Finished product performance testing system for rubber and plastic products

Abstract

The invention relates to the technical field related to performance detection of rubber and plastic products, and specifically includes a finished product performance detection system of rubber and plastic products, comprising: setting an elastic modulus micro-area on the rubber and plastic product to locate rubber weaknesses; generating a point cloud model based on a structure, adding strength detection points, and updating the detection area after optimizing the configuration, analyzing the sound waveform change through sound recognition, and outputting the performance detection result, so as to solve the technical problem that the performance detection of rubber and plastic products is limited to the overall performance, it is difficult to accurately evaluate the local mechanical properties, and it is impossible to timely feedback the internal defects of the rubber and plastic products, and achieve the technical effect of setting an elastic modulus micro-area on the rubber and plastic product, accurately quantifying the elastic properties of different parts, effectively identifying potential rubber weaknesses, so as to carry out targeted in-depth analysis, comprehensively consider the uniformity index and the stress response dispersion index, comprehensively evaluate the mechanical properties and internal structural integrity of the product, timely feedback the internal defects of the rubber and plastic product, and improve the performance detection efficiency and accuracy of the rubber and plastic product.

Description

Technical Field

[0001] The present invention relates to the technical field related to rubber and plastic product performance detection, and in particular to a finished product performance detection system for rubber and plastic products. Background Art

[0002] With the development of industrial technology, rubber and plastic products are widely used in the fields of automobile, aviation, medical treatment, etc. The performance requirements for rubber and plastic products are getting higher and higher, requiring them to have not only excellent mechanical properties, but also good wear resistance, heat resistance and chemical stability. However, due to the complexity of rubber and plastic product materials and the defects that may occur during the production process, conventional detection methods mainly rely on a single mapping empirical model, which is difficult to meet the requirements of modern industry for detection accuracy.

[0003] In summary, the prior art has the technical problem that the performance testing of rubber and plastic products is limited to the overall performance, it is difficult to accurately evaluate the local mechanical properties, and it is impossible to timely feedback the internal defects of the rubber and plastic products. Summary of the invention

[0004] The present application provides a finished product performance testing system for rubber and plastic products, aiming to solve the technical problems in the prior art that the performance testing of rubber and plastic products is limited to the overall performance, it is difficult to accurately evaluate the local mechanical properties, and it is impossible to timely feedback the internal defects of the rubber and plastic products.

[0005] In view of the above problems, the technical solution to implement this application is:

[0006] The present application provides a finished product performance detection system for rubber and plastic products, wherein the system includes: a modulus micro-area setting module, which is used to set M elastic modulus micro-areas on a target rubber and plastic product, wherein the elastic modulus micro-areas correspond to the local elastic modulus of the target rubber and plastic product; a weakness feature positioning module, which is used to add rubber base material information, and locate N rubber weakness features in combination with a rubber and plastic finished product performance detection example; a point cloud model generation module, which is used to generate a point cloud model based on the M elastic modulus micro-areas, combined with the N rubber weakness features, and based on the structure of the target rubber and plastic product; an addition module, which is used to add a point cloud model to the point cloud model. U strength detection center points and U strength detection edge point sets, wherein a strength detection area formed by any one of the strength detection edge point sets corresponds to a specific part of the target rubber and plastic product, and U<M+N; an optimization configuration module, used for, after adding U strength detection center points and U strength detection edge point sets, using an edge optimization algorithm to optimize the configuration with the maximum uniformity and minimum dispersed stress response of the U strength detection areas as the goal; a performance detection module, used for updating the U strength detection areas, and analyzing the sound waveform of the target rubber and plastic product when under pressure through sound recognition technology, and outputting a performance detection result.

[0007] In summary, one or more technical solutions provided in the present application solve the technical problems that the performance detection of rubber and plastic products is limited to the overall performance, it is difficult to accurately evaluate the local mechanical properties, and it is impossible to timely feedback the internal defects of rubber and plastic products. It achieves the technical effect of setting elastic modulus micro-regions on rubber and plastic products, accurately quantifying the elastic properties of different parts, effectively identifying potential rubber weaknesses, and thus conducting targeted in-depth analysis, comprehensively considering uniformity indicators and stress response dispersion indicators, comprehensively evaluating the mechanical properties and internal structural integrity of the products, timely feedback the internal defects of rubber and plastic products, and improving the efficiency and accuracy of performance detection of rubber and plastic products. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A structural schematic diagram of a finished product performance testing system for rubber and plastic products is provided for this application;

[0009] Figure 2 The present application provides a schematic flow chart of the execution steps of generating an elastic modulus distribution map of a modulus micro-region setting module in a finished product performance detection system for rubber and plastic products.

[0010] Explanation of the reference numerals: modulus micro-area setting module M100, weakness feature positioning module M200, point cloud model generation module M300, optimization configuration module M500, performance detection module M600. DETAILED DESCRIPTION

[0011] Example

[0012] The present application is described in detail below with reference to the accompanying drawings. Figure 1 As shown, the present application provides a finished product performance detection system for rubber and plastic products, the system comprising:

[0013] The modulus micro-region setting module M100 is used to set M elastic modulus micro-regions on the target rubber and plastic product, and the elastic modulus micro-regions correspond to the local elastic modulus of the target rubber and plastic product; the weakness feature positioning module M200 is used to add rubber base material information, and locate N rubber weakness features in combination with rubber and plastic finished product performance detection examples; the point cloud model generation module M300 is used to generate a point cloud model based on the M elastic modulus micro-regions, combined with the N rubber weakness features, and taking the structure of the target rubber and plastic product as the basic architecture.

[0014] Specifically, the elastic modulus micro-area refers to multiple small areas selected on the target rubber and plastic products, which are used to measure and analyze the local elastic modulus of these areas. The elastic modulus is the ability of the material to resist deformation and reflects the rigidity of the material; the rubber base material information includes the chemical composition of the rubber, production process parameters and historical performance data, etc., which are used to analyze and compare the differences between the actual performance and theoretical performance of rubber and plastic products. The rubber weakness characteristics refer to the potential defect areas or areas with weaker performance located on the rubber and plastic products. By detecting these characteristics, potential quality problems of the product can be identified.

[0015] Set elastic modulus micro-areas, select and set M elastic modulus micro-areas on the target rubber and plastic products. The setting of the elastic modulus micro-areas needs to evenly cover the surface of the entire product so as to fully reflect the elastic modulus of each part of the product; use a high-precision imaging device to scan the surface of the product and select the micro-area position; determine the specific position and size of each micro-area to ensure even coverage of the surface of the product, represent the elastic modulus of each area, and form a rubber and plastic product with multiple elastic modulus micro-areas to provide basic data for subsequent testing.

[0016] Add rubber base material information, collect and add rubber base material information, including rubber chemical composition, production process parameters, etc.; input this information into the detection system for reference and comparison during the detection process; combine with rubber and plastic finished product performance detection examples, analyze and locate N rubber weakness characteristics. Rubber weaknesses are often areas in rubber and plastic products that are prone to defects or insufficient performance. Determine the weak areas in rubber and plastic products to provide a basis for further detection.

[0017] Generate a point cloud model based on the M elastic modulus micro-areas and N rubber weakness features, take the structure of the target rubber and plastic product as the basic framework, and use three-dimensional scanning technology to generate a point cloud model; the point cloud model reflects the surface and internal structure of the rubber and plastic product through a three-dimensional coordinate data set obtained by scanning and measuring.

[0018] Through the above steps, multiple elastic modulus micro-areas and strength detection points are set, combined with high-precision imaging and thermal data acquisition, it is possible to accurately detect tiny defects and performance changes inside rubber and plastic products, and use machine learning algorithms to conduct in-depth learning and analysis of the detection data to improve the efficiency and accuracy of data processing. It is possible to quickly analyze and predict the performance status of rubber and plastic products, achieve a comprehensive evaluation of the comprehensive performance of rubber and plastic products, and output key indicators such as compressive strength, elastic modulus distribution uniformity, and potential weak areas.

[0019] Add a module M400 for adding U intensity detection center points and U intensity detection edge point sets in the point cloud model, where the intensity detection area formed by any one intensity detection edge point set corresponds to a specific part of the target rubber and plastic product, and U < M + N; an optimization configuration module M500 for, after adding U intensity detection center points and U intensity detection edge point sets, using an edge optimization algorithm to perform optimization configuration with the maximum uniformity and minimum dispersion stress response of the U intensity detection areas as the goals; a performance detection module M600 for updating the U intensity detection areas and analyzing the sound waveform deformation sound pattern of the target rubber and plastic product under pressure through voice recognition technology, and outputting a performance detection result.

[0020] Specifically, the intensity detection center points and edge point sets are detection points added in the point cloud model for further refining and optimizing intensity detection; the edge optimization algorithm is used to achieve an optimal configuration under multi-objective conditions, and the specific goals include maximum uniformity and minimum dispersion stress response; the sound wave signal is used to analyze the sound waveform deformation of the rubber and plastic product under pressure, so as to identify the performance of the product.

[0021] Add intensity detection points, add U intensity detection center points and U intensity detection edge point sets in the point cloud model, where the intensity detection area formed by any one intensity detection edge point set corresponds to a specific part of the target rubber and plastic product, and U < M + N; perform optimization configuration through an edge optimization algorithm to ensure the maximum uniformity and minimum dispersion stress response of the intensity detection area, and update the U intensity detection areas so that they can fully cover the key strength areas and potential weaknesses of the rubber and plastic product.

[0022] Through voice recognition technology, analyze the sound waveform deformation sound pattern of the target rubber and plastic product under pressure; record and process the sound wave signal, separate the characteristic frequencies related to the internal structure change of the material; combine with a standard sound pattern database for comparison, analyze the sound pattern difference, and output a performance detection result, including internal defects and structural discontinuities. Through voice recognition technology, output a performance detection result to comprehensively evaluate the quality of the rubber and plastic product. Further, by analyzing the sound waveform deformation sound pattern of the rubber and plastic product under pressure through voice recognition technology, internal defects and structural discontinuities can be accurately identified, providing a strong guarantee for the high-quality detection of the rubber and plastic product.

[0023] Further, as Figure 2 shown, the modulus micro-region setting module M100 is further used to execute the following method:

[0024] A high-precision imaging device is used to analyze the surface of the target rubber and plastic product, and M elastic modulus micro-areas are selected; while applying pressure to a first elastic modulus micro-area among the M elastic modulus micro-areas, heat change data of the first elastic modulus micro-area is collected to obtain a first heat data set; based on the first heat data set, the M elastic modulus micro-areas are traversed to obtain M heat data sets, and an elastic modulus distribution map is generated in combination with the pressure parameters of the M elastic modulus micro-areas, and the elastic modulus distribution map is used to reflect the distribution characteristics of the U intensity detection edge point sets.

[0025] High-precision imaging devices are used to accurately analyze the surface of rubber and plastic products and obtain detailed images of the surface and internal structure, such as scanning electron microscopes and atomic force microscopes; thermal data sets refer to the thermal changes in the elastic modulus micro-areas when pressure is applied, reflecting the thermodynamic properties of the material under stress; elastic modulus distribution maps are maps generated based on thermal data and pressure parameters of multiple elastic modulus micro-areas, and are used to display the local elastic modulus distribution characteristics of rubber and plastic products.

[0026] Select and set M elastic modulus micro-areas on the target rubber and plastic product, use a high-precision imaging device to scan the surface of the product, and select the micro-area position; determine the specific position and size of each micro-area to ensure uniform coverage of the surface of the product, represent the elastic modulus of each area, and form a rubber and plastic product with multiple elastic modulus micro-areas, providing basic data for subsequent testing.

[0027] A high-precision imaging device is used to analyze the surface of the target rubber and plastic product, select M elastic modulus micro-areas, obtain a detailed image of the surface of the rubber and plastic product, determine the specific position and size of the micro-area, ensure uniform coverage, and accurately select the position and size of the elastic modulus micro-area to provide a basis for the collection of thermal data.

[0028] While applying pressure to the first elastic modulus micro-region among the M elastic modulus micro-regions, collect the thermal change data of the first elastic modulus micro-region, obtain the first thermal data set, record the applied force and the thermal change of the micro-region, and ensure the accuracy and completeness of the data; obtain the thermal data of the first elastic modulus micro-region to provide a reference for subsequent traversal.

[0029] Based on the first thermal data set, the M elastic modulus micro-areas are traversed to obtain M thermal data sets. The same pressure and heat change data are collected for each elastic modulus micro-area to ensure that the data of each micro-area are comparable. The thermal data sets of all elastic modulus micro-areas are obtained to provide a data basis for generating an elastic modulus distribution map.

[0030] Combined with the pressure parameters of the M elastic modulus micro-regions, an elastic modulus distribution map is generated. The elastic modulus distribution map reflects the elastic modulus and its distribution characteristics of each micro-region, which is used to further analyze and optimize the setting of strength detection points, form a detailed elastic modulus distribution map, and provide a basis for reflecting the distribution characteristics of the strength detection edge point set.

[0031] Based on the elastic modulus distribution map, the strength detection edge point set is reasonably set to optimize the detection process to ensure the reliability and accuracy of the detection results; the generation and analysis of the elastic modulus distribution map makes the detection results more comprehensive, can reflect the performance differences of various parts of rubber and plastic products, and provide detailed performance evaluation. Through systematic data collection and map generation, the efficiency and accuracy of data processing are improved, and the performance status of rubber and plastic products can be quickly analyzed and predicted.

[0032] Furthermore, the optimization configuration module M500 is used to execute the following method:

[0033] Based on the elastic modulus distribution map, the key strength area of ​​the target rubber and plastic product is identified; the U strength detection center points and the U strength detection edge point sets are combined to complete the initialization configuration of the U strength detection areas; after completing the initialization configuration, the uniformity index E of the first strength detection center point and the first strength detection edge point set, the second strength detection center point and the second strength detection edge point set, ..., the Uth strength detection center point and the Uth strength detection edge point set is evaluated. i and stress response dispersion index S i , and perform iterative optimization.

[0034] Based on the elastic modulus distribution map, the key strength area of ​​the target rubber and plastic product is identified, the elastic modulus distribution in the map is analyzed, the areas with greater stress and possible weak areas are determined, and the key strength area of ​​the rubber and plastic product is determined, providing a basis for the setting of subsequent strength detection points.

[0035] The U intensity detection center points and the U intensity detection edge point sets are combined to complete the initial configuration of the intensity detection area; the specific location of each detection area and the distribution of detection points are determined to ensure that the detection points cover all key intensity areas, and the initial layout of the intensity detection points is completed to provide a basis for further optimization.

[0036] Evaluate the uniformity index E of the first intensity detection center point and the first intensity detection edge point set, the second intensity detection center point and the second intensity detection edge point set, ..., the U-th intensity detection center point and the U-th intensity detection edge point set i and stress response dispersion index S i , where the uniformity index E iIt is used to measure the uniformity of the distribution of detection points in the region, and the stress response dispersion index S i Used to measure the response differences of the test points when subjected to stress; calculate and record the uniformity and stress response dispersion data of each test point to provide a reference for the optimization process.

[0037] Through the edge optimization algorithm, the detection point configuration is iteratively optimized with the maximum uniformity and minimum dispersed stress response as the goal; in each iteration, the position and distribution of the detection points are adjusted, and the uniformity and stress response dispersion indicators are re-evaluated until the optimal configuration is reached. The optimization of the detection point configuration is completed, uniform distribution and minimum stress response dispersion are achieved, and the accuracy and reliability of detection are improved.

[0038] Through the above steps, the edge optimization algorithm is used to iteratively optimize the detection points to ensure the uniformity of the detection area and the minimum dispersed stress response, improve the stability and repeatability of the detection, optimize the detection process and data processing capabilities, and provide a strong guarantee for the high-quality production and application of rubber and plastic products.

[0039] Furthermore, the finished product performance detection system of the rubber and plastic product is also used to perform the following method:

[0040] The uniformity index E i and stress response dispersion index S i ; Evaluate the optimization objective function F of the first intensity detection center point and the first intensity detection edge point set, the second intensity detection center point and the second intensity detection edge point set, ..., the U-th intensity detection center point and the U-th intensity detection edge point set= ; Among them, w1 and w2 are the weight coefficients corresponding to the uniformity index and the stress response dispersion index respectively.

[0041] In a feasible implementation manner, the uniformity index E i Used to measure the uniformity of the distribution of detection points in the region; stress response dispersion index S i It is used to measure the response difference of the detection point when subjected to force. It has been verified that the optimization objective function F= First, by optimizing the weight configuration of the uniformity index E in the objective function, the detection points in the strength detection area are more evenly distributed, which improves the comprehensiveness of the detection; second, by optimizing the weight configuration of the uniformity index S i The weight configuration makes the response of each detection point more consistent when subjected to force, reduces detection errors, and improves the stability and reliability of detection.

[0042] Generally speaking, by adjusting the weight coefficients w1 and w2 in the optimization objective function, we can flexibly respond to different detection needs, find the best balance between uniformity and stress response dispersion, and improve the adaptability of the detection scheme; enhance the stability of the detection area configuration: during the iterative optimization process, continuously adjust and evaluate the detection point configuration to ensure that the final detection area has the greatest uniformity and the smallest stress response dispersion, thereby improving the stability of the detection results.

[0043] Furthermore, the finished product performance detection system of the rubber and plastic product is also used to perform the following method:

[0044] The uniformity index E i = ; where x ij is the elastic modulus of the jth intensity detection edge point in the i-th intensity detection area, is the mean elastic modulus of the i-th strength detection area, and n is the number of strength detection edge points in the i-th strength detection area.

[0045] Preferably, the uniformity index E i = ,By optimizing the uniformity index Ei, the detection points in the intensity detection area are distributed more evenly,,reducing the performance differences between the detection points, ensuring that the points in each intensity detection area are evenly distributed,,and improving the comprehensiveness and representativeness of the detection.

[0046] Overall, the uniformity index E i The optimized configuration makes the detection results of each area more consistent during the detection process, reducing the data fluctuation caused by uneven point distribution. Furthermore, by adjusting the uniformity index E i Continuous optimization and iteration have improved the stability and accuracy of data in the detection area and ensured the reliability of the detection results.

[0047] Furthermore, the finished product performance detection system of the rubber and plastic product is also used to perform the following method:

[0048] The stress response dispersion index S i = ;in, is the sample variance of the i-th intensity detection area, is the overall variance.

[0049] Preferably, the stress response dispersion index S i = , by optimizing the stress response dispersion index S i , making the response of each detection point more consistent when subjected to force, reducing the fluctuation of data during the detection process, improving the stability of the detection, and optimizing the stress response dispersion index S i, which helps ensure the consistency of test results and makes the performance evaluation of each test area more accurate and reliable.

[0050] In general, the stress response dispersion index S i The continuous optimization and iteration of the stress response dispersion index S i The evaluation and optimization ensures that the points in each intensity detection area are reasonably distributed, thus improving the effectiveness of the overall detection solution.

[0051] Furthermore, the performance detection module M600 is used to perform the following method:

[0052] When under pressure, acoustic sensors are arranged at key stress-bearing parts of the rubber and plastic products to synchronously record the sound wave signals generated during the pressure process; the sound wave signals are processed using spectrum analysis technology to separate the characteristic frequencies related to the changes in the internal structure of the material, and compared with the standard voiceprint database to analyze the voiceprint differences and identify performance test results, which include internal defects and structural discontinuities.

[0053] Identify the types of rubber and plastic products to be tested and their expected application environments, understand the possible internal defects or structural discontinuities; design the layout of acoustic sensors based on the structural characteristics and expected stress conditions of the rubber and plastic products. Identify the key stress-bearing locations, which are usually stress concentration areas or locations prone to fatigue damage.

[0054] Select a suitable acoustic sensor, considering its sensitivity, frequency response range and durability, to ensure that it can accurately capture the weak sound wave signals when under pressure; establish a test platform that can apply controllable pressure to rubber and plastic products, and ensure that the acoustic sensor can be stably installed in the predetermined position.

[0055] Install acoustic sensors at the key stress-bearing parts of rubber and plastic products to ensure good contact between the sensors and the test materials and reduce external noise interference; start the test platform to apply pressure to the rubber and plastic products, and turn on the acoustic sensors to synchronously record the sound wave signals generated during the pressure process. The entire process needs to ensure signal continuity and time synchronization.

[0056] Filter the original sound wave signal to remove environmental noise and other irrelevant signals to ensure the accuracy of subsequent analysis; use fast Fourier transform (FFT) or other spectrum analysis techniques to convert time domain signals into frequency domain signals to facilitate the observation of different frequency components; identify characteristic frequencies related to changes in the internal structure of the material in the spectrum diagram. These characteristic frequencies often correspond to the inherent vibration mode of the material or abnormal responses caused by defects.

[0057] Collect the sound wave signals of healthy rubber and plastic products under similar conditions, establish a standard voiceprint database as a reference; compare the spectrum characteristics of the current test sample with the standard voiceprint database, and analyze the voiceprint differences. Use statistical methods or machine learning algorithms to enhance the accuracy of recognition; based on the voiceprint differences, determine whether there are internal defects (such as bubbles, cracks), structural discontinuities or other performance problems, and give corresponding diagnostic conclusions.

[0058] In the actual application process, it also includes summarizing the analysis results to form a detailed test report, including test methods, data charts, analysis conclusions and recommended measures. Based on the test results, the performance test situation is fed back to the production and R&D team, and suggestions for improving product design or production processes are put forward. It combines physical experiments with data analysis, and through advanced signal processing technology and intelligent algorithms, it realizes non-destructive evaluation of the internal state of rubber and plastic products, which helps to improve product quality and manufacturing process level.

[0059] Furthermore, the performance detection module M600 is also used to execute the following method:

[0060] The test data processing flow is integrated, and deep learning is performed using machine learning algorithms to determine a finished product quality assessment model; the finished product quality assessment model allows remote access and instant decision adjustments.

[0061] Summarize the data obtained from elastic modulus detection, heat change analysis, sound waveform voiceprint recognition, and other links, as well as the production parameters of rubber and plastic products, raw material information, etc.; eliminate outliers, fill in missing values, standardize or normalize data to ensure data quality for machine learning algorithm processing; based on professional knowledge and preliminary exploratory analysis, select or construct features that are valuable for finished product quality prediction, such as the mean elastic modulus, stress response indicators, etc.

[0062] According to the nature of the problem (such as classification or regression) and data characteristics, select appropriate machine learning algorithms, such as support vector machines, random forests, neural networks, etc., or directly adopt deep learning frameworks such as convolutional neural networks (CNN), recurrent neural networks (RNN), etc.; divide the data set into training sets and validation sets to ensure the generalization ability of the model; use the training set data to train the selected model, optimize the model parameters through iteration, and minimize the loss function.

[0063] Evaluate model performance on the validation set and adjust model structure or parameters based on evaluation metrics (such as accuracy, recall, F1 score, etc.); apply cross-validation techniques to further ensure the stability and reliability of the model; use grid search, random search, or Bayesian optimization to find the best model configuration.

[0064] Integrate the trained model into the detection system, design an interface to receive detection data and output quality assessment results; ensure seamless connection between the model and other detection links (such as voiceprint analysis and elastic modulus detection) to form a complete data processing link.

[0065] Develop RESTful APIs or web services so that the model can be accessed remotely over the network; set user access rights to ensure data security and privacy protection; build a visual interface to display test results and model predictions in real time, allowing decision makers to remotely view and instantly adjust production parameters or take improvement measures based on model recommendations.

[0066] In the actual application process, it also includes regularly updating model training data, incorporating test results of new batches of products, maintaining the timeliness of the model, continuously monitoring the performance of the model in actual applications, regularly evaluating and performing necessary model updates or retraining, establishing a user feedback mechanism, collecting problems encountered during use or suggestions for improvement, and continuously optimizing the model and the entire detection system.

[0067] Through the above operations, an efficient finished product quality assessment system is built to support remote monitoring and instant decision-making, effectively improving the quality control level and production efficiency of rubber and plastic products.

[0068] In summary, the beneficial effects of the embodiments of the present application are:

[0069] 1. Through fine elastic modulus micro-area analysis and thermal data collection, the local mechanical properties of rubber and plastic products are accurately reflected. The edge optimization algorithm is used to optimize the layout of the detection area, ensuring the uniformity of the detection results and the accuracy of the stress response, reducing misjudgment and missed judgment.

[0070] 2. The application of sound recognition technology enables the analysis of the sound waveform changes when under pressure, which helps to find defects at an early stage. At the same time, with the help of algorithms and machine learning, the degree of automation of detection is greatly improved, and the detection efficiency and quality control level are improved.

[0071] 3. Comprehensive consideration of uniformity, stress response and potential defects provides a scientific basis for the comprehensive performance evaluation of rubber and plastic products, and contributes to the continuous improvement and optimization of product quality.

[0072] 4. When the product is under pressure, acoustic sensors are placed at the key stress-bearing parts of the rubber and plastic products to simultaneously record the sound wave signals generated during the pressure process; spectrum analysis technology is used to process the sound wave signals, separate the characteristic frequencies related to the changes in the internal structure of the material, and compare them with the standard voiceprint database to analyze the voiceprint differences and identify the performance test results, which include internal defects and structural discontinuities. It integrates physical experiments and data analysis, and through advanced signal processing technology and intelligent algorithms, it realizes non-destructive evaluation of the internal state of rubber and plastic products, which helps to improve product quality and manufacturing process level.

[0073] In summary, any step can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor, and no unnecessary restrictions are made here.

[0074] Furthermore, the above-mentioned technical scheme only reflects the preferred technical scheme of the technical scheme of the embodiment of the present application. Some changes that may be made to some parts thereof by technicians in this technical field all reflect the novel principles of the embodiment of the present application. Obviously, technicians in this field can make various changes and modifications to the present application without departing from the scope of the present application.

Claims

1. The finished product performance testing system of rubber and plastic products is characterized by: The system comprises: A modulus micro-region setting module, used to set M elastic modulus micro-regions on the target rubber and plastic product, wherein the elastic modulus micro-regions correspond to the local elastic modulus of the target rubber and plastic product; Weakness feature location module, used to add rubber base material information, combine rubber and plastic finished product performance test examples, and locate N rubber weakness features; A point cloud model generation module, for generating a point cloud model based on the M elastic modulus micro-regions, in combination with the N rubber weakness features, and taking the structure of the target rubber and plastic product as a basic framework; An additional module is used to add U intensity detection center points and U intensity detection edge point sets in the point cloud model; An optimization configuration module is used to optimize the configuration by using an edge optimization algorithm after adding U strength detection center points and U strength detection edge point sets, with the maximum uniformity and minimum dispersed stress response of the U strength detection areas as the goal; A performance detection module, used to update the U strength detection areas, and analyze the sound waveform of the target rubber and plastic product when it is under pressure through sound recognition technology, and output the performance detection result; Wherein, the modulus micro-region setting module further includes: Using a high-precision imaging device, the surface of the target rubber and plastic product is analyzed, and M elastic modulus micro-regions are selected; While applying pressure to a first elastic modulus micro-region among the M elastic modulus micro-regions, collecting heat change data of the first elastic modulus micro-region to obtain a first heat data set; Based on the first heat data set, traverse the M elastic modulus micro-regions to obtain M heat data sets, and generate an elastic modulus distribution map in combination with the pressure parameters of the M elastic modulus micro-regions, wherein the elastic modulus distribution map is used to reflect the distribution characteristics of the U strength detection edge point sets; Wherein, the optimization configuration module includes: Based on the elastic modulus distribution map, identifying the key strength area of ​​the target rubber and plastic product; The U intensity detection center points and the U intensity detection edge point sets are combined to complete the initialization configuration of the U intensity detection areas; After completing the initialization configuration, the uniformity index Ei and the stress response dispersion index Si of the first intensity detection center point and the first intensity detection edge point set, the second intensity detection center point and the second intensity detection edge point set, ..., the Uth intensity detection center point and the Uth intensity detection edge point set are evaluated, and iterative optimization is performed; Among them, the uniformity index Ei and the stress response dispersion index Si; Evaluate the optimization objective function F of the first intensity detection center point and the first intensity detection edge point set, the second intensity detection center point and the second intensity detection edge point set, ..., the U-th intensity detection center point and the U-th intensity detection edge point set= ; Among them, w1 and w2 are the weight coefficients corresponding to the uniformity index and the stress response dispersion index respectively; Wherein, the uniformity index Ei= ; Where xij is the elastic modulus of the jth intensity detection edge point in the i-th intensity detection area, is the mean value of the elastic modulus of the i-th strength detection area, and n is the number of strength detection edge points in the i-th strength detection area; Wherein, the stress response dispersion index Si= ; in, is the sample variance of the i-th intensity detection area, is the overall variance; Wherein, the performance detection module includes: When under pressure, an acoustic sensor is arranged at a key stress-bearing position of the rubber and plastic product to synchronously record the sound wave signal generated during the pressure process; The acoustic wave signal is processed using spectrum analysis technology to separate characteristic frequencies related to changes in the internal structure of the material, and compared with a standard voiceprint database to analyze voiceprint differences and identify performance test results, including internal defects and structural discontinuities.

2. The finished product performance detection system of rubber and plastic products according to claim 1, characterized in that: The performance detection module also includes: Integrate the inspection data processing process, use machine learning algorithms, conduct deep learning, and determine the finished product quality assessment model; The finished product quality assessment model allows remote access and instant decision adjustments.

Images