi-factor coupling simulation on the material physical and chemical simulation parameters to obtain material coupling simulation data; performing material performance evaluation on the material coupling simulation data to generate material coupling performance data; Step S3: Detecting the performance change trend of the material coupling performance data to obtain performance change trend data; Perform performance evolution detection on performance change trend data to obtain material performance evolution data; A performance evaluation model is constructed based on material coupling performance data and material performance evolution data to obtain a rubber material performance evaluation model; Step S4: performing rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain a rubber material performance evaluation result; visually displaying the rubber material performance evaluation result to generate a rubber material performance data evaluation report.

2. The performance data evaluation method of rubber material according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire original data of rubber material; Step S12: performing data cleaning processing on the original data of the rubber material to obtain the cleaned data of the rubber material; performing data outlier detection on the cleaned data of the rubber material to generate material data outliers; Step S13: dividing the material data abnormal values ​​into missing values ​​and error values, filling the missing values, and removing the error values ​​to obtain abnormal value processing data; Step S14: normalizing the abnormal value processed data to obtain material normalized data; standardizing the material normalized data to generate standard rubber material data; Step S15: Identify the material physical properties of the standard rubber material data to generate material physical property data; identify the material chemical properties of the standard rubber material data to generate material chemical property data; and perform physicochemical feature marking on the material physical property data and the material chemical property data to obtain material physicochemical feature data.

3. The performance data evaluation method of rubber material according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting working condition characteristics from standard rubber material data to obtain rubber working condition characteristic data; performing working condition parameter mapping on the rubber working condition characteristic data to generate working condition parameter mapping data; Step S22: performing scene determination on the working condition parameter mapping data to obtain preliminary working condition scene data; performing similarity detection on the preliminary working condition scene data to obtain scene similarity data; Step S23: performing rubber working condition scene matching on the preliminary working condition scene data according to the scene similarity data to obtain rubber working condition scene data; Step S24: mapping the material physicochemical characteristic data to material physicochemical simulation parameters according to the rubber working condition scenario data to obtain material physicochemical simulation parameters; performing material multi-factor coupling simulation on the material physicochemical simulation parameters to obtain material coupling simulation data; Step S25: performing material performance evaluation on the material coupling simulation data to generate material coupling performance data.

4. The performance data evaluation method of rubber material according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: recording the stress impact degree of the rubber working condition scene data to obtain the scene stress impact degree; performing rubber deformation influence detection on the rubber working condition scene data according to the scene stress impact degree to generate deformation influence data; Step S242: recording the temperature and humidity parameters of the rubber working condition scene data to obtain the scene temperature and humidity parameters; performing rubber chemical corrosion impact detection on the rubber working condition scene data according to the scene temperature and humidity parameters to generate chemical corrosion impact data; Step S243: performing material physical influence simulation on the material physicochemical characteristic data according to the deformation influence data to obtain material physical influence simulation data; performing material chemical influence simulation on the material physicochemical characteristic data according to the chemical corrosion influence data to obtain material chemical influence simulation data; Step S244: perform feature influence weight assignment on the material physical influence simulation data and the material chemical influence simulation data to obtain simulation weight assignment data; perform material multi-factor coupling simulation on the material physicochemical feature data based on the simulation weight assignment data to obtain material coupling simulation data.

5. The performance data evaluation method of rubber material according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: performing a tensile strength test on the material coupling simulation data to obtain material tensile strength data; performing a material elastic state test on the material tensile strength data to generate material elastic state data; Step S252: performing a material toughness state detection on the material elastic state data to obtain material toughness state data; performing a material deformation critical state judgment based on the material elastic state data and the material toughness state data to obtain deformation state critical data; Step S253: recording the material fixed form duration of the deformation state critical data to generate the fixed form duration; dividing the fixed form duration into time levels to obtain form time level data; Step S254: Map the morphological time level data to the material physical deformation level to obtain material physical deformation level data; evaluate the material physical properties based on the material physical deformation level data to generate material physical property data.

6. The performance data evaluation method of rubber material according to claim 3, characterized in that: Step S25 further includes the following steps: Step S255: performing a chemical reaction test on the material coupling simulation data to obtain material chemical reaction data; performing a chemical stability test on the material chemical reaction data to generate material chemical stability data; Step S256: judging the acid resistance of the material based on the material chemical stability data to obtain the acid resistance of the material; judging the alkali resistance of the material based on the material chemical stability data to obtain the alkali resistance of the material; Step S257: Correlate the chemical resistance of the material according to the acid resistance and alkali resistance of the material to generate material chemical resistance data; Step S258: mapping the material chemical resistance data to the material chemical corrosion resistance level to obtain the material chemical corrosion resistance level data; evaluating the material chemical performance of the material chemical corrosion resistance level data to generate the material chemical performance data; Step S259: Perform material performance evaluation on the material physical performance data and the material chemical performance data to generate material coupling performance data.

7. The performance data evaluation method of rubber material according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing a performance change trend detection on the material coupling performance data to obtain performance change trend data; performing a performance evolution detection on the performance change trend data to obtain material performance evolution data; Step S32: merging the material coupling performance data and the material performance evolution data to obtain a material performance characteristic data set; Step S33: dividing the material performance characteristic data set into a training set and a test set according to a ratio of 8:2 to obtain a material performance characteristic training set and a material performance characteristic test set; Step S34: constructing a performance evaluation pre-model according to the material performance characteristic training set, and setting initial parameters to obtain a rubber material performance evaluation pre-model; training the rubber material performance evaluation pre-model through the material performance characteristic test set to obtain a rubber material performance evaluation training model; Step S35: performing a model cross-validation evaluation on the rubber material performance evaluation training model through the material performance feature training set, specifically calculating the model accuracy, recall rate and F1 score index, and obtaining the training model evaluation data; Step S36: adjusting the model parameters of the rubber material performance evaluation training model according to the training model evaluation data to obtain the rubber material performance evaluation model.

8. The method for evaluating performance data of rubber material according to claim 7, characterized in that: Step S31 includes the following steps: Step S311: extracting the performance test time of the material coupling performance data to obtain the material performance test time; Step S312: Perform material physical strength time variation detection on the material coupling performance data according to the performance test time to generate a physical performance time variation feature; perform material chemical strength time variation detection on the material coupling performance data according to the performance test time to generate a chemical performance time variation feature; Step S313: identifying performance change trends based on the time-varying characteristics of the physical properties and the time-varying characteristics of the chemical properties, and obtaining performance change trend data; Step S314: determining the time series of the performance change trend data to obtain performance time series data; dividing the performance time series data into time stages to generate performance time stage data; Step S315: Calculate the performance evolution rate of the performance time stage data to obtain the performance evolution rate; identify the performance evolution state of the performance change trend data according to the performance evolution rate to generate material performance evolution data.

9. The performance data evaluation method of rubber material according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: inputting the original data of the rubber material into the rubber material performance evaluation model to perform performance index mapping processing to obtain performance index mapping data; Step S42: Performing a working condition scenario indicator evaluation on the performance indicator mapping data to generate working condition scenario indicator data; performing a material physicochemical characteristic evaluation on the working condition scenario indicator data to obtain physicochemical characteristic performance evaluation data; Step S43: marking the performance level of the physical and chemical characteristic performance evaluation data to obtain the rubber material performance evaluation result; Step S44: Graphically process the rubber material performance evaluation results to obtain performance evaluation graphical results; compile a visual report of the performance evaluation graphical results to generate a rubber material performance data evaluation report.

10. A performance data evaluation system for rubber material, characterized in that: Used to execute the performance data evaluation method of the rubber material as claimed in claim 1, the performance data evaluation system of the rubber material comprises: The rubber material data processing module is used to obtain the original data of the rubber material; perform data preprocessing on the original data of the rubber material to obtain the standard rubber material data; perform physical and chemical feature recognition on the standard rubber material data to obtain the material physical and chemical feature data; The material coupling performance simulation module is used to match the standard rubber material data with the rubber working condition scenario to obtain the rubber working condition scenario data; to map the material physical and chemical simulation parameters to the material physical and chemical characteristic data according to the rubber working condition scenario data to obtain the material physical and chemical simulation parameters; to perform material multi-factor coupling simulation on the material physical and chemical simulation parameters to obtain the material coupling simulation data; to perform material performance evaluation on the material coupling simulation data to generate the material coupling performance data; The material performance evaluation model construction module is used to detect the performance change trend of the material coupling performance data to obtain the performance change trend data; perform performance evolution detection on the performance change trend data to obtain the material performance evolution data; and construct a performance evaluation model based on the material coupling performance data and the material performance evolution data to obtain the rubber material performance evaluation model; The material performance evaluation and display module is used to perform rubber material performance evaluation on the original data of the rubber material based on the rubber material performance evaluation model to obtain the rubber material performance evaluation results; the rubber material performance evaluation results are visually displayed to generate a rubber material performance data evaluation report.

Images