A fabric flame retardant detection data analysis method and system

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for analyzing flame retardant fabric detection data. The method comprises: obtaining initial data points containing flame retardant performance parameters at various locations on the fabric; determining an initial data set and a target data set; calculating the degree of fit of the initial data set and the target data set; calculating the degree of deviation of the target data point; determining a sequence of the degree of deviation and calculating an upper abnormal threshold; calculating a model parameter value; and obtaining abnormal data points in the data set using a single-classification support vector machine model based on the model parameter value, so as to realize data analysis of flame retardant fabric detection. The present invention comprehensively analyzes the degree of fit of the data set and the sub-data set of the data point, as well as the degree of deviation of the data point, and uses the result of the quartile method to determine the upper abnormal threshold, thereby avoiding misjudgment caused by fixed model parameter values ​​in traditional methods and improving the accuracy of abnormal data point detection.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for analyzing fabric flame retardancy detection data. Background Art

[0002] The application of flame-retardant clothing in high-risk industries such as oil and gas, petrochemicals, electricity, and firefighting is crucial. They provide a vital layer of protection for professionals working in these environments. Flame-retardant clothing is a fabric made of flame-retardant materials. It has excellent ignition resistance and can prevent re-ignition after contact with the fire source, thereby effectively reducing the risk of fire to the wearer. Therefore, when using flame-retardant fabrics, it is necessary to ensure that their production quality meets the standard requirements. In the production process of flame-retardant fabrics, there may be problems such as uneven material distribution or processing errors at the edges and center parts, resulting in differences in flame-retardant properties of different parts of the fabric. Therefore, by performing anomaly detection on the parameter data sampled and tested at different parts of the fabric, the flame retardancy of the fabric is evaluated by combining the difference between the abnormal data and the standard parameters. The one-class support vector machine (One-Class SVM) model is specifically used for anomaly detection. In the flame-retardant performance test of fabrics, it can effectively identify abnormal points that are significantly different from normal data points, and quickly obtain fabric samples with abnormal flame-retardant properties, thereby ensuring product quality.

[0003] The patent application document with the publication number CN112613233A discloses a model for discovering abnormal data of environmental monitoring based on a single-classification support vector machine model. A single-classification support vector machine model is established through training set samples; and the parameters corresponding to normal values ​​and outliers are defined according to the boundary determined by the model to complete the delineation of the model boundary; and the construction of the single-classification support vector machine model is completed. After the model is trained, the unknown data value is newly added to the existing model as a test set; and the conclusion is obtained by judging whether the input data point is an outlier point based on whether it is within the boundary. The model can construct the normal sample boundary of the feature space through known environmental monitoring data, and use the model constructed by existing data to detect and screen the newly added data points for abnormal values, so as to achieve the purpose of quality management of environmental monitoring data. The model can realize dynamic modeling of environmental monitoring data, and determine the outliers in the training data through the model, and discover the abnormal data in the environmental monitoring data.

[0004] However, the above patent application document does not solve the problem that the traditional single-classification support vector machine model The parameter value is used to determine the proportion of abnormal data points in the training data set, which leads to the model's inaccurate detection of abnormal points. The complexity of different fabric production makes it difficult to use experience to preset parameter values. If the parameter value is set too large, normal data points may be misclassified as abnormal points. If it is set too small, the real abnormal data points may be missed. This will not only reduce the accuracy of fabric flame retardant testing, but also increase the quality control risk in the production process, thus affecting the quality and safety of the final product. Summary of the invention

[0005] In order to solve the single classification support vector machine model by preset The parameter value is used to determine the proportion of data points considered to be abnormal in the training data set, which leads to the problem that the model is not accurate enough in detecting abnormal points. The present invention provides a method and system for analyzing fabric flame retardant detection data.

[0006] In a first aspect, the present invention provides a method for analyzing fabric flame retardant detection data, which adopts the following technical solution:

[0007] A fabric flame retardant detection data analysis method comprises: obtaining initial data points containing flame retardant performance parameters at various positions on the fabric to obtain an initial data set; taking any initial data point as a target data point, and taking a data set not containing the target data point as a target data set of the target data point; performing regression fitting on all data points in the initial data set and the target data set respectively to obtain an initial hyperplane and a target hyperplane; calculating the fitting degree of the initial data set and the target data set respectively based on the distance characteristics of the initial data set and the target data set, wherein the distance characteristics are the mean and the range of the vertical distances from all data points in the data set to the hyperplane; calculating the fitting degree of the initial data set and the target data set based on the distance characteristics of the initial data set and the target data set respectively, wherein the distance characteristics are the mean and the range of the vertical distances from all data points in the data set to the hyperplane; calculating the fitting degree of the initial data set and the target data set based on the distance characteristics of the initial data set and the target data set. The degree of fitting of the target data point and the vertical distance from the target data point to the initial hyperplane are used to calculate the degree of deviation of the target data point; according to the degree of deviation of all data points, all data points are sorted by the quartile method to obtain a degree of deviation sequence; based on the third quartile and the interquartile range in the degree of deviation sequence, the upper abnormal threshold is calculated; the data points with sequence numbers greater than the upper abnormal threshold in the degree of deviation sequence are recorded as suspicious data points, and the model parameter values ​​are calculated based on the number of all data points in the degree of deviation sequence and the number of suspicious data points; according to the model parameter values, the single-classification support vector machine model is used to obtain the abnormal data points in the data set to realize data analysis of fabric flame retardant detection.

[0008] The beneficial effect is that by comprehensively analyzing the degree of fit of the data set and the sub-data set of the data point, as well as the degree of deviation of the data point, and using the results of the quartile method to determine the abnormal warning threshold, the traditional method of fixed The misjudgment caused by parameter values ​​improves the accuracy of abnormal data point detection; by automatically calculating and adjusting The parameter value avoids the inadaptability caused by manually setting fixed values, can be flexibly adjusted according to the characteristics of the data set, and enhances the adaptability of the model; at the same time, it improves the accuracy of fabric flame retardant performance testing, reduces false positives and false negatives, and improves the reliability of test results.

[0009] Furthermore, the flame retardant performance parameters include afterflame time, smoldering time and damage length.

[0010] Furthermore, the regression fitting is performed using the least squares method.

[0011] Furthermore, the fitting degree of the initial data set satisfies the following relationship:

[0012] ; In the formula, is the fitting degree of the initial data set, is the number of initial data points, For the The vertical distance from the initial data point to the initial hyperplane, is the maximum value of the vertical distance from the initial data point to the initial hyperplane, is the minimum value of the vertical distance from the initial data point to the initial hyperplane, is a natural exponential function.

[0013] The beneficial effects are: by comprehensively considering the vertical distance from the initial data point to the initial hyperplane and introducing the normalization processing of the maximum and minimum values, the fitting of the entire initial data set can be more comprehensively reflected; the distance of the data points is smoothed by the natural exponential function, so that the change of the fitting degree is more stable, avoiding the drastic fluctuation of the fitting degree due to the abnormal change of a single data point, and improving the stability of the overall evaluation.

[0014] Furthermore, the degree of deviation satisfies the following relationship:

[0015] ; In the formula, For the The degree of deviation of the target data point, For the The degree of fit of the target data set for the target data points, is the fitting degree of the initial data set, For the The vertical distance from the target data point to the initial hyperplane, is the standard normalization function.

[0016] The beneficial effects are: by combining the fitting error of the data point and its vertical distance to the hyperplane, the degree of deviation of the data point can be measured more accurately, which helps to identify suspicious data points; through normalization processing, the influence of different feature scales on the deviation can be eliminated, making the model more consistent when processing data of different scales; combining local fitting error and geometric distance, the model can better adapt to local changes when processing data with complex local structures, thereby improving the overall fitting accuracy.

[0017] Furthermore, the upper abnormal threshold satisfies the following relationship:

[0018] ; In the formula, is the upper abnormal warning threshold, is the third quartile in the deviation degree sequence, is the interquartile range within the deviation degree series.

[0019] The beneficial effects are: by calculating the upper abnormal threshold through the third quartile and the interquartile range, the outliers in the data, that is, the data points far away from the normal distribution, can be effectively identified and detected; compared with the traditional method based on the mean and standard deviation, the use of the third quartile and the interquartile range can better deal with extreme values ​​in the data, avoid misjudgment and excessive sensitivity to extreme data, and enhance the robustness of outlier detection.

[0020] Furthermore, the model parameter values ​​satisfy the following relationship:

[0021] ; In the formula, is the model parameter value, is the number of suspicious data points in the deviation degree series, is the number of all data points in the deviation sequence.

[0022] The beneficial effects are: by calculating the model parameter values, the proportion of suspicious data points in the data can be clearly quantified, helping analysts understand the data quality; through clear model parameter values, intuitive decision support can be provided for data analysis, helping analysts make reasonable judgments.

[0023] Furthermore, the data analysis for realizing flame retardant detection of fabrics includes: in response to any parameter of the flame retardant performance parameters of any abnormal data point being greater than the standard value, determining that the flame retardant performance of the fabric is unqualified, and completing the data analysis for flame retardant detection of the fabric.

[0024] In a second aspect, the present invention provides a fabric flame retardant detection data analysis system, which adopts the following technical solution:

[0025] A fabric flame retardant detection data analysis system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned fabric flame retardant detection data analysis method is implemented.

[0026] By adopting the above technical solution, the above-mentioned fabric flame retardant detection data analysis method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0027] The present invention has the following technical effects:

[0028] By dynamically analyzing the vertical distance from the data points of various parts of the fabric to the hyperplane and the change in the degree of set fitting after excluding the data point, the deviation degree of the data point is comprehensively evaluated; the model parameter value is determined by using the distribution law of the data point deviation degree, avoiding the problem of misclassification or missed detection caused by improper preset model parameter values ​​in the traditional single-classification support vector machine model. The classification result can effectively identify the differences in flame retardant properties of various parts in fabric production, thereby improving the accuracy and reliability of fabric flame retardant detection and providing guarantee for product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers are the same or corresponding parts.

[0030] Figure 1 The present invention is a flowchart of a fabric flame retardant detection data analysis method according to an embodiment of the present invention.

[0031] Figure 2 It is a box plot of a deviation degree sequence in a fabric flame retardant detection data analysis method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0034] The embodiment of the present invention discloses a method for analyzing fabric flame retardant detection data, referring to Figure 1 , comprising steps S1 to S7:

[0035] S1: Obtain initial data points including flame retardant performance parameters of various parts of the fabric.

[0036] It should be noted that since the working environment of industries such as electricity, chemical industry, and firefighting is often accompanied by dangers such as high temperature and flame, it is necessary to wear flame-retardant clothes to complete the work to protect personnel from fire damage. Flame-retardant clothing is made of flame-retardant materials processed into fabrics. Fabrics with good flame retardancy can ensure that there will be no re-ignition in flame contact or high temperature environment. Therefore, when using fabrics to make flame-retardant clothing, it is necessary to test the flame retardancy of the fabrics. At present, the most commonly used method is to test the flame retardancy by the vertical combustion method. This method cuts a small piece of fabric and hangs it vertically, and ignites the flame below it. After a certain period of ignition, the flame is extinguished, and the afterburning time, smoldering time, and damaged length are recorded. Considering that there may be uneven material distribution or processing errors in the edge and center parts of the actual flame-retardant fabric production process, there are differences in the flame retardant properties of different parts of the fabric. Therefore, different parts of the fabric are sampled separately, and the vertical combustion method is used to test them separately under the condition of setting the same ignition time, and the flame retardant performance parameter data of each part are obtained and the data points are constructed.

[0037] Specifically, the flame retardant performance parameters include afterflame time, smoldering time and damaged length.

[0038] S2: Determine the initial dataset and target dataset.

[0039] It should be noted that the test data points are sampled from different parts of the fabric, and the data set is regressed and fitted until the residual value from each data point to the hyperplane is minimized to obtain the initial (target) hyperplane, which can reflect the ideal trend of the test data point set.

[0040] All initial data points constitute an initial data set; any initial data point is used as a target data point, and a data set that does not contain the target data point is used as a target data set of the target data point; regression fitting is performed on all data points in the initial data set and the target data set respectively to obtain an initial hyperplane and a target hyperplane.

[0041] Specifically, the regression fitting is performed using the least squares method.

[0042] S3: Calculate the degree of fit between the initial data set and the target data set.

[0043] It should be noted that the analysis of the degree of fit helps to understand the internal structure of the data point set. The distribution of the vertical distance from the data point to the target hyperplane can reflect the dispersion of the data, for example, whether there is a regular clustering, whether there are some areas where the data points vary greatly. By calculating the degree of fit, the overall distribution characteristics of the data point set can be obtained.

[0044] The fitting degree of the initial data set and the target data set is calculated based on the distance features of the initial data set and the target data set respectively, wherein the distance features are the mean and range of the vertical distances from all data points in the data set to the hyperplane.

[0045] Specifically, the fitting degree of the initial data set satisfies the following relationship:

[0046] ;

[0047] In the formula, is the fitting degree of the initial data set, is the number of initial data points, For the The vertical distance from the initial data point to the initial hyperplane, is the maximum value of the vertical distance from the initial data point to the initial hyperplane, is the minimum value of the vertical distance from the initial data point to the initial hyperplane, is a natural exponential function.

[0048] in, Represents the range of the vertical distances from all initial data points in the initial data set to the initial hyperplane. The smaller the value, the more similar the vertical distances from the data points in the initial data set to the initial hyperplane of the initial data set and the more evenly distributed. It represents the mean of the vertical distances from all initial data points to the initial hyperplane. The smaller the value, the closer the data points in the data set are to the initial hyperplane of the initial data set. If the vertical distances from the initial data points to the initial hyperplane in the initial data set are more evenly distributed and the initial data points are closer to the initial hyperplane in the initial data set, the better the fitting degree of the initial data set is. Therefore, the above two indicators are combined to obtain the fitting degree of the initial data set.

[0049] The calculation method of the fitting degree of the target data set of the target data point is the same as the fitting degree of the initial data set, which will not be repeated here.

[0050] S4: Calculate the deviation degree of the target data point.

[0051] It should be noted that in the fabric production process, if the equipment fails or is improperly controlled during weaving or stretching, resulting in uneven tension, the material distribution at the edge and center will be inconsistent. For example, the edge may be subject to greater tension, causing the fiber to be stretched and affecting performance. Therefore, the flame retardant effect of different parts of the fabric may be different, which means that there are differences in the data points detected for each part under the same experimental conditions. Once there is a difference in the data point, the data point will significantly reduce the degree of fit of the data point set and will be farther away from the target hyperplane than the normal data point. Therefore, for each data point, the degree of fit of the remaining data point set except for itself, that is, the sub-data set, is calculated, and the degree of deviation of the data point is analyzed in combination with the difference in the degree of fit with the data set.

[0052] Based on the degree of fit between the initial data set and the target data set, and the vertical distance from the target data point to the initial hyperplane, the degree of deviation of the target data point is calculated.

[0053] Specifically, the degree of deviation satisfies the following relationship:

[0054] ;

[0055] In the formula, For the The degree of deviation of the target data point, For the The degree of fit of the target data set for the target data points, is the fitting degree of the initial data set, For the The vertical distance from the target data point to the initial hyperplane, is the standard normalization function.

[0056] in, Indicates The square value of the difference in the degree of fit between the target data set and the initial data set for the target data point. The larger the value, the greater the change in the degree of fit of the data set after removing the data point, which means that the data point has a greater impact on the fit of the overall data set and may be significantly different from the remaining data points. In this case, if the first The larger the vertical distance from the target data point to the initial hyperplane, the greater the deviation of the current data point.

[0057] S5: Determine the deviation degree sequence and calculate the upper abnormal threshold.

[0058] It should be noted that the traditional single-class support vector machine model is based on empirical preset The parameter value, that is, the model parameter value, is used as the proportion of data points considered abnormal in the training data set to identify abnormal data points. However, the complexity of fabrics in actual production makes it difficult to preset a suitable model parameter value through experience. If the model parameter value is not set properly, it will lead to misclassification of abnormal detection. The data points with higher deviation are more likely to be due to the uneven distribution of materials. Therefore, in order to identify data points with differences, the quartile method can be used to analyze the distribution of the deviation data above the upper limit, and consider them as data points with differences (the deviation is significantly higher than the rest of the normal deviation).

[0059] According to the degree of deviation of all data points, all data points are sorted using the quartile method (sorted in ascending order according to the degree of deviation) to obtain a deviation degree sequence; Figure 2 As shown, the upper abnormal threshold is calculated based on the third quartile in the deviation degree sequence (located at the 75% position of the deviation degree sequence) and the interquartile range (the difference between the third quartile and the first quartile located at the 25% position of the deviation degree sequence).

[0060] Specifically, the upper abnormal threshold satisfies the following relationship:

[0061] ;

[0062] In the formula, is the upper abnormal warning threshold, is the third quartile in the deviation degree sequence, is the interquartile range within the deviation degree series.

[0063] S6: Calculate model parameter values.

[0064] It should be noted that the most suitable model parameter value for the test data of the fabric is evaluated by using the proportion of different data points, so that it is more consistent with the distribution of actual data.

[0065] Data points whose sequence numbers in the deviation degree sequence are greater than the upper abnormal threshold are recorded as suspicious data points, and the model parameter values ​​are calculated based on the number of all data points in the deviation degree sequence and the number of suspicious data points.

[0066] Specifically, the model parameter values ​​satisfy the following relationship:

[0067] ;

[0068] In the formula, is the model parameter value, is the number of suspicious data points in the deviation degree series, is the number of all data points in the deviation sequence.

[0069] in, It indicates the percentage of suspicious data points in the deviation degree sequence. The larger the value is, the more data points in the deviation degree sequence are identified as suspicious data points. The model parameter value in the model is used to control the balance between the support vector and the abnormal data points. Taking the proportion of suspicious data points as the value of the model parameter can more accurately reflect the abnormal situation in the data set, thereby improving the accuracy of the model in identifying abnormal data.

[0070] S7: Based on the model parameter values, the single-classification support vector machine model is used to obtain abnormal data points in the data set to realize data analysis of fabric flame retardant detection.

[0071] It should be noted that the calculated model parameter values ​​are applied to the single-classification support vector machine model, and all data points in the initial data set are trained to identify abnormal data points. If the data point of the test result of a certain part is an abnormal point, it means that there is a significant difference between the test result of this part and the test results of the corresponding parts of other normal data points, that is, the flame retardant effect of this part is worse than that of the parts corresponding to other normal data points. Then if all the parameters of the abnormal data point meet the corresponding standard parameter values, it is considered that the flame retardant performance of the fabric is qualified. According to the national standard of GB / T 5455-2014 vertical method, the qualified standards for the flame retardant performance of fabrics are afterburning time ≤5s, smoldering time ≤5s, and damaged length ≤16cm.

[0072] Specifically, the data analysis for realizing flame retardant testing of fabrics includes:

[0073] In response to any one of the flame retardant performance parameters of any abnormal data point being greater than the standard value, the flame retardant performance of the fabric is determined to be unqualified, and the data analysis of the fabric flame retardant detection is completed.

[0074] An embodiment of the present invention further discloses a fabric flame retardant detection data analysis system, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a fabric flame retardant detection data analysis method according to the present invention is implemented.

[0075] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0076] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0077] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0078] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing fabric flame retardant detection data, characterized in that: include: Obtaining initial data points containing flame retardant performance parameters at various locations on the fabric to obtain an initial data set; Take any initial data point as the target data point, and take the data set that does not contain the target data point as the target data set of the target data point; Perform regression fitting on all data points in the initial data set and the target data set respectively to obtain the initial hyperplane and the target hyperplane; Based on the distance features of the initial data set and the target data set, the fitting degree of the initial data set and the target data set are calculated. The fitting degree of the initial data set satisfies the following relationship: ； In the formula, is the fitting degree of the initial data set, is the number of initial data points, For the The vertical distance from the initial data point to the initial hyperplane, is the maximum value of the vertical distance from the initial data point to the initial hyperplane, is the minimum value of the vertical distance from the initial data point to the initial hyperplane, is a natural exponential function; the calculation method of the fitting degree of the target data set is the same as the calculation method of the fitting degree of the initial data set; The distance feature is the mean and range of the vertical distances from all data points in the data set to the hyperplane. Based on the degree of fit between the initial data set and the target data set, and the vertical distance from the target data point to the initial hyperplane, the deviation degree of the target data point is calculated. The deviation degree satisfies the following relationship: ； In the formula, For the The degree of deviation of the target data point, For the The degree of fit of the target data set for the target data points, For the The vertical distance from the target data point to the initial hyperplane, is a standard normalization function; according to the degree of deviation of all data points, all data points are sorted using the quartile method to obtain a deviation degree sequence; based on the third quartile and interquartile range in the deviation degree sequence, the upper abnormal threshold is calculated; The data points with sequence numbers greater than the upper abnormal threshold in the deviation degree sequence are recorded as suspicious data points, and the model parameter values ​​are calculated based on the number of all data points in the deviation degree sequence and the number of suspicious data points; According to the model parameter values, the single-classification support vector machine model is used to obtain abnormal data points in the data set to realize data analysis of fabric flame retardant detection.

2. The method for analyzing fabric flame retardancy detection data according to claim 1, characterized in that: The flame retardant performance parameters include afterflame time, smoldering time and damaged length.

3. The method for analyzing fabric flame retardancy detection data according to claim 1, characterized in that: The regression fitting is performed using the least squares method.

4. The method for analyzing fabric flame retardancy detection data according to claim 1, characterized in that: The upper abnormal threshold satisfies the following relationship: ； In the formula, is the upper abnormal warning threshold, is the third quartile in the deviation degree sequence, is the interquartile range within the deviation degree series.

5. The method for analyzing fabric flame retardancy detection data according to claim 1, characterized in that: The model parameter values ​​satisfy the following relationship: ； In the formula, is the model parameter value, is the number of suspicious data points in the deviation degree series, is the number of all data points in the deviation sequence.

6. The method for analyzing fabric flame retardancy detection data according to claim 1, characterized in that: The data analysis to achieve flame retardant fabric testing includes: In response to any one of the flame retardant performance parameters of any abnormal data point being greater than the standard value, the flame retardant performance of the fabric is determined to be unqualified, and the data analysis of the fabric flame retardant detection is completed.

7. A fabric flame retardant detection data analysis system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for analyzing fabric flame retardant detection data according to any one of claims 1 to 6 is implemented.

Images