A control method and system for non-woven fabric production line

Abstract

The present invention relates to the technical field of non-woven fabric production line control, specifically a control method and system for a non-woven fabric production line, comprising: collecting videos of a uniform fiber web on a working production line before and after it enters a needling machine to obtain a needling raw material video and a needling effect video; extracting frames of the needling effect video at a first time interval to obtain a needling effect image, and inputting the pre-processed needling effect image into a needle state classification model for classification; if a blunt needle production image is identified, calculating the total number of blunt needle images within a specified time period to obtain a first number; if the first number exceeds a preset threshold, adjusting the current parameters to the corresponding stage optimal control parameters; if a damaged needle production image is identified, calculating the total number of damaged needle images within a specified time period to obtain a second number, and if the second number exceeds a preset threshold, replacing the needle. This method improves the stability of product quality by precisely regulating and controlling production line control parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of non-woven fabric production line control, and in particular to a control method and system for a non-woven fabric production line. Background Art

[0002] Unlike woven fabrics, which are made from yarns, nonwovens do not contain yarns. Instead, fibers are bonded together physically or chemically, making them generally lightweight and flexible. Therefore, nonwovens are widely used in medical, sanitary, and industrial applications. Needle-punched nonwovens are a type of nonwoven fabric in which fibers are bonded together primarily through a needle-punching process.

[0003] Existing needle-punched nonwoven production lines have essentially achieved automated production, enabling mass production of nonwovens. The production process for needle-punched nonwovens involves multiple steps, particularly the needle-punching process, which significantly differs from other types of nonwoven production lines.

[0004] During the acupuncture process in existing intelligent production lines, the tips of the needles wear and age as the needles are continuously needled, affecting their puncture performance. While existing intelligent control systems have a certain degree of adaptive capability, they do not fully consider the state of the needles during processing. Although some researchers have taken needle replacement into consideration, current methods rely primarily on a single indicator of wear level, are still inadequate in identifying needle replacements and struggle to optimize control parameters based on different needle states. A control method specifically tailored to the acupuncture process in production lines is urgently needed to obtain more precise production line control parameters while ensuring continuous and stable operation of the line and consistent product quality.

[0005] To this end, a control method and system for a non-woven fabric production line are proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide a control method and system for a non-woven fabric production line, which realizes real-time monitoring and dynamic control of the needle status through video acquisition and image analysis. It includes collecting videos before and after the fiber web enters the needling machine, performing quality inspection on the needling raw material image and extracting frames to process the needling effect image. The image is classified by a trained needle status classification model, and the production images of blunt needles and damaged needles are identified, and the first quantity and the second quantity are calculated based on the detection results. When the first quantity exceeds the preset threshold, the current control parameters of the needling machine are adjusted to the optimal control parameters of the corresponding stage; when the second quantity exceeds the preset threshold, the needles are replaced. Through dynamic monitoring and production line parameter adjustment, this method realizes adaptive control parameter optimization under different working conditions while ensuring the continuous and stable operation of the production line and the consistency of product quality, thereby improving the stability of product quality.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A control method for a nonwoven fabric production line, comprising:

[0009] Collect the video of the uniform fiber web on the production line before it enters the needle loom to obtain the video of the needle-punched raw material;

[0010] Performing quality inspection based on the acupuncture raw material video, and triggering a production line warning if the quality inspection fails; the current parameters of the acupuncture stage of the working production line are preset standard control parameters;

[0011] If the quality inspection is passed, a video of the uniform fiber web on the working production line passing through the needling machine is collected to obtain a needling effect video;

[0012] Extracting frames from the acupuncture effect video at a first time interval to obtain a plurality of first acupuncture effect images;

[0013] preprocessing the acupuncture effect image to obtain a standard acupuncture effect image;

[0014] Inputting the standard acupuncture effect image into a trained needle state classification model for classification into normal production images, blunt needle production images, and damaged needle production images; the needle state classification model is trained based on historical production data;

[0015] If the blunt needle production image is identified, a first number is calculated; the first number is the total number of the blunt needle production images identified within a specified time;

[0016] If the damaged needle production image is identified, a second number is calculated; the second number is the total number of the damaged needle production images identified within the specified time;

[0017] When the first number exceeds a first preset threshold, identifying the blunt needle stage of the blunt needle production image, and adjusting the current parameter to the optimal control parameter of the corresponding stage according to the blunt needle stage;

[0018] When the second number exceeds a second preset threshold, the needles of the needling machine are replaced.

[0019] Furthermore, collecting the video of the uniform fiber web on the working production line before entering the needling machine includes:

[0020] The first high-definition camera is installed behind the web laying device and just above the conveyor belt in front of the needle loom, with the shooting direction of the first high-definition camera vertically downward.

[0021] Furthermore, performing the quality inspection based on the acupuncture raw material video includes:

[0022] Extracting frames from the acupuncture raw material video at the first time interval to obtain a plurality of first acupuncture raw material images;

[0023] Preprocessing the acupuncture raw material image to obtain a standard acupuncture raw material image;

[0024] The standard needle-punched raw material image is input into a trained fiber web quality assessment model to obtain a quality inspection result; the quality inspection result includes qualified and unqualified.

[0025] Furthermore, the web quality assessment model includes:

[0026] The input layer is used to receive the input image and perform preliminary feature representation processing;

[0027] A feature extraction layer, configured to extract key features of the input image and obtain basic features of the web, wherein the basic features of the web include texture features, edge features, uniformity features, and fiber distribution features of the web; the feature extraction layer comprises a plurality of convolutional layers and a plurality of pooling layers;

[0028] The multi-scale feature fusion layer is used to fuse the feature information of different scales from different convolutional layers and obtain multi-scale fusion features through convolution operations of different receptive fields;

[0029] An attention mechanism layer, which is used to optimize feature representation through a channel attention mechanism and a spatial attention mechanism; the channel attention mechanism is used to weight different feature channels to obtain weighted channel features, and the spatial attention mechanism is used to focus on key areas of the image to obtain weighted spatial features;

[0030] A feature fusion layer is used to fuse the weighted channel features and the weighted spatial features optimized by the channel attention mechanism and the spatial attention mechanism to obtain a final fused feature;

[0031] An anomaly detection layer, configured to detect anomalies on the final fused features; comprising an autoencoder module, configured to reconstruct the basic web features and calculate a reconstruction error; when the reconstruction error exceeds a preset threshold, the input image is judged to be abnormal and an abnormality warning message is directly output; if no abnormality is detected, quality classification is continued;

[0032] The classification layer is used to classify the final fusion features through the fully connected layer to obtain the quality inspection result.

[0033] Furthermore, if the quality inspection is passed, collecting a video of the uniform fiber web on the working production line after it passes through the needling machine includes:

[0034] A second high-definition camera is installed just above the area between the needle loom and the winding device, with the shooting direction of the second high-definition camera vertically downward.

[0035] Furthermore, the process of obtaining the first quantity and the second quantity includes:

[0036] When the blunt needle production image is identified, a blunt needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image; the blunt needle effect video clip is framed at a second time interval to obtain a plurality of second acupuncture effect images; the first time interval is greater than the second time interval;

[0037] Counting the number of the blunt needle production images in all the second acupuncture effect images to obtain the first number;

[0038] When the damaged needle production image is identified, a damaged needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image;

[0039] Extracting frames from the damaged needle effect video clip at the second time interval to obtain a plurality of third acupuncture effect images;

[0040] The second number is obtained by counting the number of the blunt needle production images in all the third acupuncture effect images.

[0041] Furthermore, the acquisition of the historical production data includes:

[0042] The historical production data includes historical acupuncture effect images and historical annotation data in different states; the historical annotation data includes needle state annotations corresponding to the historical acupuncture effect images; the different states include normal operation state, blunt needle state and damaged needle state;

[0043] acquiring the historical acupuncture effect images and the historical annotation data in the normal operating state, the blunt needle state, and the damaged needle state from an operation and maintenance database, respectively; the operation and maintenance database records the historical needle working condition images corresponding to the historical acupuncture effect images;

[0044] The acquisition of the historical annotation data includes:

[0045] Acquire a standard working condition image of the needle, wherein the standard working condition image of the needle is acquired after the needle is replaced as a whole but before it starts working;

[0046] Calculating the average wear of the needles by analyzing the historical working condition image of the needles and the standard working condition image of the needles;

[0047] The historical acupuncture effect images are annotated according to the average wear amount of the needles to obtain the historical annotated data.

[0048] Furthermore, inputting the standard acupuncture effect image into the trained acupuncture state classification model for classification includes:

[0049] The standard acupuncture effect image is input into the trained needle state classification model to obtain the predicted needle wear amount. According to the predicted needle wear amount, the standard acupuncture effect image is divided into the normal production image, the blunt needle production image and the damaged needle production image.

[0050] Furthermore, the process of obtaining the optimal control parameters in the stage includes:

[0051] Identifying the blunt needle stage of the blunt needle production image according to the predicted needle wear amount; the blunt needle stage includes an early stage, a middle stage, and a late stage;

[0052] Obtaining control parameters and final product quality indicators corresponding to the initial stage, mid-stage, and late stage from the operation and maintenance database, respectively, to obtain initial product data, mid-stage product data, and late product data;

[0053] Identifying the key control parameters of the initial product data, the mid-term product data, and the late product data through correlation analysis to obtain the key control parameters of the initial product data, the mid-term product data, and the late product data;

[0054] For each stage, a regression model is constructed to analyze the relationship between the key control parameters of the stage and the quality indicators of the final product, thereby obtaining an initial regression model, a mid-term regression model, and a late-stage regression model;

[0055] Construct a comprehensive objective function;

[0056] By using the initial regression model, the mid-term regression model and the late-term regression model to predict the effects of different control parameter combinations, the optimal control parameters of each stage are searched through the optimization algorithm to obtain the initial optimal control parameters, the mid-term optimal control parameters and the late-term optimal control parameters.

[0057] A control system for a nonwoven fabric production line, comprising:

[0058] The raw material video acquisition module is used to collect the video of the uniform fiber web on the working production line before entering the needling machine to obtain the needling raw material video; the current parameters of the needling stage of the working production line are the preset standard control parameters;

[0059] A raw material quality inspection module is used to perform quality inspection based on the acupuncture raw material video. If the raw material fails the quality inspection, a production line warning is triggered;

[0060] A needling effect video acquisition module is configured to acquire a video of the uniform fiber web on the production line passing through the needling machine if the quality inspection is passed, to obtain a needling effect video;

[0061] An image processing module is configured to extract frames from the acupuncture effect video at a first time interval to obtain a plurality of first acupuncture effect images; and pre-process the acupuncture effect images to obtain standard acupuncture effect images;

[0062] a model classification module for inputting the standard acupuncture effect image into a trained needle state classification model for classification into normal production images, blunt needle production images, and damaged needle production images; the needle state classification model is trained based on historical production data;

[0063] a quantity calculation module, configured to calculate a first quantity if the blunt needle production image is identified; the first quantity being the total number of the blunt needle production images identified within a specified time; and to calculate a second quantity if the damaged needle production image is identified; the second quantity being the total number of the damaged needle production images identified within the specified time;

[0064] A control adjustment module is configured to identify the blunt needle stage of the blunt needle production image when the first quantity exceeds a first preset threshold value, and adjust the current parameters to the optimal control parameters of the corresponding stage according to the blunt needle stage; and replace the needles of the needling machine when the second quantity exceeds a second preset threshold value.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] 1. This invention proposes a fiber web quality assessment model that can, without affecting the normal operation of the production line, use a video of the needling raw material to obtain real-time information about the state of a uniform fiber web before it enters the needling machine. By performing real-time quality inspection on the needling raw material video, a reliable foundation is provided for the subsequent classification of standard needling effect images, eliminating the interference of external raw material factors on quality inspection. At the same time, the fiber web quality assessment model integrates an attention mechanism layer, which optimizes feature representation through channel attention and spatial attention mechanisms, enabling the model to automatically focus on important areas and key features in the fiber web image, thereby improving the model's sensitivity and accuracy to small defects and quality issues in the fiber web. Furthermore, the model introduces an anomaly detection layer, which uses an autoencoder to reconstruct the basic features of the fiber web and calculate the reconstruction error. This layer can accurately identify unseen abnormal samples, output anomaly warnings in a timely manner, and prevent abnormal data from affecting subsequent classification decisions. This not only improves detection accuracy but also enhances the robustness of the system, ensuring that any production issues can be quickly discovered and addressed. The present invention can realize efficient raw material quality inspection before the fiber web enters the needling machine, provides effective raw material guarantee, ensures the consistency and stability of the raw materials before needling, makes subsequent parameter adjustment more accurate, and helps to improve the stability of the overall product quality.

[0067] 2. By using the first time interval for rough inspection, potential blunt and damaged needle problems in the production process can be quickly screened without affecting production efficiency. When a blunt or damaged needle production image is identified during the rough inspection process, the corresponding video clip is further fine-framed at the second time interval to obtain more inspection samples, thereby conducting a more detailed analysis of the production status within that time period. This dual time interval design ensures a balance between inspection efficiency and accuracy; during preliminary screening, rough inspection can quickly identify potential problems, and when problems arise, fine inspection can provide higher inspection accuracy and sample quantity statistics to ensure that the problems can be accurately identified and quantified. By counting the number of blunt and damaged needle images, the system can quickly respond to changes in the status of production equipment and provide real-time feedback for subsequent adaptive control, thereby effectively improving the adaptive control capabilities of the production line.

[0068] 3. The control method for a nonwoven fabric production line proposed in this invention predicts needle wear and breaks down the needle blunting stage into early, mid, and late stages. This staged division enables more precise control of the production line, enabling targeted adjustments for different needle wear states and avoiding the problem of a single control strategy failing at different stages. Correlation analysis using historical data from the operations and maintenance database identifies key control parameters for each stage, and a regression model analyzes the relationship between control parameters and product quality, ensuring the scientific and rational selection of control parameters. Furthermore, by constructing a comprehensive objective function and employing an optimization algorithm to search for optimal control parameters, a balance between different control indicators is ensured, achieving overall optimization. This further improves the accuracy of production line control and the stability of product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A flow chart of a control method for a non-woven fabric production line provided by an embodiment of the present invention;

[0070] Figure 2 A schematic top view of the layout of various devices on a non-woven fabric production line provided by an embodiment of the present invention;

[0071] Figure 3 A structural diagram of a fiber web quality assessment model provided by an embodiment of the present invention;

[0072] Figure 4 This is a structural diagram of a control system for a non-woven fabric production line of the present invention.

[0073] In the figure: 1. Uniform fiber web before entering the needling machine; 2. First high-definition camera; 3. Laying device; 4. Needling machine; 5. Conveyor belt; 6. Uniform fiber web after entering the needling machine; 7. Second high-definition camera; 8. Winding device. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0075] Currently, nonwoven production lines in large factories are largely automated. Needle-punched nonwovens in existing factories typically use a high-speed needling process. The needle bar, a crucial component in the nonwoven needlepunch process, houses a large number of needles. The needle bar's upward and downward motion punctures the fiber web at a high frequency. This constant high-frequency puncturing inevitably accumulates wear on the needle bar, ultimately causing the needle punching results to deviate from the desired quality.

[0076] Existing automated production lines struggle to monitor needle status in real time, often requiring shutdowns for inspections, which significantly impacts the overall production efficiency of nonwovens. Existing methods rely primarily on the length of time needles have been in use to assess whether needle replacement is necessary. This approach lacks accurate assessment of actual wear and tear, making it impossible to identify needle wear or damage in a timely manner. This can lead to reduced product quality or premature equipment replacement, increasing production costs. Furthermore, the use-time assessment method cannot be dynamically adjusted based on actual operating conditions, nor can it cope with complex production environments and varying needle wear rates. This results in insufficient automation and flexibility in the production line, making it difficult to ensure production continuity and stability.

[0077] To this end, a control method and system for a non-woven fabric production line are proposed, which are illustrated by the following embodiments.

[0078] Example 1:

[0079] Company A, a company primarily engaged in the manufacture of industrial textile products and fabric processing, operates multiple production lines responsible for processing raw materials for needle-punched textiles. To improve the quality of its needle-punched nonwovens, Company A implemented a rigorous quality inspection process. Quality analysis and problem identification by the quality inspection department revealed that product quality issues primarily occurred within the needle-punching process. Issues such as needle wear and uneven needling impacted the stability and consistency of the final product. Consequently, Company A proposed and implemented a control method for its nonwoven production line, including:

[0080] See Figure 1 In S10, a video of a uniform fiber web on the working production line before entering the needling machine is collected to obtain a needling raw material video; a quality inspection is performed based on the needling raw material video; if the needling raw material fails the quality inspection, a production line alarm is triggered, prompting a check of the raw material status and suspension of production; current parameters of the needling stage of the working production line are preset standard control parameters; if the needling raw material passes the quality inspection, a video of the uniform fiber web on the working production line after passing through the needling machine is collected to obtain a needling effect video;

[0081] In this embodiment, other variables that may affect the image need to be strictly controlled during the production line. The quality and properties of the raw materials must be kept consistent to eliminate the impact of material changes on the image. The production line's environmental conditions (such as temperature, humidity, and light) need to be kept constant. This can be achieved by controlling environmental equipment such as thermostats, air flow control devices, and constant light source systems to prevent environmental factors from interfering with the image data. Furthermore, the key parameters of the equipment's operation should be maintained in a stable state.

[0082] Further, see Figure 2 , the video of the uniform fiber web 1 on the working production line before entering the needle loom 4 includes:

[0083] like Figure 2 As shown, the working production line runs from left to right, and the first high-definition camera 2 is installed directly above the conveyor belt 5 after the web laying device 3 and in front of the needling machine 4, and the shooting direction of the first high-definition camera 2 is vertically downward.

[0084] The first high-definition camera is installed in a fixed position and can stably capture the video of the uniform fiber web before it enters the needling machine, thereby realizing accurate monitoring of the state of the uniform fiber web before it enters the needling machine, and can obtain in real time the complete state image of the fiber web before entering the needling process; providing a high-quality data basis for subsequent quality inspection.

[0085] Furthermore, performing the quality inspection based on the acupuncture raw material video includes:

[0086] Extracting frames from the acupuncture raw material video at the first time interval to obtain a plurality of first acupuncture raw material images;

[0087] Preprocessing the acupuncture raw material image to obtain a standard acupuncture raw material image;

[0088] The standard needle-punched raw material image is input into a trained fiber web quality assessment model to obtain a quality inspection result; the quality inspection result includes qualified and unqualified.

[0089] By extracting frames at the first time interval, images can be extracted at fixed intervals for quality inspection without affecting production line speed. This ensures that the fiber web is monitored before entering the needle loom. This frame extraction method eliminates the need for frame-by-frame analysis of the entire video, significantly reducing computational effort and inspection time.

[0090] Furthermore, if Figure 3 As shown, the fiber web quality assessment model includes:

[0091] The input layer is used to receive the input image and perform preliminary feature representation processing;

[0092] A feature extraction layer, configured to extract key features of the input image and obtain basic features of the web, wherein the basic features of the web include texture features, edge features, uniformity features, and fiber distribution features of the web; the feature extraction layer comprises a plurality of convolutional layers and a plurality of pooling layers;

[0093] The multi-scale feature fusion layer is used to fuse the feature information of different scales from different convolutional layers and obtain multi-scale fusion features through convolution operations of different receptive fields;

[0094] An attention mechanism layer, which is used to optimize feature representation through a channel attention mechanism and a spatial attention mechanism; the channel attention mechanism is used to weight different feature channels to obtain weighted channel features, and the spatial attention mechanism is used to focus on key areas of the image to obtain weighted spatial features;

[0095] A feature fusion layer is used to fuse the weighted channel features and the weighted spatial features optimized by the channel attention mechanism and the spatial attention mechanism to obtain a final fused feature;

[0096] An anomaly detection layer, configured to detect anomalies on the final fused features; comprising an autoencoder module, configured to reconstruct the basic web features and calculate a reconstruction error; when the reconstruction error exceeds a preset threshold, the input image is judged to be abnormal and an abnormality warning message is directly output; if no abnormality is detected, quality classification is continued;

[0097] Specifically, the anomaly detection layer includes an autoencoder module for reconstructing the basic web features. First, the autoencoder module consists of an encoder and a decoder. The encoder compresses the basic web features into a low-dimensional feature representation, and the decoder reconstructs the compressed low-dimensional features to generate reconstructed web features. The reconstruction error between the original basic web features and the reconstructed web features is calculated. If the reconstruction error exceeds a preset anomaly threshold, the sample is judged to be anomaly and an anomaly warning message is directly output. If the reconstruction error does not exceed the preset anomaly threshold, the sample is considered normal and its features are further input into the classification layer for quality classification.

[0098] The classification layer is used to classify the final fusion features through the fully connected layer to obtain the quality inspection result.

[0099] Table 1. Quality inspection comparison experiment data table

[0100]

[0101] In order to verify the quality inspection effect of raw materials (uniform fiber mesh) based on the fiber mesh quality assessment model proposed in the present invention, a comparative experiment was designed to compare and analyze the defective rate in the production of needle-punched non-woven fabrics and the accuracy of raw material quality inspection through different raw material inspection methods. The experiment is divided into three groups. Experiment 1 uses the fiber mesh quality assessment model proposed in the present invention for quality inspection; Experiment 2 uses the traditional CNN two-classification model to detect the fiber mesh raw materials. The CNN two-classification model includes multiple convolutional layers, multiple pooling layers and a fully connected layer, and finally outputs a two-classification result (qualified or unqualified); Experiment 3 is a group that did not undergo quality inspection and is used for comparison. The subsequent processes of the three groups of experiments remain consistent, refer to Figure 1From S20 to S80, only the raw material inspection method in S10 is different.

[0102] Referring to Table 1, the quality inspection method based on the fiber web quality assessment model adopted in this embodiment can effectively reduce the defective rate of products, and the inspection accuracy is significantly higher than that of the traditional inspection model.

[0103] The present invention achieves efficient evaluation of fiber mesh quality by introducing a fiber mesh quality assessment model and combining it with a multi-layer structure design. The feature extraction layer obtains basic features of the fiber mesh, such as texture, edge, uniformity, and fiber distribution, through convolution layers and pooling layers, ensuring that subtle information of the fiber mesh structure is accurately extracted. The multi-scale feature fusion layer fuses information from different receptive fields through convolution operations of different scales, ensuring that the model is robust when processing features of different sizes and morphologies. The attention mechanism layer further optimizes feature representation through channel attention and spatial attention mechanisms, enabling the model to automatically focus on key areas and important features in the fiber mesh image, thereby improving the model's sensitivity and accuracy to fiber mesh defects and quality issues. The introduced anomaly detection layer reconstructs the basic features of the fiber mesh through an autoencoder module and calculates the reconstruction error to detect potential unseen abnormal samples. When the reconstruction error exceeds the preset threshold, an abnormality warning can be issued in a timely manner to prevent abnormal samples from affecting subsequent quality classification. The introduction of the fiber web quality assessment model not only improves the accuracy of fiber web quality detection, but also enhances the robustness of the system, ensuring the rapid discovery and handling of fiber web quality problems, laying the foundation for the subsequent needle status classification based on needle effect images, ensuring that the raw materials meet the standards, and preventing them from introducing additional interference that affects subsequent analysis, thereby improving the automation level of the production line and the consistency of products.

[0104] Further, see Figure 2 If the quality inspection is passed, the video of the uniform fiber web 6 on the working production line after passing through the needle loom 4 includes:

[0105] like Figure 2 As shown, the working production line runs from left to right, and the second high-definition camera 7 is installed just above the area 8 between the needling machine 4 and the winding device, and the shooting direction of the second high-definition camera 7 is vertically downward.

[0106] This video acquisition method ensures real-time monitoring of the final needling effect of the web after the needling process is complete. It helps accurately capture changes in the web's state after needling, particularly key quality indicators such as needle strength, fiber distribution, and web uniformity. Placing the camera between the needling machine and the winder prevents interference with subsequent web processing, allowing the system to promptly identify potential quality issues or process anomalies before the web is further processed or rolled up. This layout not only improves the accuracy of quality inspections but also provides timely warnings to prevent unqualified webs from entering the next production stage, thereby enhancing the overall quality control efficiency and automation level of the production line.

[0107] See Figure 1 In S20, the acupuncture effect video is framed at a first time interval to obtain a plurality of first acupuncture effect images. This method can flexibly adjust the monitoring interval according to the life cycle of the needle. For example, the first time interval is often longer in the early stage, which can save computing resources, while the first acupuncture effect images can be collected more frequently in the middle and late stages of the life cycle of the needle.

[0108] The acupuncture effect video is a continuous, uninterrupted monitoring video. Those skilled in the art can set the first time interval based on actual conditions. Generally, the first time interval is set larger in the early stages after the needle bank is replaced, and can be gradually reduced as the cumulative operating time increases. In this embodiment, the cumulative operating time of the needle bank is close to its expected lifespan, so the first time interval is set to 1 hour.

[0109] See Figure 1 In S30, pre-processing the acupuncture effect image to obtain a standard acupuncture effect image;

[0110] See Figure 1 In S40, the standard acupuncture effect image is input into a trained needle state classification model to obtain a predicted needle wear amount, and then classified according to the predicted wear amount into normal production images (0≤predicted needle wear amount<30%), blunt needle production images (30%≤predicted needle wear amount≤70%), and damaged needle production images (70%<predicted needle wear amount≤100%); the needle state classification model is trained based on historical production data;

[0111] Furthermore, the acquisition of the historical production data includes:

[0112] The historical production data includes historical acupuncture effect images and historical annotation data in different states; the historical annotation data includes needle state annotations corresponding to the historical acupuncture effect images; the different states include normal operation state, blunt needle state and damaged needle state;

[0113] acquiring the historical acupuncture effect images and the historical annotation data in the normal operating state, the blunt needle state, and the damaged needle state from an operation and maintenance database, respectively; the operation and maintenance database records the historical needle working condition images corresponding to the historical acupuncture effect images;

[0114] The acquisition of the historical annotation data includes:

[0115] Acquire a standard working condition image of the needle, wherein the standard working condition image of the needle is acquired after the needle is replaced as a whole but before it starts working;

[0116] Calculating the average wear of the needles by analyzing the historical working condition image of the needles and the standard working condition image of the needles;

[0117] The historical acupuncture effect images are annotated according to the average wear amount of the needles to obtain the historical annotated data.

[0118] By acquiring and analyzing historical production data under different conditions, including historical acupuncture effect images and corresponding historical annotation data, the present invention can provide an accurate reference and optimization basis for the real-time production process of the current production line. By extracting historical images and annotation data of normal operating conditions, blunt needle conditions, and damaged needle conditions from the operation and maintenance database, and combining them with standard working condition images after needle replacement, the average wear of the needles can be accurately calculated. This helps to make intelligent judgments and predictions about the current state of needles in production based on historical data, thereby identifying potential equipment problems in advance and avoiding the limitations of traditional maintenance that relies on fixed time periods. Through the annotation and analysis of such historical data, the system can predict the actual wear of the needles based on the acupuncture effect images, and adaptively adjust the current production parameters or directly replace the needles based on the predicted wear of the needles, thereby improving the real-time monitoring capability and response speed of the production line, ensuring the stability of the acupuncture process and the consistency of product quality. At the same time, this intelligent analysis based on historical data provides an important reference for preventive maintenance, extending the service life of the equipment and reducing the risk of downtime.

[0119] Furthermore, inputting the standard acupuncture effect image into the trained acupuncture state classification model for classification includes:

[0120] The standard acupuncture effect image is input into the trained needle state classification model to obtain the predicted needle wear amount. According to the predicted needle wear amount, the standard acupuncture effect image is divided into the normal production image, the blunt needle production image and the damaged needle production image.

[0121] The present invention realizes intelligent classification and prediction of needle wear status by inputting standard acupuncture effect images into a trained needle state classification model. The predicted needle wear amount output by the model can accurately divide the acupuncture effect images into normal production images, blunt needle production images, and damaged needle production images. Through the automated classification of needle status, the different wear stages of needles can be identified in a timely manner without the need for downtime inspection, avoiding the lag and inaccuracy of downtime inspection and empirical judgment. When the needle wear reaches the passivation or damage state, the corresponding maintenance or replacement operation can be automatically triggered, thereby ensuring the continuity of the production process and the stability of product quality. In addition, this model-based classification method can significantly reduce the frequency of downtime inspections, improve the degree of automation of the production line, extend the service life of the needles, and optimize the overall efficiency of the production process.

[0122] See Figure 1 In S50, if the blunt needle production image is recognized, a first number is calculated; the first number is the total number of the blunt needle production images recognized within a specified time;

[0123] See Figure 1 In S60, if the damaged needle production image is identified, a second number is calculated; the second number is the total number of the damaged needle production images identified within the specified time;

[0124] Furthermore, the process of obtaining the first quantity and the second quantity includes:

[0125] When the blunt needle production image is identified, a blunt needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image; the blunt needle effect video clip is framed at a second time interval to obtain a plurality of second acupuncture effect images; the first time interval is greater than the second time interval;

[0126] Counting the number of the blunt needle production images in all the second acupuncture effect images to obtain the first number;

[0127] When the damaged needle production image is identified, a damaged needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image;

[0128] Extracting frames from the damaged needle effect video clip at the second time interval to obtain a plurality of third acupuncture effect images;

[0129] The second number is obtained by counting the number of the blunt needle production images in all the third acupuncture effect images.

[0130] The present invention further obtains video clips within the corresponding time period by identifying the production images of blunt needles and damaged needles, and performs frame extraction processing according to a smaller second time interval, thereby generating more acupuncture effect images for analysis. By finely extracting frames from the key time period, more production effect images of the production process within this time period (the time period where problems may exist) can be accurately captured. Compared to the original larger first time interval, the second time interval provides a higher time resolution, can generate a large number of test samples, improve the accuracy of problem identification, and reduce errors caused by inaccurate classification of a single sample. By increasing the number of samples, random fluctuations in the data can be effectively smoothed, reducing the impact of abnormalities or classification errors in a certain sample on the overall test results.

[0131] See Figure 1 In S70, when the first number exceeds a first preset threshold, identifying the blunt needle stage of the blunt needle production image, and adjusting the current parameter to the optimal control parameter of the corresponding stage according to the blunt needle stage;

[0132] In this embodiment, one day, during the continuous monitoring of the production line, a video of the acupuncture effect is obtained and frames are extracted on an hourly basis to obtain multiple first acupuncture effect images; among the multiple first acupuncture effect images, a certain image is identified as a blunt needle production image, and at this time, a blunt needle effect video clip within one hour before and after is obtained based on the timestamp of the image; that is, if the timestamp of the blunt needle production image is 19:00 on October 23, 2024, the time range of the video clip is from 18:00 on October 23, 2024 to 22:00 on October 23, 2024.

[0133] Those skilled in the art can set the second time interval according to specific circumstances. In this embodiment, the second time interval is 10 minutes.

[0134] The video clips were framed at 10-minute intervals to obtain 12 images of the second acupuncture effect;

[0135] The 12 second acupuncture effect images are sequentially input into the trained needle state classification model for classification, and are classified into normal production images, blunt needle production images, and damaged needle production images. After statistical analysis, 10 blunt needle production images, 1 normal production image, and 1 blunt needle production image are ultimately obtained. The first number is 10. In this embodiment, the first preset threshold is 5. Therefore, the first number exceeds the first preset threshold. Subsequently, the blunt needle stage is identified based on these 10 blunt needle production images, and the current parameters are adjusted to the optimal control parameters for the corresponding stage based on the identified blunt needle stage.

[0136] Furthermore, the process of obtaining the optimal control parameters in the stage includes:

[0137] Based on the predicted needle wear, the blunt needle stage of the blunt needle production image is identified; the blunt needle stage includes an initial stage, a middle stage, and a late stage; the state of the needle is expressed as a percentage (30% to 70%), from initial wear to late wear. The blunt needle stage includes an initial stage (30% ≤ predicted needle wear < 50%), a middle stage (50% ≤ predicted needle wear < 60%), and a late stage (60% ≤ predicted needle wear ≤ 70%).

[0138] The control parameters and final product quality indicators corresponding to the initial stage, mid-term stage and late stage are respectively obtained from the operation and maintenance database to obtain initial product data, mid-term product data and late product data; the final product quality indicator is a comprehensive evaluation indicator of key quality parameters obtained after testing by the quality inspection department.

[0139] Identifying key control parameters in the initial product data, the mid-term product data, and the late product data through correlation analysis, wherein the key control parameters include needling speed, needling pressure, needling frequency, web tension, and feed speed, and obtaining the initial key control parameters, the mid-term key control parameters, and the late key control parameters;

[0140] For each stage, a regression model is constructed to analyze the relationship between the key control parameters of the stage and the quality indicators of the final product, thereby obtaining an initial regression model, a mid-term regression model, and a late-stage regression model;

[0141] Construct a comprehensive objective function J x :

[0142] J x =α·(q(x)-q target ) 2 +β·(t v +t p +t f +t T +t s );

[0143] Where: (q(x)-q target ) 2 is the quality index q(x) and the target product quality value q target The deviation between them, x represents the vector of control parameters, including needling speed v, needling pressure p, needling frequency f, web tension T and feeding speed s, α is the first weight, β is the second weight, t v To adjust the downtime caused by the needling speed v, t p To adjust the downtime caused by the needling pressure p, t f To adjust the downtime caused by the acupuncture frequency f, t T To adjust the downtime caused by the web tension T, ts It is the downtime caused by adjusting the feed speed s; if the needling speed, needling pressure, needling frequency, web tension and feed speed do not need to be adjusted, the corresponding downtime is 0.

[0144] The following constraints are constructed to ensure that each key control parameter is within the specified range:

[0145]

[0146] Among them, v min is the lower limit of acupuncture speed, v max is the upper limit of acupuncture speed, p min is the lower limit of acupuncture pressure, p max is the upper limit of acupuncture pressure, f min is the lower limit of acupuncture frequency, f max is the upper limit of acupuncture frequency, T min is the lower limit of web tension, T max is the upper limit of web tension, s min is the lower limit of feed rate, s max is the upper limit of feed speed,

[0147] Minimize the comprehensive objective function J x .

[0148] By using the initial regression model, the mid-term regression model and the late-term regression model to predict the effects of different control parameter combinations, the optimal control parameters of each stage are searched through the optimization algorithm to obtain the initial optimal control parameters, the mid-term optimal control parameters and the late-term optimal control parameters.

[0149] The present invention subdivides the blunt needle stage into three stages: early, middle and late stages based on the prediction of needle wear, and constructs a regression model according to actual production data in each stage, thereby realizing dynamic adjustment of key control parameters (such as needling speed, needling pressure, etc.) at different stages. By optimizing the key control parameters of each stage, it is ensured that the needles can maintain optimal process control at different wear stages during the production process, thereby ensuring the stability of product quality. In addition, the constructed comprehensive objective function not only takes into account the deviation between the product quality index and the target value, but also introduces the downtime factor related to the adjustment of the control parameters. The parameter combination of each stage is searched through the optimization algorithm, which improves the efficiency of obtaining the optimal parameters. This parameter optimization method can extend the service life of the needles while ensuring product quality, reduce unnecessary downtime, improve the overall automation and stability of the production line, and ultimately improve product consistency and production efficiency.

[0150] See Figure 1 In S80, when the second number exceeds a second preset threshold, the needles of the needling machine are replaced.

[0151] To verify the effectiveness of the control method for a nonwoven fabric production line, several comparative experiments were designed. Each production line had the same initial needle bar (a newly replaced bar) and underwent continuous production for the same period of time. Except for the needling process, all other control parameters and environmental parameters (workshop temperature and humidity) were identical. Referring to Table 2, Experiment A illustrates a control method for a nonwoven fabric production line proposed in this embodiment. Through real-time monitoring of the production line and detection of needling effect images, this method enables precise identification of needle status and adaptive parameter adjustment. This method optimizes needle lifecycles without compromising production efficiency, thereby reducing downtime, extending needle bar life, and maximizing production line efficiency. Experiment B relies on a fixed cumulative needle usage time to determine needle replacement cycles, disregarding actual wear. While simple to operate, this method often results in premature or delayed needle replacement. Results show that this method results in prolonged downtime, shortens needle bar life, and compromises production efficiency. Experiment C utilizes computer vision technology to capture needle bar images in real time and calculate needle wear through image analysis. Needle bar replacement is initiated when the real-time wear reaches a threshold. While Experiment C provided a certain degree of accuracy, it required frequent downtime for testing, impacting overall production efficiency. While the needle bank lifespan was improved, the excessive downtime significantly increased maintenance time, thereby reducing the yield of standard products. This comparative experiment concluded that the nonwoven production line control method proposed in this invention outperformed existing testing methods in terms of increasing standard product output, reducing downtime, and extending needle bank lifespan.

[0152] Table 2. Comparative experimental data of different needle status recognition methods

[0153]

[0154] Furthermore, in order to verify the effectiveness of the control parameter adjustment method, another set of comparative experiments was designed. Except for the different control parameter adjustment methods, the rest of the steps of Experiment 1, Experiment 2 and Experiment 3 are the same. Figure 1 ,Experiments 1, 2, and 3 differ only in the current parameter adjustment step in S70 (different control parameter adjustment strategies).

[0155] Experiment 1 is a control method based on the optimization of the optimal control parameters in stages proposed by the present invention. It adopts stage-by-stage control parameter adjustment. By identifying the blunt needle stage of the blunt needle production image, according to historical data, each blunt needle stage (early, middle and late) corresponds to a set of optimal parameter adjustment data corresponding to the current stage, and the production parameters can be dynamically adjusted at each stage. Experiment 1 adopts the following method: Figure 1 The complete method flow is shown.

[0156] See Figure 1S40 in Experiment 1 is classified according to the predicted wear amount, which is divided into normal production images (0≤needle predicted wear amount <30%), blunt needle production images (30%≤needle predicted wear amount ≤70%), and damaged needle production images (70%<needle predicted wear amount ≤100%); the blunt needle stage in subsequent Experiments 2 and 3 is also divided according to the same wear amount standard.

[0157] Experiment 2 is a traditional method based on fixed control parameters. Historical production data is filtered from the operation and maintenance database based on a specified needle wear range (30% ≤ needle wear ≤ 70%) corresponding to the blunt needle stage, generating filtered historical data. Fixed control parameters are obtained by combining the optimal control parameters from the filtered historical data. These fixed values ​​are fixed and do not change with the current production line conditions. When the first value exceeds a first preset threshold, the current parameters are adjusted to the fixed control parameters obtained from the filtered historical data.

[0158] Experiment 3 is a control method based on the optimization of the optimal control parameters of the overall blunt needle stage. The specific design process is as follows:

[0159] The control parameters corresponding to the specified needle wear range (30% ≤ needle wear ≤ 70%) and the final product quality indicators (without distinguishing between the early, middle and late stages of blunt needles) are obtained from the operation and maintenance database to obtain blunt needle product data; the final product quality indicators are comprehensive evaluation indicators of key quality parameters obtained after testing by the quality inspection department.

[0160] Identify key control parameters in the blunt needle product data through correlation analysis, including needling speed, needling pressure, needling frequency, web tension, and feed speed, and obtain a set of key control parameters;

[0161] Constructing a regression model to analyze the relationship between key control parameters and the final product quality indicators to obtain a blunt needle regression model (without distinguishing between early blunt needle, middle blunt needle and late blunt needle);

[0162] Starting with the construction of a comprehensive objective function, the subsequent steps are the same as those in Method 1. Specifically, using the constructed comprehensive objective function, key control parameters are optimized, a regression model is used to predict the effects of different control parameter combinations, and an optimization algorithm is used to search for the optimal control parameters. Ultimately, when the first quantity exceeds a first preset threshold, the current parameters are adjusted to the optimal control parameters. This optimal control parameter is based on the overall blunt needle stage, rather than the optimal control parameters for the sub-stages of the blunt needle stage (early blunt needle, mid-blunt needle, and late blunt needle).

[0163] Table 3. Control parameter adjustment comparison experiment data table

[0164]

[0165] Table 3 shows the comparative experimental results of different control parameter adjustment methods. Experiment 1 performed three parameter adjustments during the blunt needle stage. For each identified stage, the production line control parameters were adjusted to the optimal control parameters for the initial, mid-term, and final stages, respectively. Experiments 2 and 3, on the other hand, performed only one parameter adjustment, and their product qualification rates were lower than those of Experiment 1.

[0166] The present invention collects needling raw material videos and needling effect videos in real time, and combines them with a trained needle state classification model to ensure that the uniform fiber web meets the quality requirements, focusing on the key link of needling, thereby achieving real-time monitoring of the needle state in the needling production process. By extracting frames of the needling effect images at a first time interval and classifying them, it is possible to accurately identify the production images of blunt needles and damaged needles, and automatically adjust the control parameters or trigger needle replacement based on the relationship between the first quantity and the second quantity and the preset threshold. This production line control method avoids the lag of traditional methods that rely on the accumulated use time of needles or manual inspections, and greatly improves the automation level and response speed of the production line. By dynamically adjusting the production control parameters at the blunt needle stage, it is possible to maintain consistency in product quality at different wear stages, reduce unnecessary downtime and losses, extend the service life of the needles, and ensure production efficiency and the stability of the final product.

[0167] Example 2:

[0168] Company B is a manufacturer of non-woven fabrics. It has an automated non-woven production line. To further improve product quality, Company B has applied a control system for the non-woven production line. Figure 4 Shown include:

[0169] The raw material video acquisition module is used to collect the video of the uniform fiber web on the working production line before entering the needling machine to obtain the needling raw material video; the current parameters of the needling stage of the working production line are the preset standard control parameters;

[0170] A raw material quality inspection module is used to perform quality inspection based on the acupuncture raw material video. If the raw material fails the quality inspection, a production line warning is triggered;

[0171] A needling effect video acquisition module is configured to acquire a video of the uniform fiber web on the production line passing through the needling machine if the quality inspection is passed, to obtain a needling effect video;

[0172] An image processing module is configured to extract frames from the acupuncture effect video at a first time interval to obtain a plurality of first acupuncture effect images; and pre-process the acupuncture effect images to obtain standard acupuncture effect images;

[0173] a model classification module for inputting the standard acupuncture effect image into a trained needle state classification model for classification into normal production images, blunt needle production images, and damaged needle production images; the needle state classification model is trained based on historical production data;

[0174] a quantity calculation module, configured to calculate a first quantity if the blunt needle production image is identified; the first quantity being the total number of the blunt needle production images identified within a specified time; and to calculate a second quantity if the damaged needle production image is identified; the second quantity being the total number of the damaged needle production images identified within the specified time;

[0175] A control adjustment module is configured to identify the blunt needle stage of the blunt needle production image when the first quantity exceeds a first preset threshold value, and adjust the current parameters to the optimal control parameters of the corresponding stage according to the blunt needle stage; and replace the needles of the needling machine when the second quantity exceeds a second preset threshold value.

[0176] Furthermore, performing the quality inspection based on the acupuncture raw material video includes:

[0177] Extracting frames from the acupuncture raw material video at the first time interval to obtain a plurality of first acupuncture raw material images;

[0178] Preprocessing the acupuncture raw material image to obtain a standard acupuncture raw material image;

[0179] The standard needle-punched raw material image is input into a trained fiber web quality assessment model to obtain a quality inspection result; the quality inspection result includes qualified and unqualified.

[0180] Furthermore, the web quality assessment model includes:

[0181] The input layer is used to receive the input image and perform preliminary feature representation processing;

[0182] A feature extraction layer, configured to extract key features of the input image and obtain basic features of the web, wherein the basic features of the web include texture features, edge features, uniformity features, and fiber distribution features of the web; the feature extraction layer comprises a plurality of convolutional layers and a plurality of pooling layers;

[0183] The multi-scale feature fusion layer is used to fuse the feature information of different scales from different convolutional layers and obtain multi-scale fusion features through convolution operations of different receptive fields;

[0184] An attention mechanism layer, which is used to optimize feature representation through a channel attention mechanism and a spatial attention mechanism; the channel attention mechanism is used to weight different feature channels to obtain weighted channel features, and the spatial attention mechanism is used to focus on key areas of the image to obtain weighted spatial features;

[0185] A feature fusion layer is used to fuse the weighted channel features and the weighted spatial features optimized by the channel attention mechanism and the spatial attention mechanism to obtain a final fused feature;

[0186] An anomaly detection layer, configured to detect anomalies on the final fused features; comprising an autoencoder module, configured to reconstruct the basic web features and calculate a reconstruction error; when the reconstruction error exceeds a preset threshold, the input image is judged to be abnormal and an abnormality warning message is directly output; if no abnormality is detected, quality classification is continued;

[0187] Specifically, the anomaly detection layer includes an autoencoder module for reconstructing the basic web features. First, the autoencoder module consists of an encoder and a decoder. The encoder compresses the basic web features into a low-dimensional feature representation, and the decoder reconstructs the compressed low-dimensional features to generate reconstructed web features. The reconstruction error between the original basic web features and the reconstructed web features is calculated. If the reconstruction error exceeds a preset anomaly threshold, the sample is judged to be anomaly and an anomaly warning message is directly output. If the reconstruction error does not exceed the preset anomaly threshold, the sample is considered normal and its features are further input into the classification layer for quality classification.

[0188] The classification layer is used to classify the final fusion features through the fully connected layer to obtain the quality inspection result.

[0189] Specifically, the input layer receives image data and performs preliminary processing, followed by three sets of convolutional and pooling layers to extract key features of the fiber mesh. The first convolutional layer uses 64 3x3 convolution kernels and outputs a feature map through the ReLU activation function. After the first pooling, the size of the feature map is halved. The second convolutional and pooling layers then further extract and downsample the feature map, using 128 convolution kernels for feature extraction. The third convolutional layer uses 256 convolution kernels. Finally, after three pooling cycles, a 32×32×256 feature map is obtained.

[0190] Furthermore, if the quality inspection is passed, collecting a video of the uniform fiber web on the working production line after it passes through the needling machine includes:

[0191] A second high-definition camera is installed just above the area between the needle loom and the winding device, with the shooting direction of the second high-definition camera vertically downward.

[0192] Furthermore, the process of obtaining the first quantity and the second quantity includes:

[0193] When the blunt needle production image is identified, a blunt needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image; the blunt needle effect video clip is framed at a second time interval to obtain a plurality of second acupuncture effect images; the first time interval is greater than the second time interval;

[0194] Counting the number of the blunt needle production images in all the second acupuncture effect images to obtain the first number;

[0195] When the damaged needle production image is identified, a damaged needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image;

[0196] Extracting frames from the damaged needle effect video clip at the second time interval to obtain a plurality of third acupuncture effect images;

[0197] The second number is obtained by counting the number of the blunt needle production images in all the third acupuncture effect images.

[0198] Furthermore, the acquisition of the historical production data includes:

[0199] The historical production data includes historical acupuncture effect images and historical annotation data in different states; the historical annotation data includes needle state annotations corresponding to the historical acupuncture effect images; the different states include normal operation state, blunt needle state and damaged needle state;

[0200] acquiring the historical acupuncture effect images and the historical annotation data in the normal operating state, the blunt needle state, and the damaged needle state from an operation and maintenance database, respectively; the operation and maintenance database records the historical needle working condition images corresponding to the historical acupuncture effect images;

[0201] The acquisition of the historical annotation data includes:

[0202] Acquire a standard working condition image of the needle, wherein the standard working condition image of the needle is acquired after the needle is replaced as a whole but before it starts working;

[0203] Calculating the average wear of the needles by analyzing the historical working condition image of the needles and the standard working condition image of the needles;

[0204] The historical acupuncture effect images are annotated according to the average wear amount of the needles to obtain the historical annotated data.

[0205] Furthermore, inputting the standard acupuncture effect image into the trained acupuncture state classification model for classification includes:

[0206] The standard acupuncture effect image is input into the trained needle state classification model to obtain the predicted needle wear amount. According to the predicted needle wear amount, the standard acupuncture effect image is divided into the normal production image, the blunt needle production image and the damaged needle production image.

[0207] Furthermore, the process of obtaining the optimal control parameters in the stage includes:

[0208] Identifying the blunt needle stage of the blunt needle production image according to the predicted needle wear amount; the blunt needle stage includes an early stage, a middle stage, and a late stage;

[0209] Obtaining control parameters and final product quality indicators corresponding to the initial stage, mid-stage, and late stage from the operation and maintenance database, respectively, to obtain initial product data, mid-stage product data, and late product data;

[0210] Identifying the key control parameters of the initial product data, the mid-term product data, and the late product data through correlation analysis to obtain the key control parameters of the initial product data, the mid-term product data, and the late product data;

[0211] For each stage, a regression model is constructed to analyze the relationship between the key control parameters of the stage and the quality indicators of the final product, thereby obtaining an initial regression model, a mid-term regression model, and a late-stage regression model;

[0212] Construct a comprehensive objective function;

[0213] By using the initial regression model, the mid-term regression model and the late-term regression model to predict the effects of different control parameter combinations, the optimal control parameters of each stage are searched through the optimization algorithm to obtain the initial optimal control parameters, the mid-term optimal control parameters and the late-term optimal control parameters.

[0214] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A control method for a nonwoven fabric production line, characterized in that: include: Collect the video of the uniform fiber web on the production line before it enters the needle loom to obtain the video of the needle-punched raw material; A quality inspection is performed based on the video of the needle-punched raw material. If the video fails the quality inspection, a production line warning is triggered. The quality inspection includes inputting the image of the needle-punched raw material into a fiber web quality assessment model. The fiber web quality assessment model includes an autoencoder module for reconstructing basic features of the fiber web and calculating a reconstruction error. When the reconstruction error exceeds a preset threshold, the image of the needle-punched raw material is judged to be abnormal. If the video passes the quality inspection, a video of the uniform fiber web on the working production line after passing through the needling machine is collected to obtain a video of the needling effect. The current parameters of the needling stage of the working production line are preset standard control parameters. Extracting frames from the acupuncture effect video at a first time interval to obtain a plurality of first acupuncture effect images; preprocessing the acupuncture effect image to obtain a standard acupuncture effect image; Inputting the standard acupuncture effect image into a trained needle state classification model for classification into normal production images, blunt needle production images, and damaged needle production images; the needle state classification model is trained based on historical production data; If the blunt needle production image is identified, a first number is calculated; the first number is the total number of the blunt needle production images identified within a specified time; If the damaged needle production image is identified, a second number is calculated; the second number is the total number of the damaged needle production images identified within the specified time; When the first number exceeds a first preset threshold, identifying the blunt needle stage of the blunt needle production image, and identifying the blunt needle stage of the blunt needle production image based on the predicted needle wear amount; the blunt needle stage includes an early stage, a middle stage, and a late stage; according to the blunt needle stage, adjusting the current parameter to the corresponding stage optimal control parameter; obtaining the stage optimal control parameter is achieved by constructing and minimizing a comprehensive objective function; When the second number exceeds a second preset threshold, the needles of the needling machine are replaced.

2. The control method for a nonwoven fabric production line according to claim 1, characterized in that: The video of collecting the uniform fiber web on the working production line before entering the needle loom includes: The first high-definition camera is installed behind the web laying device and just above the conveyor belt in front of the needle loom, with the shooting direction of the first high-definition camera vertically downward.

3. The control method for a nonwoven fabric production line according to claim 1, characterized in that: The quality inspection based on the acupuncture raw material video includes: Extracting frames from the acupuncture raw material video at the first time interval to obtain a plurality of first acupuncture raw material images; Preprocessing the acupuncture raw material image to obtain a standard acupuncture raw material image; The standard needle-punched raw material image is input into a trained fiber web quality assessment model to obtain a quality inspection result; the quality inspection result includes qualified and unqualified.

4. The control method for a nonwoven fabric production line according to claim 3, characterized in that: The web quality assessment model includes: The input layer is used to receive the input image and perform preliminary feature representation processing; A feature extraction layer, configured to extract key features of the input image to obtain basic features of the web, wherein the basic features of the web include texture features, edge features, uniformity features, and fiber distribution features of the web; the feature extraction layer comprises a plurality of convolutional layers and a plurality of pooling layers; The multi-scale feature fusion layer is used to fuse the feature information of different scales from different convolutional layers and obtain multi-scale fusion features through convolution operations of different receptive fields; An attention mechanism layer, which is used to optimize feature representation through a channel attention mechanism and a spatial attention mechanism; the channel attention mechanism is used to weight different feature channels to obtain weighted channel features, and the spatial attention mechanism is used to focus on key areas of the image to obtain weighted spatial features; A feature fusion layer is used to fuse the weighted channel features and the weighted spatial features optimized by the channel attention mechanism and the spatial attention mechanism to obtain a final fused feature; An anomaly detection layer, configured to detect anomalies on the final fused features; comprising an autoencoder module, configured to reconstruct the basic web features and calculate a reconstruction error; when the reconstruction error exceeds a preset threshold, the input image is judged to be abnormal and an abnormality warning message is directly output; if no abnormality is detected, quality classification is continued; The classification layer is used to classify the final fusion features through the fully connected layer to obtain the quality inspection result.

5. The control method for a nonwoven fabric production line according to claim 1, characterized in that: If the quality inspection is passed, collecting a video of the uniform fiber web on the production line after it passes through the needling machine includes: A second high-definition camera is installed just above the area between the needle loom and the winding device, with the shooting direction of the second high-definition camera vertically downward.

6. The control method for a nonwoven fabric production line according to claim 1, characterized in that: The process of obtaining the first quantity and the second quantity includes: When the blunt needle production image is identified, a blunt needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image; the blunt needle effect video clip is framed at a second time interval to obtain a plurality of second acupuncture effect images; the first time interval is greater than the second time interval; Counting the number of the blunt needle production images in all the second acupuncture effect images to obtain the first number; When the damaged needle production image is identified, a damaged needle effect video clip within the specified time period is obtained according to the timestamp of the blunt needle production image; Extracting frames from the damaged needle effect video clip at the second time interval to obtain a plurality of third acupuncture effect images; The second number is obtained by counting the number of the blunt needle production images in all the third acupuncture effect images.

7. The control method for a nonwoven fabric production line according to claim 1, characterized in that: The acquisition of the historical production data includes: The historical production data includes historical acupuncture effect images and historical annotation data in different states; the historical annotation data includes needle state annotations corresponding to the historical acupuncture effect images; the different states include normal operation state, blunt needle state and damaged needle state; acquiring the historical acupuncture effect images and the historical annotation data in the normal operating state, the blunt needle state, and the damaged needle state from an operation and maintenance database, respectively; the operation and maintenance database records the historical needle working condition images corresponding to the historical acupuncture effect images; The acquisition of the historical annotation data includes: Acquire a standard working condition image of the needle, wherein the standard working condition image of the needle is acquired after the needle is replaced as a whole but before it starts working; Calculating the average wear of the needles by analyzing the historical working condition image of the needles and the standard working condition image of the needles; The historical acupuncture effect images are annotated according to the average wear amount of the needles to obtain the historical annotated data.

8. The control method for a nonwoven fabric production line according to claim 1, characterized in that: Inputting the standard acupuncture effect image into the trained acupuncture state classification model for classification includes: The standard acupuncture effect image is input into the trained needle state classification model to obtain the predicted needle wear amount. According to the predicted needle wear amount, the standard acupuncture effect image is divided into the normal production image, the blunt needle production image and the damaged needle production image.

9. The control method for a nonwoven fabric production line according to claim 1, characterized in that: The process of obtaining the optimal control parameters in this stage includes: Identifying the blunt needle stage of the blunt needle production image according to the predicted needle wear amount; the blunt needle stage includes an early stage, a middle stage, and a late stage; Obtaining control parameters and final product quality indicators corresponding to the initial stage, mid-stage, and late stage from the operation and maintenance database, respectively, to obtain initial product data, mid-stage product data, and late product data; Identifying the key control parameters of the initial product data, the mid-term product data, and the late product data through correlation analysis to obtain the key control parameters of the initial product data, the mid-term product data, and the late product data; For each stage, a regression model is constructed to analyze the relationship between the key control parameters of the stage and the quality indicators of the final product, thereby obtaining an initial regression model, a mid-term regression model, and a late-stage regression model; Construct a comprehensive objective function; By using the initial regression model, the mid-term regression model and the late-term regression model to predict the effects of different control parameter combinations, the optimal control parameters of each stage are searched through the optimization algorithm to obtain the initial optimal control parameters, the mid-term optimal control parameters and the late-term optimal control parameters.

10. A control system for a non-woven fabric production line, characterized in that: Executing the method according to claim 1, comprising: The raw material video acquisition module is used to collect the video of the uniform fiber web on the working production line before entering the needling machine to obtain the needling raw material video; the current parameters of the needling stage of the working production line are the preset standard control parameters; A raw material quality inspection module is used to perform quality inspection based on the acupuncture raw material video. If the raw material fails the quality inspection, a production line warning is triggered; A needling effect video acquisition module is configured to acquire a video of the uniform fiber web on the production line passing through the needling machine if the quality inspection is passed, to obtain a needling effect video; An image processing module is configured to extract frames from the acupuncture effect video at a first time interval to obtain a plurality of first acupuncture effect images; and pre-process the acupuncture effect images to obtain standard acupuncture effect images; a model classification module for inputting the standard acupuncture effect image into a trained needle state classification model for classification into normal production images, blunt needle production images, and damaged needle production images; the needle state classification model is trained based on historical production data; a quantity calculation module, configured to calculate a first quantity if the blunt needle production image is identified; the first quantity being the total number of the blunt needle production images identified within a specified time period; and to calculate a second quantity if the damaged needle production image is identified; The second number is the total number of damaged needle production images identified within the specified time; A control adjustment module is configured to identify the blunt needle stage of the blunt needle production image when the first quantity exceeds a first preset threshold value, and adjust the current parameters to the optimal control parameters of the corresponding stage according to the blunt needle stage; and replace the needles of the needling machine when the second quantity exceeds a second preset threshold value.

Images