Intelligent detection method for sewing defects of overcoat

Abstract

The invention relates to the technical field of sewing, and provides an intelligent detection method for overcoat sewing defects. The method comprises the following steps: obtaining a target overcoat design drawing, carrying out functional region division, matching material information according to a division result, and generating a material-functional region mapping graph; collecting the stitched image region by region to obtain an image data stream; activating a defect feature extraction model, and inputting a data stream for defect characterization after channel matching to obtain a suture deviation stream and a feature set; process parameters are collected, matching is carried out in combination with the feature set and the suture deviation flow, and a process-deviation associated data set is generated; and identifying the key data set through multi-scale fitting, and evaluating to generate a defect detection report. The technical problems of inaccurate defect detection and insufficient real-time performance caused by fluctuation of process parameters of different functional areas in the overcoat sewing process are solved, and the effects of improving the detection precision and adaptability by combining synchronous analysis and multi-scale fitting of the process parameters and the sewing line deviation data are achieved.

Description

Technical Field

[0001] The present application relates to the field of sewing technology, and in particular to an intelligent detection method for sewing defects of coats. Background Art

[0002] In the traditional clothing production process, especially in the sewing process of coats, problems such as seam deviation, uneven stitching, and sewing defects in the zipper and button areas often affect the quality of the finished product. Existing sewing quality inspection mainly relies on manual inspection, which is not only time-consuming and inefficient, but also prone to omissions or misjudgments due to human factors. Especially in the case of complex sewing processes and diverse materials, it is difficult for manual inspection to maintain consistency. In addition, coats are high-end clothing and usually use a variety of different materials, such as wool, silk, polyester, etc. These materials have different requirements for sewing processes, which further increases the difficulty of defect detection. Summary of the invention

[0003] The present application provides an intelligent detection method for coat sewing defects, aiming to solve the technical problems of inaccurate defect detection and insufficient real-time performance due to fluctuations in process parameters of different functional areas during the coat sewing process.

[0004] In view of the above problems, the present application provides an intelligent detection method for coat seam defects.

[0005] The present application provides an intelligent detection method for coat stitching defects, the method comprising: obtaining a target coat design drawing, dividing functional areas based on the target coat design drawing, matching material information according to the division result, and generating a material-functional area mapping diagram; performing region-by-region stitching image acquisition on the division result based on a high-precision visible light camera to obtain stitching image data streams of each functional area; activating a defect feature extraction model, performing channel matching according to the material-functional area mapping diagram, inputting stitching image data streams of each functional area according to the matching result to perform defect characterization extraction, and obtaining stitch deviation streams and stitch deviation feature sets of different materials; collecting real-time process parameters of stitching equipment, combining the stitch deviation feature set, performing homologous functional area time series matching on the real-time process parameters of the stitching equipment and the stitch deviation stream, and generating process-deviation association data sets of different functional areas; performing multi-scale fitting on the process-deviation association data sets of the different functional areas, and identifying key process-deviation association data sets; inputting the key process-deviation association data sets into a stitching defect association analyzer for quality assessment, and generating a stitching defect detection report in combination with stitching quality tolerance.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The above-mentioned intelligent detection method for coat stitching defects divides the functional areas of the coat based on the design drawings of the target coat, and matches the corresponding material information according to the division results of each area to generate a material-functional area mapping map. The role of this mapping map is to ensure that there is a one-to-one correspondence between each area and the material characteristics, providing a basis for subsequent detection. Subsequently, a high-precision visible light camera is used to collect images of the stitching process of each area one by one according to the division of the functional areas, and obtain the stitching image data stream of each area. The defect feature extraction model is then activated, and channel matching is performed through the material-functional area mapping map, and the corresponding stitching image is input into the internal channel of the model to extract the stitching deviation flow and defect feature set corresponding to each material. The purpose of this step is to ensure that the detection process can accurately identify the potential stitching defects of each area based on different material characteristics. After that, the real-time process parameters of the stitching equipment are collected, and these process parameters are matched with the stitching deviation data of each functional area for homologous time series. Through this matching, a data set reflecting the association between the stitching process and defects in each functional area is generated. Then, multi-scale fitting is performed on the process-deviation correlation data sets of each area to identify the process parameters and deviation characteristics that are most critical to the stitching quality. The identified key process-deviation data sets are then input into the stitching defect correlation analyzer, and combined with the tolerance standards of the actual stitching quality of different materials, a stitching defect detection report is generated. This report can help production personnel understand the stitching quality of different functional areas of the coat in real time, thereby effectively improving detection accuracy and reducing defect rates.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 is a schematic flow chart of an intelligent detection method for sewing defects of coats in one embodiment;

[0011] Figure 2 A schematic diagram of a process for constructing a defect feature extraction model for an intelligent detection method for sewing defects of coats in an embodiment. DETAILED DESCRIPTION

[0012] The embodiment of the present application provides an intelligent detection method for coat sewing defects, thereby solving the technical problems of inaccurate defect detection and insufficient real-time performance due to fluctuations in process parameters of different functional areas during the coat sewing process.

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0015] Examples, such as Figure 1 As shown, the present application provides an intelligent detection method for coat stitching defects, the method comprising:

[0016] Obtain a target coat design drawing, divide the functional areas based on the target coat design drawing, match the material information according to the division result, and generate a material-functional area mapping diagram.

[0017] In an embodiment of the present application, the system terminal first obtains the design drawing of the target coat, which shows in detail the overall structure of the coat and the specific design of each part. Based on this drawing, the system terminal divides the various functional areas of the coat, such as the collar, cuffs, buttons, zippers, pockets, etc., and determines different functional areas. Then, based on the divided functional areas and combined with the specific design information of each part, the material information used in these functional areas is obtained, such as different materials such as cotton, wool, and silk. Through this matching process, the system terminal generates a material-functional area mapping diagram. This mapping diagram details each functional area of ​​the coat and the corresponding material information, for example, the collar area-wool, the button area-polyester, etc. This mapping diagram will serve as the basis for subsequent image acquisition and defect detection to ensure that the system terminal can accurately match the corresponding material information in different functional areas.

[0018] The division results are stitched and collected area by area based on a high-precision visible light camera to obtain stitched image data streams of each functional area.

[0019] In one embodiment, after completing the division of the functional areas of the coat, the system terminal uses a high-precision visible light camera to shoot each divided functional area one by one, and collects image data during the stitching process area by area. The high-precision visible light camera will focus on different functional areas of the coat in turn to ensure that the stitching details of each area are accurately captured. Through this process, the system terminal obtains the stitching image data stream of each functional area, which will reflect the defects and deviations that may occur in different areas during the stitching process, ensuring that the stitching conditions of each area are accurately recorded, providing a basis for subsequent defect detection.

[0020] Furthermore, the present application provides a method for collecting images of the segmentation results by stitching them region by region based on a high-precision visible light camera, including:

[0021] Material information based on the material-functional area mapping diagram is used to extract material features in a material feature library to obtain multiple material features of the target coat; a multi-angle adjustment strategy of the high-precision visible light camera is configured based on the multiple material features; and multi-angle light adaptability of the high-precision visible light camera is optimized based on the multi-angle adjustment strategy.

[0022] Preferably, the system terminal extracts the material information of each functional area of ​​the coat from the obtained material-functional area mapping diagram, and uses this material information as an index to input it into the material feature library for matching, extracting the characteristics of each material, including reflectivity, light absorption capacity, texture roughness, transparency, etc., to provide a basis for camera configuration, ensuring that it can adapt to the needs of different materials during shooting. Among them, this material feature library is constructed based on big data retrieval, including multiple materials and their corresponding characteristics. After obtaining multiple material features of the coat, the system terminal configures a multi-angle adjustment strategy of a high-precision visible light camera based on these features. The core of this strategy is to adjust the shooting angle and parameters of the high-precision visible light camera according to the characteristics of different materials. For example, for materials with high reflectivity (such as silk), configure the camera to avoid strong light reflection from the front and adjust it to side angle shooting to reduce reflection interference. For materials with strong light absorption (such as wool or cotton), configure the camera to increase the exposure time and collect light from multiple angles to ensure that the details of the material texture can be clearly presented. For materials with rough texture (such as cheesecloth), increase the contrast to enhance the camera's capture of material texture details. The system terminal configures a camera angle adjustment strategy based on the material characteristics of each functional area to ensure that the material characteristics are accurately reflected. Subsequently, according to the configured multi-angle adjustment strategy, the system terminal optimizes the multi-angle light adaptability of the high-precision visible light camera. Specifically, the camera's top-view angle and side-view angle are dynamically adjusted according to the multi-angle adjustment strategy, so that it can shoot each material from different angles to adapt to the reflective characteristics and texture details of each material and reduce the deviation caused by single light. The ambient light or the built-in light source of the camera is automatically adjusted according to the multi-angle adjustment strategy to ensure that each functional area is well lit during shooting to avoid excessive brightness or darkness. In addition, the focus and exposure parameters of the camera are dynamically adjusted when shooting at different angles to ensure that the material details at each shooting angle can be clearly displayed. Through this optimization process, the camera can automatically adjust the light and angle according to the material characteristics of each functional area of ​​the coat to ensure the acquisition of high-quality image data and provide the best image basis for subsequent defect detection.

[0023] The defect feature extraction model is activated, channel matching is performed according to the material-functional area mapping diagram, and the stitched image data stream of each functional area is input according to the matching result to perform defect characterization extraction, so as to obtain the suture deviation stream and suture deviation feature set of different materials.

[0024] In one embodiment, after obtaining the stitched image data stream of each functional area, the system terminal activates the defect feature extraction model, which contains multiple defect feature extraction channels, each defect feature extraction channel corresponds to a material, and is used to identify and analyze defect features in the coat stitching process. Subsequently, the defect feature extraction channel is matched according to the material information of each functional area recorded in the material-functional area mapping diagram, and the functional area is identified for each defect feature extraction channel. After that, the system terminal inputs the stitched image data stream of each functional area according to the identification of each channel, and the defect feature extraction channel will extract defect representations based on the received stitched image data stream, generate stitch deviation streams and stitch deviation feature sets of different materials, and specifically describe the defects and deviation problems that may exist in the stitching of each area.

[0025] Further, if Figure 2 As shown, the present application provides a method for constructing a target three-dimensional model, including:

[0026] The historical stitching database is connected, and the stitching image data streams of each functional area are used to perform similarity matching in the historical stitching database to obtain a first root node, wherein the first root node includes historical stitching image data streams, historical stitching deviation streams and historical stitching deviation feature sets of different functional areas; based on the first root node, a first-level expansion is performed in the historical stitching database to obtain a first-level expansion leaf node; based on the first-level expansion leaf node, a second-level expansion is performed in the historical stitching database to obtain a second-level expansion leaf node; by expanding to H-level expansion leaf nodes layer by layer, a multi-level expansion leaf node is obtained, wherein H≥2; with H level to the first root node as the direction, the multi-level expansion leaf nodes are reversely aggregated to construct clusters of each functional area; data integration is performed on the clusters of each functional area, and material division is performed according to the integration results to obtain a sample data set; a defect feature extraction model is constructed based on the sample data set.

[0027] Preferably, the system terminal is connected to the historical stitching database through a reserved port, and the historical stitching database stores a large amount of data of the historical stitching process, including historical stitching image data streams, historical suture deviation streams and historical suture deviation feature sets, wherein the historical suture deviation stream is a defective stitching image, and the historical suture deviation feature set corresponds to the historical suture deviation stream one by one. Subsequently, the system terminal uses the stitching image data streams of each functional area to perform similarity matching in the historical stitching database. Taking the collar as an example, the system terminal calculates multiple similarities between the stitching image data stream of the collar and the historical stitching image data streams in the historical stitching database. These similarities are then compared with the similarity threshold, and the similarities greater than or equal to the similarity threshold are screened out, and the historical stitching image data stream corresponding to the screened similarity, and the historical suture deviation stream and historical suture deviation feature set corresponding to the historical stitching image data stream are added to the first root node. Afterwards, the system terminal performs a first-level expansion in the historical stitching database based on the first root node, that is, searches for similar historical records on the basis of the first root node to generate a first-level expansion leaf node. On this basis, the first-level expansion leaf node continues to be expanded at a second level, and more similar data are searched to generate a second-level expansion leaf node. Through such an expansion process, the expansion is performed layer by layer to H-level expansion leaf nodes, where H is greater than or equal to 2. Each layer of expansion adds more historical data, making the sample set of the model richer. For the stitched image data streams of the remaining functional areas, the system terminal uses the same method as above to determine the first root node of the stitched image data streams of these functional areas, and expands layer by layer based on the first root node to obtain H-level expansion leaf nodes of each functional area. After expanding to the H level, the system terminal starts to trace back from the H-level expansion leaf node to the first root node for reverse aggregation. This process integrates all the expanded leaf node data together to construct clusters of different functional areas. For the clusters of these functional areas, the system terminal performs data integration, that is, aggregates the data in all clusters together, and then divides the aggregated results according to the material, distinguishes the historical stitched image data streams, historical suture deviation streams and historical suture deviation feature sets corresponding to different materials, and generates a sample data set. Then, the system terminal trains multiple defect feature extraction channels based on multiple material sample data in the sample data set, and each defect feature extraction channel corresponds to a material. Finally, multiple defect feature extraction channels are integrated to construct a defect feature extraction model for subsequent coat stitching defect detection to ensure detection accuracy and adaptability.

[0028] Taking wool material as an example, the system terminal divides the wool material sample data in the sample data set into a training set and a validation set, and trains the constructed initial defect feature extraction channel through the training set. After the training, the validation set is used for verification to evaluate the performance of the channel. Among them, the initial defect feature extraction channel can be constructed based on convolutional neural networks, support vector machines, etc. Taking convolutional neural networks as an example, a convolutional neural network is used to construct an initial defect feature extraction channel structure, including input layer, output layer, convolution layer, pooling layer, fully connected layer, etc. Then, the weight of the initial defect feature extraction channel is initialized by random numbers, etc., and the training set is input into the initialized initial defect feature extraction channel for forward propagation, and the prediction results including suture deviation flow and suture deviation feature set are calculated layer by layer through input layer, convolution layer, pooling layer, fully connected layer, output layer, etc. Subsequently, the cross entropy loss function is used to calculate the loss value between the prediction result and the sample data, and the gradient of the loss to the weight of each layer is calculated layer by layer through back propagation. Then, the gradient descent algorithm is used to optimize the channel parameters and adjust the weights to minimize the value of the loss function. Repeat the above process until the maximum number of iterations is reached. After the training is completed, the validation set is used to test the channel performance and evaluate the accuracy of the channel in the classification tasks of the stitch deviation flow and stitch deviation feature set. If the accuracy meets the expected expectations, the current initial defect feature extraction channel is output as the final wool material defect feature extraction channel. Otherwise, the hyperparameters such as the learning rate and the number of training batches are adjusted to further improve the defect characterization extraction effect of the wool material defect feature extraction channel.

[0029] Further, the present application provides a method of performing a first-level expansion in a historical stitching database based on the first root node to obtain a first-level expanded leaf node, including:

[0030] The historical stitching database is traversed based on the first root node to obtain a first extended neighborhood; a similarity distance evaluation is performed on the first root node and the first extended neighborhood to obtain a second extended neighborhood; and random sampling is performed based on the second extended neighborhood to obtain a first-level extended leaf node.

[0031] Optionally, after obtaining the first root node, the system terminal traverses the historical stitching database according to the characteristics of the first root node and searches for other historical data with similar characteristics to form a first extended neighborhood. The first extended neighborhood includes all historical stitching data that have a high degree of similarity to the first root node. After obtaining the first extended neighborhood, the system terminal measures the similarity of the first root node and all data in the first extended neighborhood. Commonly used similarity measurement methods include Euclidean distance, cosine similarity, dynamic time warping, etc. Taking Euclidean distance as an example, the system terminal calculates the similarity distance between the first root node and all data in the neighborhood, and then uses 1 to 1 and the sum of the similarity distances to quantify the similarity between the first root node and the remaining historical stitching data. Subsequently, according to the calculated similarity, the historical stitching data in the first extended neighborhood is filtered, and the historical stitching data with a similarity greater than or equal to the similarity threshold with the first root node is selected to form a second extended neighborhood. This step ensures that the extended nodes are all historical stitching data that are highly related to the first root node. After that, the system terminal randomly samples the second extended neighborhood according to the preset data volume. The purpose of random sampling is to select representative and diverse historical data from the second extended neighborhood, rather than simply selecting the nearest node. Random sampling can prevent the channel from overfitting to a certain type of feature, thereby improving the generalization ability of the channel. In addition, uniform sampling, weighted sampling by similarity, etc. can also be used to ensure that different types of data are included in the sampling results. Through random sampling, the system terminal generates a first-level extended leaf node. These first-level extended leaf nodes represent the historical stitching data related to the first root node and its extended neighborhood, and will serve as important data for subsequent expansion or model training.

[0032] Furthermore, the present application provides a method of performing reverse aggregation on the multi-level extended leaf nodes from level H to the first root node to construct a sample data set, including:

[0033] Perform a central tendency analysis on the historical stitched image data stream, historical suture deviation stream and historical suture deviation feature set in the H-level extended leaf node to obtain the H-level historical stitched image aggregate data stream, the H-level historical suture aggregate deviation stream and the H-level historical suture aggregate deviation feature set; add the H-level historical stitched image aggregate data stream, the H-level historical suture aggregate deviation stream and the H-level historical suture aggregate deviation feature set to the H-1-level extended leaf node for central tendency analysis, and trace back level by level until the first-level historical stitched image aggregate data stream, the first-level historical suture aggregate deviation stream and the first-level historical suture aggregate deviation feature set are added to the first similarity root node to generate a sample training data set.

[0034] Optionally, after obtaining H-level extended leaf nodes, the system terminal extracts common features by performing aggregation operations on the historical stitched image data stream of each H-level extended leaf node, that is, using the mean image method to average the pixels of multiple similar stitched images to obtain the aggregated H-level historical stitched image aggregate data stream. This step helps to remove accidental interference and noise and highlight the main features. Similar to the historical stitched image data stream, the system terminal performs the same operation on the historical seam deviation stream of each H-level extended leaf node to obtain an H-level historical seam aggregate deviation stream. By performing mean processing on the features in the historical seam deviation feature set of each H-level extended leaf node, an H-level historical seam aggregate deviation feature set is obtained. Subsequently, the system terminal adds the H-level historical stitched image aggregated data stream, H-level historical suture aggregated deviation stream, and H-level historical suture aggregated deviation feature set representing the entire H-level extended leaf node to the H-1-level extended leaf node, and then performs the same central trend analysis on the H-1-level extended leaf node. By tracing back level by level, the data of each level (such as H-2 level, H-3 level) of the extended leaf node is merged with the data of the previous level, and the central trend analysis and aggregation operations are repeated until the first-level extended leaf node is traced back. After the final aggregation operation is completed on the first-level extended leaf node, the data has undergone multiple trend analyses and aggregations to form a highly integrated data set. In the first-level extended leaf node, the system terminal finally integrates the highly integrated data set with the historical stitched image data stream, historical suture deviation stream, and historical suture deviation feature set of the first root node. This integration result represents the integrated data between extended leaf nodes at different levels, thereby obtaining a sample data set. This sample data set retains the core features of historical data at different levels and can be used for channel training to ensure that the channel can capture various possible stitching defects and deviation patterns.

[0035] The real-time process parameters of the suturing equipment are collected, combined with the suture deviation feature set, and the real-time process parameters of the suturing equipment and the suture deviation flow are matched in time series with the same functional area to generate process-deviation association data sets of different functional areas.

[0036] In one embodiment, the system terminal collects the process parameters of the suture equipment in real time, including stitch speed, fabric feed speed, tension setting value, stitch length setting value, etc. These process parameters reflect the specific working conditions of the suture equipment when performing suture operations in different functional areas (such as collars, cuffs, pockets, etc.). Subsequently, these process parameters are combined with the suture deviation feature set. The suture deviation feature set contains the suture quality problems of each functional area, such as suture deviation, uneven stitches, exposed thread ends, etc. In order to ensure that the process parameters and suture deviation features can be effectively associated, the system terminal performs time sequence matching of these data in the same functional area. This means that the system terminal will match the process parameters at each time point with the suture deviation corresponding to the same time point according to the timeline, ensuring that the device state at the same time corresponds to the suture result. Through this matching, the system terminal generates a process-deviation association data set, which associates the suture process parameters of each functional area with the corresponding suture deviation features. Different functional areas may have different suture processes and deviation patterns. Such an associated data set can help further analyze the suture quality problems in each area and identify the process parameters that may cause these problems, providing a basis for subsequent defect detection.

[0037] Multi-scale fitting is performed on the process-deviation association data sets of the different functional areas to identify key process-deviation association data sets.

[0038] In one embodiment, after obtaining the process-deviation association data sets of different functional areas, the system terminal will perform multi-scale fitting on these data sets. The process of multi-scale fitting is to gradually fit the relationship between process parameters and suture deviation in different process parameter dimensions. Specifically, the system terminal will analyze the impact on suture deviation according to the stitch speed, fabric feed speed, tension setting value, and stitch length setting value in the process parameters for the suture process of different functional areas. By fitting at different scales, the system terminal can more comprehensively capture the complex relationship between process parameters and suture deviation, and obtain the process parameters that have the greatest impact on suture quality. This process helps to eliminate the interference of noise and abnormal data, and more accurately identify which process parameters are highly correlated with suture deviation. Finally, the system terminal identifies the key process-deviation association data set, which contains process parameters and suture features that have a significant impact on suture deviation for subsequent quality evaluation.

[0039] Furthermore, the present application provides a method of performing multi-scale fitting on the process-deviation correlation data sets of the different functional areas to identify key process-deviation correlation data sets of the different functional areas, including:

[0040] Homologous matching is performed on the process-deviation association data sets of the different functional areas to obtain a homologous process-deviation set; process parameter decomposition is performed on the homologous process-deviation set to obtain multiple single-parameter deviation control groups; dynamic correlation analysis is performed on the multiple single-parameter deviation control groups based on a preset sliding window to obtain multiple single-parameter correlations; single-parameter matching is performed on the process-deviation association data sets of the different functional areas based on the multiple single-parameter correlations to obtain a key process-deviation association data set.

[0041] Preferably, the system terminal performs homologous matching on the process-deviation associated data sets of different functional areas, that is, matches the process parameters and stitch deviation data of the same coat. This means that the system terminal will ensure that all process parameters and stitch deviation features come from the stitching process of the same coat. By matching the coat data from the same source to obtain a homologous process-deviation set, the process-deviation relationship of the coat in the entire stitching process can be more accurately reflected. Subsequently, the process parameters in the homologous process-deviation set are decomposed. The process parameters are composed of multiple variables, such as stitch speed, fabric feed speed, tension setting value, stitch length setting value, etc. Taking a coat as an example, the system terminal decomposes the process parameters of the coat separately and associates them with the stitch deviation features of each functional area of ​​the coat to form multiple single parameter deviation control groups. Each control group corresponds to a process parameter and the stitch deviation feature of each functional area. Afterwards, each single parameter deviation control group is intercepted using a preset sliding window to obtain multiple single parameter deviation sequences of each single parameter deviation control group. Taking the stitch speed deviation sequence as an example, the system terminal performs normalization processing through the maximum-minimum method, that is, the difference between the current value and the minimum value of the parameter is used to calculate the ratio of the difference between the maximum value of the parameter and the minimum value of the parameter to obtain a single-parameter normalized deviation sequence. Then, the stitch speed standard sequence is obtained as the reference sequence for subsequent calculations. This stitch speed standard sequence is set based on historical experience. Then, the absolute difference between the stitch speed deviation sequence and the reference sequence is calculated at each time point, the minimum difference and the maximum difference are statistically calculated, and then the correlation at each time point is calculated according to the correlation dynamic analysis formula. The correlation dynamic analysis formula is as follows: Among them, ε i (k) is the correlation degree at the kth time point, k is the time point, i is the sequence number of the process parameter, Δ min is the minimum difference, Δ max is the maximum difference, ρ is the resolution coefficient, usually taken as 0.5, Δ i(k) is the absolute difference between the deviation sequence of the i-th process parameter and the reference sequence at the k-th time point. After calculating the correlation at each time point, the system terminal accumulates all the correlations of the stitch speed deviation sequence, and then performs mean calculation to obtain the deviation sequence correlation of the stitch speed deviation sequence. Finally, the same calculation is performed on the remaining deviation sequences to obtain multiple deviation sequence correlations, and then the deviation sequence correlations of the same single parameter deviation control group are averaged to obtain multiple single parameter correlations. After obtaining multiple single parameter correlations, the system terminal matches the multiple single parameter correlations with the process-deviation correlation data sets of different functional areas, that is, the single parameter correlations belonging to the same functional area are integrated together, and then the single parameter correlation with the largest correlation is selected to extract parameters from the process-deviation correlation data set of the functional area to obtain the key process-deviation correlation data set. Through this operation, the system terminal can identify the process parameters that have the most significant impact on the suture quality, providing an important basis for subsequent quality evaluation.

[0042] Furthermore, the present application provides that before dynamically analyzing the correlation of the multiple single parameter deviation control groups based on a preset sliding window, the method includes:

[0043] The lag effect is determined for the multiple single parameter deviation control groups to obtain a lag effect sequence for each single parameter deviation control group; the lag effect sequence is verified based on a lag effect threshold to determine the lag time; if the lag time is not 0, the single parameter deviation control group corresponding to the lag time is time-shifted.

[0044] Optionally, for each single parameter deviation control group, the system terminal analyzes whether there is a time lag effect between the process parameter and the suture deviation. The hysteresis effect can be determined by a variety of methods, and the commonly used method includes cross-correlation analysis, that is, by calculating the correlation between the process parameter sequence and the suture deviation sequence at different time lags, it is determined whether there is a significant lag. In order to accurately evaluate the time lag effect, the system terminal determines the hysteresis effect of multiple single parameter deviation control groups through the constructed hysteresis effect evaluation operator, calculates the hysteresis correlation at each time point, and obtains the hysteresis effect sequence of each single parameter deviation control group. Subsequently, according to the time sequence, the hysteresis correlation and the hysteresis effect threshold are compared for each hysteresis effect sequence. If there is a hysteresis correlation greater than or equal to the hysteresis effect threshold, the system terminal extracts the first hysteresis correlation greater than or equal to the hysteresis effect threshold, and the time point corresponding to this hysteresis correlation is used as the hysteresis time. If it does not exist, the hysteresis time is set to 0, indicating that there is no hysteresis effect. Afterwards, based on the non-zero lag time, the system terminal performs a time series adjustment (translation) on the single parameter deviation control group of the process parameter, that is, the time series of the process parameter is translated forward or backward by the corresponding lag time, so that the process parameter and the suture deviation can synchronously reflect the actual situation. The single parameter deviation control group after time series translation will be more matched, making the subsequent correlation analysis more accurate.

[0045] Furthermore, the present application provides a method for determining the hysteresis effect of the multiple single parameter deviation control groups to obtain the hysteresis effect sequence of each single parameter deviation control group, including:

[0046] A hysteresis effect evaluation operator is constructed, wherein the hysteresis effect evaluation operator includes a hysteresis effect evaluation function, and the hysteresis effect evaluation function is specifically as follows:

[0047] Optionally, the hysteresis effect evaluation operator includes an input layer, an output layer, and a calculation layer. The calculation layer has a built-in hysteresis effect evaluation function, which is used to analyze the hysteresis effect between process parameters (such as stitch speed, tension, etc.) and suture deviation. The hysteresis effect evaluation function is as follows: Wherein, CCF(k) is the result of hysteresis effect, which indicates the correlation between process parameter sequence and suture deviation sequence at hysteresis time k. k is hysteresis time, which indicates the hysteresis time step between time series. n is the length of time series, i.e. the number of data points in single parameter deviation control group. X(t) is process parameter sequence, which indicates the process parameter value at time point t, including but not limited to stitch speed, fabric feed speed, tension setting value, stitch length setting value. Y(t+k) is the suture deviation at time t+k in suture deviation sequence, which indicates the suture deviation value at time point t+k. X is the average value of process parameter sequence, and Y is the average value of suture deviation sequence.

[0048] The key process-deviation association data set is input into the stitching defect association analyzer for quality assessment, and combined with the stitching quality tolerance, a stitching defect detection report is generated.

[0049] In one embodiment, the system terminal inputs multiple key process-deviation association data sets into the stitching defect association analyzer. The stitching defect association analyzer also includes multiple stitching defect association analysis channels, each stitching defect association analysis channel corresponding to a material. The system terminal matches the stitching defect association analysis channel through the material identification in the key process-deviation association data set, and inputs the corresponding key process-deviation association data set. Each stitching defect association analysis channel will perform a comprehensive quality assessment on the input data to determine the predicted stitching quality of the functional area corresponding to each key process-deviation association data set. Among them, the construction method of the stitching defect association analyzer is the same as the aforementioned defect feature extraction model. Subsequently, the predicted stitching quality is judged in combination with the stitching quality tolerance, that is, the set acceptable defect range. If the predicted stitching quality exceeds the preset tolerance range, the system terminal marks the functional area as having a quality problem and generates a stitching defect detection report, which includes the stitching quality of the functional area with quality problems, the specific defect description, and the process parameters with the greatest impact. This report can help understand the problems in the stitching process, optimize the process flow, and improve the overall quality.

[0050] In summary, the embodiments of the present application have at least the following technical effects:

[0051] The embodiment of the present application obtains the design drawings of the target coat, divides the functional areas, and matches the material information to generate a material-functional area mapping diagram. Then, a high-precision visible light camera is used to collect stitching image data from different functional areas area by area, activate the defect feature extraction model, and extract the suture deviation flow and feature set of different material areas through channel matching. At the same time, the real-time process parameters of the suture equipment are collected, and the process-deviation association data set is generated by timing matching with the homologous functional area of ​​the suture deviation flow. Subsequently, the key process-deviation association data set is identified through multi-scale fitting, and it is input into the suture defect association analyzer, combined with the suture quality tolerance, and finally a suture defect detection report is generated. In addition, the defect feature extraction model is extended by connecting to the historical suture database, and similar nodes are constructed based on historical data and multi-level aggregation is performed to generate a sample data set. The sample data set is used to construct a defect feature extraction model with prediction and detection capabilities. In order to further refine the analysis, multi-scale fitting involves process parameter decomposition and sliding window correlation analysis of homologous matching data, and timing adjustment for hysteresis effects. The evaluation of the hysteresis effect is completed by constructing an evaluation operator and applying relevant evaluation functions, ultimately achieving intelligent detection of potential defects in the sewing process. These technical effects jointly solve the technical problems of inaccurate defect detection and insufficient real-time performance due to fluctuations in process parameters in different functional areas during the coat sewing process, and achieve the effect of improving the accuracy and adaptability of detection by combining synchronous analysis and multi-scale fitting of process parameters and stitch deviation data.

[0052] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0054] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent detection method for coat stitching defects, characterized in that: The method comprises: Obtaining a target coat design drawing, dividing the functional areas based on the target coat design drawing, matching material information according to the division result, and generating a material-functional area mapping diagram; Based on a high-precision visible light camera, stitching images are collected area by area on the division results to obtain stitching image data streams of each functional area; Activate the defect feature extraction model, perform channel matching according to the material-functional area mapping diagram, input the stitched image data stream of each functional area according to the matching result to perform defect characterization extraction, and obtain the suture deviation stream and suture deviation feature set of different materials; Collecting real-time process parameters of suturing equipment, combining the suture deviation feature set, performing time series matching of homologous functional areas on the real-time process parameters of suturing equipment and the suture deviation flow, and generating process-deviation association data sets of different functional areas; Performing multi-scale fitting on the process-deviation correlation data sets of the different functional areas to identify key process-deviation correlation data sets; The key process-deviation association data set is input into the stitching defect association analyzer for quality assessment, and combined with the stitching quality tolerance, a stitching defect detection report is generated.

2. The intelligent detection method for coat stitching defects according to claim 1, characterized in that: Construct a defect feature extraction model, the method includes: Connecting to a historical stitching database, using the stitched image data streams of each functional area to perform similarity matching in the historical stitching database, to obtain a first root node, wherein the first root node includes historical stitched image data streams of different functional areas, historical stitch deviation streams, and historical stitch deviation feature sets; Performing a first-level expansion in the historical stitching database based on the first root node to obtain a first-level expanded leaf node; Based on the first-level expanded leaf node, performing a second-level expansion in the historical stitching database to obtain a second-level expanded leaf node; By expanding layer by layer to H-level expansion leaf nodes, a multi-level expansion leaf node is obtained, where H ≥ 2; Taking level H to the first root node as the direction, reversely aggregate the multi-level extended leaf nodes to construct clusters of each functional area; Integrate the data of the functional area clusters, divide the materials according to the integration results, and obtain a sample data set; A defect feature extraction model is constructed based on the sample data set.

3. The intelligent detection method for coat stitching defects according to claim 2, characterized in that: Based on the first root node, a first-level expansion is performed in the history stitching database to obtain a first-level expansion leaf node, the method comprising: Traversing the historical stitching database based on the first root node to obtain a first extended neighborhood; Performing similarity distance evaluation on the first root node and the first extended neighborhood to obtain a second extended neighborhood; Random sampling is performed based on the second extended neighborhood to obtain a first-level extended leaf node.

4. The intelligent detection method for coat stitching defects according to claim 2, characterized in that: Taking level H to the first root node as the direction, the multi-level extended leaf nodes are reversely aggregated to construct a sample data set, and the method includes: Performing a central tendency analysis on the historical stitched image data stream, the historical suture deviation stream, and the historical suture deviation feature set in the H-level extended leaf nodes to obtain an H-level historical stitched image aggregate data stream, an H-level historical suture aggregate deviation stream, and an H-level historical suture aggregate deviation feature set; The H-level historical stitched image aggregate data stream, the H-level historical seam aggregate deviation stream and the H-level historical seam aggregate deviation feature set are added to the H-1-level extended leaf node for central tendency analysis, and then traced back level by level until the first-level historical stitched image aggregate data stream, the first-level historical seam aggregate deviation stream and the first-level historical seam aggregate deviation feature set are added to the first similarity root node to generate a sample training data set.

5. The intelligent detection method for coat stitching defects according to claim 1, characterized in that: Performing multi-scale fitting on the process-deviation correlation data sets of the different functional areas to identify key process-deviation correlation data sets of the different functional areas, the method comprising: Performing homology matching on the process-deviation association data sets of the different functional areas to obtain homology process-deviation sets; Decomposing the homologous process-deviation set by process parameters to obtain a plurality of single parameter deviation control groups; Performing a dynamic correlation analysis on the multiple single parameter deviation control groups based on a preset sliding window to obtain multiple single parameter correlations; Single parameter matching is performed on the process-deviation correlation data sets of the different functional areas based on the multiple single parameter correlation degrees to obtain a key process-deviation correlation data set.

6. The intelligent detection method for coat stitching defects according to claim 5, characterized in that: Before dynamically analyzing the correlation of the multiple single parameter deviation control groups based on a preset sliding window, the method includes: Performing hysteresis effect determination on the multiple single parameter deviation control groups to obtain a hysteresis effect sequence of each single parameter deviation control group; Verifying the hysteresis effect sequence based on a hysteresis effect threshold to determine a hysteresis time; If the lag time is not 0, the single parameter deviation control group corresponding to the lag time is time-shifted.

7. The intelligent detection method for coat stitching defects according to claim 6, characterized in that: Determining the hysteresis effect of the multiple single parameter deviation control groups to obtain the hysteresis effect sequence of each single parameter deviation control group includes: A hysteresis effect evaluation operator is constructed, wherein the hysteresis effect evaluation operator includes a hysteresis effect evaluation function, and the hysteresis effect evaluation function is specifically as follows: Wherein, CCF(k) is the hysteresis effect result, k is the hysteresis time, n is the length of the time series, X(t) is the process parameter sequence, including but not limited to stitch speed, fabric feed speed, tension setting value, stitch length setting value, Y(t+k) is the stitch deviation at time t+k in the stitch deviation sequence, is the average value of the process parameter sequence, is the average value of the suture deviation series.

8. The intelligent detection method for coat stitching defects according to claim 6, characterized in that: Based on the high-precision visible light camera, the image of the segmentation result is stitched region by region, and before the image of the target coat is stitched by the high-precision visible light camera, the method includes: Extracting material features from a material feature library based on the material information of the material-functional area mapping diagram to obtain a plurality of material features of the target coat; Configuring a multi-angle adjustment strategy for the high-precision visible light camera based on the multiple material features; The multi-angle light adaptability of the high-precision visible light camera is optimized based on the multi-angle adjustment strategy.

Images