A Gradient Color Car Wrap Film Grading and Testing Method and System

Abstract

This application provides a method and system for grading and detecting gradient color automotive film, relating to the field of automotive film technology. The method includes: acquiring spectral reflectance data of the automotive film under test in the visible light band and extracting chromaticity gradient distribution characteristics; configuring dynamic change vectors; dividing into N detection grids and simultaneously measuring the thickness uniformity data and surface roughness of each detection grid; performing multimodal fusion of the dynamic change vectors and thickness uniformity data; evaluating the comprehensive quality index of the automotive film under test based on the range of the coupling coefficient matrix and surface roughness; performing dynamic grading using a grading threshold range; and determining defect mapping coordinates under the automotive film grade label. This application solves the technical problem of inaccurate quality assessment or missed detection due to the lack of dynamic and accurate quality grading. By dynamically grading the film quality using a grading threshold range, defects in gradient color automotive film can be quickly located, improving the accuracy of quality assessment.

Description

Technical Field

[0001] This application relates to the field of automotive film technology, and in particular to a method and system for grading and detecting gradient color automotive film. Background Technology

[0002] Gradient color car wrap film is a type of automotive protective film that features a color gradient effect, typically used to enhance the aesthetics of a car body. Its key characteristic is the smooth transition from one color to another on the film surface. However, traditional inspection methods for gradient color car wrap films mostly rely on visual inspection or simple color difference measurements, making it difficult to comprehensively assess all quality indicators of the film surface. Especially in the inspection of gradient color films, because the color changes continuously, simply relying on color difference measurements is insufficient to accurately detect subtle color differences or uneven gradient effects.

[0003] Furthermore, the testing of the physical properties of gradient color car wrap films (such as film thickness and surface roughness) often focuses on a single feature, neglecting the interrelationships between different physical properties. Traditional quality assessment methods often use pass / fail as the sole criterion, making it impossible to accurately grade the quality of the film and achieve detailed quality assessment. This leads to missed or misjudged defects, thus affecting the precision and accuracy of quality inspection.

[0004] In summary, existing technologies suffer from technical problems such as inaccurate quality assessment or missed detections due to their reliance on single physical characteristics or visual inspections and the lack of dynamic and accurate quality grading. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for grading and detecting gradient color car wrap films, in order to solve the technical problems in the prior art, which rely heavily on a single physical characteristic or visual inspection and lack dynamic and accurate quality grading, resulting in inaccurate quality assessment or missed detection.

[0006] In view of the above problems, this application provides a method and system for grading and detecting gradient color car wrap films.

[0007] In a first aspect, this application provides a method for grading and detecting gradient color automotive wrap films. This method is implemented using a gradient color automotive wrap film grading and detection system. The method includes: acquiring spectral reflectance data of the automotive wrap film under test in the visible light band and extracting chromaticity gradient distribution characteristics; configuring a first dynamic change vector obtained from a combination of hue and saturation, a second dynamic change vector obtained from a combination of lightness and hue, and a third dynamic change vector obtained from a combination of lightness and saturation based on the chromaticity gradient distribution characteristics; dividing the automotive wrap film under test into N detection grids and simultaneously measuring the thickness uniformity data and surface roughness of each detection grid; performing multimodal fusion of the first, second, and third dynamic change vectors with the thickness uniformity data to generate a coupling coefficient matrix; evaluating the comprehensive quality index of the automotive wrap film under test based on the range between the coupling coefficient matrix and the surface roughness; dynamically grading the comprehensive quality index using a grading threshold range; and determining defect mapping coordinates under the automotive wrap film grade identifier.

[0008] Optionally, the car wrap film to be tested is scanned, and reflectance spectral data within a preset wavelength range is collected. The reflectance spectral data is subjected to baseline correction processing, and reflectance feature values ​​are extracted. Based on the reflectance feature values, a continuous spectral reflectance curve is reconstructed, and the gradient change rate of reflectance between adjacent wavelengths is determined. The chromaticity gradient distribution characteristics are determined according to the ratio of the difference in the gradient change rate of reflectance between adjacent wavelengths to the wavelength difference.

[0009] Optionally, the reconstructed continuous spectral reflectance curve is converted to generate a hue angle distribution heatmap; abnormal abrupt change regions in the hue angle distribution heatmap are identified and marked as potential color difference defects; based on the potential color difference defects, the chromaticity gradient smoothness is quantified according to the hue angle standard deviation and saturation gradient direction consistency index, and the chromaticity gradient smoothness is used to configure the directional component of the first dynamic change vector.

[0010] Optionally, a dual-wavelength laser interferometer is configured, wherein the first wavelength is used to measure the substrate thickness and the second wavelength is used to detect the surface coating thickness; using the dual-wavelength laser interferometer, the interference fringe offset of each of the N detection grids is determined to obtain the thickness difference distribution between the substrate and the coating; based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the chromaticity gradient smoothness, and a coupling degree index associated with the first dynamic change vector is configured.

[0011] Optionally, for each detection grid, a local linear regression function is established between the chromaticity gradient smoothness and the thickness difference distribution between the substrate and the coating; using the local linear regression function between the chromaticity gradient smoothness and the thickness difference distribution between the substrate and the coating, multi-scale correlation analysis is performed to obtain the multi-scale correlation coefficient r corresponding to each detection grid; based on the multi-scale correlation coefficient r, a coupling degree index associated with the first dynamic change vector is configured.

[0012] Optionally, a sliding window analysis is used to determine the spatial overlap between the abnormal mutation region and the thickness abnormal region, and an overlap index is configured; based on the multi-scale correlation coefficient r and the overlap index, the cumulative variance contribution rate is determined; based on the directional component of the first dynamic change vector, combined with the multi-scale correlation coefficient r and the cumulative variance contribution rate, a coupling index associated with the first dynamic change vector is established.

[0013] Optionally, singular value decomposition is performed on the coupling coefficient matrix to determine the first quality index corresponding to the largest singular value; the range of surface roughness is logarithmically transformed and then weighted and summed with the first quality index, wherein the weighting coefficient is dynamically adjusted according to the application scenario of the car wrap film.

[0014] Optionally, when scratches and / or bubbles are detected on the surface, the defect area ratio is introduced as a penalty factor; the penalty factor is used to correct the overall quality index.

[0015] Optionally, the color repair area is located based on the defect mapping coordinates under the car wrap grade mark; a local color repair robot is activated, and the microfluidic nozzle of the local color repair robot is controlled to perform color repair operation in conjunction with the color repair area; at the same time, the color gradient consistency of the color repair area is checked during the color repair operation.

[0016] Secondly, this application also provides a gradient color car wrap grading detection system for performing a gradient color car wrap grading detection method as described in the first aspect, wherein the gradient color car wrap grading detection system includes: a feature extraction module for acquiring spectral reflectance data of the car wrap film under test in the visible light band and extracting chromaticity gradient distribution features; a change vector configuration module for configuring a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation based on the chromaticity gradient distribution features; and a detection network. The network partitioning module is used to divide the film under test into N detection grids and simultaneously measure the thickness uniformity data and surface roughness of each detection grid. The multimodal fusion module is used to perform multimodal fusion of the first dynamic change vector, the second dynamic change vector, the third dynamic change vector and the thickness uniformity data to generate a coupling coefficient matrix. The dynamic grading module is used to evaluate the comprehensive quality index of the film under test based on the range of the coupling coefficient matrix and the surface roughness, and to dynamically grade the comprehensive quality index using a grading threshold range to determine the defect mapping coordinates under the film grade label.

[0017] One or more technical solutions provided in this application have at least the following beneficial effects:

[0018] By acquiring the spectral reflectance data of the automotive film under test in the visible light band and extracting the chromaticity gradient distribution characteristics; based on the chromaticity gradient distribution characteristics, configuring a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation; dividing the automotive film under test into N detection grids, and simultaneously measuring the thickness uniformity data and surface roughness of each detection grid; performing multimodal fusion of the first, second, and third dynamic change vectors with the thickness uniformity data to generate a coupling coefficient matrix; evaluating the comprehensive quality index of the automotive film under test based on the range of the coupling coefficient matrix and the surface roughness, dynamically classifying the comprehensive quality index using a grading threshold range, and determining the defect mapping coordinates under the automotive film grade label. In other words, by acquiring the spectral reflectance data of the car wrap film in the visible light band and extracting the color gradient distribution characteristics, the overall quality index of the car wrap film can be comprehensively evaluated, the quality of the car wrap film can be dynamically graded, the defect mapping coordinates under the grade label can be accurately determined, and the defects of the gradient color car wrap film can be quickly located, thereby improving the accuracy of quality assessment.

[0019] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the grading and testing method for gradient color car wrap film according to this application.

[0022] Figure 2 This is a schematic diagram of the structure of a gradient color car wrap grading and detection system according to this application.

[0023] Figure labeling: Feature extraction module 11, Change vector configuration module 12, Detection network partitioning module 13, Multimodal fusion module 14, Dynamic hierarchical module 15. Detailed Implementation

[0024] This application provides a method and system for grading and detecting gradient color automotive film, solving the technical problem in existing technologies where quality assessment is inaccurate or leads to missed detections due to reliance on single physical characteristics or visual inspection and a lack of dynamic and accurate quality grading. By acquiring the spectral reflectance data of the automotive film in the visible light band and extracting the color gradient distribution characteristics, the system comprehensively evaluates the overall quality index of the automotive film, achieving dynamic grading of the film quality, accurately determining the defect mapping coordinates under the grade label, and thus quickly locating defects in the gradient color automotive film, improving the accuracy of quality assessment.

[0025] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0026] Example 1, please refer to the appendix. Figure 1 This application provides a method for grading and detecting gradient color automotive wrap films. The method is executed using a gradient color automotive wrap film grading and detection system, and specifically includes the following steps:

[0027] S100: Acquire the spectral reflectance data of the car wrap film under test in the visible light band and extract the chromaticity gradient distribution characteristics.

[0028] Furthermore, this application S100 includes:

[0029] Scan the car wrap film to be tested, collect reflectance spectral data within a preset wavelength range, perform baseline correction on the reflectance spectral data, and extract reflectance feature values; based on the reflectance feature values, reconstruct the continuous spectral reflectance curve, and determine the gradient change rate of reflectance between adjacent wavelengths; determine the chromaticity gradient distribution characteristics according to the ratio of the difference in the gradient change rate of reflectance between adjacent wavelengths to the wavelength difference.

[0030] Specifically, the test involves scanning the automotive film under test and acquiring reflectance spectral data within a preset wavelength range using a spectral scanning device. This data includes the reflectance intensity of light at different wavelengths. The preset wavelength range is typically determined based on the visible light band, such as the electromagnetic band between approximately 400 nm and 700 nm. Since reflectance spectral data can be affected by instrument or environmental factors, baseline correction is usually required to eliminate these unwanted influences. The correction process removes the effects of factors such as inhomogeneous instrument response and environmental interference, ensuring that the reflectance spectral data more accurately reflects the optical properties of the automotive film itself. Baseline correction is a data preprocessing technique used to eliminate systematic errors introduced during instrumentation or measurement, ensuring that the reflectance spectral data accurately reflects the optical properties of the film itself.

[0031] Based on baseline-corrected data, reflectance feature values ​​are extracted, including reflectance values ​​at specific wavelengths, representing the reflectance characteristics of the automotive film across various wavelength bands. Reflectance feature values ​​refer to the numerical values ​​of certain key points in the reflection spectrum (such as reflectance values ​​at certain wavelengths), representing the film surface's ability to reflect light of specific wavelengths, and are fundamental to analyzing the film's optical properties. Using these reflectance feature values, a continuous-spectral reflectance curve is reconstructed, demonstrating the automotive film's reflection behavior at various wavelengths, representing the reflectance variation of the film across the entire preset wavelength range, and intuitively determining the color distribution and gradation characteristics of the automotive film.

[0032] Based on the continuous spectral reflectance curve, the gradient rate of reflectance between adjacent wavelengths is calculated by determining the difference in reflectance between any two adjacent wavelengths. The gradient rate represents the speed at which reflectance changes between two adjacent wavelengths. A high gradient rate typically indicates a larger variation in the film's optical properties, while a low gradient rate indicates a more uniform reflectance characteristic. For example, the reflectance variation from 450 nm to 500 nm is 0.55 to 0.60, a relatively small gradient; while the reflectance variation from 550 nm to 600 nm is 0.58 to 0.62, a slightly larger gradient.

[0033] By calculating the ratio of the difference in reflectance gradient rate between adjacent wavelengths to the wavelength difference, the chromaticity gradient distribution characteristics are extracted, describing the smoothness or gradient effect of the color change in the car wrap film. For example, from 0.55 to 0.60, the gradient is (0.60-0.55) / (500-450)=0.05 / 50=0.001, where the rate of change is unitless, the wavelength is in nanometers, and the result is a unitless value. The chromaticity gradient distribution characteristic describes the color change of the car wrap film, determined based on the ratio of the gradient rate of reflectance between adjacent wavelengths to the wavelength difference. Accurately extracting the chromaticity gradient distribution characteristics of the car wrap film using spectral reflectance data and gradient rates helps in a deeper understanding of the color changes in the car wrap film.

[0034] S200: Based on the chromaticity gradient distribution characteristics, configure a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation.

[0035] Furthermore, this application S200 includes:

[0036] The reconstructed continuous spectral reflectance curve is converted to generate a hue angle distribution heatmap; abnormal abrupt change regions in the hue angle distribution heatmap are identified and marked as potential color difference defects; based on the potential color difference defects, the chromaticity gradient smoothness is quantified according to the hue angle standard deviation and saturation gradient direction consistency index, and the chromaticity gradient smoothness is used to configure the directional component of the first dynamic change vector.

[0037] Specifically, based on the chromaticity gradient distribution characteristics, information about the color changes on the surface of the car wrap film is obtained, describing how the color changes from one area to another, such as changes in hue, saturation, and lightness. Hue, saturation, and lightness are used to assess the smoothness of the color transition and further identify potential defect areas. Hue is one of the basic attributes describing color, representing the type or name of the color, such as red, blue, etc., and is usually represented by a color wheel angle. In the HSV or HSL color model, it is expressed in degrees (e.g., 0° represents red, 120° represents green, and 240° represents blue). Saturation describes the purity or intensity of a color; the higher the saturation, the more vibrant the color; the lower the saturation, the darker the color. Lightness refers to the brightness or intensity of light in a color, usually describing the transition from black (low lightness) to white (high lightness).

[0038] Based on changes in hue and saturation, a first dynamic change vector is configured. The direction of this vector indicates the trend of color change, while its magnitude indicates the intensity of the color change. The reconstructed continuous spectral reflectance is curve-converted to convert reflectance data into hue angles, and a hue angle distribution heatmap is plotted based on reflectance characteristics at different wavelengths. Hue angle data reflects the color type (hue) at each wavelength. Using color models such as HSV (Hue, Saturation, Lightness) or HSL (Hue, Saturation, Lightness) models, the corresponding hue angle value can be calculated based on the reflectance data for each wavelength.

[0039] Using a heatmap tool, hue angle data is presented as a heatmap. Colors in the graph represent different hue angles, visually displaying the color distribution on the car wrap surface, such as which areas show significant color variation. In the generated hue angle distribution heatmap, areas with abrupt color changes are identified; these areas typically exhibit sudden jumps in hue angle. For example, the hue angle in some areas may abruptly jump from one color value to another extreme value; such abrupt changes usually indicate material inhomogeneity or defect areas. When areas with abrupt hue angle changes are identified, these areas are marked as potential color difference defects, resulting from uneven production, raw material issues, or unstable surface quality. For example, suppose a region in the heatmap experiences a sharp jump in hue angle from yellow (60°) to purple (270°), indicating an abnormal color change in that area, potentially suggesting a color difference defect.

[0040] For areas with potential color difference defects, the standard deviation of the hue angle in that area is calculated, reflecting the degree of dispersion of the hue angle values. A larger standard deviation indicates a more uneven color change in that area. The smoothness of color change is judged by calculating the consistency of the saturation gradient direction. If the saturation gradient is consistent in direction within a certain area, the color change is relatively smooth. If the direction change is abrupt, the color gradient in that area is not smooth, indicating a defect. Based on the hue angle standard deviation and the saturation gradient direction consistency index, the smoothness of the chromaticity gradient in that area is quantified. A higher chromaticity gradient smoothness value indicates a smoother color transition, while a lower value indicates a more abrupt color change, potentially indicating a color difference defect. Chromaticity gradient smoothness is used to quantify the smoothness of color change; the smoother the gradient, the higher the chromaticity gradient smoothness value. Based on the quantified chromaticity gradient smoothness, the direction component of the first dynamic change vector is configured. A higher chromaticity gradient smoothness and a more consistent direction of the first dynamic change vector indicate a smoother color change.

[0041] Similarly, based on changes in lightness and hue, the analysis of color brightness and variability over space or time generates a second dynamic change vector. The direction of this vector represents the trend of color brightness change, while its magnitude represents the intensity of the brightness and hue changes. Based on changes in lightness and saturation, the analysis of color brightness and purity changes extracts lightness and saturation values ​​from reflectivity data. This analysis further analyzes the changes in brightness and purity of the paint protection film surface color, generating a third dynamic change vector. The direction of this vector represents the trend of brightness and purity change, while its magnitude represents the intensity of the brightness and purity changes. This multi-dimensional analysis of paint protection film surface color using dynamic change vectors provides refined detection of color changes, effectively identifying color unevenness and potential defect areas.

[0042] S300: Based on the car wrap film to be tested, divide it into N detection grids, and simultaneously measure the thickness uniformity data and surface roughness of each detection grid.

[0043] Specifically, the vehicle wrap film to be tested is divided into N detection grids, and the surface of the film is divided into multiple small regions (grids) for testing various performance indicators (such as thickness uniformity, surface roughness, etc.) of each region. The number and size of the grids can be set according to the size of the vehicle wrap film and the required testing precision. Generally speaking, the smaller the grid, the more detailed the test data can be obtained, but the workload of calculation and analysis also increases.

[0044] Thickness measurements are performed on each grid area using precision instruments (such as laser thickness gauges and ultrasonic thickness gauges) to measure and record the thickness of the car wrap film. Multiple measurements are taken at each grid point to obtain the thickness distribution within that grid. By comparing the thicknesses at each measurement point, the thickness uniformity of each grid can be calculated. Significant variations in the thickness of a particular grid indicate potential thickness inhomogeneity in that area. Film thickness uniformity refers to whether the thickness of the car wrap film remains consistent across different regions. Uneven thickness can lead to fluctuations in film performance, affecting the lifespan and appearance of the car wrap film.

[0045] The surface roughness of each grid region is measured using roughness measuring instruments (such as profilometers, white light interferometers, etc.). The minute undulations on the surface of the car wrap are scanned and recorded. The measured roughness values ​​can be expressed by parameters such as Ra (arithmetic mean roughness) or Rz (ten-point mean roughness) to determine the smoothness of the surface of each grid region, thereby evaluating the surface quality of the car wrap.

[0046] To ensure the uniformity of thickness and the accuracy of surface roughness data for each grid, a synchronous measurement method is typically employed. This means that the measuring equipment needs to simultaneously acquire the thickness and roughness data for each grid at the same time or within the shortest possible timeframe. Synchronous measurement avoids measurement errors caused by time differences and ensures the consistency of the data.

[0047] By dividing the surface of the car wrap film into multiple small grids and simultaneously measuring its thickness uniformity and surface roughness, a refined quality assessment of the car wrap film can be performed. This allows for the identification and quantification of potential defects on the surface of the car wrap film, thereby improving the accuracy of quality inspection.

[0048] S400: The first dynamic change vector, the second dynamic change vector, the third dynamic change vector and the thickness uniformity data are fused in a multimodal manner to generate a coupling coefficient matrix.

[0049] Furthermore, this application S400 includes:

[0050] A dual-wavelength laser interferometer is configured, wherein the first wavelength is used to measure the substrate thickness and the second wavelength is used to detect the surface coating thickness; using the dual-wavelength laser interferometer, the interference fringe offset of each of the N detection grids is determined to obtain the thickness difference distribution between the substrate and the coating; based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the chromaticity gradient smoothness, and a coupling degree index associated with the first dynamic change vector is configured.

[0051] For each detection grid, a local linear regression function is established between the chromaticity gradient smoothness and the thickness difference distribution between the substrate and the coating; using the local linear regression function between the chromaticity gradient smoothness and the thickness difference distribution between the substrate and the coating, multi-scale correlation analysis is performed to obtain the multi-scale correlation coefficient r corresponding to each detection grid; based on the multi-scale correlation coefficient r, a coupling degree index associated with the first dynamic change vector is configured.

[0052] A sliding window analysis is used to determine the spatial overlap between the abnormal mutation region and the thickness abnormal region, and an overlap index is configured. Based on the multi-scale correlation coefficient r and the overlap index, the cumulative variance contribution rate is determined. Based on the directional component of the first dynamic change vector, combined with the multi-scale correlation coefficient r and the cumulative variance contribution rate, a coupling index associated with the first dynamic change vector is established.

[0053] Specifically, the chromaticity gradient distribution characteristics (i.e., the first, second, and third dynamic change vectors) are fused with thickness uniformity data in a multimodal manner to comprehensively consider the color and thickness of the automotive film, thereby improving the accuracy of quality assessment. First, the three dynamic change vectors and thickness uniformity data are standardized to eliminate the influence of unit differences between different data, allowing for comparison and fusion of different data on the same scale. The coupling coefficient matrix is ​​generated by calculating the correlation between different modes. The correlation between the first, second, and third dynamic change vectors and the thickness uniformity data is calculated using methods such as correlation coefficients or covariance. Based on the correlation data, a coupling coefficient matrix is ​​constructed, reflecting the correlation strength between each data mode. The coupling coefficient matrix is ​​a mathematical matrix used to describe the correlation strength between multiple variables (such as thickness uniformity, chromaticity gradient, etc.), assess the correlation between various detection indicators, and provide a basis for subsequent defect assessment.

[0054] Coupling coefficients represent the correlation or degree of coupling between different features. Each element in the matrix represents the degree of coupling between two features, reflecting the strength of their relationship. The matrix is ​​typically constructed based on correlation calculations between different features. Coupling coefficients calculated from the first, second, and third dynamic variation vectors and thickness uniformity data are arranged in matrix form to obtain a coupling coefficient matrix, where each matrix element corresponds to the degree of coupling between two features. The quality of each region is then evaluated based on the coupling coefficient matrix. A high coupling coefficient indicates a strong correlation between color gradation and thickness uniformity, generally signifying better quality automotive film; conversely, a low coupling coefficient may indicate uneven quality or defects.

[0055] A dual-wavelength laser interferometer is a device that uses the principle of laser interference for precision measurement. It measures the thickness of an object's surface or interior by emitting two laser beams of different wavelengths that interfere with each other. The two wavelengths can be used to measure the thickness of different layers, such as the thickness of the substrate and the thickness of the coating. The substrate is the main material layer of the car wrap film, usually metal or plastic, serving as a support for the coating. The substrate thickness refers to the actual thickness of this material layer. The surface coating is the outer protective layer of the car wrap film, typically consisting of a layer of paint or film; its thickness affects the film's durability and performance.

[0056] When configuring a dual-wavelength laser interferometer, two different wavelengths of laser beams are selected based on the optical properties of the material under test. The first wavelength is used to measure the thickness of the substrate, and the second wavelength is used to measure the thickness of the coating. These two wavelengths of laser beams will produce interference effects with the surfaces of the substrate and the coating, respectively. Using two different wavelengths of laser light can effectively distinguish the thickness of the coating and the substrate, avoiding the problem of interference to different material layers that may occur when using only one wavelength.

[0057] A laser interferometer illuminates the surface under test with a laser beam and measures the offset of the interference fringes. Each grid point generates a set of interference fringes, reflecting the thickness variation at that point. Different thicknesses of the substrate and coating cause phase differences in the reflected waves, resulting in the offset of the interference fringes, which can be calculated to determine the thickness difference between the substrate and coating. The offset typically has a mathematical relationship with the thickness difference. For example, assuming the offset of the interference fringes is Δx, the thickness difference Δd can be estimated by the ratio of the fringe offset to the wavelength of the light wave.

[0058] Measurements are performed on N inspection grids, and the thickness difference between the substrate and coating is calculated for each grid point. For each grid point, the thickness difference between the substrate and coating is calculated using the corresponding physical formula based on the interference fringe offset and wavelength information. The thickness difference is calculated for all grid points, ultimately yielding the distribution of the thickness difference between the substrate and coating, including the difference for each grid point. This visually indicates whether the film surface is uniform and whether there are weak or defective areas.

[0059] For each monitoring grid, a local linear regression model is established to describe the relationship between chromaticity gradient smoothness and the thickness difference between the substrate and the coating. The chromaticity gradient smoothness and the thickness difference between the substrate and the coating are extracted for each monitoring grid. Local linear regression is used to calculate the relationship between chromaticity gradient smoothness and the thickness difference for each grid. The neighborhood data of each grid point is fitted to obtain the local linear regression function, ensuring that even with significant differences between different grids, local features can be modeled. Local linear regression is a statistical method used to perform regression analysis on local regions in data. By fitting the neighborhood data of each point, a local model is built to obtain trends or relationships within the local region.

[0060] Multiscale correlation analysis is used to analyze the correlation between chroma gradient smoothness and thickness difference distributions at different scales. Multiscale analysis is a technique used to identify and analyze patterns and correlations exhibited at different scales (hierarchies). Multiscale analysis refers to analyzing the correlation between chroma gradient smoothness and thickness difference at different scales (i.e., different grid sizes). Different scales may reveal different quality issues (such as large-scale inhomogeneities or localized minor defects). Multiscale analysis involves detection grids of different sizes, which can be adjusted according to actual needs. Larger scales can capture global trends, while smaller scales help reveal local details. At each scale, the correlation between chroma gradient smoothness and thickness difference distributions is calculated using the Pearson correlation coefficient formula to obtain the multiscale correlation coefficient. The multiscale correlation coefficient r is a numerical value used to measure the linear correlation between chroma gradient smoothness and thickness difference at different scales, typically the Pearson correlation coefficient. The r values ​​calculated at multiple scales can represent the strength of their correlation at different scales.

[0061] Sliding window analysis is a common signal or data processing method that analyzes the spatial overlap between regions of abrupt changes and thickness anomalies by defining a window on the data and sliding that window across the data. Regions of abrupt changes refer to areas in a color gradient map of a car wrap surface where color changes are drastic or discontinuous, potentially indicating coating defects or unevenness. Regions of thickness anomalies refer to areas in a car wrap thickness distribution map where there are significant thickness variations, typically indicating uneven or abnormal thickness of the substrate or coating. Spatial overlap refers to the degree to which regions of abrupt changes and thickness anomalies coincide in space, usually determined by calculating the ratio of the intersection to the union of the two regions.

[0062] Define a fixed-size window (e.g., a 3x3, 5x5, or 7x7 grid) that slides across the image, analyzing anomalous and thickness anomaly regions within each window. Slide this window across the color gradient and thickness distribution maps of the automotive film, examining the spatial locations of anomalous abrupt changes and thickness anomalies within each window. For each sliding window, calculate the spatial overlap between the anomalous abrupt change and thickness anomaly regions; this is calculated as the ratio of the intersection to the union of the two regions. The overlap index reflects the degree of overlap between the two anomalous regions within that window.

[0063] The cumulative variance contribution rate is a weighted value used to measure the contribution of multiple features (such as chroma gradation smoothness, multi-scale correlation coefficient, and overlap index) to the overall quality assessment. Based on the multi-scale correlation coefficient and overlap index, the variance of each feature (e.g., chroma gradation smoothness, correlation coefficient, overlap, etc.) is calculated. Then, the contribution of each feature to the total variance is calculated, i.e., the ratio of each feature's variance to the total variance, which is obtained by summing the variances of all features. The cumulative variance contribution rate represents the cumulative contribution of each feature to the total variance, progressively summing the contribution rates of each feature until the contributions of all features are taken into account, thus understanding the importance and influence of each feature in the overall quality assessment.

[0064] The directional component of the first dynamic change vector is composed of changes in hue and saturation, describing the color change trend of the car wrap film. A directional component, representing the directionality of color change, can be obtained by calculating the changes in hue and saturation on each detection grid. The coupling index combines the directional component of the first dynamic change vector (representing the direction of hue change) with the multi-scale correlation coefficient r and the cumulative variance contribution rate, such as: Coupling Index = a*r + b*directional component of the first dynamic change vector + c*cumulative variance contribution rate, where a, b, and c are the influence weights of the multi-scale correlation coefficient, the directional component of the first dynamic change vector, and the cumulative variance contribution rate, respectively.

[0065] A high coupling degree index indicates a strong correlation between multiple characteristics such as color gradation and coating thickness variation, suggesting relatively good quality of the car wrap film. A low coupling degree index indicates a weaker relationship between these characteristics, potentially indicating irregular defects or uneven quality. The coupling degree index quantifies the interrelationships between various quality characteristics (such as color gradation smoothness, thickness distribution, and color difference) and their overall impact on quality assessment, reflecting the degree of coordination and correlation among these characteristics in the quality evaluation of car wrap films.

[0066] By employing methods such as dual-wavelength laser interferometry, local regression analysis, and multi-scale correlation analysis, high-precision analysis of automotive film quality can be achieved, particularly establishing a precise quantitative relationship between thickness differences and color variations. Sliding window analysis and overlap indices help accurately identify potential defect areas on the automotive film surface, especially for defects such as uneven coating thickness or uneven color gradients. By establishing coupling indices, the quality characteristics of different areas of the automotive film can be comprehensively evaluated, contributing to improving the overall quality level of the automotive film.

[0067] S500: Based on the range between the coupling coefficient matrix and the surface roughness, evaluate the comprehensive quality index of the car wrap film to be tested, use a grading threshold range to dynamically grade the comprehensive quality index, and determine the defect mapping coordinates under the car wrap film grade label.

[0068] Specifically, the overall quality index of the car wrap film is obtained by weighted summation based on the coupling coefficient matrix and the range of surface roughness. The weighting coefficients can be adjusted according to actual needs and the importance of the test data. The specific process is described in detail in the corresponding steps; for the sake of brevity, only a brief summary is provided here. A grading threshold range is set based on the range of the overall quality index. This grading threshold range divides the overall quality index into different levels, typically including high, medium, and low quality grades. This is set according to different quality requirements to classify the car wrap film, allowing customers to receive products with different quality levels. For example, an overall quality index greater than or equal to 0.8 is considered excellent, greater than or equal to 0.6 and less than 0.8 is good, greater than or equal to 0.4 and less than 0.6 is acceptable, and less than 0.4 is unacceptable. The grading thresholds are dynamically adjusted based on the overall quality index of the car wrap film, combined with actual application scenarios and customer requirements.

[0069] Using a tiered threshold range, the comprehensive quality index is dynamically graded to determine the quality level of the car wrap film and assign it a corresponding grade label. Each grade label corresponds to different quality standards and defect tolerances. For example, a superior quality index within the excellent range indicates that the surface quality of the car wrap film is very high, suitable for high-requirement scenarios; a good quality index within the good range indicates that the surface quality of the car wrap film is relatively good, suitable for daily use; a qualified quality index within the qualified range indicates that the car wrap film meets basic quality requirements and is suitable for general scenarios; and a substandard quality index within the substandard range indicates that the car wrap film has obvious defects and needs to be repaired or remanufactured.

[0070] Based on a comprehensive quality assessment, surface defects in the car wrap film, such as scratches, bubbles, and color differences, are detected to identify defect areas. The location and size of the defects are then used to determine their mapping coordinates. These defect mapping coordinates map the location and type of defects onto a coordinate system, pinpointing the specific location of defects on the film surface. This helps in locating repair areas and conducting quality control. Based on the type and location of the defects on the car wrap film surface, image processing algorithms or sensor data are used to generate the defect mapping coordinates. The assessment results and defect mapping coordinates are then fed back to the control center, where a local color-matching robot performs the color-matching repair.

[0071] By comprehensively considering multiple quality factors through the coupling coefficient matrix and the range of surface roughness, the quality of automotive film can be comprehensively and accurately evaluated. Through comprehensive quality assessment and grading, its quality level can be clearly indicated, facilitating flexible evaluation of automotive film quality. By generating defect mapping coordinates and identifying grades, defects in the automotive film can be quickly and accurately located and repaired, effectively guiding quality control and repair work, thereby ensuring the quality stability and efficient production of automotive film and improving the accuracy of quality assessment.

[0072] Furthermore, this application S500 includes:

[0073] The coupling coefficient matrix is ​​subjected to singular value decomposition to determine the first quality index corresponding to the largest singular value; the range of surface roughness is logarithmically transformed and then weighted and summed with the first quality index, wherein the weighting coefficient is dynamically adjusted according to the application scenario of the car wrap film.

[0074] Specifically, singular value decomposition (SVD) is performed on the coupling coefficient matrix. SVD is a matrix decomposition method in linear algebra that decomposes a matrix into the product of three matrices: a left singular matrix (representing the direction of data features), a diagonal matrix (containing singular values), and a right singular matrix (representing the projection of the data into another feature space). SVD extracts the main information of the matrix, with the largest singular value typically representing the most important feature. The largest singular value is the maximum value in the matrix and usually represents the most important feature. In quality assessment, the largest singular value is often associated with the dominant factors affecting the quality of automotive film. Therefore, the largest singular value can be used as the primary quality indicator. The primary quality indicator, obtained through SVD, represents the most significant quality information in the coupling coefficient matrix. The primary quality indicator is usually the matrix feature corresponding to the largest singular value, reflecting the dominant factors affecting the quality of automotive film.

[0075] The range of surface roughness is the difference between the maximum and minimum values, reflecting the degree of surface variation. Performing a logarithmic transformation on the roughness range compresses roughness data with a large range of variation, making it easier to process and compare in analysis. Logarithmic transformation is a common data preprocessing method, especially suitable for data that grows exponentially or has extreme values. Performing a logarithmic transformation on the surface roughness range helps to compress the data range and reduce the impact of outliers.

[0076] The weighting coefficients are dynamically adjusted based on the application scenario of the car wrap film. Different application scenarios may have different requirements for color gradation (the primary quality indicator) and surface roughness. For example, in high-end automotive paint where quality requirements are high, color gradation may be more important than surface roughness; while in other application scenarios, surface roughness may have a higher priority. The weighting coefficients are adjusted based on the actual usage environment, customer requirements, or the specific application characteristics of the car wrap film. Based on the determined weighting coefficients, the primary quality indicator (maximum singular value) and the logarithmic range of surface roughness are combined using a weighted summation method to obtain the comprehensive quality index. Comprehensive Quality Index = w1 * Primary Quality Indicator + w2 * Logarithmically Transformed Roughness Range, where w1 and w2 are dynamically adjusted weighting coefficients. The calculated comprehensive quality index comprehensively evaluates the quality of the car wrap film, considering both color characteristics (through the maximum singular value) and surface characteristics (through the roughness range), enabling multi-faceted quality monitoring of the car wrap film.

[0077] Furthermore, this application also includes the following steps:

[0078] When scratches and / or bubbles are detected on the surface, the percentage of defect area is introduced as a penalty factor; the penalty factor is used to correct the overall quality index.

[0079] Specifically, surface scratches refer to linear or irregular cracks or scratches on the surface of the car wrap film, usually caused by external force or friction. Bubbles are gas clumps present on or within the surface of the car wrap film, typically formed during the coating process when gas is not completely expelled, resulting in an uneven surface and affecting visual appeal and functionality. The presence of scratches on the car wrap film surface is detected using methods such as high-resolution cameras or laser scanning. Bubble detection can be achieved through surface inspection (visual inspection or optically based detection methods). Bubbles typically appear optically as surface irregularities or abnormal light reflection. The presence and size of bubbles can be accurately measured using laser interferometers or high-resolution optical equipment.

[0080] When scratches or bubbles are detected on the surface of the gradient color car wrap, the area of ​​the defective region is extracted using image processing techniques, typically determined by calculating the number of pixels in the defective area or the actual surface area. The area of ​​the defective region is then divided by the total surface area of ​​the car wrap to obtain the defect area percentage. A penalty factor, a coefficient used to adjust the overall quality index, is calculated based on the defect area percentage: Penalty Factor = 1 + α * Defect Area Percentage, where α is a constant coefficient used to adjust the intensity of the penalty. When defects such as scratches and bubbles are present on the car wrap surface, the penalty factor is used to adjust the quality indicators to reflect the negative impact of these defects on the overall quality.

[0081] The overall quality index is corrected using a penalty factor. The corrected overall quality index can be expressed by the formula: Corrected Overall Quality Index = Original Overall Quality Index * (1 - Penalty Factor). With the corrected overall quality index, quality control personnel can better assess the actual quality of the car wrap film. If the corrected overall quality index is lower than the preset quality standard, it indicates that there are relatively serious defects on the surface of the car wrap film (such as scratches, bubbles, etc.). By introducing the defect area ratio as a penalty factor, the impact of surface defects on overall quality can be effectively taken into account, enhancing the accuracy of quality assessment. Even if the car wrap film is of good quality in other aspects, an accurate assessment can still be made if there are obvious scratches or bubbles. By combining the defect area ratio and quality correction, defects can be identified more sensitively, especially in the detection of minor or low-visibility defects, ensuring that no potential problems are missed.

[0082] Furthermore, this application also includes the following steps:

[0083] Based on the defect mapping coordinates under the car wrap grade label, locate the color repair area; start the local color repair robot, and control the microfluidic nozzle of the local color repair robot to perform color repair operation in conjunction with the color repair area; at the same time, during the color repair operation, check the color gradient consistency of the color repair area.

[0084] Specifically, based on the detected defects on the car wrap surface, including the type, location, and size of the defects, the defect location data is converted into a coordinate system to identify the areas on the car wrap surface that need repair. The defect mapping coordinates refer to a spatial coordinate system established by detecting the location and type of defects on the car wrap surface. Each defect location has a corresponding coordinate on the car wrap surface; these coordinates can be used to locate the defect area for repair or other treatments. Defects are classified and mapped according to the car wrap's grade. Different grades of car wrap may contain different types and sizes of defects. Using the mapped coordinate information, the repair area is accurately located, thereby improving repair efficiency and accuracy.

[0085] Once the repair area is determined, the repair robot is activated. The robot's microfluidic nozzles automatically adjust via the control center to perform precise repair operations within the designated area. The repair robot uses image recognition and a coordinate system for precise positioning, ensuring that repair operations are performed only in the required areas, avoiding waste and incorrect spraying. The microfluidic nozzles precisely adjust the spray volume and coverage based on the size and shape of the defect area. The robot's control center can adjust the nozzle's operating status in real time, ensuring uniform coating coverage of the defect area to achieve the ideal color repair effect. The microfluidic nozzle is a precision spraying device that accurately controls the spray volume, spray position, and spray speed of the paint. Using fluid dynamics principles, it regulates the flow of liquid through tiny control units, thereby ensuring the uniformity and precision of the coating.

[0086] During the color matching process, the color gradient consistency of the repaired area is monitored in real time, including the detection of hue, saturation, and brightness. This ensures a smooth color change in the repaired area and a natural transition with the surrounding area, avoiding obvious color differences or color blocks. A color gradient consistency check algorithm is used to analyze the changes in hue, saturation, and brightness of the repaired area and evaluate its transition effect with the surrounding area. When an inconsistency in the color gradient is detected, the repair operation is automatically adjusted to ensure the repair effect meets requirements. If the color gradient consistency check fails, optimization is achieved through multiple adjustments to the spraying until the color gradient of the repaired area matches the surrounding area, achieving the best repair effect. The color gradient consistency check refers to detecting the color changes in the repaired area of ​​the car wrap film to ensure that the color of the repaired area is consistent with the color of the surrounding area in terms of color gradient. By detecting the smooth transition of parameters such as hue, saturation, and brightness, the repair effect is ensured to be natural and without abrupt changes.

[0087] With precise control of the local color-matching robot and microfluidic nozzle, local repair can be performed in designated defect areas, avoiding unnecessary coating and resource waste. The color gradient consistency inspection effectively ensures that the color of the repaired area transitions naturally and smoothly with the surrounding area, avoiding obvious color differences and inconsistencies, and improving the overall aesthetics and quality standards of the car wrap.

[0088] In summary, the gradient color car wrap grading detection method provided in this application has the following beneficial effects:

[0089] By acquiring the spectral reflectance data of the automotive film under test in the visible light band and extracting the chromaticity gradient distribution characteristics; based on the chromaticity gradient distribution characteristics, configuring a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation; dividing the automotive film under test into N detection grids, and simultaneously measuring the thickness uniformity data and surface roughness of each detection grid; performing multimodal fusion of the first, second, and third dynamic change vectors with the thickness uniformity data to generate a coupling coefficient matrix; evaluating the comprehensive quality index of the automotive film under test based on the range of the coupling coefficient matrix and the surface roughness, dynamically classifying the comprehensive quality index using a grading threshold range, and determining the defect mapping coordinates under the automotive film grade label. In other words, by acquiring the spectral reflectance data of the car wrap film in the visible light band and extracting the color gradient distribution characteristics, the overall quality index of the car wrap film can be comprehensively evaluated, the quality of the car wrap film can be dynamically graded, the defect mapping coordinates under the grade label can be accurately determined, and the defects of the gradient color car wrap film can be quickly located, thereby improving the accuracy of quality assessment.

[0090] Example 2: Based on the same inventive concept as the gradient color car wrap grading detection method in Example 1, this application also provides a gradient color car wrap grading detection system. Please refer to the appendix. Figure 2 The gradient color car wrap grading and detection system includes:

[0091] The feature extraction module 11 is used to acquire the spectral reflectance data of the car wrap film under test in the visible light band and extract the chromaticity gradient distribution features; the change vector configuration module 12 is used to configure a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation based on the chromaticity gradient distribution features; the detection network division module 13 is used to divide the car wrap film under test into N detection grids and simultaneously measure the thickness uniformity data and surface roughness of each detection grid; the multimodal fusion module 14 is used to perform multimodal fusion of the first dynamic change vector, the second dynamic change vector, the third dynamic change vector and the thickness uniformity data to generate a coupling coefficient matrix; the dynamic grading module 15 is used to evaluate the comprehensive quality index of the car wrap film under test based on the range of the coupling coefficient matrix and the surface roughness, and dynamically grade the comprehensive quality index using a grading threshold range to determine the defect mapping coordinates under the car wrap film grade label.

[0092] Furthermore, the feature extraction module 11 in the gradient color car wrap grading detection system is also used for:

[0093] Scan the car wrap film to be tested, collect reflectance spectral data within a preset wavelength range, perform baseline correction on the reflectance spectral data, and extract reflectance feature values; based on the reflectance feature values, reconstruct the continuous spectral reflectance curve, and determine the gradient change rate of reflectance between adjacent wavelengths; determine the chromaticity gradient distribution characteristics according to the ratio of the difference in the gradient change rate of reflectance between adjacent wavelengths to the wavelength difference.

[0094] Furthermore, the change vector configuration module 12 in the gradient color car wrap grading detection system is also used for:

[0095] The reconstructed continuous spectral reflectance curve is converted to generate a hue angle distribution heatmap; abnormal abrupt change regions in the hue angle distribution heatmap are identified and marked as potential color difference defects; based on the potential color difference defects, the chromaticity gradient smoothness is quantified according to the hue angle standard deviation and saturation gradient direction consistency index, and the chromaticity gradient smoothness is used to configure the directional component of the first dynamic change vector.

[0096] Furthermore, the multimodal fusion module 14 in the gradient color car wrap grading detection system is also used for:

[0097] A dual-wavelength laser interferometer is configured, wherein the first wavelength is used to measure the substrate thickness and the second wavelength is used to detect the surface coating thickness; using the dual-wavelength laser interferometer, the interference fringe offset of each of the N detection grids is determined to obtain the thickness difference distribution between the substrate and the coating; based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the chromaticity gradient smoothness, and a coupling degree index associated with the first dynamic change vector is configured.

[0098] Furthermore, the multimodal fusion module 14 in the gradient color car wrap grading detection system is also used for:

[0099] For each detection grid, a local linear regression function is established between the chromaticity gradient smoothness and the thickness difference distribution between the substrate and the coating; using the local linear regression function between the chromaticity gradient smoothness and the thickness difference distribution between the substrate and the coating, multi-scale correlation analysis is performed to obtain the multi-scale correlation coefficient r corresponding to each detection grid; based on the multi-scale correlation coefficient r, a coupling degree index associated with the first dynamic change vector is configured.

[0100] Furthermore, the multimodal fusion module 14 in the gradient color car wrap grading detection system is also used for:

[0101] A sliding window analysis is used to determine the spatial overlap between the abnormal mutation region and the thickness abnormal region, and an overlap index is configured. Based on the multi-scale correlation coefficient r and the overlap index, the cumulative variance contribution rate is determined. Based on the directional component of the first dynamic change vector, combined with the multi-scale correlation coefficient r and the cumulative variance contribution rate, a coupling index associated with the first dynamic change vector is established.

[0102] Furthermore, the dynamic grading module 15 in the gradient color car wrap grading detection system is also used for:

[0103] The coupling coefficient matrix is ​​subjected to singular value decomposition to determine the first quality index corresponding to the largest singular value; the range of surface roughness is logarithmically transformed and then weighted and summed with the first quality index, wherein the weighting coefficient is dynamically adjusted according to the application scenario of the car wrap film.

[0104] Furthermore, the dynamic grading module 15 in the gradient color car wrap grading detection system is also used for:

[0105] When scratches and / or bubbles are detected on the surface, the percentage of defect area is introduced as a penalty factor; the penalty factor is used to correct the overall quality index.

[0106] Furthermore, the dynamic grading module 15 in the gradient color car wrap grading detection system is also used for:

[0107] Based on the defect mapping coordinates under the car wrap grade label, the color repair area is located; a local color repair robot is activated, and the microfluidic nozzle of the local color repair robot is controlled to perform color repair operations in conjunction with the color repair area; simultaneously, during the color repair operation, the color gradient consistency of the color repair area is checked. The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Figure 1 The gradient color car wrap grading detection method and specific examples in Embodiment 1 are also applicable to the gradient color car wrap grading detection system in this embodiment. Through the foregoing detailed description of the gradient color car wrap grading detection method, those skilled in the art can clearly understand the gradient color car wrap grading detection system in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0108] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0109] Obviously, those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A method for grading and detecting gradient color car wrap film, characterized in that, include: Acquire the spectral reflectance data of the car wrap film under test in the visible light band, and extract the chromaticity gradient distribution characteristics; Based on the chromaticity gradient distribution characteristics, a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation are configured. Based on the car wrap film to be tested, divide it into N detection grids, and simultaneously measure the thickness uniformity and surface roughness of each detection grid. The first dynamic change vector, the second dynamic change vector, and the third dynamic change vector are fused with the thickness uniformity data in a multimodal manner to generate a coupling coefficient matrix. Based on the range between the coupling coefficient matrix and the surface roughness, the comprehensive quality index of the car wrap film under test is evaluated. The comprehensive quality index is dynamically classified using a grading threshold range, and the defect mapping coordinates under the car wrap film grade label are determined. This includes acquiring the spectral reflectance data of the car wrap film under test in the visible light band and extracting the chromaticity gradient distribution features, including: Scan the car wrap film to be tested, collect the reflectance spectral data within a preset wavelength range, perform baseline correction processing on the reflectance spectral data, and extract reflectance feature values; Based on the reflectance characteristic value, the continuous spectrum reflectance curve is reconstructed to determine the gradient rate of change of reflectance between adjacent wavelengths. The chromaticity gradient distribution characteristics are determined based on the ratio of the difference in the gradient change rate of reflectance between adjacent wavelengths to the wavelength difference. Specifically, based on the chromaticity gradient distribution characteristics, the configuration of the first dynamic change vector obtained by the combination of hue and saturation includes: The reconstructed continuous spectral reflectance curve is converted to generate a hue angle distribution heatmap; Identify anomalous abrupt change regions in the hue angle distribution heatmap and mark them as potential color difference defects; Based on the potential color difference defects, the chromaticity gradient smoothness is quantified according to the hue angle standard deviation and saturation gradient direction consistency index. The chromaticity gradient smoothness is used to configure the directional component of the first dynamic change vector. The method further includes performing multimodal fusion of the first dynamic change vector, the second dynamic change vector, and the third dynamic change vector with the thickness uniformity data to generate a coupling coefficient matrix, and also includes: A dual-wavelength laser interferometer is configured, wherein the first wavelength is used to measure the thickness of the substrate and the second wavelength is used to detect the thickness of the surface coating. Using the dual-wavelength laser interferometer, the interference fringe offset of each of the N detection grids is determined, and the thickness difference distribution between the substrate and the coating is obtained. Based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the color gradient smoothness to configure a coupling index associated with the first dynamic change vector. Specifically, based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the color gradient smoothness to configure a coupling index associated with the first dynamic change vector, including: For each detection grid, a local linear regression function is established to correlate the color gradient smoothness with the thickness difference distribution between the substrate and the coating. Using the local linear regression function of the color gradient smoothness and the thickness difference distribution between the substrate and the coating, multi-scale correlation analysis is performed to obtain the multi-scale correlation coefficient r corresponding to each detection grid; Based on the multi-scale correlation coefficient r, configure a coupling index associated with the first dynamic change vector; The coupling degree index associated with the first dynamic change vector is configured based on the multi-scale correlation coefficient r, including: A sliding window analysis method is used to determine the spatial overlap between the abnormal mutation region and the thickness anomaly region, and an overlap index is configured. Based on the multi-scale correlation coefficient r and the overlap index, the cumulative variance contribution rate is determined; Based on the directional component of the first dynamic change vector, and combined with the multi-scale correlation coefficient r and the cumulative variance contribution rate, a coupling index associated with the first dynamic change vector is established. The evaluation of the overall quality index of the vehicle coating film under test, based on the range between the coupling coefficient matrix and the surface roughness, further includes: Perform singular value decomposition on the coupling coefficient matrix to determine the first quality index corresponding to the largest singular value; After performing a logarithmic transformation on the range of the surface roughness, the sum is weighted and summed with the first quality index, wherein the weighting coefficient is dynamically adjusted according to the application scenario of the car wrap film.

2. The method for grading and detecting gradient color car wrap film as described in claim 1, characterized in that, When scratches and / or bubbles are detected on the surface, the percentage of defect area is introduced as a penalty factor. The overall quality index is corrected using the penalty factor.

3. The method for grading and detecting gradient color car wrap film as described in claim 2, characterized in that, The process of dynamically classifying the comprehensive quality index and determining the defect mapping coordinates under the car wrap film grade label also includes: Locate the color-matching repair area based on the defect mapping coordinates under the car wrap grade label; The local color-matching robot is activated, and the microfluidic nozzle of the local color-matching robot is controlled to perform color-matching operations in conjunction with the color-matching repair area. Meanwhile, during the color correction operation, the color gradient consistency of the color correction repair area is checked.

4. A grading and detection system for gradient color car wrap film, characterized in that, The step of implementing the gradient color car wrap grading detection method according to any one of claims 1 to 3, wherein the gradient color car wrap grading detection system comprises: The feature extraction module is used to acquire the spectral reflectance data of the car wrap film under test in the visible light band and extract the color gradient distribution features; The change vector configuration module is used to configure a first dynamic change vector obtained by combining hue and saturation, a second dynamic change vector obtained by combining lightness and hue, and a third dynamic change vector obtained by combining lightness and saturation based on the chromaticity gradient distribution characteristics. The detection network division module is used to divide the film to be tested into N detection grids and simultaneously measure the thickness uniformity and surface roughness of each detection grid. The multimodal fusion module is used to perform multimodal fusion of the first dynamic change vector, the second dynamic change vector, the third dynamic change vector and the thickness uniformity data to generate a coupling coefficient matrix; The dynamic grading module is used to evaluate the comprehensive quality index of the car wrap film under test based on the range between the coupling coefficient matrix and the surface roughness, and to dynamically grade the comprehensive quality index using a grading threshold range, and to determine the defect mapping coordinates under the car wrap film grade label. This includes acquiring the spectral reflectance data of the car wrap film under test in the visible light band and extracting the chromaticity gradient distribution features, including: Scan the car wrap film to be tested, collect the reflectance spectral data within a preset wavelength range, perform baseline correction processing on the reflectance spectral data, and extract reflectance feature values; Based on the reflectance characteristic value, the continuous spectrum reflectance curve is reconstructed to determine the gradient rate of change of reflectance between adjacent wavelengths. The chromaticity gradient distribution characteristics are determined based on the ratio of the difference in the gradient change rate of reflectance between adjacent wavelengths to the wavelength difference. Specifically, based on the chromaticity gradient distribution characteristics, the configuration of the first dynamic change vector obtained by the combination of hue and saturation includes: The reconstructed continuous spectral reflectance curve is converted to generate a hue angle distribution heatmap; Identify anomalous abrupt change regions in the hue angle distribution heatmap and mark them as potential color difference defects; Based on the potential color difference defects, the chromaticity gradient smoothness is quantified according to the hue angle standard deviation and saturation gradient direction consistency index. The chromaticity gradient smoothness is used to configure the directional component of the first dynamic change vector. The system further performs multimodal fusion of the first dynamic change vector, the second dynamic change vector, and the third dynamic change vector with the thickness uniformity data to generate a coupling coefficient matrix. A dual-wavelength laser interferometer is configured, wherein the first wavelength is used to measure the thickness of the substrate and the second wavelength is used to detect the thickness of the surface coating. Using the dual-wavelength laser interferometer, the interference fringe offset of each of the N detection grids is determined, and the thickness difference distribution between the substrate and the coating is obtained. Based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the color gradient smoothness to configure a coupling index associated with the first dynamic change vector. Specifically, based on the thickness difference distribution between the substrate and the coating, a multi-scale correlation analysis is performed with the color gradient smoothness to configure a coupling index associated with the first dynamic change vector, including: For each detection grid, a local linear regression function is established to correlate the color gradient smoothness with the thickness difference distribution between the substrate and the coating. Using the local linear regression function of the color gradient smoothness and the thickness difference distribution between the substrate and the coating, multi-scale correlation analysis is performed to obtain the multi-scale correlation coefficient r corresponding to each detection grid; Based on the multi-scale correlation coefficient r, configure a coupling index associated with the first dynamic change vector; The coupling degree index associated with the first dynamic change vector is configured based on the multi-scale correlation coefficient r, including: A sliding window analysis method is used to determine the spatial overlap between the abnormal mutation region and the thickness anomaly region, and an overlap index is configured. Based on the multi-scale correlation coefficient r and the overlap index, the cumulative variance contribution rate is determined; Based on the directional component of the first dynamic change vector, and combined with the multi-scale correlation coefficient r and the cumulative variance contribution rate, a coupling index associated with the first dynamic change vector is established. The system evaluates the overall quality index of the coating film under test based on the range between the coupling coefficient matrix and the surface roughness. The system also performs the following method: Perform singular value decomposition on the coupling coefficient matrix to determine the first quality index corresponding to the largest singular value; After performing a logarithmic transformation on the range of the surface roughness, the sum is weighted and summed with the first quality index, wherein the weighting coefficient is dynamically adjusted according to the application scenario of the car wrap film.

Images