A method and system for evaluating the color fastness of yam-dyed silk fabrics

Abstract

This invention relates to the field of textile quality testing technology, specifically disclosing a method and system for evaluating the color fastness of yam-dyed silk fabrics. This invention acquires the microscopic morphology of the surface and the distribution characteristics of internal chemical substances in the yam-dyed silk fabric, quantitatively analyzes the factors influencing color fastness, firstly identifies water-sensitive areas based on surface images and three-dimensional data, extracts groove depth, roughness, and water-stain sensitivity index, and calculates the composite influence factor of surface defects. Simultaneously, it uses energy dispersive spectroscopy and other techniques to analyze the concentration and distribution of unbound iron ions and tannin dyes, obtaining an iron ion migration risk index. Combining the above parameters, a comprehensive color fastness evaluation coefficient is obtained through normalization and weighted calculation. Finally, the color fastness level is determined by comparing it with a preset threshold range. This method integrates physical and chemical factors to achieve a more accurate and comprehensive color fastness evaluation, providing a reliable basis for quality control.

Description

Technical Field

[0001] This invention relates to the field of textile quality testing technology, and in particular to a method and system for evaluating the color fastness of yam-dyed silk fabrics. Background Technology

[0002] As a representative product of traditional natural dyeing techniques, yam-dyed silk fabric is widely used in high-end apparel and home textiles due to its unique color, texture, and environmentally friendly properties. Colorfastness, as a core indicator of the quality of this type of fabric, directly affects the product's lifespan and user experience. Silk fibers are inherently soft and highly absorbent. However, during the yam-dyeing process, the bonding stability of tannin dyes with silk fibers is affected by various factors such as the dyeing process and environmental humidity. Furthermore, unbound iron ions that may remain during the dyeing process are prone to migration, further exacerbating the risk of fading and discoloration.

[0003] Existing colorfastness assessment methods mostly rely on changes in appearance to determine the colorfastness grade, but they neglect the influence of microscopic morphological defects on the fabric surface (such as grooves and roughness) on the sensitivity to water stains, as well as the synergistic effect of the distribution matching between unbound iron ions and tannin dyes on color stability. This assessment method based on appearance changes cannot fully reflect the colorfastness performance of silk yam-dyed fabrics in actual use scenarios, easily leading to biased assessment results and failing to provide accurate basis for fabric production optimization and quality control. Therefore, a new colorfastness assessment method for silk yam-dyed fabrics is needed to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide a method for evaluating the color fastness of yam-dyed silk fabrics, comprising:

[0005] A method for evaluating the colorfastness of yam-dyed silk fabrics includes:

[0006] Obtain multi-dimensional feature data of the silk yam-dyed fabric to be evaluated, including surface micromorphological features and internal chemical substance distribution features.

[0007] Based on the surface micromorphology information, the surface water stain sensitive area of ​​the silk yam-dyed fabric to be evaluated is obtained, and multiple surface groove depths and surface roughness feature values ​​are obtained based on the surface water stain sensitive area, and the water stain sensitivity index is obtained based on the multiple surface groove depths.

[0008] The surface defect composite influence factor of the silk yam-dyed fabric to be evaluated is obtained based on the surface roughness characteristic value and the water stain sensitivity index.

[0009] The concentration of unbound iron ions and the concentration of tannin dye are obtained based on the internal chemical substance distribution characteristics, and the iron ion migration risk index is obtained based on the concentration of unbound iron ions.

[0010] The comprehensive color fastness evaluation coefficient is calculated based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor.

[0011] The colorfastness of the silk yam-dyed fabric to be evaluated is assessed based on the comprehensive colorfastness evaluation coefficient, and the evaluation result is obtained.

[0012] Preferably, the steps of identifying a water stain-sensitive area, obtaining multiple surface groove depths and surface roughness characteristic values ​​based on the water stain-sensitive area, and obtaining a water stain sensitivity index based on the multiple surface groove depths include:

[0013] The surface micromorphological features are segmented based on an image segmentation algorithm to obtain regions with local color deepening and regions with increased texture roughness. The regions with local color deepening and regions with increased texture roughness are then deduplicated and merged to obtain the initial water stain sensitive region.

[0014] Three-dimensional topography scanning technology is used to measure each of the initial water stain sensitive areas to obtain multiple three-dimensional point cloud coordinate sets, and principal component analysis is performed on the multiple three-dimensional point cloud coordinate sets in sequence to obtain multiple first principal component directions;

[0015] The average tilt angle is obtained based on the multiple first principal component directions, the corresponding planar component is obtained based on the average tilt angle, and the three-dimensional point cloud coordinates that are concentrated in the planar component are removed to obtain the coordinates of multiple local depression points.

[0016] The coordinates of multiple local depression points are clustered into multiple clusters according to the area of ​​a preset region. Each cluster is defined as a micro-groove unit, and the equivalent depth of each micro-groove unit is obtained. The multiple equivalent depths are used as multiple surface groove depths.

[0017] A first vertical height of the planar component is obtained, and multiple vertical height deviations are obtained sequentially based on the first vertical height and multiple equivalent depths. A mean vertical height deviation is obtained based on the multiple vertical height deviations, and a standard vertical height deviation value is obtained based on the multiple vertical height deviations and the mean vertical height deviation. A vertical height deviation feature value is obtained based on the standard vertical height deviation value and the mean vertical height deviation, and the vertical height deviation feature value is used as a surface roughness feature value.

[0018] The equivalent depth average is calculated based on multiple equivalent depths, and the equivalent depth standard deviation is obtained based on the multiple equivalent depths and the equivalent depth average. The equivalent depth coefficient is obtained based on the ratio of the equivalent depth average to the equivalent depth standard deviation, and the equivalent depth coefficient is used as the water stain sensitivity index.

[0019] Preferably, the step of obtaining the composite influence factor of surface defects of the yam-dyed silk fabric to be evaluated based on the surface roughness characteristic value and the water stain sensitivity index includes:

[0020] Calculate the surface roughness deviation based on the surface roughness characteristic value and the preset surface roughness reference value;

[0021] Calculate the water stain sensitivity deviation based on the water stain sensitivity index and the preset water stain sensitivity benchmark index;

[0022] The surface roughness deviation and the water stain sensitivity deviation are weighted and calculated to obtain the surface defect composite influence factor, wherein the calculation formula is:

[0023] ;

[0024] in, This represents the composite influence factor of surface defects. Indicates the deviation of surface roughness. Indicates the degree of water stain sensitivity deviation. This indicates the weight value of the surface roughness deviation. This indicates the weight value for water stain sensitivity deviation.

[0025] Preferably, the step of obtaining the iron ion migration risk index based on the concentration of unbound iron ions includes:

[0026] Obtain a pixel distribution map of the surface water stain sensitive area, wherein the pixel distribution map is composed of iron and carbon and oxygen as tannin characteristic elements;

[0027] The total area of ​​the corresponding region is obtained based on the pixel distribution map;

[0028] According to the pixel distribution map, the first pixel region with iron element intensity higher than a preset threshold is obtained, the first pixel region is defined as an iron enrichment abnormal region, and the first total pixel area corresponding to the iron enrichment abnormal region is obtained. The area ratio of the iron enrichment region is obtained according to the first total pixel area and the total area of ​​the region.

[0029] According to the pixel distribution map, a second pixel region with a tannin feature element intensity higher than a preset threshold is obtained. The second pixel region is defined as a tannin enrichment abnormal region, and the second total pixel area corresponding to the tannin enrichment abnormal region is obtained. The area ratio of the tannin enrichment region is obtained according to the second total pixel area and the total area of ​​the region.

[0030] The iron-tannin distribution matching degree is calculated based on the area proportion of the iron-rich region and the area proportion of the tannin-rich region.

[0031] The iron ion migration risk index is obtained by weighting the concentration of unbound iron ions, the area ratio of iron-rich regions, and the iron-tannin distribution matching degree.

[0032] Preferably, the step of calculating the comprehensive color fastness evaluation coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor includes:

[0033] The iron ion migration risk index is normalized to obtain the normalized value of the iron ion migration risk index.

[0034] The concentration of the tannin dye was normalized to obtain a normalized value of the tannin dye concentration.

[0035] The surface defect composite influence factor is normalized to obtain the normalized value of the surface defect composite influence factor;

[0036] The comprehensive color fastness evaluation coefficient is obtained by weighting the normalized value of the iron ion migration risk index, the normalized value of the tannin dye concentration, and the normalized value of the surface defect composite influence factor.

[0037] Preferably, the step of evaluating the colorfastness of the silk yam-dyed fabric to be evaluated based on the comprehensive colorfastness evaluation coefficient to obtain the evaluation result includes:

[0038] Determine the relationship between the comprehensive color fastness evaluation coefficient and the preset threshold range;

[0039] When the comprehensive color fastness evaluation coefficient is not within the preset threshold range and is less than the minimum value of the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be unqualified.

[0040] When the comprehensive color fastness evaluation coefficient is within the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be qualified.

[0041] When the comprehensive color fastness evaluation coefficient is not within the preset threshold range and is greater than the maximum value of the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be excellent.

[0042] This application also provides a color fastness evaluation system for yam-dyed silk fabrics, including:

[0043] The multi-dimensional feature acquisition module is used to acquire multi-dimensional feature data of the yam-dyed silk fabric to be evaluated. The multi-dimensional feature data includes surface micro-morphology feature information and internal chemical substance distribution feature information.

[0044] The surface morphology analysis module is used to obtain the depth of multiple surface grooves and surface roughness feature values ​​of the water stain sensitive area on the fabric surface based on the surface micromorphology feature information, and to obtain the water stain sensitivity index based on the depth of the multiple surface grooves.

[0045] The surface defect impact calculation module is used to obtain the surface defect composite impact factor of the silk yam-dyed fabric to be evaluated based on the surface roughness characteristic value and the water stain sensitivity index.

[0046] The chemical substance analysis module is used to obtain the concentration of unbound iron ions and the concentration of tannin dye based on the internal chemical substance distribution characteristics information, and to obtain the iron ion migration risk index based on the concentration of unbound iron ions.

[0047] The comprehensive color fastness calculation module is used to calculate the comprehensive color fastness evaluation coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor.

[0048] The color fastness assessment module is used to assess the color fastness of the silk yam-dyed fabric to be assessed based on the comprehensive color fastness assessment coefficient, and obtain the assessment result.

[0049] Preferably, the surface morphology analysis module includes:

[0050] The sensitive region extraction unit is used to perform edge segmentation on the surface micro-morphology feature information based on the image segmentation algorithm to obtain regions with local color deepening and regions with increased texture roughness, and to merge the regions with local color deepening and regions with increased texture roughness to obtain the initial water stain sensitive region.

[0051] The point cloud acquisition unit is used to measure each of the initial water stain sensitive areas using three-dimensional topography scanning technology to obtain multiple three-dimensional point cloud coordinate sets, and to perform principal component analysis on the multiple three-dimensional point cloud coordinate sets in sequence to obtain multiple first principal component directions.

[0052] The local depression point coordinate acquisition unit is used to obtain the average tilt angle based on the multiple first principal component directions, obtain the corresponding planar component based on the average tilt angle, and remove the three-dimensional point cloud coordinates that are concentrated in the planar component to obtain multiple local depression point coordinates.

[0053] An equivalent depth calculation unit is used to cluster multiple local depression point coordinates into multiple clusters according to a preset area, wherein each cluster is defined as a micro-groove unit, and the equivalent depth of each micro-groove unit (the difference between its deepest point and the average height of the surrounding area) is obtained, and multiple equivalent depths are used as multiple surface groove depths.

[0054] A surface roughness feature extraction unit is used to obtain a first vertical height of a planar component, and sequentially obtain multiple vertical height deviations based on the first vertical height and multiple equivalent depths, obtain an average vertical height deviation based on the multiple vertical height deviations, obtain a standard vertical height deviation value based on the multiple vertical height deviations and the average vertical height deviation, obtain a vertical height deviation feature value based on the standard vertical height deviation value and the average vertical height deviation, and use the vertical height deviation feature value as a surface roughness feature value.

[0055] The water stain sensitivity index calculation unit is used to calculate the average equivalent depth based on multiple equivalent depths, obtain the standard deviation of the equivalent depth based on the multiple equivalent depths and the average equivalent depth, obtain the equivalent depth coefficient based on the ratio of the average equivalent depth to the standard deviation of the equivalent depth, and use the equivalent depth coefficient as the water stain sensitivity index.

[0056] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0057] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0058] The beneficial effects of this application are as follows: This invention obtains the surface microstructure and internal chemical substance distribution characteristics of yam-dyed silk fabric, and quantitatively analyzes the factors affecting color fastness. First, based on surface images and three-dimensional data, water-sensitive areas are identified, and groove depth, roughness, and water-stain sensitivity index are extracted. The composite influence factor of surface defects is calculated. At the same time, the concentration and distribution of unbound iron ions and tannin dyes are analyzed using energy dispersive spectroscopy and other technologies to obtain the iron ion migration risk index. Combining the above parameters, a comprehensive color fastness evaluation coefficient is obtained through normalization and weighted calculation. Finally, the color fastness level is determined by comparing it with a preset threshold range. This method integrates physical and chemical factors to achieve a more accurate and comprehensive color fastness evaluation, providing a reliable basis for quality control. Attached Figure Description

[0059] Figure 1 This is a schematic diagram of a method flow according to an embodiment of this application.

[0060] Figure 2 This is a schematic diagram of the system structure according to an embodiment of this application.

[0061] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0062] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0063] like Figure 1 As shown, this application provides a method for evaluating the color fastness of yam-dyed silk fabric, including:

[0064] A method for evaluating the colorfastness of yam-dyed silk fabrics includes:

[0065] S1. Obtain multi-dimensional feature data of the yam-dyed silk fabric to be evaluated. The multi-dimensional feature data includes surface micro-morphological feature information and internal chemical substance distribution feature information.

[0066] S2. Obtain the surface water stain sensitive area of ​​the silk yam-dyed fabric to be evaluated based on the surface micromorphology feature information, and obtain multiple surface groove depths and surface roughness feature values ​​based on the surface water stain sensitive area, and obtain the water stain sensitivity index based on the multiple surface groove depths.

[0067] S3. Obtain the composite influence factor of surface defects of the silk yam-dyed fabric to be evaluated based on the surface roughness characteristic value and the water stain sensitivity index.

[0068] S4. Obtain the concentration of unbound iron ions and the concentration of tannin dye based on the internal chemical substance distribution characteristics information, and obtain the iron ion migration risk index based on the concentration of unbound iron ions.

[0069] S5. Calculate the comprehensive color fastness evaluation coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor.

[0070] S6. Evaluate the color fastness of the silk yam-dyed fabric to be evaluated based on the comprehensive color fastness evaluation coefficient, and obtain the evaluation result.

[0071] As described in steps S1-S6 above, in existing technologies, color fastness assessment largely relies on changes in appearance to determine the grade. This method fails to fully consider the impact of microscopic morphological defects on the fabric surface on its sensitivity to water stains, and also ignores the synergistic effect of the distribution matching of unbound iron ions and tannin dyes on color stability. Consequently, the assessment results cannot fully reflect the color fastness performance of the fabric in actual use scenarios, resulting in a certain degree of bias. This invention first obtains multi-dimensional characteristic data of the silk yam-dyed fabric to be evaluated, including surface microscopic morphological feature information and internal chemical substance distribution feature information. Technically, surface microscopic morphological feature information can be collected using high-resolution microscopes, three-dimensional morphology scanners, and other equipment to obtain microscopic structural images and related three-dimensional data of the fabric surface; internal chemical substance distribution feature information can be obtained using energy dispersive spectroscopy, high-performance liquid chromatography, and other detection technologies to determine the concentration and distribution of unbound iron ions, tannin dyes, and other substances. The physical significance of this step lies in the fact that colorfastness is a comprehensive reflection of the interaction between the fabric's surface condition and its internal chemical substances. The surface micromorphology determines the way and extent of the fabric's contact with the external environment (such as water stains), while the type, concentration, and distribution of internal chemical substances directly affect the binding stability of dyes and fibers and the ion migration characteristics. Only by obtaining both types of data simultaneously can a comprehensive basis be provided for subsequent evaluation. For example, if there are many micro-grooves on the fabric surface, it will be easier to absorb water stains, thus affecting the stability of the dye. On the other hand, an excessively high concentration of unbound iron ions may accelerate fading. Therefore, the two types of data obtained through S1 can comprehensively cover the core physical and chemical factors affecting colorfastness.

[0072] Based on the surface micromorphology information, the surface water stain sensitive area is obtained, and then multiple surface groove depths, surface roughness characteristic values ​​and water stain sensitivity indices are obtained. In terms of technical implementation, firstly, edge segmentation is performed on the surface micro-morphology image based on image segmentation algorithms to identify areas with local color deepening and areas with increased texture roughness. These areas are sensitive areas where water stains are easily retained and can affect color fastness. After deduplication and merging, the initial water stain sensitive areas are obtained. Subsequently, three-dimensional morphology scanning technology is used to measure each initial water stain sensitive area, obtain a three-dimensional point cloud coordinate set, and perform principal component analysis to obtain the first principal component direction. Then, the average tilt angle and the corresponding planar component are calculated. After removing the three-dimensional point cloud coordinates of the planar component, the remaining coordinates are the coordinates of the local depression points. These local depression point coordinates are clustered into multiple clusters according to the preset area. Each cluster is defined as a micro-groove unit, and the difference between its deepest point and the average height of the surrounding area is the equivalent depth, which is used as the surface groove depth. At the same time, the vertical height deviation is calculated by the first vertical height of the planar component and each equivalent depth. Then, the vertical height deviation feature value is calculated by the mean and standard deviation, which is used as the surface roughness feature value. Finally, the equivalent depth coefficient is calculated by the mean and standard deviation of the equivalent depth, which is used as the water stain sensitivity index. The physical significance of this step lies in the fact that the microscopic grooves and roughness of the fabric surface directly affect its ability to absorb and retain water stains. The deeper and more unevenly distributed the grooves, the easier it is for water stains to accumulate, which in turn exacerbates dye dissolution or ion migration, affecting color fastness. The water stain sensitivity index quantifies this sensitivity, providing a quantitative basis for subsequent evaluation. For example, when there are many deep and unevenly distributed microscopic grooves on the fabric surface, its water stain sensitivity index will be higher, meaning that the risk of color fastness damage is greater after contact with water stains in actual use. At the same time, it can quantify the influence of this surface condition into specific parameters.

[0073] The composite influence factor of surface defects is obtained based on surface roughness characteristic values ​​and water stain sensitivity index. Technically, a preset surface roughness benchmark value and a preset water stain sensitivity benchmark index are first set. These two benchmark values ​​are standard reference values ​​derived from statistical analysis of test data from a large number of similar qualified fabrics. The surface roughness deviation is obtained by calculating the percentage difference between the surface roughness characteristic value and the benchmark value. Similarly, the water stain sensitivity deviation is obtained by calculating the percentage difference between the water stain sensitivity index and the benchmark index. Thus, the surface roughness deviation and water stain sensitivity deviation reflect the degree of deviation of the fabric surface roughness and water stain sensitivity index from the standard state, respectively. The composite influence factor of surface defects integrates these two single indicators into a comprehensive parameter, quantifying the overall impact of surface micro-defects on color fastness. Furthermore, this value intuitively reflects the comprehensive negative impact of surface defects on color fastness, providing a core quantitative indicator of surface factors for subsequent comprehensive evaluation.

[0074] The concentrations of unbound iron ions and tannin dyes are obtained based on the distribution characteristics of internal chemical substances, leading to an iron ion migration risk index. Technically, a pixel distribution map of the water-sensitive area on the surface is obtained using techniques such as energy dispersive spectroscopy (EDS). This map consists of the distribution information of iron and tannin characteristic elements (carbon and oxygen). Based on this pixel distribution map, the total area of ​​the region is calculated, along with the area of ​​the first pixel region (iron enrichment anomaly region) where the iron intensity exceeds a preset threshold, and the area of ​​the second pixel region (tannin enrichment anomaly region) where the tannin characteristic element intensity exceeds a preset threshold. The proportions of the iron-rich region and the tannin-rich region are then calculated. The matching degree between these two proportions is used to calculate the iron-tannin distribution matching degree. If the proportions are close and the distribution areas overlap significantly, the matching degree is high, indicating that the iron ions are relatively stably bound to tannins, resulting in a low migration risk. Finally, the concentration of unbound iron ions, the proportion of the iron-rich region area, and the iron-tannin distribution matching degree are weighted and calculated to obtain the iron ion migration risk index. The physical significance of this step lies in the fact that the migration of unbound iron ions is a crucial chemical factor leading to fabric fading. The higher the concentration of unbound iron ions, the more pronounced their enrichment in localized areas, and the worse the match between the iron ion concentration and the tannin dye distribution, the higher the risk of migration and fading. For example, if a fabric has a high concentration of unbound iron ions, with the iron-rich area accounting for 0.3% of the total area and the tannin-rich area accounting for only 0.1%, indicating a low iron-tannin distribution match, the iron ion migration risk index will be high. This means that during use, iron ions are more likely to migrate and disrupt the bond between the dye and the fiber, leading to a decrease in colorfastness. Furthermore, this step allows for precise quantification of this chemical risk factor.

[0075] The comprehensive color fastness assessment coefficient is calculated based on the iron ion migration risk index, tannin dye concentration, and surface defect composite influence factor. Technically, these three parameters are first normalized, converting parameters with different dimensions and numerical ranges into normalized values ​​between 0 and 1 to eliminate the influence of dimensional differences. The normalization process can use the min-max normalization method, i.e., (actual parameter value - minimum parameter value) / (maximum parameter value - minimum parameter value), where the maximum and minimum values ​​are determined based on a large amount of test data from similar fabrics. Subsequently, the three normalized values ​​are weighted, with the weights determined through experimental verification and statistical analysis based on the significance of each parameter's influence on color fastness. The final comprehensive color fastness assessment coefficient is then obtained. The physical significance of this step lies in the fact that the comprehensive color fastness assessment coefficient integrates the influence of surface defects (physical factors) and internal chemical properties (chemical factors) on color fastness, transforming multiple single influencing parameters into a comprehensive quantitative index, providing a core basis for subsequent color fastness grade determination.

[0076] Colorfastness is evaluated based on a comprehensive colorfastness assessment coefficient to obtain the evaluation result. Technically, a preset threshold range is first set, determined based on industry standards, product quality requirements, and extensive experimental data; for example, a pass / fail threshold range of [0.4, 0.7] is set. Then, the relationship between the comprehensive colorfastness assessment coefficient and this range is determined: if the coefficient is less than the minimum value of the range (e.g., 0.4), the colorfastness is deemed unqualified; if it is within the range, it is deemed qualified; if it is greater than the maximum value of the range (e.g., 0.7), it is deemed excellent. The physical significance of this step lies in establishing a correspondence between the comprehensive coefficient and the colorfastness grade through the preset threshold range, realizing the transformation from quantitative indicators to qualitative evaluation results, and providing a clear standard for quality judgment in practical applications. For example, if the overall color fastness evaluation coefficient of a fabric is 0.35, which is less than the minimum value of 0.4 in the preset threshold range, it means that its color fastness level is low under the influence of surface defects and internal chemical substances, and it is prone to fading and discoloration in actual use, and is judged as unqualified; while when the coefficient is 0.8, it means that its various influencing factors are well controlled and its color fastness performance is excellent, and is judged as excellent.

[0077] In summary, this invention, through a systematic process from multi-dimensional feature data collection to comprehensive coefficient evaluation, comprehensively covers the surface physical and internal chemical factors affecting the color fastness of yam-dyed silk fabrics. Compared with existing evaluation techniques that only rely on changes in appearance color, it can more accurately and comprehensively reflect the actual color fastness performance of the fabric, effectively reduce evaluation bias, and provide accurate basis for fabric production optimization and quality control.

[0078] In one embodiment, step S2, which identifies a water stain-sensitive area and obtains multiple surface groove depths and surface roughness feature values ​​based on the water stain-sensitive area, and then obtains a water stain sensitivity index based on the multiple surface groove depths, includes:

[0079] S21. Based on the image segmentation algorithm, the surface micro-morphology feature information is segmented at the edge to obtain the region with local color deepening and the region with increased texture roughness. The region with local color deepening and the region with increased texture roughness are deduplicated and merged to obtain the initial water stain sensitive region.

[0080] S22. Three-dimensional topography scanning technology is used to measure each of the initial water stain sensitive areas to obtain multiple three-dimensional point cloud coordinate sets, and principal component analysis is performed on the multiple three-dimensional point cloud coordinate sets in sequence to obtain multiple first principal component directions;

[0081] S23. Obtain the average tilt angle according to the multiple first principal component directions, obtain the corresponding planar component according to the average tilt angle, and remove the multiple three-dimensional point cloud coordinates that are concentrated in the planar component to obtain multiple local concave point coordinates.

[0082] S24. The coordinates of multiple local depression points are clustered into multiple clusters according to the area of ​​a preset region. Each cluster is defined as a micro-groove unit. The equivalent depth of each micro-groove unit (the difference between its deepest point and the average height of the surrounding area) is obtained, and the multiple equivalent depths are used as multiple surface groove depths.

[0083] S25. Obtain the first vertical height of the planar component, and obtain multiple vertical height deviations in sequence according to the first vertical height and multiple equivalent depths, obtain the average vertical height deviation according to the multiple vertical height deviations, obtain the standard vertical height deviation value according to the multiple vertical height deviations and the average vertical height deviation, obtain the vertical height deviation feature value according to the standard vertical height deviation value and the average vertical height deviation, and use the vertical height deviation feature value as the surface roughness feature value.

[0084] S26. Calculate the average equivalent depth based on the multiple equivalent depths, obtain the standard deviation of the equivalent depth based on the multiple equivalent depths and the average equivalent depth, obtain the equivalent depth coefficient based on the ratio of the average equivalent depth to the standard deviation of the equivalent depth, and use the equivalent depth coefficient as the water stain sensitivity index.

[0085] As described in steps S21-S26 above, step S21 of this invention performs edge segmentation on the surface micro-morphological feature information based on an image segmentation algorithm to obtain regions exhibiting local color deepening and regions with increased texture roughness. These two types of regions are then deduplicated and merged to obtain the initial water stain sensitive region. The surface micro-morphological feature information is obtained by capturing images of the fabric surface using a high-resolution microscope. These images clearly show the texture, depressions, and color distribution details of the fabric surface. Technically, the image segmentation algorithm can combine threshold segmentation with edge detection. First, a color grayscale threshold and a texture roughness threshold are set. Regions in the image with grayscale values ​​below the preset threshold (corresponding to local color deepening) and texture pixel gradients above the preset threshold (corresponding to increased texture roughness) are initially selected. Then, a morphological deduplication algorithm is used to remove overlapping parts and merge adjacent regions of the same type to finally obtain the initial water stain sensitive region. The physical significance of this step lies in the fact that areas of localized color deepening are usually locations on the fabric surface where impurities or dyes have accumulated, while areas with increased texture roughness are mostly areas around gaps formed by interwoven fibers or microscopic protrusions. Both types of areas are characterized by easy water absorption and difficulty in evaporation, making them key surface areas affecting colorfastness. For example, when uneven dyeing processes result in locally darker striped areas on the fabric surface, and these areas have obvious textures, image segmentation algorithms can accurately identify them as initial water-sensitive areas, laying the foundation for subsequent targeted analysis. This step, through targeted screening by the algorithm, effectively improves the accuracy of water-sensitive area identification and avoids invalid analysis of irrelevant surface areas.

[0086] Step S22 involves using 3D topographic scanning technology to measure each initial water stain sensitive area, obtaining multiple 3D point cloud coordinate sets. Principal component analysis (PCA) is then performed on these sets to obtain multiple first principal component directions. Technically, 3D topographic scanning can be achieved using a laser scanning microscope. This microscope scans the initial water stain sensitive area point by point with a laser beam, recording the 3D spatial coordinates of each scan point, thus forming a 3D point cloud coordinate set for that area. Each initial water stain sensitive area corresponds to an independent 3D point cloud coordinate set. During PCA, the x, y, and z axis coordinates of the 3D point cloud coordinate set are used as variables. Eigenvalues ​​and eigenvectors are calculated using the covariance matrix. The eigenvector with the largest eigenvalue is the first principal component direction, which reflects the main distribution trend of the 3D point cloud data, i.e., the overall extension direction of the initial water stain sensitive area. The physical significance of this step is that the 3D point cloud coordinate set can fully present the three-dimensional structure of the initial water stain sensitive area, while the first principal component direction can clearly define the main morphological orientation of the area, providing directional guidance for subsequent separation of planar components and extraction of depression features. For example, if an initial water stain sensitive area extends in a long strip, the direction of the first principal component obtained by principal component analysis is consistent with the direction of this long strip extension. Subsequently, the overall planar trend of the area can be separated based on this direction, thereby accurately extracting local depression features. This step, through the combination of three-dimensional data acquisition and principal component analysis, achieves accurate characterization of the three-dimensional structure of the sensitive area, providing high-precision data support for subsequent parameter calculations.

[0087] Step S23 involves obtaining the average tilt angle based on multiple first principal component directions, acquiring the corresponding planar component based on the average tilt angle, and removing the 3D point cloud coordinates that are concentrated in the planar component to obtain multiple local depression point coordinates. Technically, the angles between all first principal component directions and the horizontal plane are first calculated, and their arithmetic mean is taken as the average tilt angle. Then, a planar equation is constructed based on this average tilt angle. The 3D space plane corresponding to this planar equation is the planar component, which reflects the overall planar trend of the initial water stain sensitive area. Subsequently, the vertical distance from each 3D point cloud coordinate to the plane is calculated using the point-to-plane distance formula. Points with a distance less than a preset threshold (usually set to 0.1 μm, determined based on the fabric fiber diameter) are identified as points in the planar component and removed. The remaining points are the local depression point coordinates. The physical significance of this step is that the 3D structure of the initial water stain sensitive area includes both an overall planar trend and local depression features. The planar component corresponds to the reference plane of the area, while the local depression point coordinates correspond to the microscopic grooves on the fabric surface. These microscopic grooves are the core spaces for water stain retention. For example, the overall plane of the initial water stain sensitive area is tilted at 5°. After constructing the plane component based on this tilt angle, the points on the plane are removed. The remaining points are mostly concentrated in the low-lying areas below the plane. The set of these points is the coordinate of the local depression point. This step achieves accurate positioning of key surface defects (micro-grooves) by separating the plane component and the depression point, providing direct data for subsequent quantification of groove depth.

[0088] Step S24 involves clustering multiple local depression points into clusters based on a preset area. Each cluster is defined as a micro-groove unit, and the equivalent depth of each micro-groove unit is obtained. These multiple equivalent depths are then used as the surface groove depths. Technically, the clustering employs a density-based clustering algorithm (DBSCAN). The preset area corresponds to the neighborhood radius and minimum number of points parameters in the algorithm. By setting the neighborhood radius (e.g., 5 μm) and the minimum number of points (e.g., 50 points), local depression points whose distance is less than the neighborhood radius and whose number of points meets the minimum requirement are clustered into a single cluster. Each cluster corresponds to an independent micro-groove unit. The equivalent depth is calculated by first identifying the point with the smallest z-axis coordinate (the deepest point) in each cluster, then calculating the average z-axis coordinate of all points in that cluster (the average height of the surrounding area). The difference between the two is the equivalent depth of the micro-groove unit. The physical significance of this step lies in the fact that the clustered areas of local depression coordinates correspond to the actual micro-grooves on the fabric surface. The equivalent depth quantifies the depth of each micro-groove, and the surface groove depth is a key parameter affecting water stain retention. The deeper the groove, the longer the water stain retention time, and the more significant the negative impact on color fastness. For example, if the deepest point of a micro-groove unit corresponding to a cluster has a z-axis coordinate of 2μm and the average height of the surrounding area has a z-axis coordinate of 5μm, then its equivalent depth is 3μm. This value intuitively reflects the depth characteristics of the micro-groove. This step achieves accurate division of micro-grooves through clustering algorithms and quantifies the groove depth through equivalent depth calculation, providing core parameters for subsequent water stain sensitivity index calculation.

[0089] Step S25 involves obtaining the first vertical height of the planar component, and then sequentially obtaining multiple vertical height deviations based on the first vertical height and each equivalent depth. The average vertical height deviation is then calculated, followed by a standard vertical height deviation value based on the multiple vertical height deviations and the average. Finally, a vertical height deviation characteristic value is obtained based on the standard vertical height deviation value and the average vertical height deviation, and this value is used as the surface roughness characteristic value. Technically, the first vertical height is the average of the z-axis coordinates of all points on the planar component. The vertical height deviation is the difference (absolute value) between each equivalent depth and the first vertical height. The average vertical height deviation is the arithmetic mean of all vertical height deviations, and the standard vertical height deviation is the standard deviation of all vertical height deviations. The vertical height deviation characteristic value is calculated by the ratio of the standard vertical height deviation value to the average vertical height deviation. The physical significance of this step is that the vertical height deviation reflects the height difference between each micro-groove and the regional reference surface (planar component), while the vertical height deviation characteristic value comprehensively reflects the dispersion of these differences, quantitatively reflecting the surface roughness level of the fabric. The higher the surface roughness, the more complex the water stain adsorption path on the surface, and the stronger the adsorption capacity. For example, the first vertical height of an initial water stain sensitive area is 4 μm, the equivalent depths of the three micro-groove units are 3 μm, 2 μm, and 5 μm, respectively, and the corresponding vertical height deviations are 1 μm, 2 μm, and 1 μm. The average vertical height deviation is 1.33 μm, the standard vertical height deviation is 0.577 μm, and the characteristic value of the vertical height deviation is 0.434. The smaller this value is, the more uniform the surface roughness is, and vice versa. This step achieves accurate quantification of surface roughness through multi-step parameter calculation, making up for the shortcomings of traditional single roughness parameters that cannot fully reflect the surface state.

[0090] Step S26 involves calculating the average equivalent depth based on multiple equivalent depths, obtaining the standard deviation of the equivalent depth based on the multiple equivalent depths and the average equivalent depth, and finally obtaining the equivalent depth coefficient based on the ratio of the average equivalent depth to the standard deviation of the equivalent depth, which is used as the water stain sensitivity index. Technically, the average equivalent depth is the arithmetic mean of the equivalent depths of all micro-groove units, the standard deviation of the equivalent depth is the square root of the sum of the squares of the differences between all equivalent depths and the average, and the equivalent depth coefficient is the average equivalent depth divided by the standard deviation of the equivalent depth (when the standard deviation is 0, the coefficient is a fixed proportion of the average equivalent depth). The physical significance of this step is that the average equivalent depth reflects the overall depth level of the micro-grooves, the standard deviation of the equivalent depth reflects the uniformity of the distribution of the depth of each micro-groove, and the ratio of the two (the water stain sensitivity index) can comprehensively quantify the sensitivity of the fabric surface to water stains. The higher the index, the deeper and more uniformly distributed the micro-grooves are, and the higher the water stain sensitivity. For example, the equivalent depths of three micro-grooves in a certain fabric are 3μm, 4μm, and 5μm, respectively, with an average equivalent depth of 4μm, a standard deviation of 1μm, and a water stain sensitivity index of 4. If the equivalent depths of another fabric are 2μm, 4μm, and 6μm, with the same average of 4μm, but a standard deviation of 2μm, and a water stain sensitivity index of 2, it indicates that the former has a more uniform distribution of micro-grooves and is more sensitive to water stains. This step, by combining two key parameters, achieves accurate quantification of water stain sensitivity, providing a core basis for the subsequent calculation of the composite influence factor of surface defects.

[0091] In one embodiment, step S3, which involves obtaining the composite influence factor of surface defects in the yam-dyed silk fabric to be evaluated based on the surface roughness characteristic value and the water stain sensitivity index, includes:

[0092] S31. Calculate the surface roughness deviation based on the surface roughness characteristic value and the preset surface roughness reference value;

[0093] S32. Calculate the water stain sensitivity deviation based on the water stain sensitivity index and the preset water stain sensitivity benchmark index;

[0094] S33. The surface roughness deviation and the water stain sensitivity deviation are weighted and calculated to obtain the surface defect composite influence factor, wherein the calculation formula is:

[0095] ;

[0096] in, This represents the composite influence factor of surface defects. Indicates the deviation of surface roughness. Indicates the degree of water stain sensitivity deviation. This indicates the weight value of the surface roughness deviation. This indicates the weight value for water stain sensitivity deviation.

[0097] As described in steps S31-S33 above, step S31 of this invention calculates the surface roughness deviation based on the surface roughness characteristic value and the preset surface roughness reference value. The surface roughness characteristic value is calculated by taking the vertical height deviation of the first vertical height of the planar component and multiple equivalent depths, and then calculating the vertical height deviation characteristic value using the mean and standard deviation. The preset surface roughness reference value is determined by statistical analysis of test data from a large number of similar qualified silk yam-dyed fabrics, identifying the median or optimal value within the standard surface roughness characteristic value range. For example, by statistically analyzing the surface roughness characteristic values ​​of 1000 qualified fabrics, the average value of 0.3 is taken as the preset surface roughness reference value. Technically, the surface roughness deviation is calculated using a relative deviation formula: the absolute value of (surface roughness characteristic value - preset surface roughness reference value) divided by the preset surface roughness reference value. The larger this value, the greater the difference between the actual surface roughness of the fabric and the standard state. The physical significance of this step lies in the fact that surface roughness characteristic values ​​can only reflect the quantitative degree of surface roughness of the fabric, but cannot reflect the deviation of this degree from the acceptable standard. Surface roughness deviation, on the other hand, can intuitively quantify this deviation and clarify the severity of surface roughness defects. For example, if the surface roughness characteristic value of a fabric to be evaluated is 0.45, and the preset surface roughness benchmark value is 0.3, the surface roughness deviation is calculated to be (0.45-0.3) / 0.3=0.5. This indicates that the surface roughness of the fabric is 50% higher than the standard state, the difference between its surface depressions and protrusions is more significant, and the risk of water stain accumulation is higher. This step, through comparison with the benchmark value, achieves a quantitative assessment of surface roughness defects.

[0098] Step S32 calculates the water stain sensitivity deviation based on the water stain sensitivity index and a preset water stain sensitivity benchmark index. The preset water stain sensitivity benchmark index is also determined based on statistical data from a large number of similar qualified fabrics. For example, the average water stain sensitivity index of qualified fabrics, which is 4, is taken as the preset water stain sensitivity benchmark index. Technically, the calculation method for water stain sensitivity deviation is consistent with that for surface roughness deviation, using a relative deviation formula: the absolute value of (water stain sensitivity index - preset water stain sensitivity benchmark index) divided by the preset water stain sensitivity benchmark index. The physical significance of this step is that the water stain sensitivity index quantifies the fabric's sensitivity to water stains. However, the requirements for water stain sensitivity vary in different application scenarios. By comparing the deviation with the preset benchmark index, it can be determined whether the sensitivity meets the acceptable standard and the extent of deviation. For example, if the water stain sensitivity index of a fabric to be evaluated is 6 and the preset water stain sensitivity benchmark index is 4, the calculated water stain sensitivity deviation is (6-4) / 4=0.5, which means that the fabric is 50% more sensitive to water stains than the standard state, has a stronger ability to absorb and retain water stains, and has a higher risk of dye leaching. This step converts the water stain sensitivity into a quantitative value of deviation from the standard through benchmark comparison, providing a unified dimension of parameter support for multi-factor integration.

[0099] Step S33 involves weighting the surface roughness deviation and water stain sensitivity deviation to obtain a composite influence factor for surface defects. Technically, the weight values ​​w1 and w2 are determined based on the significance of the two surface factors' impact on color fastness, using orthogonal experimental design. For example, orthogonal experiments with different combinations of w1 and w2 are designed, and color fastness is measured on multiple fabrics. The correlation between the calculated composite influence factor for surface defects under different weight combinations and the actual color fastness is analyzed, ultimately determining the weight combination with the highest correlation. Assuming that experiments have verified that the impact of surface roughness deviation on color fastness is slightly less than that of water stain sensitivity deviation, w1 = 0.4, w2 = 0.6, and the sum of w1 and w2 is 1 to ensure the rationality of the weighted calculation. The physical significance of this step is that surface roughness deviation and water stain sensitivity deviation reflect the impact of surface defects on color fastness from different dimensions. They have a synergistic effect; neither parameter alone can fully reflect the comprehensive impact of surface defects. Weighted calculation integrates the two deviations into a single comprehensive factor, quantifying the overall negative impact of surface defects on color fastness. For example, if the surface roughness deviation of a fabric to be evaluated is 0.5, the water stain sensitivity deviation is 0.5, w1=0.4, and w2=0.6, the surface defect composite influence factor calculated using the formula is 0.5*. 0.4+0.5*0.6=0.5. This value comprehensively reflects the overall deviation of the fabric surface roughness and water stain sensitivity from the standard state. It provides a core indicator that can reflect the overall impact of surface defects for subsequent comprehensive color fastness assessment. This step achieves the systematic integration of multiple surface factors through weight allocation and weighted integration, making the quantitative results more consistent with the actual color fastness influence mechanism.

[0100] In summary, steps S31-S33, through a progressive process of calculating deviation based on benchmark comparison and weighted integration to form a composite factor, achieve precise quantification of the impact of surface defects on silk yam-dyed fabrics. Compared to existing technologies that analyze single surface parameters individually and lack comprehensive integration, this series of steps, by introducing preset benchmark values, gives surface parameters a standard comparative meaning. Weighted calculation achieves the synergistic integration of multiple surface factors, and the resulting composite impact factor of surface defects comprehensively and objectively reflects the overall impact of surface physical defects on color fastness. Specifically, the determination of benchmark values ​​is based on a large amount of measured data, ensuring the scientific nature of the comparison; the setting of weight values ​​is verified through orthogonal experiments, ensuring the rationality of the integration. These technical designs are directly related to the surface physical characteristics and color fastness impact mechanism of silk yam-dyed fabrics, effectively improving the comprehensiveness and accuracy of surface defect impact assessment. This provides a reliable quantitative basis for the subsequent calculation of the comprehensive color fastness assessment coefficient, thereby helping the entire color fastness assessment method achieve more accurate assessment results.

[0101] In one embodiment, step S4, which involves obtaining the iron ion migration risk index based on the concentration of unbound iron ions, includes:

[0102] S41. Obtain a pixel distribution map within the surface water stain sensitive area, wherein the pixel distribution map is composed of iron and carbon and oxygen as tannin characteristic elements;

[0103] S42. Obtain the total area of ​​the corresponding region based on the pixel distribution map;

[0104] S43. Obtain the first pixel region with iron element intensity higher than a preset threshold according to the pixel distribution map, define the first pixel region as an iron enrichment abnormal region, obtain the first total pixel area corresponding to the iron enrichment abnormal region, and obtain the iron enrichment region area ratio according to the first total pixel area and the total area of ​​the region.

[0105] S44. Obtain a second pixel region with a tannin feature element intensity higher than a preset threshold according to the pixel distribution map, define the second pixel region as a tannin enrichment abnormal region, obtain the second total pixel area corresponding to the tannin enrichment abnormal region, and obtain the tannin enrichment region area ratio according to the second total pixel area and the total area of ​​the region.

[0106] S45. Calculate the iron-tannin distribution matching degree based on the area ratio of the iron-rich region and the area ratio of the tannin-rich region.

[0107] S46. The iron ion migration risk index is obtained by weighting the concentration of unbound iron ions, the area ratio of the iron-rich region, and the iron-tannin distribution matching degree.

[0108] As described in steps S41-S46 above, step S41 of this invention involves obtaining a pixel distribution map within the surface water stain sensitive area. This pixel distribution map is composed of iron and carbon and oxygen, which are characteristic elements of tannins. The surface water stain sensitive area originates from the initial water stain sensitive area obtained in step S21. The acquisition of the pixel distribution map relies on energy dispersive spectroscopy (EDS) analysis. An EDS spectrometer scans the surface water stain sensitive area to detect the distribution positions and intensities of iron, carbon, and oxygen elements within the area. The element intensities are converted into pixel grayscale values, thus forming a pixel distribution map that characterizes the element distribution with different grayscale values. Different elements correspond to different grayscale ranges, facilitating subsequent differentiation and identification. The physical significance of this step lies in the fact that the surface water stain sensitive area is a core region where water stains easily accumulate. Iron ions in this area interact more frequently with tannin dyes, and their distribution directly affects the migration probability of iron ions. The pixel distribution map can intuitively present the spatial distribution of iron and tannin characteristic elements, providing a visual data foundation for subsequent quantitative analysis. For example, if the iron intensity is high in a certain local area within the surface water stain sensitive area, the corresponding pixel distribution image will show a high gray value at that location, while the surrounding carbon and oxygen elements have low intensity and low gray value. This indicates that there may be iron ion enrichment in that local area and that it is separated from the distribution of tannin dye. This provides an intuitive basis for the subsequent accurate identification of the enriched area. This step, through the combination of energy dispersive spectroscopy and image conversion, realizes the visual characterization of chemical substance distribution and lays the data foundation for subsequent quantitative analysis.

[0109] Step S42 involves obtaining the total area of ​​the corresponding region based on the pixel distribution map. Technically, using the boundary of the pixel distribution map as a benchmark, the total number of pixels in the image is counted. This, combined with the actual area ratio of each pixel as set during energy dispersive spectroscopy analysis, yields the total area of ​​the region, i.e., the actual physical area of ​​the surface water-sensitive region. The physical significance of this step lies in the fact that the total area serves as the benchmark for subsequent calculations of the area ratio of various enriched regions. Only by clearly defining the overall region size can the relative scale of the enriched region be quantified through its proportion, thereby reflecting the degree of chemical enrichment. For example, if the pixel distribution map of a surface water-sensitive region contains 10,000 pixels, and each pixel corresponds to an actual area of ​​1 μm², then the total area of ​​this region is 10,000 μm². Subsequently, by counting the number of pixels corresponding to iron enrichment, its proportion of the overall region can be calculated. This step, by determining the area benchmark, provides the necessary prerequisite for subsequent calculations of the enrichment ratio, ensuring the accuracy of the quantification results.

[0110] Step S43 involves identifying the first pixel region with iron intensity exceeding a preset threshold based on the pixel distribution map. This region is defined as an iron-enriched anomalous region. The first total pixel area of ​​this region is then calculated, and the iron-enriched region area ratio is determined based on the first total pixel area and the total area of ​​the region. Technically, the preset threshold is set based on statistical data of iron intensity from a large number of similar qualified silk yam-dyed fabrics. The maximum iron intensity of qualified fabrics is taken as the preset threshold. When the iron grayscale value of a pixel in the pixel distribution map exceeds this threshold, the pixel is determined to be an iron-enriched point. All consecutive iron-enriched points constitute the first pixel region (iron-enriched anomalous region). The first total pixel area is the total number of pixels within the iron-enriched anomalous region multiplied by the actual area corresponding to a single pixel. The iron-enriched region area ratio is the ratio of the first total pixel area to the total area of ​​the region. The physical significance of this step lies in the fact that areas where the iron intensity exceeds a preset threshold indicate that the iron ion content is far above normal levels, belonging to abnormal areas of excessive iron ion enrichment. Iron ions in these areas are prone to migration due to their high concentration. The proportion of the iron-rich area quantifies the relative scale of this abnormal enrichment; the higher the proportion, the wider the extent of iron ion over-enrichment and the greater the risk of migration. For example, if the total area of ​​a surface water-sensitive region is 10,000 μm², and the first total pixel area of ​​the iron-rich abnormal region is 2,000 μm², then the proportion of the iron-rich area is 20%, indicating that 20% of the area within this region has excessive iron ion enrichment. These areas are high-risk regions for iron ion migration. This step, through threshold screening and proportion calculation, quantifies the degree of iron ion enrichment, providing key parameters for subsequent risk assessment.

[0111] Step S44 involves identifying second pixel regions where the intensity of tannin feature elements exceeds a preset threshold based on the pixel distribution map. These regions are defined as tannin enrichment anomalies. The second total pixel area of ​​this region is then calculated, and the proportion of the tannin-enriched region area is determined based on the second total pixel area and the total area of ​​the region. Technically, the tannin feature elements are carbon and oxygen. The preset threshold is also determined based on statistical data of carbon and oxygen element intensity in qualified fabrics. The maximum value of the combined carbon and oxygen element intensity in qualified fabrics is taken as the preset threshold. When the combined carbon and oxygen element grayscale value of a pixel in the pixel distribution map exceeds this threshold, it is identified as a tannin-enriched point. Consecutive tannin-enriched points constitute the second pixel region (tannin enrichment anomaly region). The calculation method for the second total pixel area is the same as that for the first total pixel area. The proportion of the tannin-enriched region area is the ratio of the second total pixel area to the total area of ​​the region. The physical significance of this step lies in the fact that the main constituent elements of tannin dyes are carbon and oxygen. Abnormal enrichment areas indicate a high tannin dye content in those areas. Tannin dyes can combine with iron ions to form stable complexes, inhibiting iron ion migration. The area ratio of tannin-enriched regions quantifies the enrichment scale of tannin dyes, providing a basis for subsequent analysis of the iron-tannin synergistic effect. For example, in the aforementioned surface water stain sensitive area, the second total pixel area of ​​the abnormal tannin enrichment region is 1500 μm², indicating that 15% of this area has excessive tannin dye enrichment. These areas may inhibit the migration of surrounding iron ions. This step, through targeted screening and proportion calculation of tannin characteristic elements, quantifies the degree of tannin dye enrichment, providing key parameters for subsequent distribution matching analysis.

[0112] Step S45 calculates the iron-tannin distribution matching degree based on the area proportions of iron-rich regions and tannin-rich regions. Technically, a cosine similarity algorithm is used to calculate the matching degree. The area proportions of iron-rich regions and tannin-rich regions are treated as two vectors, and the matching degree is determined by the cosine value of the angle between these vectors. The closer the cosine value is to 1, the higher the matching degree, meaning the enrichment scales of iron ions and tannin dyes are more similar and their distributions are more synergistic. Conversely, the closer the cosine value is to 0, the lower the matching degree, indicating more separation in their distributions. Furthermore, the spatial overlap of the two types of enriched regions in the pixel distribution map can be used for correction. If the spatial overlap is high, the matching degree is appropriately increased based on the cosine similarity; conversely, it is appropriately decreased. The physical significance of this step lies in the fact that the distribution matching between iron ions and tannin dyes directly affects the migration risk of iron ions. When the enrichment ratios of the two are close and their spatial overlap is high, iron ions can fully combine with tannin dyes to form stable complexes, reducing the migration risk. When the ratios differ greatly and they are spatially separated, iron ions are difficult to bind to tannin dyes, increasing the migration risk. For example, in a fabric, the iron-rich area accounts for 20% and the tannin-rich area accounts for 18%, with a spatial overlap of 80%. The basic matching degree calculated using cosine similarity is 0.95. After correction for overlap, the final iron-tannin distribution matching degree is 0.98, indicating good synergy between the two distributions and a low risk of iron ion migration. If another fabric has an iron enrichment ratio of 20% and a tannin enrichment ratio of 5%, with a spatial overlap of 10%, the matching degree may only be 0.2, significantly increasing the risk of iron ion migration. This step, through comprehensive analysis of ratios and spatial overlap, achieves accurate quantification of the iron-tannin distribution matching, providing key synergistic parameters for subsequent risk index integration.

[0113] Step S46 involves a weighted calculation based on the concentration of unbound iron ions, the proportion of iron-rich regions, and the matching degree of iron-tannin distribution to obtain the iron ion migration risk index. The concentration of unbound iron ions is obtained by detecting the distribution characteristics of internal chemical substances using high-performance liquid chromatography (HPLC). Specifically, internal chemical substances are separated using a chromatograph, and the actual concentration of unbound iron ions is calculated by comparing the chromatographic peak area corresponding to iron ions with a standard curve. In terms of technical implementation, the weight values ​​for weighted calculation are determined through orthogonal experiments. Experimental schemes with different weight combinations are designed, and iron ion migration is measured on multiple groups of fabrics. The correlation between the risk index calculated under different weight combinations and the actual migration amount is analyzed, and the optimal weight allocation is finally determined. Assuming that the experiment has verified that the weight of the concentration of unbound iron ions is w3=0.5, the weight of the area ratio of iron-rich regions is w4=0.3, and the weight of the iron-tannin distribution matching degree is w5=0.2 (the matching degree is a negative indicator, and 1-matching degree is used for weighting in the calculation), the calculation formula is: Iron ion migration risk index = normalized value of unbound iron ion concentration × w3 + area ratio of iron-rich regions × w4 + (1-iron-tannin distribution matching degree) × w5. The concentration of unbound iron ions needs to be normalized first to convert it into a value between 0 and 1 to eliminate dimensional differences. The physical significance of this step lies in the fact that the concentration of unbound iron ions reflects the absolute content of iron ions and is a fundamental factor in migration risk; the area ratio of iron-rich regions reflects the local enrichment degree of iron ions and is a spatial factor in migration risk; and the iron-tannin distribution matching degree reflects the binding ability of tannin dyes on iron ions and is a factor in inhibiting migration risk. By weighted calculation, these three key factors are integrated into a comprehensive risk index, which can comprehensively quantify the overall risk of iron ion migration. For example, if a fabric has a normalized unbound iron ion concentration of 0.6, an iron-rich area ratio of 0.2, and an iron-tannin distribution matching degree of 0.98, then the iron ion migration risk index = 0.6 × 0.5 + 0.2 × 0.3 + (1 - 0.98) × 0.2 = 0.364, indicating that the fabric has a low iron ion migration risk. If another fabric has a normalized unbound iron ion concentration of 0.8, an iron-rich area ratio of 0.3, and a distribution matching degree of 0.2, then the risk index = 0.8 × 0.5 + 0.3 × 0.3 + (1 - 0.2) × 0.2 = 0.65, indicating a significantly higher migration risk. This step, through multi-factor weighted integration, achieves a comprehensive quantification of iron ion migration risk, providing core chemical factor indicators for subsequent comprehensive color fastness assessment.

[0114] In summary, steps S41-S46, through a progressive technical process from visualizing chemical substance distribution to quantifying the risk index, achieve a precise assessment of the iron ion migration risk in yam-dyed silk fabrics. Compared to existing technologies that only focus on the concentration of a single chemical substance and lack synergistic analysis of distribution, this series of steps visualizes the distribution of chemical substances through energy dispersive spectroscopy (EDS), quantifies the degree of local enrichment of substances through enrichment ratio calculation, demonstrates the synergistic effect of multiple substances through distribution matching analysis, and finally integrates the results through weighted calculation to form an iron ion migration risk index. The technical design of each step is directly related to the chemical properties and colorfastness influencing mechanisms of yam-dyed silk fabrics. Among these features, the acquisition of pixel distribution maps provides accurate data for distribution analysis, the calculation of enrichment ratio quantifies the degree of local anomalies, the analysis of distribution matching degree makes up for the limitations of single substance assessment, and the weighted calculation realizes the comprehensive integration of multiple factors. The synergistic effect of these technical features effectively improves the comprehensiveness and accuracy of iron ion migration risk assessment, provides a reliable chemical factor quantification basis for the subsequent calculation of comprehensive color fastness assessment coefficient, and thus helps the entire color fastness assessment method achieve more accurate assessment results that are more in line with actual use scenarios.

[0115] In one embodiment, step S5, which calculates the comprehensive color fastness assessment coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor, includes:

[0116] S51. Normalize the iron ion migration risk index to obtain the normalized value of the iron ion migration risk index.

[0117] S52. Normalize the concentration of the tannin dye to obtain a normalized value of the tannin dye concentration.

[0118] S53. Normalize the surface defect composite influence factor to obtain the normalized value of the surface defect composite influence factor.

[0119] S54. The normalized value of the iron ion migration risk index, the normalized value of the tannin dye concentration, and the normalized value of the surface defect composite influence factor are weighted and calculated to obtain the comprehensive color fastness evaluation coefficient.

[0120] As described in steps S51-S54 above, this invention calculates a comprehensive colorfastness evaluation coefficient by weighting the normalized values ​​of the iron ion migration risk index, tannin dye concentration, and surface defect composite influence factor. Technically, the weight values ​​for the weighted calculation are determined through orthogonal experiments combined with correlation analysis. The specific process is as follows: multiple different weight combination schemes are designed; for each scheme, multiple silk yam-dyed fabrics with known colorfastness grades are selected, and their comprehensive colorfastness evaluation coefficients are calculated. Then, correlation analysis is performed between the evaluation coefficients and the actual colorfastness grades, and the weight combination with the highest correlation is selected as the final weight. Assuming experimental verification shows that tannin dye concentration has the most significant positive impact on color fastness, with a weight of w6=0.4; the iron ion migration risk index has the next most significant negative impact, with a weight of w7=0.3; and the indirect impact of the surface defect composite influence factor is relatively small, with a weight of w8=0.3. The sum of w6, w7, and w8 is 1 to ensure the logical rationality of the weighted calculation. The calculation formula is: Comprehensive color fastness assessment coefficient = Normalized value of tannin dye concentration × w6 + (1 - Normalized value of iron ion migration risk index) × w7 + (1 - Normalized value of surface defect composite influence factor) × w8. Here, the iron ion migration risk index and the surface defect composite influence factor are negative indicators and need to be converted into positive contribution values ​​through 1 - normalization. The physical significance of this step is that the three normalized parameters affect color fastness from three dimensions: positive support, negative damage, and indirect negative impact. Through reasonable weight allocation, the role of key influencing factors can be highlighted, enabling the comprehensive color fastness assessment coefficient to objectively reflect the synergistic effect of each factor. For example, the normalized value of the tannin dye concentration of a fabric to be evaluated is 0.467, the normalized value of the iron ion migration risk index is 0.429, and the normalized value of the surface defect composite influence factor is 0.4. Substituting these values ​​into the formula, the comprehensive color fastness evaluation coefficient is calculated as follows: 0.467×0.4+(1-0.429)×0.3+(1-0.4)×0.3=0.5381. This value comprehensively reflects the color fastness level of the fabric under the combined effect of chemical stability and surface physical state, providing a precise quantitative basis for subsequent grade determination. This step, through scientific weight allocation and weighted integration, achieves the systematic integration of multi-dimensional influencing factors, making the comprehensive evaluation results more consistent with the actual performance of the color fastness of yam-dyed silk fabrics.

[0121] In one embodiment, step S6, which evaluates the colorfastness of the silk yam-dyed fabric to be evaluated based on the comprehensive colorfastness evaluation coefficient to obtain the evaluation result, includes:

[0122] S61. Determine the relationship between the comprehensive color fastness evaluation coefficient and the preset threshold range;

[0123] When the comprehensive color fastness evaluation coefficient is not within the preset threshold range and is less than the minimum value of the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be unqualified.

[0124] When the comprehensive color fastness evaluation coefficient is within the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be qualified.

[0125] When the comprehensive color fastness evaluation coefficient is not within the preset threshold range and is greater than the maximum value of the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be excellent.

[0126] As described in step S61 above, the first step of this invention is to determine a preset threshold range. This threshold range is comprehensively formulated based on industry quality standards, a large amount of measured data from similar fabrics, and the needs of actual application scenarios. Specifically, samples of silk yam-dyed fabrics of different quality grades (known as excellent, qualified, and unqualified) are collected. By calculating the comprehensive color fastness evaluation coefficient of each sample, these coefficients are statistically analyzed to determine the distribution range of the coefficients of qualified samples. The minimum value of this range is set as the minimum value of the preset threshold range, and the maximum value is set as the maximum value of the preset threshold range. At the same time, combined with the industry's requirements for the color fastness of high-end fabrics, coefficients exceeding the maximum value of the qualified range and showing excellent performance are corresponding to the excellent grade, while those below the minimum value of the qualified range are corresponding to the unqualified grade. For example, by statistically analyzing the comprehensive color fastness evaluation coefficients of 1000 samples, it was found that the coefficients of qualified samples are concentrated between 0.4 and 0.7. Therefore, the preset threshold range is set as [0.4, 0.7], where 0.4 is the minimum value and 0.7 is the maximum value.

[0127] The next step is to determine the relationship between the overall colorfastness assessment coefficient and the preset threshold range. Technically, this is achieved through a simple numerical comparison logic: first, it checks if the coefficient is less than the minimum value of the preset threshold range; then, it checks if it is greater than the maximum value; finally, it determines if it falls within the range. The physical significance of this step is that when the overall colorfastness assessment coefficient is less than the minimum value, it indicates severe surface defects in the fabric, a high risk of iron ion migration, and insufficient tannin dye binding stability, meaning the colorfastness level cannot meet basic usage requirements. When the coefficient is within the range, it indicates that the combined effect of various influencing factors is within an acceptable range, and the colorfastness meets the standard requirements. When the coefficient is greater than the maximum value, it indicates that the fabric surface structure is regular, the risk of iron ion migration is low, and the tannin dye binding is stable, meaning the colorfastness performance is better than the conventional standard. For example, if the overall color fastness evaluation coefficient of a fabric to be evaluated is 0.35, which is less than the minimum value of 0.4 in the preset threshold range, it means that the fabric is prone to fading due to water stains and iron ion migration in actual use, and is judged as unqualified; if the coefficient is 0.55, which is within the range of [0.4, 0.7], it means that its color fastness can meet the needs of daily use, and is judged as qualified; if the coefficient is 0.82, which is greater than the maximum value of 0.7 in the range, it means that its performance in all aspects is excellent and its color fastness level is high, and is judged as excellent.

[0128] Finally, the evaluation results are output based on the judgment. Technically, the numerical comparison results are mapped to corresponding quality level identifiers through program logic, directly feeding this information back to the user. The physical significance of this step lies in transforming abstract quantitative data into intuitive level conclusions, lowering the barrier to using the evaluation results, making it easier for production managers to quickly determine whether fabric quality meets standards, and also making it easier for downstream companies to select suitable fabric products based on the level. For example, when purchasing yam-dyed silk fabrics, garment manufacturers can directly select excellent-grade fabrics for high-end apparel production and qualified-grade fabrics for regular products, avoiding after-sales problems caused by insufficient colorfastness.

[0129] In summary, step S61 achieves precise grading and evaluation of color fastness in yam-dyed silk fabrics by pre-setting scientific threshold ranges and establishing clear numerical judgment logic. Compared to existing technologies that rely on manual observation and lack unified standards, this step establishes a standardized grading system based on the comprehensive color fastness evaluation coefficient obtained by integrating multiple factors mentioned above. The determination of the pre-set threshold ranges is based on a large amount of measured data and industry needs, ensuring the scientific and reasonable nature of the grading. The numerical comparison method guarantees the objectivity and consistency of the evaluation results, effectively avoiding the subjective bias of manual evaluation. Furthermore, this step transforms the quantitative coefficients into intuitive quality levels, improving the practicality of the evaluation results and providing a reliable decision-making basis for fabric production optimization, quality control, and downstream applications, thus solving the problems of poor consistency and insufficient practicality in existing technologies.

[0130] like Figure 2 As shown, this application also provides a color fastness evaluation system for yam-dyed silk fabrics, comprising:

[0131] The multi-dimensional feature acquisition module is used to acquire multi-dimensional feature data of the yam-dyed silk fabric to be evaluated. The multi-dimensional feature data includes surface micro-morphology feature information and internal chemical substance distribution feature information.

[0132] The surface morphology analysis module is used to obtain the depth of multiple surface grooves and surface roughness feature values ​​of the water stain sensitive area on the fabric surface based on the surface micromorphology feature information, and to obtain the water stain sensitivity index based on the depth of the multiple surface grooves.

[0133] The surface defect impact calculation module is used to obtain the surface defect composite impact factor of the silk yam-dyed fabric to be evaluated based on the surface roughness characteristic value and the water stain sensitivity index.

[0134] The chemical substance analysis module is used to obtain the concentration of unbound iron ions and the concentration of tannin dye based on the internal chemical substance distribution characteristics information, and to obtain the iron ion migration risk index based on the concentration of unbound iron ions.

[0135] The comprehensive color fastness calculation module is used to calculate the comprehensive color fastness evaluation coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor.

[0136] The color fastness assessment module is used to assess the color fastness of the silk yam-dyed fabric to be assessed based on the comprehensive color fastness assessment coefficient, and obtain the assessment result.

[0137] In one embodiment, the surface morphology analysis module includes:

[0138] The sensitive region extraction unit is used to perform edge segmentation on the surface micro-morphology feature information based on the image segmentation algorithm to obtain regions with local color deepening and regions with increased texture roughness, and to merge the regions with local color deepening and regions with increased texture roughness to obtain the initial water stain sensitive region.

[0139] The point cloud acquisition unit is used to measure each of the initial water stain sensitive areas using three-dimensional topography scanning technology to obtain multiple three-dimensional point cloud coordinate sets, and to perform principal component analysis on the multiple three-dimensional point cloud coordinate sets in sequence to obtain multiple first principal component directions.

[0140] The local depression point coordinate acquisition unit is used to obtain the average tilt angle based on the multiple first principal component directions, obtain the corresponding planar component based on the average tilt angle, and remove the three-dimensional point cloud coordinates that are concentrated in the planar component to obtain multiple local depression point coordinates.

[0141] An equivalent depth calculation unit is used to cluster multiple local depression point coordinates into multiple clusters according to a preset area, wherein each cluster is defined as a micro-groove unit, and the equivalent depth of each micro-groove unit (the difference between its deepest point and the average height of the surrounding area) is obtained, and multiple equivalent depths are used as multiple surface groove depths.

[0142] A surface roughness feature extraction unit is used to obtain a first vertical height of a planar component, and sequentially obtain multiple vertical height deviations based on the first vertical height and multiple equivalent depths, obtain an average vertical height deviation based on the multiple vertical height deviations, obtain a standard vertical height deviation value based on the multiple vertical height deviations and the average vertical height deviation, obtain a vertical height deviation feature value based on the standard vertical height deviation value and the average vertical height deviation, and use the vertical height deviation feature value as a surface roughness feature value.

[0143] The water stain sensitivity index calculation unit is used to calculate the average equivalent depth based on multiple equivalent depths, obtain the standard deviation of the equivalent depth based on the multiple equivalent depths and the average equivalent depth, obtain the equivalent depth coefficient based on the ratio of the average equivalent depth to the standard deviation of the equivalent depth, and use the equivalent depth coefficient as the water stain sensitivity index.

[0144] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0145] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0146] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in this application and in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0147] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0148] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for evaluating the color fastness of a true silk and morinda officinalis dyed fabric, characterized by, include: Obtain multi-dimensional feature data of the silk yam-dyed fabric to be evaluated, including surface micromorphological features and internal chemical substance distribution features. Based on the surface micromorphology information, the surface water stain sensitive areas of the yam-dyed silk fabric to be evaluated are obtained. Multiple surface groove depths and surface roughness feature values ​​are obtained based on these surface water stain sensitive areas. A water stain sensitivity index is then obtained based on the multiple surface groove depths, including: The surface micromorphological features are segmented based on an image segmentation algorithm to obtain regions with local color deepening and regions with increased texture roughness. The regions with local color deepening and regions with increased texture roughness are then deduplicated and merged to obtain the initial water stain sensitive region. Three-dimensional topography scanning technology is used to measure each of the initial water stain sensitive areas to obtain multiple three-dimensional point cloud coordinate sets, and principal component analysis is performed on the multiple three-dimensional point cloud coordinate sets in sequence to obtain multiple first principal component directions; The average tilt angle is obtained based on the multiple first principal component directions, the corresponding planar component is obtained based on the average tilt angle, and the three-dimensional point cloud coordinates that are concentrated in the planar component are removed to obtain the coordinates of multiple local depression points. The coordinates of multiple local depression points are clustered into multiple clusters according to the area of ​​a preset region. Each cluster is defined as a micro-groove unit, and the equivalent depth of each micro-groove unit is obtained. The multiple equivalent depths are used as multiple surface groove depths. A first vertical height of the planar component is obtained, and multiple vertical height deviations are obtained sequentially based on the first vertical height and multiple equivalent depths. The average vertical height deviation is obtained based on the multiple vertical height deviations, and a standard vertical height deviation value is obtained based on the multiple vertical height deviations and the average vertical height deviation. A vertical height deviation feature value is obtained based on the standard vertical height deviation value and the average vertical height deviation, and the vertical height deviation feature value is used as a surface roughness feature value. The equivalent depth average is calculated based on multiple equivalent depths, and the equivalent depth standard deviation is obtained based on the multiple equivalent depths and the equivalent depth average. The equivalent depth coefficient is obtained based on the ratio of the equivalent depth average to the equivalent depth standard deviation, and the equivalent depth coefficient is used as the water stain sensitivity index. The surface defect composite influence factor of the silk yam-dyed fabric to be evaluated is obtained based on the surface roughness characteristic value and the water stain sensitivity index, including: Calculate the surface roughness deviation based on the surface roughness characteristic value and the preset surface roughness reference value; Calculate the water stain sensitivity deviation based on the water stain sensitivity index and the preset water stain sensitivity benchmark index; The surface roughness deviation and the water stain sensitivity deviation are weighted and calculated to obtain the surface defect composite influence factor, wherein the calculation formula is: ； wherein, represents a surface defect complexing impact factor, represents a surface roughness deviation degree, represents a water stain sensitivity deviation degree, represents a surface roughness deviation degree weight value, represents a water stain sensitivity deviation degree weight value; The concentrations of unbound iron ions and tannin dyes are obtained based on the internal chemical substance distribution characteristics. An iron ion migration risk index is then obtained based on the unbound iron ion concentration, including: Obtain a pixel distribution map of the surface water stain sensitive area, wherein the pixel distribution map is composed of iron and carbon and oxygen as tannin characteristic elements; The total area of ​​the corresponding region is obtained based on the pixel distribution map; According to the pixel distribution map, the first pixel region with iron element intensity higher than a preset threshold is obtained, the first pixel region is defined as an iron enrichment abnormal region, and the first total pixel area corresponding to the iron enrichment abnormal region is obtained. The area ratio of the iron enrichment region is obtained according to the first total pixel area and the total area of ​​the region. According to the pixel distribution map, a second pixel region with a tannin feature element intensity higher than a preset threshold is obtained. The second pixel region is defined as a tannin enrichment abnormal region, and the second total pixel area corresponding to the tannin enrichment abnormal region is obtained. The area ratio of the tannin enrichment region is obtained according to the second total pixel area and the total area of ​​the region. The iron-tannin distribution matching degree is calculated based on the area proportion of the iron-rich region and the area proportion of the tannin-rich region. The iron ion migration risk index is obtained by weighting the concentration of unbound iron ions, the area ratio of iron-rich regions, and the iron-tannin distribution matching degree. The comprehensive color fastness evaluation coefficient is calculated based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor. The colorfastness of the silk yam-dyed fabric to be evaluated is assessed based on the comprehensive colorfastness evaluation coefficient, and the evaluation result is obtained.

2. The true silk optimump ber dyeing fabric color fastness evaluation method according to claim 1, characterized in that, The step of calculating the comprehensive color fastness assessment coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor includes: The iron ion migration risk index is normalized to obtain the normalized value of the iron ion migration risk index. The concentration of the tannin dye was normalized to obtain a normalized value of the tannin dye concentration. The surface defect composite influence factor is normalized to obtain the normalized value of the surface defect composite influence factor; The comprehensive color fastness evaluation coefficient is obtained by weighting the normalized value of the iron ion migration risk index, the normalized value of the tannin dye concentration, and the normalized value of the surface defect composite influence factor.

3. The method for evaluating the color fastness of yam-dyed silk fabric according to claim 1, characterized in that, The step of evaluating the colorfastness of the silk yam-dyed fabric to be evaluated based on the comprehensive colorfastness evaluation coefficient to obtain the evaluation result includes: Determine the relationship between the comprehensive color fastness evaluation coefficient and the preset threshold range; When the comprehensive color fastness evaluation coefficient is not within the preset threshold range and is less than the minimum value of the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be unqualified. When the comprehensive color fastness evaluation coefficient is within the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be qualified. When the comprehensive color fastness evaluation coefficient is not within the preset threshold range and is greater than the maximum value of the preset threshold range, the color fastness of the silk yam-dyed fabric to be evaluated is determined to be excellent.

4. A system for evaluating the colorfastness of yam-dyed silk fabrics, used to perform the method for evaluating the colorfastness of yam-dyed silk fabrics as described in any one of claims 1-3, characterized in that, include: The multi-dimensional feature acquisition module is used to acquire multi-dimensional feature data of the yam-dyed silk fabric to be evaluated. The multi-dimensional feature data includes surface micro-morphology feature information and internal chemical substance distribution feature information. The surface morphology analysis module is used to obtain the depth of multiple surface grooves and surface roughness feature values ​​of the water stain sensitive area on the fabric surface based on the surface micromorphology feature information, and to obtain the water stain sensitivity index based on the depth of the multiple surface grooves. The surface defect impact calculation module is used to obtain the surface defect composite impact factor of the silk yam-dyed fabric to be evaluated based on the surface roughness characteristic value and the water stain sensitivity index. The chemical substance analysis module is used to obtain the concentration of unbound iron ions and the concentration of tannin dye based on the internal chemical substance distribution characteristics information, and to obtain the iron ion migration risk index based on the concentration of unbound iron ions. The comprehensive color fastness calculation module is used to calculate the comprehensive color fastness evaluation coefficient based on the iron ion migration risk index, the tannin dye concentration, and the surface defect composite influence factor. The color fastness assessment module is used to assess the color fastness of the silk yam-dyed fabric to be assessed based on the comprehensive color fastness assessment coefficient, and obtain the assessment result.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images