Performance detection method and system for lauryl sodium sulfate

Abstract

The invention discloses a lauryl sodium sulfate performance detection method and system, and relates to the field related to intelligent detection.The method comprises the steps that a target purpose is read, performance requirement analysis is conducted, and related performance indexes are determined; component detection is carried out, and target component information is determined; image acquisition is carried out, an image acquisition result is identified and analyzed, and target structure information is obtained; constructing an analogue simulation experiment field, performing a simulation experiment, and generating a simulation test image set; performing performance evaluation through a performance evaluation unit to obtain a plurality of performance evaluation coefficients; and performing weighted fusion to generate a comprehensive performance evaluation coefficient, performing judgment through a preset performance coefficient threshold, and outputting a target performance detection result. The technical problems of low detection efficiency and insufficient accuracy and reliability of a detection result caused by long test period and limited test range of the existing lauryl sodium sulfate performance detection are solved, and the technical effect of rapid, comprehensive and accurate detection is achieved.

Description

Technical Field

[0001] The present application relates to the field of intelligent detection, and in particular to a performance detection method and system for sodium dodecyl sulfate. Background Art

[0002] With the rapid development of the chemical industry, sodium dodecyl sulfate, as an important surfactant, has occupied a pivotal position in daily life and industrial applications. From detergents, cosmetics to industrial cleaners and other fields, the performance of sodium dodecyl sulfate directly affects the quality of the product and user experience. Therefore, it is particularly important to accurately and efficiently detect and evaluate the performance of sodium dodecyl sulfate. Traditional sodium dodecyl sulfate performance testing methods mainly rely on laboratory physical and chemical tests. Although these methods can obtain certain performance parameters of sodium dodecyl sulfate, they cannot meet the needs of rapid testing due to the long test cycle, and due to the limited test range, the performance of sodium dodecyl sulfate cannot be fully evaluated.

[0003] In the current related technologies, the performance testing of sodium dodecyl sulfate has technical problems such as low testing efficiency, insufficient accuracy and reliability of test results due to long testing cycle and limited testing range. Summary of the invention

[0004] The present application provides a performance detection method and system for sodium dodecyl sulfate, which adopts the method of reading the target use of the sodium dodecyl sulfate to be detected, analyzing its performance requirements, and using an integrated analysis unit, a structure recognition unit and a simulation experiment field to quickly obtain the target component information and target structure information of the sodium dodecyl sulfate. The performance evaluation unit performs performance evaluation on a simulated test image set to obtain multiple performance evaluation coefficients, and uses an influence scalar for weighted fusion to generate a comprehensive performance evaluation coefficient. The comprehensive performance evaluation coefficient is judged by a preset performance coefficient threshold, and the target performance detection result and other technical means are output, thereby achieving the technical effect of realizing rapid, comprehensive and accurate detection of the performance of sodium dodecyl sulfate.

[0005] The present application provides a performance detection method for sodium lauryl sulfate, comprising:

[0006] The target use of the sodium dodecyl sulfate to be detected is read, and the target use is transferred to the performance analysis unit for performance requirement analysis to determine related performance indicators, wherein the related performance indicators include performance attributes and influencing scalars; the component detection of the sodium dodecyl sulfate to be detected is performed by the integrated analysis unit to determine the target component information; the image of the sodium dodecyl sulfate to be detected is captured, and the image capture result is recognized and analyzed by the structure recognition unit to obtain the target structure information; a simulation test field is constructed, and a simulation experiment is performed based on the target component information and the target structure information to generate a simulation test image set; the performance of the simulation test image set is evaluated by the performance evaluation unit to obtain a plurality of performance evaluation coefficients, wherein the performance evaluation coefficients correspond to the performance attributes one by one; the plurality of performance evaluation coefficients are weighted and fused based on the influencing scalar to generate a comprehensive performance evaluation coefficient, and the comprehensive performance evaluation coefficient is judged by a preset performance coefficient threshold to output the target performance detection result.

[0007] In a possible implementation, before transferring the target usage to the performance analysis unit for performance requirement analysis, the following processing is performed:

[0008] Taking the sodium dodecyl sulfate to be detected as a constraint condition, a sample usage data set is obtained based on industrial big data retrieval; the sample usage data set is clustered based on preset usage purposes, and data with usage effects greater than expected effects in multiple clustering data sets are extracted to obtain multiple standard clustering data sets, wherein the preset usage purposes include multiple usage types; performance attribute analysis is performed on the multiple standard clustering data sets in turn to determine multiple associated performance indicators; based on a classification decision tree, the performance analysis unit is generated with the multiple usage types and the multiple associated performance indicators as construction data.

[0009] In a possible implementation, the performance attribute analysis is performed on the multiple standard clustering data sets in sequence to determine multiple associated performance indicators, and the following processing is performed:

[0010] A first standard clustering data set is selected, and performance attribute analysis and attribute importance evaluation are performed on the first standard clustering data set to obtain multiple first performance analysis data sets, wherein each first performance analysis data set includes multiple performance attributes and multiple attribute importances; based on the multiple first performance analysis data sets, the occurrence frequency of performance attributes is counted, and performance attributes greater than a frequency threshold are selected as first key performance attributes to obtain multiple first key performance attributes; multiple attribute importance sets of the multiple first key performance attributes are obtained, and mean calculation is performed to obtain multiple first attribute importances; first associated performance indicators are constructed based on the multiple first key performance attributes and the multiple first attribute importances, and added to the multiple associated performance indicators.

[0011] In a possible implementation, before the component detection of the sodium dodecyl sulfate to be detected by the integrated analysis unit, the following processing is performed:

[0012] Build a liquid chromatography detection module, a gas chromatography detection module, a mass spectrometry detection module and an infrared spectrum detection module; call historical detection records, and respectively count the detection accuracy and detection stability of the liquid chromatography detection module, the gas chromatography detection module, the mass spectrometry detection module and the infrared spectrum detection module; perform credibility evaluation based on the detection accuracy and detection stability, determine the credibility weight, and respectively identify the liquid chromatography detection module, the gas chromatography detection module, the mass spectrometry detection module and the infrared spectrum detection module according to the credibility weight, and construct the integrated analysis unit.

[0013] In a possible implementation, a simulation experiment field is constructed to perform the following processing:

[0014] The target application scenario of the sodium dodecyl sulfate to be detected is obtained, and the condition parameters of the target application scenario are quantified to determine the target application condition parameters; based on industrial big data, information retrieval is performed with the sodium dodecyl sulfate to be detected and the target application condition parameters as constraints to obtain a sample experimental data set, wherein the sample experimental data includes sample composition information, sample structure information and sample test images; an experimental test model is built based on a feedforward neural network, and supervised training and feedback verification are performed on the experimental test model through the sample experimental data set to obtain a convergence experimental test model that meets the expected convergence index; the simulation test field is built according to the fusion of the convergence experimental test model and the three-dimensional visual platform.

[0015] In a possible implementation, before the performance evaluation unit performs performance evaluation on the simulated test image set, the following processing is performed:

[0016] Based on the performance analysis unit, multiple performance attributes are obtained, and a first performance attribute is selected; the first performance attribute is analyzed, and a first performance evaluation indicator is configured, wherein the first performance evaluation indicator includes multiple first evaluation parameters and multiple parameter influence coefficients, and the parameter influence coefficients are obtained by evaluating the coefficient of variation algorithm; based on the first performance evaluation indicator, a first analysis feature set is determined, and the convolution neural network is supervised and trained with the first analysis feature set as a convolution target to obtain a first convolution channel; based on the first convolution channel, the performance evaluation unit is built.

[0017] In a possible implementation, the performance evaluation unit is built based on the first convolution channel, and the following processing is performed:

[0018] The first performance evaluation indicator is embedded in the first convolution channel to generate a first evaluation channel; using the same method for obtaining the first evaluation channel, multiple evaluation channels of the multiple performance attributes are sequentially obtained, and the performance evaluation unit is constructed according to the multiple evaluation channels.

[0019] The present application also provides a performance detection system for sodium lauryl sulfate, comprising:

[0020] A performance requirement analysis module, the performance requirement analysis module is used to read the target use of the sodium dodecyl sulfate to be detected, and transfer the target use to the performance analysis unit for performance requirement analysis, and determine the associated performance indicators, wherein the associated performance indicators include performance attributes and influencing scalars; a component detection module, the component detection module is used to perform component detection on the sodium dodecyl sulfate to be detected through an integrated analysis unit to determine target component information; an image acquisition module, the image acquisition module is used to perform image acquisition on the sodium dodecyl sulfate to be detected, and identify and analyze the image acquisition results through a structure recognition unit to obtain target structure information; a simulation experiment module, the The simulation experiment module is used to construct a simulation experiment field, conduct simulation experiments based on the target component information and the target structure information, and generate a simulation test image set; the performance evaluation module is used to perform performance evaluation on the simulation test image set through a performance evaluation unit to obtain multiple performance evaluation coefficients, wherein the performance evaluation coefficients correspond to the performance attributes one by one; the performance detection result output module is used to perform weighted fusion of the multiple performance evaluation coefficients based on the influencing scalar to generate a comprehensive performance evaluation coefficient, and judge the comprehensive performance evaluation coefficient through a preset performance coefficient threshold, and output the target performance detection result.

[0021] A performance detection method and system for sodium dodecyl sulfate proposed in the present application first reads the target use of the sodium dodecyl sulfate to be detected, and transfers the target use to a performance analysis unit for performance requirement analysis to determine related performance indicators, wherein the related performance indicators include performance attributes and influencing scalars, and then performs component detection on the sodium dodecyl sulfate to be detected through an integrated analysis unit to determine the target component information, and then performs image acquisition on the sodium dodecyl sulfate to be detected, and recognizes and analyzes the image acquisition results through a structure recognition unit to obtain target structure information, and then constructs a simulation test field, performs simulation experiments based on the target component information and target structure information, generates a simulation test image set, and then performs performance evaluation on the simulation test image set through a performance evaluation unit to obtain multiple performance evaluation coefficients, wherein the performance evaluation coefficients and performance attributes correspond one to one, and finally performs weighted fusion of multiple performance evaluation coefficients based on the influencing scalar to generate a comprehensive performance evaluation coefficient, and judges the comprehensive performance evaluation coefficient through a preset performance coefficient threshold, and outputs the target performance detection result, thereby achieving the technical effect of realizing rapid, comprehensive and accurate detection of the performance of sodium dodecyl sulfate. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A schematic flow chart of a method for detecting the performance of sodium dodecyl sulfate provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the structure of a performance detection system for sodium dodecyl sulfate provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: performance requirement analysis module 10 , component detection module 20 , image acquisition module 30 , simulation experiment module 40 , performance evaluation module 50 , performance detection result output module 60 . DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The present application example provides a method for detecting the performance of sodium lauryl sulfate. Figure 1 As shown, the method includes:

[0030] Step S100, read the target use of the sodium dodecyl sulfate to be detected, and transfer the target use to the performance analysis unit for performance requirement analysis to determine the associated performance indicators, wherein the associated performance indicators include performance attributes and impact scalars. Specifically, the predetermined use scenario or target use of the sodium dodecyl sulfate to be detected is read through a user interface or a data interface, and this information includes that the sodium dodecyl sulfate is used as a detergent, a detergent, a foaming agent, a textile auxiliary agent, etc. After reading the target use, this information is passed to the performance analysis unit through a data communication protocol, such as an API call, a message queue, a database query, etc. The performance analysis unit is a specially designed module or system component for analyzing the target use of sodium dodecyl sulfate and determining related performance indicators. After receiving the target use information, the performance analysis unit starts the corresponding analysis algorithm or queries the preset database, and determines the key performance indicators directly related to the performance of sodium dodecyl sulfate under the target use according to the target use. For example, if sodium dodecyl sulfate is used for detergents, the key performance indicators include decontamination performance, foam stability, etc. After the analysis is completed, the performance analysis unit outputs a result set containing associated performance indicators. The associated performance indicators include performance attributes and impact scalars. Among them, performance attributes refer to the specific performance requirements that sodium dodecyl sulfate needs to meet under specific uses, such as detergency performance, foaming performance, emulsification performance, etc. Each performance attribute corresponds to one or more specific measurement or evaluation standards; the impact scalar refers to the relative importance or weight of different performance attributes in the overall performance evaluation, and the impact scalar is determined based on factors such as empirical data, expert opinions or market demand.

[0031] In a possible implementation, before the target use is transferred to the performance analysis unit for performance requirement analysis, step S100 further includes step S110, taking the sodium dodecyl sulfate to be detected as a constraint condition, and obtaining a sample usage data set based on industrial big data retrieval. Specifically, determine the type, specification and other constraints of the sodium dodecyl sulfate to be detected, access the industrial big data repository (a huge data set from the industrial field, containing information such as the use and performance of various products and materials), use the constraints to search, retrieve historical usage data sets similar to the sodium dodecyl sulfate to be detected, and use the retrieved data sets as sample usage data sets. Step S120, cluster the sample usage data sets based on preset usage purposes, and extract data from multiple clustered data sets with usage effects greater than expected effects to obtain multiple standard clustered data sets, wherein the preset usage purposes include multiple usage types. Specifically, cluster analysis is performed on the sample usage data set according to the preset usage of sodium dodecyl sulfate (such as detergent, emulsifier, etc.), and the samples in the sample usage data set are divided into several non-overlapping subsets (i.e., "clusters"), and the samples in each cluster are as similar as possible, and the differences between samples in different clusters are as large as possible. The usage effect in each cluster data set is evaluated and compared with the expected effect, and the data set with the usage effect greater than the expected effect is extracted as the standard cluster data set. Step S130, the performance attribute analysis of the multiple standard cluster data sets is performed in turn, and multiple related performance indicators are determined. Specifically, the performance performance analysis of each standard cluster data set under various usage scenarios is performed, and the key attributes or indicators closely related to the performance of sodium dodecyl sulfate are identified, and the analysis results are integrated to determine multiple related performance indicators. Step S140, based on the classification decision tree, the performance analysis unit is generated with the multiple usage types and the multiple related performance indicators as the construction data. Specifically, prepare to construct data, including multiple usage types and multiple associated performance indicators, select a classification decision tree algorithm (a classification algorithm based on a tree structure, which recursively divides a data set into different subsets to construct a classification model), use the constructed data to train a classification decision tree model, and generate a performance analysis unit based on the trained model. The performance analysis unit can quickly and accurately analyze the performance requirements of sodium dodecyl sulfate based on the input usage of sodium dodecyl sulfate. This implementation method uses industrial big data and machine learning technology to accurately analyze the performance requirements of sodium dodecyl sulfate, achieving the technical effect of improving the accuracy and efficiency of the performance requirement analysis of sodium dodecyl sulfate.

[0032] In a possible implementation, step S130 further includes step S131, selecting a first standard clustering data set, and performing performance attribute analysis and attribute importance evaluation on the first standard clustering data set to obtain multiple first performance analysis data sets, wherein each first performance analysis data set includes multiple performance attributes and multiple attribute importances. Specifically, any one data set is selected from multiple standard clustering data sets as the first standard clustering data set, and for the selected first standard clustering data set, a detailed analysis of the performance attributes is performed through an expert system, a machine learning model, etc., and the importance of each performance attribute is evaluated. Step S132, based on the multiple first performance analysis data sets, the occurrence frequency of the performance attributes is counted, and the performance attributes greater than the frequency threshold are selected as the first key performance attributes to obtain multiple first key performance attributes. Specifically, multiple first performance analysis data sets are counted, the frequency of each performance attribute in all data sets is calculated, a frequency threshold is set according to business needs or experience, and the performance attributes with an occurrence frequency greater than the frequency threshold are selected as the first key performance attributes. Step S133, obtain multiple attribute importance sets of the multiple first key performance attributes, and perform mean calculation to obtain multiple first attribute importances. Specifically, from all attribute importance evaluations of each first key performance attribute, obtain its corresponding attribute importance set, perform mean calculation on the attribute importance set of each key performance attribute, and obtain the average importance of the performance attribute. Step S134, construct a first associated performance indicator based on the multiple first key performance attributes and the multiple first attribute importances, and add it to the multiple associated performance indicators. Specifically, based on the first key performance attributes obtained in steps S132 and S133 and their corresponding average importance, construct a first associated performance indicator, which is a combination of one or more key performance attributes and their importance. Add the constructed first associated performance indicator to multiple associated performance indicator sets. This implementation method determines the key performance attributes by selecting performance attributes greater than the frequency threshold, thereby achieving the technical effect of improving the accuracy and reliability of the associated performance indicators.

[0033] Step S200, the component of the sodium dodecyl sulfate to be detected is detected by the integrated analysis unit to determine the target component information. Specifically, an appropriate amount of sample is taken from the sodium dodecyl sulfate to be detected to ensure that the sample is representative and can reflect the quality of the overall product. According to different analysis requirements, the sample is pre-treated, such as dissolving, diluting, filtering, etc. The integrated analysis unit is started. The integrated analysis unit is a system that integrates a variety of analysis techniques and equipment for comprehensive component detection of sodium dodecyl sulfate. The pre-set analysis parameters and programs are loaded, and the chemical analysis equipment in the integrated analysis unit, such as a chromatograph, a mass spectrometer, a spectrometer, etc., is used to perform component analysis on the sodium dodecyl sulfate sample to be detected. The integrated analysis unit obtains information such as the content and structure of various components in the sample by chemically separating, detecting and measuring the sample. The obtained data is collected, sorted and processed to extract key target component information, including detailed information such as the main components, molecular structure, purity, etc. of sodium dodecyl sulfate.

[0034] In a possible implementation, before the component detection of the sodium dodecyl sulfate to be detected by the integrated analysis unit, step S200 further includes step S210, setting up a liquid chromatography detection module, a gas chromatography detection module, a mass spectrometry detection module and an infrared spectrum detection module. Specifically, according to the experimental requirements, prepare liquid chromatographs, gas chromatographs, mass spectrometers and infrared spectrometers, and prepare corresponding detection reagents, sample pretreatment equipment, etc., install and debug each module equipment to ensure that the equipment can work normally. According to the characteristics of the sodium dodecyl sulfate to be detected, set the parameters of each detection module, such as mobile phase ratio, chromatographic column model, detection wavelength, etc. Step S220, call historical detection records, and respectively count the detection accuracy and detection stability of the liquid chromatography detection module, gas chromatography detection module, mass spectrometry detection module and infrared spectrum detection module. Specifically, call the historical detection records of each detection module from the database, including information such as detection results, actual values, and detection time. Compare the test results in the historical test records with the actual values, calculate the accuracy of each detection module, and use indicators such as correctness or error rate to represent; analyze the fluctuation of the test results in the historical test records, and evaluate the stability and repeatability of each detection module. Step S230, based on the detection accuracy and detection stability, a credibility evaluation is performed, and the credible weight is determined, and the liquid chromatography detection module, the gas chromatography detection module, the mass spectrometry detection module, and the infrared spectrum detection module are respectively identified according to the credible weight, and the integrated analysis unit is constructed. Specifically, the detection accuracy and detection stability of each detection module are comprehensively analyzed, and a credibility evaluation is performed, which can be represented by a score or a weight. According to the credibility evaluation result, the credible weight of each detection module is determined, and the greater the weight, the higher the reliability of the module in the integrated analysis. According to the credible weight, each detection module is identified, such as using different colors, labels or numbers. Combine each detection module according to certain rules (such as parallel, series, etc.), construct an integrated analysis unit, and realize the detection analysis of multi-technology fusion. This implementation method fully utilizes the advantages of various detection technologies by building multiple detection modules (liquid chromatography, gas chromatography, mass spectrometry and infrared spectroscopy) and evaluating and weighting them based on historical detection records. Through the construction of an integrated analysis unit, it realizes the integration and complementarity of multiple detection technologies, achieving the technical effect of comprehensively and accurately detecting the components of the sodium dodecyl sulfate to be detected, and improving the accuracy and reliability of the detection results.

[0035] Step S300, image acquisition is performed on the sodium dodecyl sulfate to be detected, and the image acquisition result is identified and analyzed by the structure recognition unit to obtain the target structure information. Specifically, prepare the sodium dodecyl sulfate sample to be detected, ensure that the sample is clearly visible in the acquisition area, use a high-resolution camera, microscope or other image acquisition equipment to shoot or scan the sodium dodecyl sulfate sample, and obtain the image data of the sample. The collected image is preprocessed by image processing software or algorithm, including operations such as denoising, enhancing contrast, adjusting color balance, etc., to improve the image quality and ensure that the image can accurately reflect the structural characteristics of sodium dodecyl sulfate in subsequent analysis. Start the structure recognition unit, the structure recognition unit is constructed based on a deep learning algorithm (such as a convolutional neural network), and is used to identify and analyze the structure of sodium dodecyl sulfate in the image, input the preprocessed image data into the structure recognition unit, start the recognition algorithm, the algorithm extracts and classifies the sodium dodecyl sulfate structure in the image, and identifies the color, morphology, granularity and other structural information of sodium dodecyl sulfate. According to the recognition result, a data set or report containing the target structure information is generated.

[0036] Step S400, construct a simulation experiment field, conduct a simulation experiment based on the target component information and the target structure information, and generate a simulation test image set. Specifically, according to the experimental requirements, determine the scale and configuration of the simulation experiment field, including selecting simulation software, setting experimental parameters, configuring hardware equipment, etc., wherein the simulation experiment field is a virtual experimental environment, which is used to simulate the behavior and reaction of sodium dodecyl sulfate under real experimental conditions, and is constructed based on computer technology and simulation technology for virtual experiments and tests. The target component information and target structure information of sodium dodecyl sulfate obtained in steps S200 and S300 are input into the simulation experiment field. This information is the basic data of the simulation experiment and is used to construct a virtual sodium dodecyl sulfate sample and experimental environment. According to the purpose and requirements of the experiment, set the relevant parameters of the simulation experiment, including temperature, pressure, concentration, reaction time, etc., start the simulation experiment of the simulation experiment field, and simulate the behavior and reaction of sodium dodecyl sulfate in the virtual environment according to the input target component information and target structure information, as well as the set experimental parameters. During the simulation experiment, the changes and reactions of sodium dodecyl sulfate in the virtual environment were recorded to generate a series of simulated test images, which showed the behavioral characteristics of sodium dodecyl sulfate under different experimental conditions, such as color changes, morphology changes, reaction rate, etc.

[0037] In a possible implementation, a simulation test field is constructed, and step S400 further includes step S410, obtaining the target application scenario of the sodium dodecyl sulfate to be detected, and quantifying the condition parameters of the target application scenario to determine the target application condition parameters. Specifically, determine which scenarios, environments or fields the sodium dodecyl sulfate to be detected is designed or expected to be used for in actual applications, such as detergents, cosmetics, industrial cleaning, etc., and analyze various condition parameters that affect the performance of sodium dodecyl sulfate for the target application scenario, such as temperature, pH value, electrolyte concentration, etc. Collect historical data of these condition parameters in actual applications, and perform statistical analysis, such as calculating the mode value, mean value, standard deviation, etc., to determine the target application condition parameters. Step S420, based on industrial big data, information retrieval is performed with the sodium dodecyl sulfate to be detected and the target application condition parameters as constraints to obtain a sample experimental data set, wherein the sample experimental data includes sample composition information, sample structure information and sample test images. Specifically, the industrial big data platform is used to search for relevant experimental data by taking the sodium dodecyl sulfate to be detected and the target application condition parameters as search conditions, wherein industrial big data refers to a large amount of data generated in the industrial field, including production data, experimental data, equipment data, etc., and sample experimental data that meet the target application scenario and condition parameters are screened out from the retrieved data, and the screened sample experimental data are sorted out, including sample composition information, sample structure information, and sample test images. Step S430, build an experimental test model based on a feedforward neural network, and supervise the training and feedback verification of the experimental test model through the sample experimental data set to obtain a converged experimental test model that meets the expected convergence index. Specifically, a feedforward neural network (such as a multilayer perceptron) is used to build an experimental test model, which can simulate the performance of sodium lauryl sulfate to be detected under different conditions, and the model is trained using a sample experimental data set. By adjusting the parameters and weights of the model, the model can accurately predict the performance of the material under different conditions, and the model is constantly verified during the training process, and the degree of coincidence between the prediction results of the model and the actual experimental results is checked, and the model parameters are adjusted according to feedback. When the prediction results of the model reach a certain accuracy, and the training error and the verification error no longer decrease significantly, it is considered that the model has converged and the training is stopped. Step S440, according to the convergence experimental test model and the three-dimensional visual platform fusion to build the simulation test field. Specifically, the converged experimental test model is combined with a three-dimensional visual platform (a software or hardware platform that can present three-dimensional images and data, for realizing the visualization and analysis of complex data), and the visualization of the model is realized. The experimental test model is run on the three-dimensional visual platform to simulate the performance of sodium lauryl sulfate to be detected under different conditions, and the results of the simulation experiment are displayed by the three-dimensional visual platform, including images of material performance changes, data curves, etc.This implementation method uses industrial big data and machine learning technology to accurately predict the performance of materials under different conditions, achieving the technical effect of improving the accuracy and reliability of experimental simulations in simulation test fields.

[0038] Step S500, the performance evaluation unit performs performance evaluation on the simulated test image set to obtain a plurality of performance evaluation coefficients, wherein the performance evaluation coefficients correspond to the performance attributes one by one. Specifically, the performance evaluation unit is started, and the preset evaluation criteria and algorithm are loaded. The performance evaluation unit is a system or module for performing performance evaluation on the simulated test image set. Based on the preset evaluation criteria and algorithm, the image data is processed and analyzed to generate performance evaluation coefficients. The simulated test image set is imported into the performance evaluation unit, and matched with the simulated test image set according to the preset performance attribute list in the performance evaluation unit. Each performance attribute corresponds to one or more specific image features or data indicators. Feature extraction is performed on each image in the simulated test image set. The extracted features include color, texture, shape, dynamic change, etc. Each performance attribute is evaluated according to the extracted image features and the preset evaluation criteria. The image data is analyzed and processed using an evaluation algorithm (such as a machine learning algorithm, a statistical method, etc.) to generate a corresponding performance evaluation coefficient. The performance evaluation coefficient is an indicator used to quantify the performance of sodium dodecyl sulfate under different performance attributes. It corresponds to the performance attribute one by one and reflects the performance level of sodium dodecyl sulfate in a specific aspect.

[0039] In a possible implementation, before the performance evaluation of the simulated test image set is performed by the performance evaluation unit, step S500 further includes step S510, obtaining multiple performance attributes based on the performance analysis unit, and selecting a first performance attribute. Specifically, multiple performance attributes related to the sodium dodecyl sulfate to be detected are obtained by the performance analysis unit, and any one of the multiple performance attributes is selected as the first performance attribute of current concern, such as foaming performance. Step S520, the first performance attribute is analyzed and a first performance evaluation index is configured, wherein the first performance evaluation index includes multiple first evaluation parameters and multiple parameter influence coefficients, and the parameter influence coefficients are obtained by evaluating the coefficient of variation algorithm. Specifically, the first performance attribute (such as foaming performance) is deeply analyzed to determine the sub-indicators and influencing factors it contains, and the first performance evaluation index is configured according to the attribute analysis results, and the first performance evaluation index includes multiple first evaluation parameters (specific indicators for quantitatively evaluating a certain performance attribute, such as foaming ratio, foam stability, foam fineness, etc.) and multiple parameter influence coefficients. Among them, the parameter influence coefficient is the weight or coefficient that represents the degree of influence of the evaluation parameter on the overall performance. The coefficient of variation algorithm is used to evaluate the influence coefficient of each evaluation parameter by calculating the ratio of the standard deviation of the evaluation parameter to the mean value. Step S530, determine the first analysis feature set based on the first performance evaluation index, and use the first analysis feature set as the convolution target to supervise the convolution neural network and obtain the first convolution channel. Specifically, determine the first analysis feature set related to the first performance evaluation index, and the first analysis feature set is extracted from the original data (such as image data, etc.) and is a feature set related to the performance evaluation index. Set the first analysis feature set as the supervised training target of the convolution neural network, use labeled sample data (i.e., data with known performance attributes) to train the convolution neural network, adjust the network parameters through the back propagation algorithm, so that the network can accurately extract features related to the first performance attribute from the input data. After the training is completed, the first convolution channel for the first performance attribute is obtained, and the first convolution channel can extract features that are highly related to the first performance attribute. Step S540, build the performance evaluation unit based on the first convolution channel. Specifically, the trained first convolution channel is integrated into the performance evaluation unit, which receives a set of simulated test images of sodium dodecyl sulfate to be evaluated, extracts features related to the first performance attribute through the first convolution channel, and evaluates the performance of sodium dodecyl sulfate based on these features. This implementation achieves the technical effect of improving the accuracy and efficiency of performance evaluation by constructing an evaluation unit for specific performance attributes.

[0040] In a possible implementation, step S540 further includes step S541, embedding the first performance evaluation indicator into the first convolution channel to generate a first evaluation channel. Specifically, in the trained first convolution channel, the first performance evaluation indicator is embedded to generate a first evaluation channel, which is used to evaluate the extracted features of the convolution layer according to the first performance evaluation indicator, and the first performance evaluation coefficient is obtained by weighted calculation based on the evaluation result and the parameter influence coefficient. Step S541, using the same method for obtaining the first evaluation channel, sequentially obtain multiple evaluation channels of the multiple performance attributes, and construct the performance evaluation unit according to the multiple evaluation channels. Specifically, for each performance attribute (except the first performance attribute that has been processed), repeat steps S510 (selecting performance attributes), S520 (configuring performance evaluation indicators), S530 (determining analysis feature sets and training convolution channels) and S541 (embedding evaluation indicators and generating evaluation channels). For each performance attribute, a corresponding evaluation channel is generated, and multiple evaluation channels are integrated into a unified performance evaluation unit, so that the performance evaluation unit can simultaneously process the evaluation tasks of multiple performance attributes. This implementation embeds the performance evaluation index directly into the convolution channel, ensuring that the channel specifically extracts and evaluates features for the performance attribute, thereby achieving the technical effect of improving the accuracy of performance evaluation.

[0041] Step S600, based on the influence scalar, the multiple performance evaluation coefficients are weighted and fused to generate a comprehensive performance evaluation coefficient, and the comprehensive performance evaluation coefficient is judged by a preset performance coefficient threshold, and the target performance test result is output. Specifically, the influence scalar reflects the importance or weight of each performance evaluation coefficient in the comprehensive evaluation. The determined influence scalar is used as the weight to perform weighted fusion on multiple performance evaluation coefficients. The weighted fusion method can be selected according to the actual situation, such as weighted average, weighted summation, etc. Through weighted fusion, a value that comprehensively reflects the overall performance of sodium dodecyl sulfate is obtained, that is, a comprehensive performance evaluation coefficient. According to the experimental requirements and the performance requirements of sodium dodecyl sulfate, a preset performance coefficient threshold is set. The preset performance coefficient threshold is a numerical limit used to judge whether the performance of sodium dodecyl sulfate meets the requirements or reaches the preset standard. Compare the comprehensive performance evaluation coefficient with the preset performance coefficient threshold. If the comprehensive performance evaluation coefficient is higher than or equal to the preset performance coefficient threshold, it is judged that the performance of sodium dodecyl sulfate meets the requirements, and a positive or qualified target performance test result is output; if the comprehensive performance evaluation coefficient is lower than the preset performance coefficient threshold, it is judged that the performance of sodium dodecyl sulfate does not meet the requirements, and a negative or unqualified target performance test result is output. The embodiment of the present application adopts technical means such as reading the target use of the sodium dodecyl sulfate to be detected, analyzing its performance requirements, and using an integrated analysis unit, a structure recognition unit, and a simulation test field to quickly obtain the target component information and target structure information of the sodium dodecyl sulfate. The performance evaluation unit performs performance evaluation on the simulated test image set to obtain multiple performance evaluation coefficients, and uses the influence scalar for weighted fusion to generate a comprehensive performance evaluation coefficient. The comprehensive performance evaluation coefficient is judged by a preset performance coefficient threshold, and the target performance test result is output, thereby achieving the technical effect of realizing rapid, comprehensive, and accurate detection of the performance of sodium dodecyl sulfate.

[0042] In the above, refer to Figure 1 A performance testing method for sodium lauryl sulfate according to an embodiment of the present invention is described in detail. Figure 2 A performance detection system for sodium dodecyl sulfate according to an embodiment of the present invention is described.

[0043] A performance detection system for sodium dodecyl sulfate according to an embodiment of the present invention is used to solve the technical problems of low detection efficiency, insufficient accuracy and reliability of detection results due to long test cycle and limited test range in the existing performance detection of sodium dodecyl sulfate, so as to achieve the technical effect of rapid, comprehensive and accurate detection of the performance of sodium dodecyl sulfate. A performance detection system for sodium dodecyl sulfate includes: a performance requirement analysis module 10, a component detection module 20, an image acquisition module 30, a simulation experiment module 40, a performance evaluation module 50, and a performance detection result output module 60.

[0044] The performance requirement analysis module 10 is used to read the target use of the sodium dodecyl sulfate to be tested, and transfer the target use to the performance analysis unit for performance requirement analysis to determine related performance indicators, wherein the related performance indicators include performance attributes and impact scalars.

[0045] The component detection module 20 is used to perform component detection on the sodium dodecyl sulfate to be detected through an integrated analysis unit to determine target component information.

[0046] The image acquisition module 30 is used to acquire images of the sodium dodecyl sulfate to be detected, and to identify and analyze the image acquisition results through a structure recognition unit to obtain target structure information.

[0047] The simulation experiment module 40 is used to construct a simulation experiment field, perform a simulation experiment based on the target component information and the target structure information, and generate a simulation test image set.

[0048] The performance evaluation module 50 is used to perform performance evaluation on the simulation test image set through a performance evaluation unit to obtain a plurality of performance evaluation coefficients, wherein the performance evaluation coefficients correspond to the performance attributes one by one.

[0049] The performance test result output module 60 is used to perform weighted fusion on the multiple performance evaluation coefficients based on the impact scalar to generate a comprehensive performance evaluation coefficient, and to judge the comprehensive performance evaluation coefficient by a preset performance coefficient threshold to output a target performance test result.

[0050] The specific configuration of the performance requirement analysis module 10 will be described in detail below. As described above, before the target use is transferred to the performance analysis unit for performance requirement analysis, the performance requirement analysis module 10 may further include: a sample use data set acquisition unit is used to obtain a sample use data set based on industrial big data retrieval with the sodium dodecyl sulfate to be detected as a constraint condition; a clustering unit is used to cluster the sample use data set based on a preset use purpose, and extract data from multiple clustering data sets with use effects greater than expected effects to obtain multiple standard clustering data sets, wherein the preset use purpose includes multiple use types; a performance attribute analysis unit is used to perform performance attribute analysis on the multiple standard clustering data sets in turn, and determine multiple related performance indicators; a performance analysis construction unit is used to generate the performance analysis unit based on a classification decision tree, with the multiple use types and the multiple related performance indicators as construction data.

[0051] Among them, the performance attribute analysis is performed on the multiple standard clustering data sets in turn to determine multiple related performance indicators. The performance attribute analysis unit may further include: a first performance analysis data set acquisition subunit is used to select a first standard clustering data set, and perform performance attribute analysis and attribute importance evaluation on the first standard clustering data set to obtain multiple first performance analysis data sets, wherein each first performance analysis data set includes multiple performance attributes and multiple attribute importances; a first key performance attribute acquisition subunit is used to count the occurrence frequency of performance attributes based on the multiple first performance analysis data sets, and select performance attributes greater than the frequency threshold as first key performance attributes to obtain multiple first key performance attributes; a first attribute importance acquisition subunit is used to obtain multiple attribute importance sets of the multiple first key performance attributes, and perform mean calculation to obtain multiple first attribute importances; a first related performance indicator construction subunit is used to construct a first related performance indicator based on the multiple first key performance attributes and the multiple first attribute importances, and add it to the multiple related performance indicators.

[0052] The specific configuration of the component detection module 20 will be described in detail below. As described above, before the component detection of the sodium lauryl sulfate to be detected is performed by the integrated analysis unit, the component detection module 20 may further include: a detection module construction unit for constructing a liquid chromatography detection module, a gas chromatography detection module, a mass spectrometry detection module, and an infrared spectrum detection module; a historical detection statistics unit for calling historical detection records, and respectively counting the detection accuracy and detection stability of the liquid chromatography detection module, the gas chromatography detection module, the mass spectrometry detection module, and the infrared spectrum detection module; a credibility evaluation unit for performing credibility evaluation based on the detection accuracy and detection stability, determining a credibility weight, and marking the liquid chromatography detection module, the gas chromatography detection module, the mass spectrometry detection module, and the infrared spectrum detection module according to the credibility weight, and constructing the integrated analysis unit.

[0053] The specific configuration of the simulation experiment module 40 will be described in detail below. As described above, to construct a simulation experiment field, the simulation experiment module 40 may further include: an application scenario condition parameter quantification unit is used to obtain the target application scenario of the sodium dodecyl sulfate to be detected, and to quantify the condition parameters of the target application scenario to determine the target application condition parameters; a sample experiment data set acquisition unit is used to perform information retrieval based on industrial big data, with the sodium dodecyl sulfate to be detected and the target application condition parameters as constraints, to obtain a sample experiment data set, wherein the sample experiment data includes sample composition information, sample structure information and sample test images; an experiment test model building unit is used to build an experiment test model based on a feedforward neural network, and to supervise the training and feedback verification of the experiment test model through the sample experiment data set to obtain a convergence experiment test model that meets the expected convergence index; a simulation experiment field building unit is used to build the simulation experiment field according to the fusion of the convergence experiment test model and the three-dimensional visual platform.

[0054] The specific configuration of the performance evaluation module 50 will be described in detail below. As described above, before the performance evaluation of the simulated test image set is performed by the performance evaluation unit, the performance evaluation module 50 may further include: a first performance attribute selection unit for obtaining multiple performance attributes based on the performance analysis unit and selecting a first performance attribute; a first performance evaluation index configuration unit for analyzing the first performance attribute and configuring a first performance evaluation index, wherein the first performance evaluation index includes multiple first evaluation parameters and multiple parameter influence coefficients, and the parameter influence coefficients are obtained by evaluating the coefficient of variation algorithm; a first convolution channel acquisition unit for determining a first analysis feature set based on the first performance evaluation index, and using the first analysis feature set as the convolution target to supervise the convolution neural network and obtain a first convolution channel; a performance evaluation construction unit for building the performance evaluation unit based on the first convolution channel.

[0055] Among them, the performance evaluation unit is built based on the first convolution channel, and the performance evaluation building unit may further include: a first evaluation channel generating subunit is used to embed the first performance evaluation indicator into the first convolution channel to generate a first evaluation channel; a performance evaluation construction subunit is used to use the same method of obtaining the first evaluation channel to sequentially obtain multiple evaluation channels of the multiple performance attributes, and construct the performance evaluation unit according to the multiple evaluation channels.

[0056] A sodium dodecyl sulfate performance detection system provided in an embodiment of the present invention can execute a sodium dodecyl sulfate performance detection method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0057] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0058] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A performance testing method for sodium lauryl sulfate, characterized in that: The method comprises: Reading the target use of the sodium dodecyl sulfate to be tested, and transferring the target use to a performance analysis unit for performance requirement analysis to determine associated performance indicators, wherein the associated performance indicators include performance attributes and impact scalars; Performing component detection on the sodium dodecyl sulfate to be detected by an integrated analysis unit to determine target component information; Capturing an image of the sodium dodecyl sulfate to be detected, and performing recognition and analysis on the image acquisition result by a structure recognition unit to obtain target structure information; Constructing a simulation experiment field, performing a simulation experiment based on the target component information and the target structure information, and generating a simulation test image set; Performing performance evaluation on the simulated test image set by a performance evaluation unit to obtain a plurality of performance evaluation coefficients, wherein the performance evaluation coefficients correspond to the performance attributes one by one; The multiple performance evaluation coefficients are weighted and fused based on the impact scalar to generate a comprehensive performance evaluation coefficient, and the comprehensive performance evaluation coefficient is judged by a preset performance coefficient threshold to output a target performance detection result.

2. The performance detection method of sodium lauryl sulfate according to claim 1, characterized in that: The target usage is transferred to the performance analysis unit for performance requirement analysis, which also includes: Taking sodium dodecyl sulfate to be detected as a constraint, the sample usage data set is obtained based on industrial big data retrieval; Clustering the sample usage data sets based on preset usage purposes, and extracting data with usage effects greater than expected effects from multiple clustered data sets to obtain multiple standard clustered data sets, wherein the preset usage purposes include multiple usage types; Performing performance attribute analysis on the plurality of standard clustering data sets in turn to determine a plurality of associated performance indicators; Based on the classification decision tree, the performance analysis unit is generated with the multiple usage types and the multiple associated performance indicators as construction data.

3. A performance detection method for sodium lauryl sulfate according to claim 2, characterized in that: The performance attributes of the plurality of standard clustering data sets are analyzed in sequence to determine a plurality of associated performance indicators, including: Selecting a first standard clustering data set, and performing performance attribute analysis and attribute importance evaluation on the first standard clustering data set to obtain a plurality of first performance analysis data sets, wherein each first performance analysis data set includes a plurality of performance attributes and a plurality of attribute importances; Based on the multiple first performance analysis data sets, counting the occurrence frequencies of performance attributes, and selecting performance attributes greater than a frequency threshold as first key performance attributes, to obtain multiple first key performance attributes; Acquire multiple attribute importance sets of the multiple first key performance attributes, and perform mean calculation to obtain multiple first attribute importances; A first associated performance indicator is constructed based on the plurality of first key performance attributes and the plurality of first attribute importances, and is added to the plurality of associated performance indicators.

4. The performance detection method of sodium lauryl sulfate according to claim 1, characterized in that: The component of the sodium lauryl sulfate to be detected is detected by an integrated analysis unit, and the method also includes: Build liquid chromatography detection module, gas chromatography detection module, mass spectrometry detection module and infrared spectrum detection module; Calling historical detection records, and respectively counting the detection accuracy and detection stability of the liquid chromatography detection module, the gas chromatography detection module, the mass spectrometry detection module, and the infrared spectrum detection module; A credibility evaluation is performed based on the detection accuracy and detection stability, a credibility weight is determined, and the liquid chromatography detection module, gas chromatography detection module, mass spectrometry detection module and infrared spectrum detection module are respectively identified according to the credibility weight to construct the integrated analysis unit.

5. The performance detection method of sodium lauryl sulfate according to claim 1, characterized in that: Construct a simulation experiment field, including: Obtaining a target application scenario of the sodium dodecyl sulfate to be detected, and quantifying condition parameters of the target application scenario to determine target application condition parameters; Based on industrial big data, information retrieval is performed with the sodium dodecyl sulfate to be detected and the target application condition parameters as constraints to obtain a sample experimental data set, wherein the sample experimental data includes sample component information, sample structure information and sample test images; Building an experimental test model based on a feedforward neural network, performing supervised training and feedback verification on the experimental test model through the sample experimental data set, and obtaining a converged experimental test model that meets the expected convergence index; The simulation experiment field is built based on the integration of the convergence experiment test model and the three-dimensional visual platform.

6. The performance detection method of sodium lauryl sulfate according to claim 1, characterized in that: The performance of the simulated test image set is evaluated by a performance evaluation unit, and the method further includes: Obtaining a plurality of performance attributes based on the performance analysis unit, and selecting a first performance attribute; Parsing the first performance attribute and configuring a first performance evaluation indicator, wherein the first performance evaluation indicator includes a plurality of first evaluation parameters and a plurality of parameter influence coefficients, and the parameter influence coefficients are obtained by evaluating through a coefficient of variation algorithm; Determine a first analysis feature set based on the first performance evaluation index, and use the first analysis feature set as a convolution target to perform supervised training on a convolutional neural network to obtain a first convolution channel; The performance evaluation unit is established based on the first convolution channel.

7. The method for detecting the performance of sodium lauryl sulfate according to claim 6, characterized in that: Building the performance evaluation unit based on the first convolution channel includes: Embedding the first performance evaluation indicator into the first convolution channel to generate a first evaluation channel; The same method of acquiring the first evaluation channel is used to sequentially acquire multiple evaluation channels of the multiple performance attributes, and the performance evaluation unit is constructed according to the multiple evaluation channels.

8. A performance detection system for sodium lauryl sulfate, characterized in that: The system is used to implement a performance detection method for sodium lauryl sulfate according to any one of claims 1 to 7, and the system comprises: A performance requirement analysis module, the performance requirement analysis module is used to read the target use of the sodium dodecyl sulfate to be detected, and transfer the target use to the performance analysis unit for performance requirement analysis to determine the associated performance indicators, wherein the associated performance indicators include performance attributes and impact scalars; A component detection module, the component detection module is used to perform component detection on the sodium dodecyl sulfate to be detected through an integrated analysis unit to determine target component information; An image acquisition module, wherein the image acquisition module is used to acquire an image of the sodium dodecyl sulfate to be detected, and to identify and analyze the image acquisition result through a structure recognition unit to obtain target structure information; A simulation experiment module, wherein the simulation experiment module is used to construct a simulation experiment field, perform a simulation experiment based on the target component information and the target structure information, and generate a simulation test image set; A performance evaluation module, the performance evaluation module is used to perform performance evaluation on the simulation test image set through a performance evaluation unit to obtain a plurality of performance evaluation coefficients, wherein the performance evaluation coefficients correspond to the performance attributes one by one; The performance detection result output module is used to perform weighted fusion on the multiple performance evaluation coefficients based on the influencing scalar to generate a comprehensive performance evaluation coefficient, and to judge the comprehensive performance evaluation coefficient by a preset performance coefficient threshold to output a target performance detection result.

Images