Fluorescence performance detection method and equipment for fluorescent textile material and medium

Abstract

The invention provides a fluorescence performance detection method and device for a fluorescent textile material and a medium, and relates to the technical field of performance detection. M doping data sets are obtained; establishing a simulation model by combining the characteristics and the process of the fluorescent dye; performing illumination color fastness virtual prediction according to the simulation model to obtain a first fluorescence performance set; simulating a scene by utilizing an HPLC (High Performance Liquid Chromatography) technology, and evaluating the fluorescence performance of the sample to obtain a second fluorescence Dividing U normal samples and V abnormal samples on the basis of the two sets of evaluation anomalies; and adjusting an abnormal sample process until V is 0, and randomly sampling to detect the fluorescence performance. The technical problems that in existing fluorescent textile material detection, fluorescence performance evaluation depends on a real sample, so that the detection period is long, and various process parameters and use scenes are difficult to comprehensively cover are solved, and the purposes of improving the fluorescence performance detection efficiency and accuracy of the fluorescent textile material, accelerating the product development period and improving the product quality are achieved through repeated iterative simulation. And the product quality stability is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of performance detection, and particularly to a fluorescence performance detection method, device and medium for fluorescent textile materials. Background Art

[0002] With the rapid development of the textile industry and the increasing diversification of consumer demands, fluorescent textile materials have gradually become the focus of market attention due to their unique visual effects and broad application prospects. Fluorescent textile materials can not only add unique colors and lusters to clothing, household items, etc., but also show important values in fields such as safety protection and anti-counterfeiting identification. However, with the expansion of production scale and the improvement of product requirements, the fluorescence performance detection of fluorescent textile materials also faces many challenges. Traditional fluorescence performance detection methods mostly rely on manual visual inspection or simple instrument equipment, which have problems such as low detection efficiency, insufficient accuracy, and being easily affected by subjective factors, and are difficult to meet the requirements of modern industrial production for efficient and accurate detection. Especially in the production process of fluorescent textile materials, the stability and consistency of fluorescence performance are crucial for product quality, and traditional methods are difficult to achieve real-time monitoring and precise control of the entire production process. Summary of the Invention

[0003] The present application provides a fluorescence performance detection method, device and medium for fluorescent textile materials, which are used to solve the technical problems in the existing detection of fluorescent textile materials that rely on physical samples for fluorescence performance evaluation, resulting in a long detection cycle and difficulty in comprehensively covering various process parameters and usage scenarios.

[0004] In view of the above problems, the present application provides a fluorescence performance detection method, device and medium for fluorescent textile materials.

[0005] In the first aspect of the present application, a method for detecting the fluorescence performance of fluorescent textile materials is provided. The method includes: obtaining a fluorescence dye doping data set of M fluorescent textile material samples, where the process parameters corresponding to the fluorescence dye doping data set include the fluorescence dye doping concentration and the doping ratio; introducing the basic characteristics of the fluorescence dye and combining with the textile material process to establish a basic simulation model, where the basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics, and the basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material; based on the basic simulation model, according to the fluorescence dye doping data set, performing virtual prediction analysis on the light fastness of the M fluorescent textile material samples to obtain a first fluorescence performance set; based on the basic simulation model, according to HPLC technology, simulating the influence of different usage scenarios on the fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability, evaluating the performance of the M fluorescent textile material samples to obtain a second fluorescence performance set; based on the first fluorescence performance set and the second fluorescence performance set, performing an abnormality assessment on the M fluorescent textile material samples, dividing them into U samples with normal performance and V samples with abnormal performance, where U + V = M; based on the U samples with normal performance, adjusting the process parameters of the V samples with abnormal performance, and after completing the process parameter adjustment, performing simulation analysis again until the number V of samples with abnormal performance is 0, and then performing fluorescence performance detection by random sampling.

[0006] In the second aspect of the present application, a device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0007] Obtain a fluorescence dye doping dataset of M fluorescent textile material samples. The process parameters corresponding to the fluorescence dye doping dataset include the fluorescence dye doping concentration and the doping ratio. Introduce the basic characteristics of the fluorescence dye, and combine with the fluorescent textile material process to establish a basic simulation model. The basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics. The basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material. Based on the basic simulation model, according to the fluorescence dye doping dataset, conduct virtual prediction analysis on the light fastness of the M fluorescent textile material samples to obtain a first set of fluorescence properties. Based on the basic simulation model, according to HPLC technology, simulate the influence of different usage scenarios on fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability, evaluate the performance of the M fluorescent textile material samples, and obtain a second set of fluorescence properties. Based on the first set of fluorescence properties and the second set of fluorescence properties, conduct an abnormal assessment on the M fluorescent textile material samples, divide them into U samples with normal performance and V samples with abnormal performance, where U + V = M. Based on the U samples with normal performance, adjust the process parameters of the V samples with abnormal performance. After completing the process parameter adjustment, conduct simulation analysis again until the number V of samples with abnormal performance is 0, and then use the method of random sampling to conduct fluorescence performance detection.

[0008] In the third aspect of the present application, a medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0009] Obtain a fluorescence dye doping dataset of M fluorescent textile material samples. The process parameters corresponding to the fluorescence dye doping dataset include the fluorescence dye doping concentration and the doping ratio. Introduce the basic characteristics of the fluorescence dye, and combine with the fluorescent textile material process to establish a basic simulation model. The basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics. The basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material. Based on the basic simulation model, according to the fluorescence dye doping dataset, conduct virtual prediction analysis on the light fastness of the M fluorescent textile material samples to obtain a first set of fluorescence properties. Based on the basic simulation model, according to HPLC technology, simulate the influence of different usage scenarios on fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability, evaluate the performance of the M fluorescent textile material samples, and obtain a second set of fluorescence properties. Based on the first set of fluorescence properties and the second set of fluorescence properties, conduct an abnormal assessment on the M fluorescent textile material samples, divide them into U samples with normal performance and V samples with abnormal performance, where U + V = M. Based on the U samples with normal performance, adjust the process parameters of the V samples with abnormal performance. After completing the process parameter adjustment, conduct simulation analysis again until the number V of samples with abnormal performance is 0, and then use the method of random sampling to conduct fluorescence performance detection.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The method provided in the embodiment of this application obtains a fluorescence dye doping data set of M fluorescent textile material samples. The process parameters corresponding to the fluorescence dye doping data set include the fluorescence dye doping concentration and the doping ratio. By introducing the basic characteristics of the fluorescence dye and combining with the fluorescent textile material process, a basic simulation model is established. The basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics. The basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material. Based on the basic simulation model and according to the fluorescence dye doping data set, virtual prediction analysis of the light fastness of the M fluorescent textile material samples is performed to obtain a first set of fluorescence properties. Based on the basic simulation model and according to HPLC technology, the influence of different usage scenarios on fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability is simulated, and the performance of the M fluorescent textile material samples is evaluated to obtain a second set of fluorescence properties. Based on the first set of fluorescence properties and the second set of fluorescence properties, abnormal evaluation of the M fluorescent textile material samples is performed, and U samples with normal performance and V samples with abnormal performance are divided, where U + V = M. Based on the U samples with normal performance, the process parameters of the V samples with abnormal performance are adjusted. After the process parameter adjustment is completed, simulation analysis is performed again until the number V of samples with abnormal performance is 0, and then fluorescence performance detection is performed by random sampling. The effect of improving the detection efficiency and accuracy of the fluorescence performance of fluorescent textile materials, accelerating the product development cycle, and ensuring the product quality stability is achieved through multiple iterative simulations. Description of the Drawings

[0012] Figure 1 It is a schematic flowchart of the fluorescence performance detection method for fluorescent textile materials provided in this application;

[0013] Figure 2 It is an internal structure diagram of a device provided in this application. Detailed Embodiments

[0014] This application provides a fluorescence performance detection method, an electronic device, and a storage medium for fluorescent textile materials, which are used to solve the technical problems in the existing fluorescence textile material detection that rely on physical samples for fluorescence performance evaluation, resulting in a long detection cycle and difficulty in comprehensively covering various process parameters and usage scenarios. The effect of improving the detection efficiency and accuracy of the fluorescence performance of fluorescent textile materials, accelerating the product development cycle, and ensuring the product quality stability is achieved through multiple iterative simulations.

[0015] Next, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited by the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention. Additionally, it should be noted that for the sake of convenience of description, only the parts related to the present invention rather than all are shown in the accompanying drawings.

[0016] Example 1, as Figure 1 shown, the present application provides a method for detecting the fluorescence performance of fluorescent textile materials, and the method includes:

[0017] Obtain a fluorescence dye doping data set of M fluorescent textile material samples, and the process parameters corresponding to the fluorescence dye doping data set include the fluorescence dye doping concentration and the doping ratio.

[0018] In the embodiments of the present application, in order to detect the fluorescence performance of fluorescent textile materials, the system terminal first obtains a fluorescence dye doping data set of M fluorescent textile material samples. This data set corresponds to the key process parameters involved in the preparation of these samples, including the doping concentration and the doping ratio of the fluorescence dye. These parameters are of great significance for understanding the performance optimization, color stability, etc. of fluorescent textile materials. Among them, the fluorescence dye doping concentration refers to the amount of fluorescence dye added to the base material during the preparation of textile materials, usually expressed as the dye content per unit mass or volume. This parameter directly affects the fluorescence intensity and color vividness of the final product. Different doping concentrations will result in different visual effects and application characteristics. The doping ratio refers to the relative ratio between the fluorescence dye and other components (such as base fibers, other dyes or additives). This ratio relationship determines the distribution uniformity and interaction of the fluorescence dye in the material, and thus affects the overall performance of the material, such as fluorescence persistence, wash resistance and environmental stability, etc.

[0019] Introduce the basic characteristics of the fluorescence dye, and combine with the fluorescent textile material process to establish a basic simulation model. The basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics, and the basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material.

[0020] In one embodiment, to understand how fluorescent dyes affect the properties of materials, the system terminal first introduces the basic characteristics of fluorescent dyes, which cover both physical and chemical aspects. Physical characteristics include the color of the fluorescent dye, the emission wavelength, the fluorescence quantum yield (i.e., the efficiency of the dye converting absorbed light energy into fluorescent radiation), and its solubility in different solvents, etc. Chemical characteristics involve the stability of the dye (such as photo-stability, thermal stability, chemical stability), reactivity (such as the reaction ability with other dyes or additives), and possible toxicity or environmental impact. Subsequently, using simulation software such as MATLAB, COMSOL Multiphysics, etc., according to the behavior characteristics of the fluorescent dye in textile materials, the basic framework of the basic simulation model is constructed, including processes such as the diffusion, adsorption, and reaction of the dye. Then, according to the introduced characteristics of the fluorescent dye and the textile material process data, key parameters in the model are set, such as the diffusion coefficient, adsorption equilibrium constant, reaction rate constant, etc. By running this simulation model in the simulation software, the system terminal can simulate the behavior process of the fluorescent dye in textile materials, observe the distribution of the fluorescent dye, and understand indicators such as concentration changes and fluorescence performance.

[0021] Based on the basic simulation model, according to the fluorescent dye doping data set, virtual prediction analysis of the light fastness of the M fluorescent textile material samples is performed to obtain the first set of fluorescent properties.

[0022] In one embodiment, in a simulation software, based on the established basic simulation model, the system terminal uses the obtained fluorescence dye doping dataset to perform virtual prediction analysis on the light fastness prediction of M fluorescent textile material samples. Specifically, the system terminal takes the parameters in the fluorescence dye doping dataset as input conditions and inputs them into the basic simulation model. According to the specific characteristics of the M fluorescent textile material samples, corresponding parameters are set in the model to ensure the accuracy and pertinence of the simulation, and different light conditions (such as light intensity, light duration, light wavelength, etc.) are set in the model to simulate the light conditions that the fluorescent textile materials may encounter in the actual use environment. Subsequently, this basic simulation model is started through the simulation software. According to the input parameters and the characteristics of the textile materials, the processes of diffusion, adsorption, reaction, etc. of the fluorescence dye in the textile materials are simulated, and the stability performance of the fluorescence dye under light conditions is concerned, that is, its ability to resist photofading and color change. Through the simulation, the light fastness performance of the M fluorescent textile material samples under specific light conditions can be calculated and predicted. This includes key indicators such as the degree of color change and the fading speed. After that, the light fastness prediction results obtained from the simulation are sorted into the first fluorescence performance set. This set contains the predicted light fastness data of the M fluorescent textile material samples and the corresponding light condition information. This process realizes the virtual prediction analysis of the light fastness of the M fluorescent textile material samples and lays a foundation for evaluating the fluorescence performance of these materials.

[0023] Based on the basic simulation model, according to HPLC technology, the effects of different usage scenarios on fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability are simulated, the performance of the M fluorescent textile material samples is evaluated, and the second fluorescence performance set is obtained.

[0024] In one embodiment, based on the basic simulation model, the system terminal utilized the relevant principles and parameters of high performance liquid chromatography (HPLC) technology to simulate the effects of different usage scenarios on the fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability of fluorescent textile material samples. This simulation process aimed to comprehensively evaluate the performance of M fluorescent textile material samples under various actual usage conditions and generate a second set of fluorescence properties accordingly. Specifically, the system terminal first utilized the principle of the fluorescence detector in HPLC technology to simulate the fluorescence emission process of fluorescent dyes under different conditions, and converted it into corresponding parameters in the basic simulation model according to the effects of the mobile phase, stationary phase, etc. in HPLC technology on fluorescent substances. Subsequently, a series of different usage scenarios were set, which covered different lighting conditions (such as intensity, wavelength, duration), environmental factors (such as temperature, humidity, pH value), mechanical stresses (such as stretching, friction), and chemical actions (such as detergents, acid-base solutions), etc. Under each usage scenario, the basic simulation model would simulate the behavioral changes of fluorescent dyes in textile materials, including their excitation and emission spectral characteristics, intermolecular interactions, and interactions with environmental factors, etc. During the simulation process, the simulation software would record the dynamic change data of fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability, and evaluate and predict how the fluorescence intensity changes with the scenario, whether the fluorescence distribution remains uniform, and whether the fluorescence signal is stable without attenuation based on these data. After completing the simulation of all scenarios, the system terminal organized the results obtained from the simulation into a second set of fluorescence properties, including the fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability data of each sample under different usage scenarios. By obtaining this set, not only can we understand the performance of each sample under different scenarios, but it also helps to more comprehensively understand the actual application potential and limitations of these fluorescent textile materials, providing reference information for subsequent anomaly assessment.

[0025] Based on the first set of fluorescence properties and the second set of fluorescence properties, an anomaly assessment is performed on the M fluorescent textile material samples, and U samples with normal performance and V samples with abnormal performance are divided, where U + V = M.

[0026] In one embodiment, the system terminal analyzes the first fluorescence performance set and the second fluorescence performance set, extracts the required indicator parameters, and sets the preset threshold for anomaly assessment according to these indicator parameters. Subsequently, the pre-constructed fluorescence failure assessment channel is called to perform anomaly assessment on M fluorescent textile material samples, to understand whether there is a potential failure risk in the fluorescent textile material samples, determine the potential fluorescent failure samples, and perform synchronous critical value verification and update on the preset threshold of the anomaly assessment according to the conditional probability distribution corresponding to the potential fluorescent failure sample group, so as to realize the dynamic adjustment of the preset threshold of the anomaly assessment. Then, the same evaluation operation as above is performed on the remaining fluorescent textile material samples to obtain V potential fluorescent failure samples, and the system terminal uses these potential fluorescent failure samples as performance anomaly samples that may have one or more performance indicators not meeting the standard. Then, the system terminal removes the V performance anomaly samples from the M fluorescent textile material samples to obtain U performance normal samples whose indicators meet or exceed the preset threshold. This classification not only helps to quickly identify potential problem samples, but also provides a basis for subsequent process parameter adjustment.

[0027] Furthermore, the present application provides an anomaly assessment of the M fluorescent textile material samples based on the first fluorescence performance set and the second fluorescence performance set, and divides them into U performance normal samples and V performance anomaly samples, including:

[0028] Based on the first fluorescence performance set and the second fluorescence performance set, initialize and configure the preset threshold for anomaly assessment of the M fluorescent textile material samples; obtain the specific usage environment defined by the M fluorescent textile material samples, and the specific usage environment includes the light intensity and the light duration under outdoor light conditions.

[0029] Preferably, in order to evaluate the performance of the M fluorescent textile material samples in a specific environment and understand whether they will show anomalies, the system terminal first sets an initial preset threshold according to the first fluorescence performance set and the second fluorescence performance set of these fluorescent textile material samples. This preset threshold will be used as the benchmark for subsequent judgment of whether the sample performance is normal. However, as the evaluation progresses, the preset threshold may be too loose or strict in some cases, resulting in misjudgment or missed judgment. Therefore, the system terminal will adjust the preset threshold according to multiple warning thresholds generated subsequently. To more accurately evaluate the performance of these samples in actual applications, the system terminal obtains the specific usage environment applicable to these fluorescent textile material samples. This specific usage environment includes the light intensity and the light duration under outdoor light conditions. These two factors are crucial for the performance of fluorescent textile materials because they will directly affect the fluorescence effect and durability of the materials.

[0030] Based on the specific usage environment, simulate the light intensity changes within different time periods, integrate a luminance meter to conduct the afterglow performance test, evaluate the durability of the M fluorescent textile material samples, and obtain the durability scores; based on the durability scores, combined with time series analysis, perform a critical value verification on the preset threshold for the abnormal evaluation of the M fluorescent textile material samples.

[0031] Preferably, in order to comprehensively evaluate the durability of the M fluorescent textile material samples, the system terminal conducts tests based on the obtained specific usage environment. First, in the simulation software, use the specific usage environment to simulate the light intensity changes within different time periods, which is to simulate various light conditions that may be encountered during actual use. Subsequently, the system terminal obtains various measurement parameters of the actual luminance meter, including the measurement range, sensitivity, response time, etc., as well as the structural parameters of the luminance meter, including the shape, length, etc., and constructs a virtual luminance meter in the simulation software according to these parameters. Then, integrate this virtual luminance meter with the basic simulation model to test the afterglow performance of the M fluorescent textile material samples. The afterglow performance is a measure of the ability of the fluorescent material to continue emitting light after the excitation stops, and is crucial for evaluating the durability of the material. Through the test, the system terminal can record the light intensity changes of each fluorescent textile material sample within a certain period of time (such as several minutes, several hours or even longer) after the excitation stops through the luminance meter, and obtain the corresponding sample afterglow time to evaluate the persistence and stability of its afterglow performance. After that, the system terminal calculates the ratio of all sample afterglow times to the reference afterglow time respectively to obtain the durability score of each fluorescent textile material sample. The durability score reflects the performance of the sample in the simulated environment and provides a quantitative basis for evaluating its durability. To ensure the accuracy of the evaluation, the system terminal constructs a multi-dimensional data matrix based on the durability scores, combined with the time series analysis method, and the fluorescent dye doping data set of the M fluorescent textile material samples. After obtaining the multi-dimensional data matrix, the system terminal extracts the fluorescent dye doping data with the lowest durability score from the multi-dimensional data matrix and obtains the corresponding fluorescent performance according to this fluorescent dye doping data. Then, perform a critical value verification on these fluorescent performances with the preset threshold for the abnormal evaluation. When there is an abnormality in the verification result, that is, when the critical value is greater than the preset threshold, the system terminal will perform a synchronous critical value verification update on the preset threshold for the abnormal evaluation according to the fluorescent failure evaluation channel to ensure that the preset threshold is neither too loose (resulting in missed judgments) nor too strict (resulting in false judgments), but can accurately reflect the actual changes in the sample performance.

[0032] Furthermore, the present application provides a method for performing a critical value verification on the preset threshold for the abnormal evaluation of the M fluorescent textile material samples based on the durability scores, combined with time series analysis, including:

[0033] Based on the durability score, combined with time series analysis, a first time series data is constructed, and the first time series data is used as the rows of a multi-dimensional data matrix; based on the fluorescence dye doping data set of the M fluorescent textile material samples, combined with the Local Outlier Factor (LOF) algorithm, the columns of the multi-dimensional data matrix are determined; through the multi-dimensional data matrix, the preset threshold for anomaly assessment is updated by synchronous critical value verification.

[0034] Optionally, the system terminal arranges the durability scores of each sample in chronological order, that is, sorts them according to the timestamps of each durability score, ensuring that the durability score data can be arranged in the order in which they are tested, thereby constructing the first time series data, and using the first time series data of each sample as a row of the multi-dimensional data matrix. The data points in each row are arranged in chronological order, reflecting the durability scores of the sample at different time points (with different lighting conditions at different time points). Subsequently, in order to more comprehensively reflect the sample characteristics, the system terminal uses the Local Outlier Factor (LOF) algorithm to analyze the data in the fluorescence dye doping data set of the M fluorescent textile material samples. The LOF algorithm calculates the local density deviation of each data and compares it with the neighbor data to identify the data with significantly lower local density than its neighbors as outliers. These outliers represent special situations or incorrect measurements in the data set. Then, the system terminal initially groups the data in the fluorescence dye doping data set of the fluorescent textile material samples according to the identified outliers, that is, separates the outliers from the normal data, and then defines the columns of the multi-dimensional data matrix according to the data characteristics of the outliers and the normal data, thereby obtaining a multi-dimensional data matrix reflecting the sample characteristics. Through the constructed multi-dimensional data matrix, the system terminal performs synchronous critical value verification on the preset threshold for anomaly assessment. In this process, the system terminal extracts the set of fluorescence performance-related process parameters using the multi-dimensional data matrix, and based on this parameter set, uses the DBSCAN algorithm to establish a fluorescence failure assessment channel. Then, according to this fluorescence failure assessment channel, it assesses whether there is a potential failure risk in the fluorescence performance of the fluorescent textile material samples and determines multiple warning thresholds. Then, the system terminal assigns weights to the preset threshold and the critical value for the current anomaly assessment according to these warning thresholds, and updates the preset threshold for anomaly assessment by weighted summation to ensure that the preset threshold is neither too loose nor too strict, improving the accuracy and effectiveness of the assessment.

[0035] Furthermore, the present application provides updating the preset threshold for anomaly assessment by synchronous critical value verification through the multi-dimensional data matrix, including:

[0036] Based on the multi-dimensional data matrix, evaluate the relationship with fluorescence performance according to the fluorescent textile material process, and extract a set of process parameters associated with fluorescence performance; through the set of process parameters associated with fluorescence performance, use the DBSCAN algorithm to establish a fluorescence failure evaluation channel; based on the fluorescence failure evaluation channel, perform conditional probability constraints, and combine with the multi-dimensional data matrix to determine potential fluorescence failure samples and trigger an early warning mechanism.

[0037] Optionally, the system terminal screens out process parameters that may be related to fluorescence performance from the constructed multi-dimensional data matrix as candidate features, including various information such as material composition, production conditions, and environmental parameters. Then, according to the nature of the data (such as whether it is continuous, whether it conforms to a normal distribution, etc.), select the Pearson correlation coefficient or the Spearman rank correlation coefficient to calculate the correlation between the candidate features and fluorescence performance, and compare the calculated correlation coefficient between each candidate feature and fluorescence performance with the correlation threshold to determine which process parameters have a significant correlation with fluorescence performance, that is, the calculated correlation coefficient is greater than or equal to the correlation threshold, and extract data according to these selected process parameters to obtain a set of process parameters associated with fluorescence performance. Subsequently, the system terminal uses DBSCAN (Density-Based Spatial Clustering of Applications with Noise algorithm) to perform clustering analysis on these key process parameters. The DBSCAN algorithm can identify high-density regions in the data (i.e., sets of similar process parameters) and divide them into different clusters. In this way, an evaluation channel for fluorescence failure can be established according to the similarity of process parameters. When the sample data in the production process passes through the evaluation channel, it can automatically judge whether there is a risk of fluorescence failure and trigger the corresponding early warning mechanism to ensure the stability and reliability of fluorescence performance.

[0038] Furthermore, the present application provides a method for establishing a fluorescence failure evaluation channel by using the set of process parameters associated with fluorescence performance and the DBSCAN algorithm, including:

[0039] Through the set of process parameters associated with fluorescence performance, use the DBSCAN algorithm to perform clustering analysis on the data in the multi-dimensional data matrix to identify sample groups with similar fluorescence performance characteristics; through the sample groups with similar fluorescence performance characteristics, establish a fluorescence failure evaluation channel, and the fluorescence failure evaluation channel is used to evaluate whether there is a potential failure risk in fluorescence performance; the key indicators corresponding to the potential failure risk include the lower limit of fluorescence intensity and the tolerance of fluorescence distribution uniformity. Through the fluorescence failure evaluation channel, each of the M fluorescent textile material samples is evaluated one by one to determine the potential fluorescence failure samples.

[0040] Optionally, based on the determined process parameter set associated with the fluorescence performance, the system terminal extracts the data corresponding to the process parameter set associated with the fluorescence performance from the multi-dimensional data matrix to construct a multi-dimensional data set. Subsequently, according to the specific distribution of the data and the clustering requirements, the radius parameter ε of the neighborhood size and the minimum number of points MinPts required to form a dense region are determined. Then, a non-visited point is randomly selected from the multi-dimensional data set as the starting point, and all the points within the ε-neighborhood of this point are calculated according to the Euclidean distance, and it is judged whether the number of them is greater than or equal to MinPts. If so, this point is marked as a core point, and a new cluster is created. Recursively add all the non-visited points within its ε-neighborhood to this cluster and continue to expand the cluster. If not, this point is marked as a noise point. Repeat the above process until all points in the data set have been visited. The DBSCAN algorithm divides the multi-dimensional data set into several clusters and possibly existing noise points. Each cluster represents a group of sample groups with similar fluorescence performance characteristics, and all the clusters together form a sample group. Then, based on this sample group, the system terminal interprets each sample group, analyzes the process parameter characteristics of the samples within the cluster, and the relationship between these parameters and the fluorescence performance, and identifies the process parameter combinations or ranges that may cause fluorescence failure. Then, according to the actual application requirements and failure modes of the fluorescent textile materials, key indicators of fluorescence failure are defined, such as the lower limit of fluorescence intensity, the tolerance of fluorescence distribution uniformity, etc. Then, based on the analysis of the clustering results and the defined key indicators, evaluation rules for fluorescence failure are formulated. These rules may include thresholds of specific process parameters, parameter combination conditions, etc., for judging whether there is a potential risk of fluorescence failure in the sample. The system terminal then encapsulates the formulated evaluation rules to form a fluorescence failure evaluation channel. This channel can automatically receive new fluorescent textile material sample data and perform real-time evaluation according to the evaluation rules. When it is necessary to evaluate M fluorescent textile material samples, the system terminal inputs the process parameter data of each of the M fluorescent textile material samples into the fluorescence failure evaluation channel, and calculates its potential failure risk according to the evaluation rules. Then, according to the evaluation results, the samples with potential fluorescence failure are identified. The process parameters of these samples may not meet the requirements of the key indicators, or are within the parameter combination range that is likely to cause fluorescence failure.

[0041] Furthermore, the present application provides conditional probability constraints based on the fluorescence failure evaluation channel, combined with the multi-dimensional data matrix, to determine potential fluorescence failure samples and trigger an early warning mechanism, including:

[0042] Based on the fluorescence failure evaluation channel, calculate the conditional probability of the fluorescence performance of each fluorescent textile material sample, and statistically count the occurrence frequency of the fluorescence failure history; calculate the conditional probability distribution corresponding to the potential fluorescence failure sample group according to the occurrence frequency of the fluorescence failure history and the potential failure risk; set an early warning mechanism according to the conditional probability distribution corresponding to the potential fluorescence failure sample group, and the early warning mechanism includes multiple early warning thresholds, and the multiple early warning thresholds correspond to different potential failure risk levels.

[0043] Optionally, when calculating the failure probability of each fluorescent textile material sample, the system terminal first inputs the fluorescence performance of each fluorescent textile material sample into the fluorescence failure evaluation channel in sequence. Inside the fluorescence failure evaluation channel, the system terminal evaluates the fluorescence performance of each sample according to the embedded evaluation rules and the sample group with similar fluorescence performance characteristics. During the evaluation process, the system terminal uses the evaluation rules to judge whether the sample to be evaluated fails, and then uses the Euclidean distance to calculate the similarity between the sample to be evaluated and the known sample group to determine the most similar sample group. If the judgment result is not failure and the matched sample group is not a failure sample group, set the failure probability of the sample to be evaluated to 0, that is, the occurrence frequency of the fluorescence failure history, and record the distribution characteristics of the matched normal sample group. Otherwise, as long as one of them is a failure, calculate the ratio of the number of failure samples in this sample group to the total number of samples in the sample group to obtain the failure probability of the sample to be evaluated, that is, the occurrence frequency of the fluorescence failure history, and record the distribution characteristics of the matched failure sample group. Subsequently, combining the occurrence frequency of the fluorescence failure history and the potential failure risk, a conditional probability distribution is constructed for the potential fluorescence failure sample group. This distribution describes the probability of the sample group having fluorescence failure under different potential failure risk levels, providing a quantitative tool for the system terminal to evaluate the fluorescence failure risk of different group samples. After that, based on the conditional probability distribution corresponding to the potential fluorescence failure sample group, the system terminal sets multiple early warning thresholds. These thresholds correspond to different potential failure risk levels, gradually strengthening the early warning measures from low to high, and assigning higher weights to the critical values when performing synchronous critical value verification and update.

[0044] Based on the U samples with normal performance, adjust the process parameters of the V samples with abnormal performance. After completing the process parameter adjustment, conduct simulation analysis again until the number V of samples with abnormal performance is 0, and then perform fluorescence performance detection by means of random sampling.

[0045] In one embodiment, after obtaining U normally-performing samples and V abnormally-performing samples, the system terminal adjusts the process parameters of the abnormally-performing samples according to the process parameters of the normally-performing samples. After the process parameters are adjusted, the same simulation analysis as described above is performed again on the adjusted samples to verify whether the adjustment is effective, with the aim of quickly evaluating whether the performance of the adjusted samples has improved. This process is repeated until all V abnormally-performing samples show normal performance through the simulation analysis, that is, until the value of V becomes 0. This represents that all performance abnormalities of the samples have been successfully resolved through the adjustment of the process parameters. After all abnormally-performing samples are adjusted, the system terminal randomly selects a part of these adjusted samples for actual fluorescence performance testing to ensure that the finally produced fluorescent textile materials can meet the expected performance standards.

[0046] Furthermore, the present application provides a method for fluorescence performance testing by random sampling, which further includes:

[0047] The occurrence frequency of the fluorescence failure history includes the relative frequencies and distribution characteristics of different failure modes; based on the random sampling frequency corresponding to the fluorescence performance testing, a loss function is defined; through the loss function, combined with the relative frequencies and distribution characteristics of different failure modes, and in comparison with the influence degrees of different failure modes on the fluorescence performance, the random sampling frequency is optimized.

[0048] Optionally, the calculated occurrence frequency of the fluorescence failure history includes the relative frequencies of different failure modes and the distribution characteristics of these failure modes in the overall population. The system terminal defines a loss function based on the requirements of the fluorescence performance testing. This loss function is a standard for measuring whether the random sampling frequency is reasonable. If the sampling frequency can accurately reflect the relative frequencies and distribution characteristics of different failure modes, the value of the loss function will be relatively low; conversely, if the sampling frequency deviates significantly from the actual situation, the value of the loss function will be high. Subsequently, using this loss function, combined with the relative frequencies and distribution characteristics of different failure modes, and in comparison with the influence degrees of different failure modes on the fluorescence performance, the failure modes with greater influence on the fluorescence performance are identified and given higher priority or more frequent sampling during random sampling. Then, based on this analysis result, the random sampling frequency is optimized. The goal of the optimization is to make the sampling frequency accurately reflect the actual situation of different failure modes and efficiently detect the problems with greater influence on the fluorescence performance, thereby reducing the testing cost and time while ensuring the testing accuracy.

[0049] In summary, the embodiments of the present application at least have the following technical effects:

[0050] In the embodiments of the present application, a fluorescence dye doping dataset is obtained, a basic simulation model is established in combination with the basic characteristics of the fluorescence dye, and the light fastness of the sample and the fluorescence performance under different usage scenarios are virtually predicted and evaluated. Through preset thresholds, specific usage environment simulation, durability scoring, and time series analysis, the samples are abnormally evaluated to divide the samples with normal and abnormal performance. Based on the normal samples, the process parameters of the abnormal samples are adjusted until the performance of all samples is normal, and finally, the fluorescence performance is detected using the optimized random sampling frequency. In addition, a fluorescence failure evaluation channel is established through a multi-dimensional data matrix and DBSCAN clustering analysis. Combining conditional probability constraints and an early warning mechanism, potential fluorescence failure samples are identified and an early warning is triggered. The entire process aims to improve the efficiency and accuracy of the performance detection of fluorescent textile materials. These technical effects together solve the technical problems in the existing detection of fluorescent textile materials, where the fluorescence performance evaluation depends on physical samples, resulting in a long detection cycle and difficulty in comprehensively covering various process parameters and usage scenarios, achieving the effect of improving the efficiency and accuracy of the fluorescence performance detection of fluorescent textile materials through multiple iterative simulations, accelerating the product development cycle, and ensuring the quality stability of the products.

[0051] Embodiment 2. Based on the same inventive concept as the fluorescence performance detection method for fluorescent textile materials in the foregoing embodiment, the present application provides a device, which may be a server, and its internal structure diagram may be as Figure 2 shown. The device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the fluorescence performance detection method for fluorescent textile materials.

[0052] Those skilled in the art can understand that Figure 2 the structure shown in

[0053] In one embodiment, a medium is provided, in which a computer program is stored. When the processor executes the computer program, the following steps are implemented: obtaining a fluorescence dye doping data set of M fluorescent textile material samples, where the process parameters corresponding to the fluorescence dye doping data set include fluorescence dye doping concentration and doping ratio; introducing the basic characteristics of the fluorescence dye, and combining with the fluorescent textile material process to establish a basic simulation model, where the basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics, and the basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material; based on the basic simulation model, according to the fluorescence dye doping data set, performing virtual prediction analysis on the light fastness of the M fluorescent textile material samples to obtain a first fluorescence performance set; based on the basic simulation model, according to HPLC technology, simulating the influence of different usage scenarios on fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability, and evaluating the performance of the M fluorescent textile material samples to obtain a second fluorescence performance set; based on the first fluorescence performance set and the second fluorescence performance set, performing abnormal evaluation on the M fluorescent textile material samples, dividing them into U samples with normal performance and V samples with abnormal performance, where U + V = M; based on the U samples with normal performance, adjusting the process parameters of the V samples with abnormal performance, and after completing the process parameter adjustment, performing simulation analysis again until the number V of the samples with abnormal performance is 0, and then performing fluorescence performance detection by means of random sampling.

[0054] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0055] The above-described embodiments merely represent several implementation manners of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. A fluorescence performance detection method for fluorescent textile materials, characterized in that, The method includes: Obtain a fluorescence dye doping dataset of M fluorescent textile material samples, where the process parameters corresponding to the fluorescence dye doping dataset include fluorescence dye doping concentration and doping ratio; Introduce the basic characteristics of the fluorescence dye, and combine with the fluorescent textile material process to establish a basic simulation model. The basic characteristics of the fluorescence dye include physical characteristics and chemical characteristics. The basic simulation model is used to simulate the behavior of the fluorescence dye in the textile material; Based on the basic simulation model, according to the fluorescence dye doping dataset, perform virtual prediction analysis of the light fastness of the M fluorescent textile material samples to obtain a first set of fluorescence properties; Based on the basic simulation model, according to HPLC technology, simulate the effects of different usage scenarios on fluorescence intensity, fluorescence distribution uniformity, and fluorescence stability, evaluate the performance of the M fluorescent textile material samples, and obtain a second set of fluorescence properties; Based on the first set of fluorescence properties and the second set of fluorescence properties, perform an anomaly assessment on the M fluorescent textile material samples, and divide them into U samples with normal performance and V samples with abnormal performance, where U + V = M; Based on the U samples with normal performance, adjust the process parameters of the V samples with abnormal performance. After completing the process parameter adjustment, perform simulation analysis again until the number V of samples with abnormal performance is 0, and then perform fluorescence performance detection by random sampling.

2. The fluorescence performance detection method for fluorescent textile materials according to claim 1, characterized in that Based on the first set of fluorescence properties and the second set of fluorescence properties, perform an anomaly assessment on the M fluorescent textile material samples, and divide them into U samples with normal performance and V samples with abnormal performance. The method includes: Based on the first set of fluorescence properties and the second set of fluorescence properties, initialize and configure a preset threshold for anomaly assessment of the M fluorescent textile material samples; Obtain the specific usage environment defined by the M fluorescent textile material samples. The specific usage environment includes the light intensity and light duration under outdoor lighting conditions; Based on the specific usage environment, simulate the light changes in different time periods, integrate a luminance meter to test the afterglow performance, evaluate the durability of the M fluorescent textile material samples, and obtain a durability score; Based on the durability score, combined with time series analysis, perform a critical value verification on the preset threshold for anomaly assessment of the M fluorescent textile material samples.

3. The fluorescence performance detection method for fluorescent textile materials according to claim 2, characterized in that, Based on the durability score, combined with time series analysis, perform a critical value verification on the preset threshold for anomaly assessment of the M fluorescent textile material samples. The method includes: Based on the durability score, combined with time series analysis, construct a first time series data, and use the first time series data as the rows of a multi-dimensional data matrix; Based on the fluorescence dye doping dataset of the M fluorescent textile material samples, combined with the Local Outlier Factor (LOF) algorithm, determine the columns of the multi-dimensional data matrix; Through the multi-dimensional data matrix, perform synchronous critical value verification and update on the preset threshold for anomaly assessment.

4. The fluorescence performance detection method for fluorescent textile materials according to claim 3, characterized in that, Through the multi-dimensional data matrix, perform synchronous critical value verification and update on the preset threshold for anomaly assessment. The method includes: Based on the multi-dimensional data matrix, evaluate the relationship with fluorescence performance according to the fluorescent textile material process, and extract the set of process parameters associated with fluorescence performance; Through the set of process parameters associated with fluorescence performance, use the DBSCAN algorithm to establish a fluorescence failure evaluation channel; Based on the fluorescence failure evaluation channel, perform conditional probability constraints, and combine with the multi-dimensional data matrix to determine potential fluorescence failure samples and trigger an early warning mechanism.

5. The fluorescence performance detection method for fluorescent textile materials according to claim 4, characterized in that, Through the set of process parameters associated with fluorescence performance, use the DBSCAN algorithm to establish a fluorescence failure evaluation channel, and the method includes: Through the set of process parameters associated with fluorescence performance, use the DBSCAN algorithm to perform clustering analysis on the data in the multi-dimensional data matrix to identify sample groups with similar fluorescence performance characteristics; Through the sample groups with similar fluorescence performance characteristics, establish a fluorescence failure evaluation channel, and the fluorescence failure evaluation channel is used to evaluate whether there is a potential failure risk in fluorescence performance; The key indicators corresponding to the potential failure risk include the lower limit of fluorescence intensity and the tolerance of fluorescence distribution uniformity. Through the fluorescence failure evaluation channel, each fluorescent textile material sample in the M fluorescent textile material samples is evaluated one by one to determine the potential fluorescence failure samples.

6. The fluorescence performance detection method for fluorescent textile materials according to claim 5, characterized in that Based on the fluorescence failure evaluation channel, perform conditional probability constraints, and combine with the multi-dimensional data matrix to determine potential fluorescence failure samples and trigger an early warning mechanism, and the method includes: Based on the fluorescence failure evaluation channel, calculate the conditional probability of the fluorescence performance of each fluorescent textile material sample, and count the historical occurrence frequency of fluorescence failure; According to the historical occurrence frequency of fluorescence failure and the potential failure risk, calculate the conditional probability distribution corresponding to the potential fluorescence failure sample group; According to the conditional probability distribution corresponding to the potential fluorescence failure sample group, set an early warning mechanism, and the early warning mechanism includes multiple warning thresholds, and the multiple warning thresholds correspond to different potential failure risk levels.

7. The fluorescence performance detection method for fluorescent textile materials according to claim 6, characterized in that, Adopt a random sampling method for fluorescence performance detection, and the method also includes: The historical occurrence frequency of fluorescence failure includes the relative frequency and distribution characteristics of different failure modes; Based on the random sampling frequency corresponding to fluorescence performance detection, define a loss function; Through the loss function, combine the relative frequency and distribution characteristics of different failure modes, and compare the influence degree of different failure modes on fluorescence performance to optimize the random sampling frequency.

8. A device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the fluorescence performance detection method for fluorescent textile materials according to any one of claims 1 to 7.

9. A medium on which a computer program is stored, characterized in that, When the computer program is executed by the processor, it implements the steps of the fluorescence performance detection method for fluorescent textile materials according to any one of claims 1 to 7.

Images