Artificial intelligence-based woven uniform fabric elasticity retentivity analysis method

Abstract

The invention discloses a woven uniform fabric elasticity retentivity analysis method based on artificial intelligence, and particularly relates to the technical field of fabric elasticity analysis. Comprising the steps of S01, numbering woven elastic uniform fabric, S02, collecting initial fabric elasticity data, S03, evaluating initial fabric elasticity retentivity, S04, analyzing fabric elasticity attenuation trend, S05, outputting the fabric elasticity retentivity, and S06, grading the fabric elasticity retentivity. According to the method, the initial fabric elasticity data of the to-be-evaluated woven elastic uniform fabric is collected, the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index are calculated, the fabric elasticity is classified, and the elasticity attenuation trend of the fabric is analyzed, so that the attenuation trend prediction result is obtained; and the initial elasticity data is quantified into an indexed result, so that the performance evaluation of the elastic uniform fabric is realized, and the whole-process intelligent management of elasticity retentivity analysis is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of fabric elasticity analysis, and more particularly to an artificial intelligence-based method for analyzing the elasticity retention of woven uniform fabrics. Background Art

[0002] Woven uniform fabrics are an important component of the industrial and commercial fields. Their elasticity retention is directly related to the service life and wearing comfort of the uniforms. Fabrics with good elasticity retention can significantly extend the service life of uniforms, reduce resource waste and cost expenditure. Elasticity retention is a measure of the ability of woven uniform fabrics to return to their original state after being subjected to external forces.

[0003] With the rapid development of artificial intelligence technology, the application of artificial intelligence is particularly prominent in the study of the elastic retention of woven uniform fabrics. By analyzing the elastic data of a large number of fabric samples and analyzing their elastic changes under different conditions, the performance of the fabric in actual use can be predicted. In the study of the elastic retention of woven uniform fabrics, the application of artificial intelligence technology can not only improve the accuracy and efficiency of the test, but also provide more scientific decision-making support for the design and production of textiles.

[0004] However, it still has some shortcomings in actual use. For example, traditional elasticity testing methods for woven uniform fabrics usually rely on physical experiments, usually determining the elasticity retention by measuring the fabric's ability to return to its original shape after being subjected to force. These methods often require a lot of time and resources, and the repeatability and consistency of the test data are difficult to guarantee. The limitations of traditional woven uniform fabric elasticity testing methods also lie in their inability to provide real-time feedback and predictions, low data processing efficiency, and inability to extract valuable patterns and trends from the data. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an artificial intelligence-based method for analyzing the elasticity retention of woven uniform fabrics, which is used to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an artificial intelligence-based method for analyzing the elasticity retention of woven uniform fabrics, comprising the following steps: Step S01: Woven elastic uniform fabric numbering: used to sequentially number the woven elastic uniform fabrics to be evaluated as 1, 2, ...i, ...n, and establish a woven uniform fabric elasticity database.

[0007] Step S02: Initial fabric elasticity data collection: used to collect initial fabric elasticity data of the woven elastic uniform fabric to be evaluated, wherein the initial fabric elasticity data includes elastic recovery rate and plastic deformation rate.

[0008] Step S03: Initial fabric elasticity retention evaluation: receiving the initial fabric elasticity data transmitted in the initial fabric elasticity data acquisition step, and obtaining the elastic recovery change rate evaluation index and plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated based on the initial fabric elasticity data.

[0009] Step S04: Fabric elastic attenuation trend analysis: Based on the mean value of the elastic recovery change rate evaluation index and the mean value of the plastic deformation change rate evaluation index, an elastic attenuation prediction model is constructed to obtain the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, and the elastic attenuation trend of the fabric under different usage conditions is analyzed.

[0010] Step S05: Outputting fabric elasticity retention: Obtaining the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, comparing it with the preset elastic attenuation rate, and outputting the fabric elasticity retention evaluation result.

[0011] Step S06: Fabric elasticity retention grading: obtaining the elastic recovery change rate evaluation index and plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated, and classifying the woven elastic uniform fabric to be evaluated into three grades: A, B, and C.

[0012] Preferably, the step S02: collecting initial fabric elasticity data is specifically as follows: S21: Based on the characteristics of the woven elastic uniform fabric to be evaluated, the pre-trained regression model recommends the elongation, i.e., stretched length = initial length * (1 + elongation); S22: The initial length of the woven elastic uniform fabric sample to be evaluated is collected by a visual sensor, the testing machine is started, and the woven elastic uniform fabric sample to be evaluated is stretched to a target elongation at a set speed, and the stretched state is maintained for a countdown; S23: Slowly unload at the same speed until the load reaches 0 N, count down to maintain the no-load state, and collect the residual length of the woven elastic uniform fabric sample to be evaluated at this time; S24: Repeat the above steps until the cycle is completed, and calculate the elastic recovery rate and plastic deformation rate of the woven elastic uniform fabric to be evaluated.

[0013] Preferably, the step S03: evaluating the initial fabric elasticity retention is specifically as follows: Obtain the elastic recovery rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the elastic recovery rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, and calculate the elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated; The plastic deformation rate of the first sample of the i-th woven elastic uniform fabric in the first cycle and the plastic deformation rate of the q-th sample of the i-th woven elastic uniform fabric in the j-th cycle are obtained, and the evaluation index of the plastic deformation change rate of the woven elastic uniform fabric to be evaluated is calculated.

[0014] Preferably, the elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated is obtained, and the average value of the elastic recovery change rate evaluation index is calculated; the plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated is obtained, and the average value of the plastic deformation change rate evaluation index is calculated.

[0015] Preferably, the elastic attenuation prediction model is constructed to obtain the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, specifically: Input features: mean value of elastic recovery change rate evaluation index, mean value of plastic deformation change rate evaluation index; spandex content , cotton content , yarn twist , fabric density ; Washing times t, washing temperature T, storage humidity H; Output label: Elastic recovery attenuation rate of woven elastic uniform fabric to be evaluated SHAP values ​​are used to interpret model predictions and quantify the contribution of each feature to the decay rate.

[0016] Preferably, the step S05: outputting the fabric elasticity retention is specifically: The elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated is obtained and compared with the preset elastic attenuation rate. If the elastic recovery attenuation rate of the woven elastic uniform fabric is greater than the preset elastic attenuation rate, it indicates that the attenuation trend prediction result of the woven elastic uniform fabric is unqualified; otherwise, it indicates that the attenuation trend prediction result of the woven elastic uniform fabric is qualified.

[0017] Preferably, the step S06: grading the elasticity retention of fabric is specifically as follows: S61: Pre-set the grading threshold intervals corresponding to the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index, and clarify the index range boundaries of the three levels A, B, and C; S62: The elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index of the fabric to be evaluated are compared with the pre-set grading threshold ranges respectively. If the elastic recovery change rate evaluation index meets the threshold condition corresponding to grade A, it is judged as grade A; if the elastic recovery change rate evaluation index meets the grade B threshold, it is judged as grade B; if the elastic recovery change rate evaluation index meets the grade C threshold, it is judged as grade C. Similarly, the plastic deformation change rate evaluation index of the fabric to be evaluated is judged as A, B, and C respectively.

[0018] Technical effects and advantages of the present invention: The present invention provides an artificial intelligence-based elastic retention analysis method for woven elastic uniform fabrics. The method collects initial fabric elasticity data of the woven elastic uniform fabric to be evaluated, calculates the elastic recovery rate and plastic deformation rate of the woven elastic uniform fabric to be evaluated, obtains the elastic recovery rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the elastic recovery rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, calculates the elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated, obtains the plastic deformation rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the plastic deformation rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, calculates the plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated, compares the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index of the fabric to be evaluated with pre-set grading threshold intervals, respectively, and if the elastic recovery change rate evaluation index meets the threshold condition corresponding to grade A, it is determined to be grade A; if the elastic recovery change rate evaluation index meets the grade B threshold, it is determined to be grade B. If the elastic recovery change rate evaluation index meets the C-level threshold, it is judged as C-level. Similarly, the plastic deformation change rate evaluation index of the fabric to be evaluated is judged as A, B, and C. The initial elastic recovery rate and plastic deformation rate reflect the elastic characteristics of the fabric from different dimensions. For all fabrics to be evaluated, these two types of data are collected according to the same standards, and a unified data benchmark is established. The initial elastic data is further quantified into an index result, and an understandable standardized elastic retention evaluation index is generated. Through the grading of fabrics, the performance evaluation of elastic uniform fabrics can be realized, which allows manufacturers to quickly distinguish the quality of fabric elastic retention performance, thereby making uniform production more in line with actual needs; The present invention provides an artificial intelligence-based elastic retention analysis method for woven uniform fabrics. Based on the mean value of the elastic recovery change rate evaluation index and the mean value of the plastic deformation change rate evaluation index, an elastic attenuation prediction model is constructed to obtain the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated. The elastic attenuation trend of the fabric under different usage conditions is analyzed, the elastic recovery attenuation rate is compared with a preset elastic attenuation rate, and the attenuation trend prediction result of the woven elastic uniform fabric is output. By combining the evaluation index and the elastic attenuation influencing characteristics, the change in elastic performance is quantified, thereby realizing full-process intelligent management of elastic retention analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention is a flowchart of an artificial intelligence-based method for analyzing the elasticity retention of woven uniform fabrics. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] See also Figure 1 As shown, the present invention provides an artificial intelligence-based method for analyzing the elasticity retention of woven uniform fabrics, comprising the following steps: The step S01: woven elastic uniform fabric numbering is used to sequentially number the woven elastic uniform fabrics to be evaluated as 1, 2, ...i, ...n, and establish a woven uniform fabric elasticity database to achieve orderly data management and improve data retrieval efficiency.

[0022] The step S02: collecting initial fabric elasticity data is used to collect initial fabric elasticity data of the woven elastic uniform fabric to be evaluated. The initial fabric elasticity data includes elastic recovery rate and plastic deformation rate. The initial elastic recovery rate and plastic deformation rate reflect the elastic characteristics of the fabric from different dimensions. For all fabrics to be evaluated, these two types of data are collected according to the same standard to establish a unified data benchmark.

[0023] In a possible design, the step S02: collecting initial fabric elasticity data is specifically as follows: S21: Based on the characteristics of the woven elastic uniform fabric to be evaluated, the pre-trained regression model recommends the elongation, i.e., stretched length = initial length * (1 + elongation); S22: The initial length of the woven elastic uniform fabric sample to be evaluated is collected by a visual sensor, the testing machine is started, and the woven elastic uniform fabric sample to be evaluated is stretched to a target elongation at a set speed, and the stretched state is maintained for a countdown; S23: Slowly unload at the same speed until the load reaches 0 N, count down to maintain the no-load state, and collect the residual length of the woven elastic uniform fabric sample to be evaluated at this time; S24: Repeat the above steps until the cycle is completed, and calculate the elastic recovery rate and plastic deformation rate of the woven elastic uniform fabric to be evaluated; Specifically, repeating the above steps may include repeated stretching of the sample at the same position and repeated stretching of the sample at different positions.

[0024] In this embodiment, it should be specifically noted that the initial fabric elasticity data collection further includes: Calculate the elastic recovery rate of a single sample and a single cycle: in, It is expressed as the elastic recovery rate of the qth sample of the i-th woven elastic uniform fabric in the j-th cycle, is the initial sample length of the i-th woven elastic uniform fabric, It is expressed as the residual length of the qth sample of the i-th woven elastic uniform fabric in the j-th cycle; The calculation formula for the elastic recovery rate of the woven elastic uniform fabric to be evaluated is: in, It is represented by the elastic recovery rate of the i-th woven elastic uniform fabric, m is the number of cycles, and e is the number of specimens; Specifically, when the elastic recovery rate of a certain woven elastic uniform fabric fluctuates more, it indicates that the quality is unstable; Calculate the plastic deformation rate of a single specimen in a single cycle: in, It is expressed as the plastic deformation rate of the qth specimen of the i-th woven elastic uniform fabric in the j-th cycle; The calculation formula for the plastic deformation rate of the woven elastic uniform fabric to be evaluated is: in, Expressed as the plastic deformation rate of the i-th woven elastic uniform fabric; Specifically, when the plastic deformation rate of a certain woven elastic uniform fabric fluctuates more, it indicates that the quality is unstable.

[0025] The step S03: evaluating the initial fabric elasticity retention: receiving the initial fabric elasticity data transmitted in the initial fabric elasticity data acquisition step, obtaining an elastic recovery change rate evaluation index and a plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated based on the initial fabric elasticity data; further quantifying the initial elasticity data into an indexed result to generate an understandable standardized elasticity retention evaluation index.

[0026] In one possible design, the step S03: evaluating the initial fabric elasticity retention is specifically as follows: Obtain the elastic recovery rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the elastic recovery rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, and calculate the elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated; The plastic deformation rate of the first sample of the i-th woven elastic uniform fabric in the first cycle and the plastic deformation rate of the q-th sample of the i-th woven elastic uniform fabric in the j-th cycle are obtained, and the evaluation index of the plastic deformation change rate of the woven elastic uniform fabric to be evaluated is calculated.

[0027] In this embodiment, it should be specifically explained that the calculation formula of the elastic recovery change rate evaluation index is: in, It is expressed as the elastic recovery change rate evaluation index of the i-th woven elastic uniform fabric, It is expressed as the elastic recovery rate of the first cycle of the first sample of the i-th woven elastic uniform fabric, It is expressed as the elastic recovery rate of the qth sample of the i-th woven elastic uniform fabric in the j-th cycle, m is the number of cycles, and e is the number of samples; The calculation formula of the plastic deformation change rate evaluation index is: in, Expressed as the evaluation index of the plastic deformation change rate of the i-th woven elastic uniform fabric, It is expressed as the plastic deformation rate of the first sample of the i-th woven elastic uniform fabric in the first cycle, It is expressed as the plastic deformation rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric.

[0028] Step S04: Fabric elastic attenuation trend analysis: Based on the average value of the elastic recovery change rate evaluation index and the average value of the plastic deformation change rate evaluation index, an elastic attenuation prediction model is constructed to obtain the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, and analyze the elastic attenuation trend of the fabric under different usage conditions; by combining the evaluation index and the elastic attenuation influence characteristics, the elastic performance changes are quantified, and the full-process intelligent management of elastic retention analysis is realized.

[0029] In a possible design, the step S04: analyzing the fabric elasticity attenuation trend is specifically as follows: S41: Obtaining an elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated, and calculating a mean value of the elastic recovery change rate evaluation index; S42: Obtaining a plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated, and calculating a mean value of the plastic deformation change rate evaluation index; S43: Constructing elastic attenuation prediction model: Input features: mean value of elastic recovery change rate evaluation index, mean value of plastic deformation change rate evaluation index; spandex content , cotton content , yarn twist , fabric density ; Washing times t, washing temperature T, storage humidity H; Output label: Elastic recovery attenuation rate of woven elastic uniform fabric to be evaluated ; S44: Use SHAP values ​​to interpret model predictions and quantify the contribution of each feature to the decay rate.

[0030] In this embodiment, it should be specifically explained that the formula for calculating the mean value of the elastic recovery change rate evaluation index is: , where n represents the number of woven elastic uniform fabrics; Calculate the mean value of the plastic deformation change rate evaluation index using the following formula: .

[0031] The present invention provides another specific embodiment, which is as follows: Input features: Output tags: ,in, It is expressed as the elastic recovery decay rate of the i-th woven elastic uniform fabric, and f is the model mapping function, which can predict the elastic decay rate of the fabric under any input feature conditions; SHAP value calculation: (target feature is TR) The SHAP value is used to interpret the model prediction results and quantify the contribution of each feature to the decay rate. The formula is: in, It is expressed as the number of features of the combination S, and M is expressed as the total number of features; : Calculate the difference between the model prediction value when the target feature TR is included and the prediction value when TR is not included; : The weight of each combination is determined by the number of features.

[0032] The step S05: outputting the elasticity retention of the fabric: obtaining the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, comparing it with the preset elastic attenuation rate, and outputting the evaluation result of the elasticity retention of the fabric.

[0033] In a possible design, the step S05: outputting the fabric elasticity retention is specifically: The elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated is obtained and compared with the preset elastic attenuation rate. If the elastic recovery attenuation rate of the woven elastic uniform fabric is greater than the preset elastic attenuation rate, it indicates that the attenuation trend prediction result of the woven elastic uniform fabric is unqualified; otherwise, it indicates that the attenuation trend prediction result of the woven elastic uniform fabric is qualified.

[0034] Step S06: Fabric elasticity retention grading: obtaining the elastic recovery change rate evaluation index and plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated, and classifying the woven elastic uniform fabric to be evaluated into three grades: A, B, and C; achieving performance evaluation of elastic uniform fabrics, allowing manufacturers to quickly distinguish the quality of fabric elasticity retention performance, thereby making uniform production more in line with actual needs.

[0035] In a possible design, the step S06: grading the elasticity retention of the fabric is specifically as follows: S61: Pre-set the grading threshold intervals corresponding to the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index, and clarify the index range boundaries of the three levels A, B, and C; S62: The elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index of the fabric to be evaluated are compared with the pre-set grading threshold ranges respectively. If the elastic recovery change rate evaluation index meets the threshold condition corresponding to grade A, it is judged as grade A; if the elastic recovery change rate evaluation index meets the grade B threshold, it is judged as grade B; if the elastic recovery change rate evaluation index meets the grade C threshold, it is judged as grade C. Similarly, the plastic deformation change rate evaluation index of the fabric to be evaluated is judged as A, B, and C respectively.

[0036] In this embodiment, it should be specifically explained that the present invention collects the initial fabric elasticity data of the woven elastic uniform fabric to be evaluated, calculates the elastic recovery rate and plastic deformation rate of the woven elastic uniform fabric to be evaluated, obtains the elastic recovery rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the elastic recovery rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, calculates the elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated, obtains the plastic deformation rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the plastic deformation rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, calculates the plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated, and compares the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index of the fabric to be evaluated with the pre-set grading threshold range respectively. If the elastic recovery change rate evaluation index meets the threshold condition corresponding to Grade A, it is determined to be Grade A; if the elastic recovery change rate evaluation index meets the Grade B threshold, it is determined to be Grade B. If the elastic recovery change rate evaluation index meets the C-level threshold, it is judged as C-level. Similarly, the plastic deformation change rate evaluation index of the fabric to be evaluated is judged as A, B, and C. The initial elastic recovery rate and plastic deformation rate reflect the elastic characteristics of the fabric from different dimensions. For all fabrics to be evaluated, these two types of data are collected according to the same standards, and a unified data benchmark is established. The initial elastic data is further quantified into an index result, and an understandable standardized elastic retention evaluation index is generated. Through the grading of fabrics, the performance evaluation of elastic uniform fabrics can be realized, which allows manufacturers to quickly distinguish the quality of fabric elastic retention performance, thereby making uniform production more in line with actual needs; The present invention constructs an elastic attenuation prediction model based on the mean value of the elastic recovery change rate evaluation index and the mean value of the plastic deformation change rate evaluation index, obtains the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, analyzes the elastic attenuation trend of the fabric under different usage conditions, compares the elastic recovery attenuation rate with the preset elastic attenuation rate, and outputs the attenuation trend prediction result of the woven elastic uniform fabric. By combining the evaluation index and the elastic attenuation influencing characteristics, the change in elastic performance is quantified, and the full-process intelligent management of elastic retention analysis is realized.

[0037] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An artificial intelligence-based method for analyzing elasticity retention of woven uniform fabrics, characterized in that: The following steps are involved: Step S01: woven elastic uniform fabric numbering: used to sequentially number the woven elastic uniform fabrics to be evaluated as 1, 2, ...i, ...n, and establish a woven uniform fabric elasticity database; Step S02: Initial fabric elasticity data collection: used to collect initial fabric elasticity data of the woven elastic uniform fabric to be evaluated, the initial fabric elasticity data including elastic recovery rate and plastic deformation rate; Step S03: Initial fabric elasticity retention evaluation: receiving the initial fabric elasticity data transmitted in the initial fabric elasticity data acquisition step, and obtaining an elastic recovery change rate evaluation index and a plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated based on the initial fabric elasticity data; Step S04: Fabric elastic attenuation trend analysis: Based on the mean elastic recovery change rate evaluation index and the mean plastic deformation change rate evaluation index, an elastic attenuation prediction model is constructed to obtain the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, and the elastic attenuation trend of the fabric under different usage conditions is analyzed; Step S05: Outputting fabric elasticity retention: Obtaining the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, comparing it with the preset elastic attenuation rate, and outputting the fabric elasticity retention evaluation result; Step S06: Fabric elasticity retention grading: obtaining the elastic recovery change rate evaluation index and plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated, and classifying the woven elastic uniform fabric to be evaluated into three grades: A, B, and C.

2. The artificial intelligence-based elasticity retention analysis method for woven uniform fabrics according to claim 1, characterized in that: The step S02: collecting initial fabric elasticity data is specifically as follows: S21: Based on the characteristics of the woven elastic uniform fabric to be evaluated, the pre-trained regression model recommends the elongation, i.e., stretched length = initial length * (1 + elongation); S22: The initial length of the woven elastic uniform fabric sample to be evaluated is collected by a visual sensor, the testing machine is started, and the woven elastic uniform fabric sample to be evaluated is stretched to a target elongation at a set speed, and the stretched state is maintained for a countdown; S23: Slowly unload at the same speed until the load reaches 0 N, count down to maintain the no-load state, and collect the residual length of the woven elastic uniform fabric sample to be evaluated at this time; S24: Repeat the above steps until the cycle is completed, and calculate the elastic recovery rate and plastic deformation rate of the woven elastic uniform fabric to be evaluated.

3. The artificial intelligence-based elasticity retention analysis method for woven uniform fabrics according to claim 1, characterized in that: The step S03: evaluating the initial fabric elasticity retention is specifically as follows: Obtain the elastic recovery rate of the first cycle of the first sample of the i-th woven elastic uniform fabric and the elastic recovery rate of the j-th cycle of the q-th sample of the i-th woven elastic uniform fabric, and calculate the elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated; The plastic deformation rate of the first sample of the i-th woven elastic uniform fabric in the first cycle and the plastic deformation rate of the q-th sample of the i-th woven elastic uniform fabric in the j-th cycle are obtained, and the evaluation index of the plastic deformation change rate of the woven elastic uniform fabric to be evaluated is calculated.

4. The artificial intelligence-based elasticity retention analysis method for woven uniform fabrics according to claim 1, characterized in that: The elastic recovery change rate evaluation index of the woven elastic uniform fabric to be evaluated is obtained, and the average value of the elastic recovery change rate evaluation index is calculated; the plastic deformation change rate evaluation index of the woven elastic uniform fabric to be evaluated is obtained, and the average value of the plastic deformation change rate evaluation index is calculated.

5. The artificial intelligence-based elasticity retention analysis method for woven uniform fabrics according to claim 1, characterized in that: The elastic attenuation prediction model is constructed to obtain the elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated, specifically: Input features: mean value of elastic recovery change rate evaluation index, mean value of plastic deformation change rate evaluation index; spandex content , cotton content , yarn twist , fabric density ; Washing times t, washing temperature T, storage humidity H; Output label: Elastic recovery attenuation rate of woven elastic uniform fabric to be evaluated SHAP values ​​are used to interpret model predictions and quantify the contribution of each feature to the decay rate.

6. The artificial intelligence-based elasticity retention analysis method for woven uniform fabrics according to claim 1, characterized in that: The step S05: outputting the fabric elasticity retention is specifically: The elastic recovery attenuation rate of the woven elastic uniform fabric to be evaluated is obtained and compared with the preset elastic attenuation rate. If the elastic recovery attenuation rate of the woven elastic uniform fabric is greater than the preset elastic attenuation rate, it indicates that the attenuation trend prediction result of the woven elastic uniform fabric is unqualified; otherwise, it indicates that the attenuation trend prediction result of the woven elastic uniform fabric is qualified.

7. The artificial intelligence-based elasticity retention analysis method for woven uniform fabrics according to claim 1, characterized in that: The step S06: fabric elasticity retention classification is specifically as follows: S61: Pre-set the grading threshold intervals corresponding to the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index, and clarify the index range boundaries of the three levels A, B, and C; S62: The elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index of the fabric to be evaluated are compared with the pre-set grading threshold ranges respectively. If the elastic recovery change rate evaluation index meets the threshold condition corresponding to grade A, it is judged as grade A; if the elastic recovery change rate evaluation index meets the grade B threshold, it is judged as grade B; if the elastic recovery change rate evaluation index meets the grade C threshold, it is judged as grade C. Similarly, the plastic deformation change rate evaluation index of the fabric to be evaluated is judged as A, B, and C respectively.

Images