Superfine yarn non-inductive operation quality tracing method

Abstract

The invention provides a superfine yarn non-inductive operation quality tracing method, and relates to the technical field of intelligent management, and the method comprises the steps: in a wire drawing area, carrying out the automatic recognition and numbering of a wire cylinder and a wire cake on a wire drawing machine through a camera and a machine vision system; the variety produced by each wire drawing machine is bound with the machine vision system, and a visual bar code is printed on the spinning cake as a unique identifier of the spinning cake and corresponds to a serial number identified by the machine vision system; after wire drawing is completed, the spinning cake is conveyed to a twisting area through the transfer channel; a camera is installed in the transfer channel, and bar code information on the spinning cakes passing through the camera is recognized and recorded through the machine vision technology, so that tracking of the spinning cakes is not interrupted in the transfer process. According to the invention, each link in the production process can be accurately monitored, and rapid positioning and solving of problems are realized, so that the production efficiency and the product quality are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, in particular to a method for tracing the quality of ultra-fine yarn without any sense of operation. Background Art

[0002] Drawing, twisting, and packaging are core steps in yarn production, each playing an irreplaceable role. Drawing, as the starting point of the production process, lays the foundation for subsequent steps, directly impacting the smoothness of the entire production process. Twisting, in turn, plays a decisive role in determining the internal structure and strength of the yarn, ensuring that the final product meets performance standards. Packaging, as the direct interface between the product and the consumer, not only impacts the product's aesthetic appearance but also influences the customer's first impression and purchasing decision.

[0003] While traditional methods already include some traceability measures, they often have numerous flaws. For example, relying on paper records or simple spreadsheets for tracking is not only inefficient but also prone to errors and data loss. When problems arise at these critical links, some traditional traceability methods are unable to quickly and accurately pinpoint the source of the problem. If a batch of yarn is found to be substandard, a company may need to invest significant manpower and time to review and inspect each production step one by one. This approach clearly cannot meet the dual demands of efficiency and quality in modern production. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method for tracing the quality of ultra-fine yarn without any sense of operation, which can accurately monitor every link in the production process, quickly locate and solve problems, thereby effectively improving production efficiency and product quality.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows: In a first aspect, a method for tracing the quality of ultra-fine yarn without sensory operation is provided, the method comprising: In the wire drawing area, cameras and machine vision systems automatically identify and number the wire bobbins and cakes on the wire drawing machines. The variety produced by each wire drawing machine is linked to the machine vision system, and a visible barcode is printed on the cake as a unique identifier, corresponding to the number recognized by the machine vision system. After the yarn is drawn, the bobbins are transported to the twisting area through a transfer channel. Cameras are installed in the transfer channel, using machine vision technology to identify and record the barcode information on the bobbins passing through, ensuring uninterrupted tracking of the bobbins during the transfer process. In the twisting area, each twisting machine is equipped with a unique machine number, which is displayed in the form of a QR code. When the yarn cake arrives at the twisting area, a scanning device is used to scan the twisting machine's QR code and the yarn cake's barcode to bind the information. After twisting, the yarn is transported to the packaging area for inspection and packaging; the robotic arm in the packaging area identifies and grabs the bobbins with QR codes; the QR code scanning equipment in the packaging area scans and confirms the bobbins to be packaged, so that each step of the operation can be traced and the entire yarn production process can be managed in a digital way.

[0006] Furthermore, the wire bobbins and wire cakes on the wire drawing machine are automatically identified and numbered through cameras and machine vision systems, including: The camera is installed at a preset position on the wire drawing machine to capture images of the wire tube and wire cake on the wire drawing machine in real time through the camera; Preprocess the collected images and perform image segmentation to separate the silk bobbins and silk cakes from the background; Get a color image from the camera, and calculate the grayscale value of each pixel in the color image; Generate a grayscale image based on the grayscale value, and calculate the new value of each pixel through the convolution operation of the Gaussian function to obtain a Gaussian filtered image; The horizontal and vertical kernels of the Sobel operator are used to perform convolution operations on the Gaussian filtered image to obtain the horizontal and vertical gradient components of each pixel. For each pixel, the gradient magnitude is calculated according to the gradient components of each pixel in the horizontal and vertical directions to obtain a gradient image containing the gradient magnitude and direction of each pixel; Traverse the gradient image of the gradient magnitude and direction of each pixel point to identify and extract the continuous edge contours in the image; For each extracted contour, calculate the number of pixels on the contour, the curvature radius or curvature angle of each point on the contour, and the overall direction of the contour or the direction of each segment; The edge features of the silk tube and silk cake are screened out based on the number of pixels on the contour, the curvature radius or curvature angle of each point on the contour, and the overall direction of the contour or the direction of each segment; Identify the silk bobbin and silk cake in the image based on their edge features, and determine their positions and postures; Each identified bobbin and cake is assigned a unique number that is associated with the image, location, and time of the bobbin and cake.

[0007] Furthermore, a grayscale image is generated according to the grayscale value, and a Gaussian function is used to calculate a new value of each pixel through a convolution operation to obtain a Gaussian filtered image, including: Calculate the grayscale values ​​of all pixels to create a new image, in which the value of each pixel is a grayscale value, wherein the new image is a grayscale image; Define the Gaussian kernel, which is a two-dimensional matrix whose values ​​are calculated according to the Gaussian function; Starting from the upper left corner of the image, select the first pixel and multiply the first pixel and its surrounding pixels by the value of the corresponding position of the Gaussian kernel; align the center of the Gaussian kernel with the selected pixel and perform the following operations: Multiply the upper left corner value of the Gaussian kernel by the pixel value at the corresponding position in the image; Multiply the upper median value of the Gaussian kernel by the pixel value at the corresponding position in the image until all values ​​of the Gaussian kernel are multiplied by the pixel value at the corresponding position in the image. Add up all the products and the result is the new pixel value at the corresponding position in the filtered image. Move the Gaussian kernel one pixel to the right until the new values ​​of all pixels in the image are calculated, and use the calculated new pixel values ​​to create a new image. The new image is the image after Gaussian filtering.

[0008] Furthermore, the horizontal and vertical kernels of the Sobel operator are used to perform convolution operations on the Gaussian filtered image to obtain the horizontal and vertical gradient components of each pixel, including: Starting from the upper left corner of the image, select a pixel as the current processing point; cover the Sobel horizontal kernel on the current pixel and its surrounding pixels, and perform a convolution operation: Multiply the upper left corner element of the horizontal kernel by the value of the corresponding image pixel; multiply the upper middle element of the horizontal kernel by the value of the corresponding image pixel, and repeat this process until all elements of the horizontal kernel are multiplied by the corresponding image pixels; add all the products together to get the horizontal gradient component of the current pixel; Use Sobel's vertical kernel to perform convolution on the same pixel and its surrounding pixels: Multiply the upper left corner element of the vertical kernel by the value of the corresponding image pixel; multiply the upper middle element of the vertical kernel by the value of the corresponding image pixel, and repeat this process until all elements of the vertical kernel are multiplied by the corresponding image pixels. Add up all the products and the result is the gradient component of the current pixel in the vertical direction; Move the current processing point one pixel to the right until the gradient components of all pixels in the image in the horizontal and vertical directions are calculated; Generate a gradient component image based on the gradient components of all pixels in the image in the horizontal and vertical directions.

[0009] Furthermore, a camera is installed at a preset position on the wire drawing machine to capture images of the wire drum and wire cake on the wire drawing machine in real time through the camera, including: Determine the set of all potential locations where the camera can be installed. Location points are fixed points around the wire drawing machine. Define the properties of each location point, including coordinates and viewing angle range. Randomly select a portion of all potential locations as the ant's initial location; assign a memory table to each ant to record the locations it has visited and the corresponding pheromone concentrations; Determine the initial concentration and volatilization rate of pheromones, and each ant chooses the next location to move to based on the pheromone concentration and heuristic information around its current location; After a certain number of iterations, the final position is determined based on the memory tables and path evaluation results of all ants; The camera is installed according to the final position point, and the camera is used to capture the images of the wire tube and wire cake on the wire drawing machine in real time.

[0010] Furthermore, the variety produced by each wire drawing machine is bound to the machine vision system. A visible barcode is printed on the wire cake as a unique identifier of the wire cake, corresponding to the number recognized by the machine vision system, including: Assign a unique number to each wire drawing machine; Print the assigned number on the silk cake in the form of a barcode as a unique identifier of the silk cake; Establish a database or lookup table to store the corresponding relationship between varieties and numbers; The collected images are pre-processed using image processing technology, and the pre-processed images are scanned and analyzed to extract the numbering information on the silk cakes; According to the extracted number information, the corresponding variety information is searched, and the variety information and number information are bound together.

[0011] Furthermore, a unique number is assigned to each wire drawing machine to produce the product, including: Determine the basic rules for numbering, including the length of the number and the character set to be used; Obtain information on all types of wire drawing machines, including name, specifications and characteristics; The number of each variety is represented as a gene code. Based on the defined gene code, an initial population is randomly generated. Each individual in the population represents a number allocation scheme. Determine the fitness function used to evaluate the quality of each individual; According to the fitness function, the corresponding individuals are selected from the current population to enter the next generation, the selected individuals are crossover-operated to generate new individuals, and the newly generated individuals are mutated until the preset number of iterations is reached to obtain the final number allocation scheme; According to the final numbering allocation plan, a unique number is assigned to the variety produced by each wire drawing machine.

[0012] In a second aspect, a non-sensing operation quality tracing system for ultra-fine yarn is applied to the method described, comprising: The encoding module is used in the wire drawing area to automatically identify and number the wire bobbins and wire cakes on the wire drawing machine through the camera and machine vision system. The product produced by each wire drawing machine is linked to the machine vision system. A visible barcode is printed on the wire cake as a unique identifier, corresponding to the number recognized by the machine vision system. The tracking module is used to transport the bobbins to the twisting area through a transfer channel after the bobbins are drawn. A camera is installed in the transfer channel, which uses machine vision technology to identify and record the barcode information on the bobbins passing through, so that the bobbins can be tracked continuously during the transfer process. The scanning module is used in the twisting area. Each twisting machine is equipped with a unique machine number, which is displayed in the form of a QR code. When the yarn cake arrives at the twisting area, the scanning device is used to scan the QR code of the twisting machine and the barcode of the yarn cake to bind the information. The processing module is used to transport the yarn to the packaging area for inspection and packaging after twisting. The robotic arm in the packaging area identifies and grabs the bobbins with QR codes. The QR code scanning equipment in the packaging area scans and confirms the bobbins to be packaged, so that each step of the operation can be traced and the entire yarn production process can be managed in a digital way.

[0013] According to a third aspect, a computing device includes: one or more processors; The storage device is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method.

[0014] In a fourth aspect, a computer-readable storage medium stores a program, which implements the method when executed by a processor.

[0015] The above solution of the present invention includes at least the following beneficial effects.

[0016] By integrating machine vision, barcode, and QR code technologies, this invention enables comprehensive monitoring and data recording of every step in the yarn production process. This significantly enhances the transparency of the production process, making every operation traceable and helping companies identify and resolve problems promptly.

[0017] Automated identification and recording systems reduce manual errors and delays, improving production efficiency. Furthermore, by accurately tracking every step, production issues can be quickly identified and addressed, effectively improving product quality. Automated traceability systems reduce the need for manual inspection and record-keeping, thereby lowering labor costs. Furthermore, by reducing waste and rework during the production process, operating costs are further reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention provides a flow chart of a method for tracing the quality of ultra-fine yarn without any sensory operation.

[0019] Figure 2 It is a schematic diagram of a non-sensing operation quality tracing system for ultra-fine yarn provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0021] like Figure 1 As shown, an embodiment of the present invention provides a method for tracing the quality of ultra-fine yarn without sensory operation, the method comprising the following steps: Step 11: In the wire drawing area, the wire bobbins and wire cakes on the wire drawing machine are automatically identified and numbered using a camera and machine vision system. The variety produced by each wire drawing machine is linked to the machine vision system, and a visible barcode is printed on the wire cake as a unique identifier, corresponding to the number recognized by the machine vision system. Step 12: After the yarn is drawn, the bobbin is sent to the twisting area through a transfer channel. A camera is installed in the transfer channel, which uses machine vision technology to identify and record the barcode information on the passing bobbin, so that the bobbin can be tracked continuously during the transfer process. Step 13: In the twisting area, each twisting machine is equipped with a unique machine number, which is displayed in the form of a QR code. When the yarn cake arrives at the twisting area, a scanning device is used to scan the QR code of the twisting machine and the barcode of the yarn cake to bind the information. Step 14: After twisting, the yarn is transported to the packaging area for inspection and packaging. The robotic arm in the packaging area identifies and grabs the bobbin with the QR code. The QR code scanning device in the packaging area scans and confirms the bobbin to be packaged, so that each step of the operation can be traced and the entire yarn production process can be managed in a digital way.

[0022] In this embodiment of the present invention, step 11 automatically identifies and numbers the wire bobbins and cakes on the wire drawing machine using a camera and machine vision system, improving identification accuracy and efficiency while avoiding human error. Binding the product type produced by each wire drawing machine to the machine vision system ensures the consistency and traceability of production data. The visual barcode printed on the cake serves as a unique identifier, facilitating accurate tracking and management of the cakes in subsequent steps.

[0023] Step 12: Install a camera in the transfer channel and use machine vision technology to identify and record the barcode information on the silk cakes, achieving continuous tracking of the silk cakes during the transfer process and avoiding the loss or interruption of tracking information. This non-sensing tracking method reduces manual intervention and improves transfer efficiency and accuracy.

[0024] In step 13, each twisting machine is assigned a unique machine number, displayed as a QR code, facilitating quick identification and recording of information. Using a scanning device, the twisting machine's QR code and the yarn cake's barcode are scanned, automatically binding the information and ensuring the integrity and consistency of production data. This binding method facilitates accurate tracing and location of any subsequent production process issues.

[0025] In step 14, a robotic arm in the packaging area identifies and grabs the bobbins bearing the QR code, improving the automation of packaging and reducing the complexity and errors associated with manual operations. A QR code scanner in the packaging area scans and confirms the bobbins to be packaged, ensuring accuracy and traceability at every step. This streamlined management of the entire yarn production process improves production management efficiency and quality, helping companies identify and resolve problems promptly, and enhancing product quality and customer satisfaction.

[0026] In a preferred embodiment of the present invention, the above step 11, automatically identifying and numbering the wire drums and wire cakes on the wire drawing machine by using a camera and a machine vision system, may include: Step 111: Install a camera at a preset position on the wire drawing machine to capture images of the wire drum and wire cake on the wire drawing machine in real time through the camera; Step 112 pre-processes the captured image and performs image segmentation to separate the silk tube and the silk cake from the background. This specifically includes: obtaining a frame of image to be processed from the real-time video stream captured by the camera; if the captured image is a color image (e.g., in RGB format), converting it to a color space more suitable for image segmentation, such as the HSV (hue, saturation, value) color space, which is more suitable for image segmentation based on color information; setting one or more thresholds based on the color, brightness, and other characteristics of the silk tube and the silk cake; these thresholds are used to distinguish the silk tube and the silk cake from the background; applying a thresholding operation to convert the image into a binary image. In a binary image, pixels above the threshold are set to one value (e.g., white), and pixels below the threshold are set to another value (e.g., black). This clearly distinguishes the silk tube and the silk cake from the background; and performing morphological operations on the binary image, such as erosion, dilation, opening, or closing. These operations can remove noise, smooth edges, or fill holes, thereby improving the image segmentation effect; use contour detection algorithms (such as Canny edge detection or FindContours function) to identify continuous edges in the binary image, which correspond to the contours of silk tubes and silk cakes; filter out contours representing silk tubes and silk cakes based on the size, shape, or other characteristics of the contours. For example, the minimum and maximum values ​​of the contour area can be set to exclude contours that are too small or too large; generate a mask based on the filtered contours. The mask is a binary image of the same size as the original image, in which the positions of the silk tubes and silk cakes are marked white, and the rest are black; use the mask to perform pixel-by-pixel multiplication with the original image to extract the images of the silk tubes and silk cakes, thereby achieving image segmentation; Step 113, obtain a frame of color image from the camera, and calculate the grayscale value of each pixel in the color image, specifically including: obtaining a frame of color image from the camera device, which is accomplished by calling the camera API or using an image processing library (such as OpenCV); using a double loop to traverse each pixel of the image. The outer loop traverses the rows (height) of the image, and the inner loop traverses the columns (width) of the image; for each pixel, calculate the grayscale value based on its RGB value. Grayscaling is the process of converting a color image into a grayscale image, where the grayscale value represents the brightness information of the pixel. For example, a weighted average method is used, that is, different weights are assigned to the three components R, G, and B according to the sensitivity of the human eye to different colors, and then a weighted average is performed; the calculated grayscale value is assigned to the pixel, which means creating a new single-channel image (grayscale image) or modifying the original image in place to convert it into a grayscale image; Step 114, generating a grayscale image according to the grayscale value, and calculating a new value of each pixel by a Gaussian function through a convolution operation to obtain a Gaussian filtered image; Step 115, performing convolution operations on the Gaussian filtered image using the Sobel operator in the horizontal and vertical directions, respectively, to obtain the gradient components of each pixel in the horizontal and vertical directions; Step 116, for each pixel, calculate the gradient amplitude according to the gradient components of each pixel in the horizontal and vertical directions to obtain a gradient image containing the gradient amplitude and direction of each pixel, specifically including: creating a new image of the same size as the original grayscale image to store the gradient amplitude and direction of each pixel, this new image is a two-channel image, one channel is used to store the gradient amplitude, and the other channel is used to store the gradient direction; use a double loop to traverse each pixel of the grayscale image. The outer loop traverses the rows (height) of the image, and the inner loop traverses the columns (width) of the image; for the currently traversed pixel, calculate the gradient amplitude and direction according to its gradient components in the horizontal and vertical directions; the horizontal gradient component and the vertical gradient component are obtained by convolving the Sobel operator with the image. Calculate the gradient amplitude and gradient direction according to the horizontal gradient component and the vertical gradient component; Step 117, traverse the gradient image of the gradient amplitude and direction of each pixel point, identify and extract the continuous edge contours in the image, specifically including: preparing an empty contour list for storing the identified edge contours; setting a gradient amplitude threshold value for determining whether the pixel point belongs to the edge; using a double loop to traverse each pixel point of the gradient image, checking its gradient amplitude, if the gradient amplitude of the current pixel point is greater than the set threshold value, then the point is considered to be an edge point. For points identified as edges, use an edge tracking algorithm (such as the hysteresis threshold method and edge tracking in Canny edge detection) to connect adjacent edge points to form a continuous edge contour. A queue or stack data structure can be used to assist the tracking process, continuously adding adjacent edge points to the contour until no adjacent edge points can be found. Each time tracking is completed, the formed contour is added to the contour list. After the traversal is completed, the resulting contour list contains all the identified continuous edge contours in the image; Step 118, for each extracted contour, calculate the number of pixel points on the contour, the curvature radius or curvature angle of each point on the contour, the overall direction of the contour or the direction of each segment, specifically including: for each contour extracted in step 117, calculate its features; traverse each point on the contour, accumulate the number of points, and obtain the length of the contour; for each point on the contour, calculate the curvature based on its positional relationship with the adjacent points. The three-point method (the current point and its front and back adjacent points) can be used to estimate the curvature radius or curvature angle of the point. The curvature radius can be obtained by calculating the radius of the circle formed by the three points, and the curvature angle can be the angle between adjacent line segments. To calculate the overall direction of the contour or the direction of each segment, the main direction of the contour can be obtained by calculating the covariance matrix of the coordinates of all points on the contour; for the direction of each segment, the contour can be divided into several segments, and the direction of each segment uses the direction of the line connecting the starting point and the end point as the direction of the segment; Step 119 : Filter edge features of the bobbin and the cake based on the number of pixels on the contour, the curvature radius or curvature angle of each point on the contour, and the overall direction or the direction of each segment of the contour; identify the bobbin and the cake in the image based on the edge features, and determine the position and posture of the bobbin and the cake; assign a unique number to each identified bobbin and cake, and associate the number with the image, position, and time of the bobbin and cake, specifically including: Based on prior knowledge or experimental data, appropriate thresholds are set for the edge features of the bobbin and cake. These features include the number of pixels on the contour, the radius or angle of curvature, and the overall or segmental orientation. All contour features calculated in step 118 are traversed, and for each contour, its feature value is checked to see if it meets the threshold conditions for the bobbin or cake. For example, a bobbin may have a large number of pixels and a specific curvature range, while a cake may have a different set of features. Contours that meet the bobbin feature threshold are classified as bobbin candidates, while contours that meet the cake feature threshold are classified as cake candidates.

[0027] For each bobbin or cake candidate contour, a shape matching algorithm (such as contour-based matching or template matching) is used to further verify its identity. Matching is performed by comparing the candidate contour with a pre-set bobbin or cake shape template. For successfully matched bobbin or cake contours, their centroid or geometric center is calculated as the bobbin or cake's position. The bobbin or cake's pose is then determined based on the contour's overall orientation or principal axis.

[0028] Assign a globally unique number to each identified bobbin or pie. This can be achieved using an incrementing counter, a UUID, or other unique identifier generation method. Associate the assigned number with the bobbin or pie's image data, calculated position and pose information, and the current timestamp. Create a data structure (such as an object, dictionary, or database record) to store this information.

[0029] In embodiments of the present invention, through image segmentation, grayscale processing, Gaussian filtering, and Sobel operator gradient calculation, images of silk bobbins and bobbins can be more accurately separated from complex backgrounds, reducing misidentification and missed identification, thereby improving recognition accuracy. Gaussian filtering effectively removes noise from images, and the Sobel operator highlights edge information within images. These processing steps enhance the system's anti-interference capabilities in complex environments and ensure recognition stability. By optimizing image processing algorithms, such as using efficient convolution operations and contour extraction methods, image processing speed can be accelerated, enabling rapid identification and numbering of silk bobbins and bobbins to meet real-time production requirements. Automatic identification and numbering reduces the need for manual intervention, enabling automated management of silk bobbins and bobbins, reducing labor costs, and improving production efficiency and management levels. Identified silk bobbins and bobbins are associated with unique numbers, ensuring consistency and traceability of production data. Accurate identification and numbering streamlines the production process, reduces production interruptions or rework caused by identification errors, further optimizes the production process, and improves overall production efficiency.

[0030] In a preferred embodiment of the present invention, the above step 111, wherein a camera is installed at a predetermined position on the wire drawing machine so as to capture images of the wire drum and the wire cake on the wire drawing machine in real time through the camera, includes: Step 1111 determines the set of potential camera installation locations. Location points are fixed points around the wire drawing machine. The properties of each location point, including coordinates and viewing angle range, are defined. This specifically involves the following steps: Preliminarily identify all possible fixed installation points around the wire drawing machine through visual inspection, such as walls, brackets, and beams. Eliminate locations that are clearly unsuitable for installation, such as high-temperature areas, near moving parts, or in confined, difficult-to-access locations. Use specialized measurement tools (such as a laser rangefinder or 3D coordinate measuring machine) to accurately measure the coordinates of each potential location point. Record the 3D coordinates (X, Y, Z) of each location point, ensuring that the coordinate system is consistent with the wire drawing machine's workspace. Place a temporary marker or simulated camera at each potential location point. Use a video camera, mobile phone camera, or other imaging device to capture photos or videos of the wire bobbins and bobbins on the wire drawing machine at each marked location. Analyze these images to assess the viewing angle range provided by each location point, paying particular attention to the presence of obstructions, reflections, or blind spots. Based on your assessment, define a field of view attribute for each location. This could be a specific angle, a percentage of field of view coverage, or a descriptive label (e.g., "full field of view," "partially blocked," etc.). Create a database or spreadsheet to store information about each potential location. Step 1112, randomly select a portion of all potential locations as the ant's initial location; assign a memory table to each ant to record the locations it has visited and the corresponding pheromone concentrations, specifically including: using a random number generator to randomly select a portion of locations from the set of potential locations determined in step 1111 as the ant's initial location. Create a memory table for each ant, which will be used to store the locations the ant has visited during the search process and the corresponding pheromone concentrations. The memory table can be implemented using data structures such as arrays, lists, or hash tables to facilitate fast search and update; during initialization, the memory table can be empty, or an initial pheromone concentration value (usually a small positive number) can be preset for each location; associate the initialized memory table with the corresponding ant, which can be achieved by maintaining references to the ant object and their respective memory tables in the algorithm's data structure. After completing the above initialization steps, the ants are ready to start their search process; Step 1113 determines the initial concentration and evaporation rate of the pheromone. Each ant selects the next location to move to based on the pheromone concentration and heuristic information around its current location. Specifically, it includes: determining an initial pheromone concentration value, which will serve as the starting concentration of pheromones on all paths. Setting a pheromone evaporation rate. The evaporation rate determines the rate at which the pheromone decreases over time, simulating the natural dissipation process of pheromones in the real world. For each ant, based on its current location, the pheromone concentration and heuristic information of the surrounding reachable locations (such as the straight-line distance to the target point, the quality of the field of view, etc.) are retrieved. Combining the pheromone concentration and heuristic information, a probability formula is used to calculate the probability of the ant moving to each reachable location. Locations with higher pheromone concentrations and better heuristic information have a higher probability of being selected. Based on the calculated probability, a random selection mechanism (such as roulette wheel selection) is used to determine the next location to which the ant will move. The probability calculation formula is: ; in, Indicates the ant's position Move to location The higher the probability value, the more likely the ant is to choose this position; Indicates location To location The pheromone concentration usually indicates the quality of the path. The higher the concentration, the more popular the path. Indicates location The heuristic information is the inverse of the distance to the target point. The closer to the target, the higher the heuristic information. Indicates location To location pheromone concentration; Indicates location The heuristic information is the inverse of the distance to the target point. represents the weight of pheromone; Represents the weight of the heuristic information. Indicates the current ant position The set of all reachable locations; Represents the current ant's location or node, where the ant evaluates the pheromone concentration and heuristic information of the surrounding reachable locations. Indicates the target location or node that the ant is considering moving to. This location is from the current location One of the reachable positions in the ant calculation moves to probability. A universal index representing all reachable locations, used to represent the locations from the current location All accessible locations.

[0031] Update the ant's memory table, recording the newly visited location and the pheromone concentration at that location. After all ants complete a move, reduce the pheromone concentration along all paths based on the set evaporation rate. For paths visited by ants, add a certain amount of pheromone to simulate the ant's pheromone release behavior. The amount of increase can be adjusted based on the quality of the path (such as length and field of view). Step 1114, after a certain number of iterations, the final location point is determined based on the memory tables of all ants and the path evaluation results, specifically including: repeating step 1113, allowing the ant colony to perform multiple iterative searches between potential location points. Each iteration will update the pheromone concentration and the ant's memory table; set a maximum number of iterations as the condition for the termination of the algorithm. This number should be enough for the ant colony to explore most of the potential location points and find a better solution. After reaching the maximum number of iterations, the search process is stopped. At this point, each ant's memory table records a complete search path and its corresponding pheromone concentration. According to the preset evaluation criteria (such as the total length of the path), the paths of all ants are evaluated. The path with the best evaluation result is selected, and its end point is the final location point of the camera installation. If there are multiple similar excellent paths, other decision-making methods (such as voting, weighted average, etc.) can be further used to determine the final position; Step 1115 involves installing the camera at the final location and using it to capture images of the bobbins and bobbins on the wire drawing machine in real time. This includes: preparing the appropriate installation materials and tools (such as a bracket, screws, and a camera) based on the final location determined in step 1114; installing the camera bracket at the final location and ensuring it is stable and reliable. The camera is secured to the bracket and its direction and angle are adjusted to ensure it can clearly capture images of the bobbins and bobbins on the wire drawing machine; connecting the camera's power cord and data transmission cable, and performing necessary debugging and testing to ensure the camera is functioning properly; connecting the camera to the monitoring system and beginning to capture and transmit image data in real time; adjusting the camera's parameters (such as focal length and exposure time) based on the actual monitoring results to optimize image quality; and setting up the monitoring system's alarm and notification functions to ensure timely response and processing when abnormal situations occur.

[0032] In this embodiment of the present invention, by comprehensively considering the coordinates and viewing angle range of potential locations and iterating through an algorithm to find the optimal solution, the selected location can ensure that it provides optimal coverage of the wire bobbins and bobbins on the wire drawing machine. This helps reduce blind spots and improve the comprehensiveness and accuracy of monitoring. A suitable installation location ensures that the camera captures clear and stable images, minimizing image quality degradation caused by poor angles or obstructions. High-quality images are crucial for subsequent image processing, analysis, and recognition. Intelligently selecting installation locations through an algorithm avoids unnecessary trial and error and manual adjustments, saving installation time and costs. Furthermore, a reasonable location selection reduces the likelihood of future camera readjustments or replacements due to poor viewing angles. The location selection method based on a heuristic optimization algorithm can find the optimal solution among multiple potential locations. This means that even if certain locations become unavailable due to environmental factors (such as lighting changes or equipment failure), the system can quickly adjust to other suitable locations to maintain continuous monitoring. The entire location selection process is automated by the algorithm, reducing the need for human intervention and improving the level of automation. This helps achieve automated monitoring and management of the wire drawing machine production process, improving production efficiency.

[0033] In a preferred embodiment of the present invention, step 114, generating a grayscale image based on the grayscale values, and calculating a new value of each pixel by a convolution operation using a Gaussian function to obtain a Gaussian filtered image, may include: Step 1141, calculate the grayscale values ​​of all pixels to create a new image, in which the value of each pixel is a grayscale value, wherein the new image is a grayscale image, specifically including: having a color image as input, this image is usually composed of three color channels: red, green, and blue (RGB), each channel corresponds to a two-dimensional matrix, and each value in the matrix represents the brightness of the color channel. For each pixel in the color image, its grayscale value needs to be calculated. The grayscale value is calculated by adding the values ​​of the three RGB channels in a certain proportion (such as linear weighting); after calculating the grayscale values ​​of all pixels, these values ​​will be used to create a new two-dimensional matrix, namely the grayscale image. In this new image, the value of each pixel is its grayscale value, which usually ranges from 0 to 255 (for 8-bit images); Step 1142: Define a Gaussian kernel. The Gaussian kernel is a two-dimensional matrix whose values ​​are calculated based on a Gaussian function. Specifically, the size of the Gaussian kernel is determined to be an odd-by-odd matrix (e.g., 3×3, 5×5, etc.) to ensure a central point. Each value of the Gaussian kernel is calculated based on a two-dimensional Gaussian function. The calculated Gaussian function values ​​are filled into the two-dimensional matrix to form the Gaussian kernel. The Gaussian kernel values ​​are normalized so that the sum of all values ​​is 1 to ensure that the brightness of the filtered image remains unchanged. Step 1143: Starting from the top left corner of the image, select the first pixel and multiply the first pixel and its surrounding pixels by the value at the corresponding position in the Gaussian kernel. Align the center of the Gaussian kernel with the selected pixel, and perform the following operations: Starting from the top left corner of the input image (here, a grayscale image), select the first pixel as the current pixel to be processed; align the center of the Gaussian kernel with the selected pixel. If the Gaussian kernel is larger than the image, the image boundary needs to be processed (such as padding or mirroring); multiply each value in the Gaussian kernel by the image pixel value at the corresponding position, and then add all the products. This process is called convolution, which is actually a weighted sum of the selected pixel and its surrounding pixels. The result of the convolution operation is the new pixel value at the corresponding position in the filtered image, which replaces the pixel value at the corresponding position in the original image. After processing the current pixel, the Gaussian kernel is shifted one pixel to the right (or downward as needed), and the convolution operation is repeated until all pixels in the image have been processed: Step 1144, multiplying the upper left corner value of the Gaussian kernel by the pixel value of the corresponding position in the image; multiplying the upper middle value of the Gaussian kernel by the pixel value of the corresponding position in the image, until all the values ​​of the Gaussian kernel are multiplied by the pixel value of the corresponding position in the image, and adding all the products to obtain the new pixel value of the corresponding position in the filtered image, specifically including: determining the pixel position in the image corresponding to the upper left corner of the current position of the Gaussian kernel; starting from the upper left corner of the Gaussian kernel, multiplying the Gaussian kernel value (weight) of the position by the pixel value of the corresponding position in the image Multiply; then, multiply the value of the upper middle position of the Gaussian kernel with the pixel value of the corresponding position in the image, where the value of the upper middle position refers to the value of the middle position of the upper half of the Gaussian kernel; and so on, from left to right, from top to bottom, multiply each value in the Gaussian kernel with the pixel value of the corresponding position in the image one by one; add up all the products obtained, and this sum is the new pixel value of the filtered image at the corresponding position of the current Gaussian kernel center. The new pixel value reflects the weighted average of the pixels at that position and its surroundings in the original image, and the weight is determined by the Gaussian kernel; Step 1145: Move the Gaussian kernel one pixel to the right until new values ​​of all pixels in the image are calculated. Create a new image using the calculated new pixel values. The new image is the Gaussian filtered image. Specifically, the following steps are performed: After completing the Gaussian filter calculation at the current position, move the Gaussian kernel one pixel position to the right; if the Gaussian kernel has reached the end of the image row, move it to the starting position of the next row; at the new position of the Gaussian kernel, repeat the convolution calculation process in step 1144 to obtain the filtered pixel value at the new position; by continuously moving the Gaussian kernel and repeating the convolution calculation until every pixel position in the image has been processed; using all the calculated new pixel values, create a new two-dimensional matrix, that is, the filtered image, in which the pixel value at each position is the value after Gaussian filtering.

[0034] In embodiments of the present invention, convolution operations can average high-frequency noise (such as salt and pepper noise and Gaussian noise) in an image, thereby reducing its impact on image quality. Gaussian filtering can smooth an image while better preserving edges and details. This is because the Gaussian function is isotropic and its smoothness gradually decreases. This allows the filter to assign different weights to pixels based on their distance from the center pixel when processing them, thereby more effectively protecting important image features. By defining a Gaussian kernel and calculating its value once, this kernel can be reused throughout the filtering process, improving computational efficiency. Furthermore, because Gaussian filtering is a linear filtering method, its computational process is relatively simple and easily parallelized, further accelerating processing speed. Grayscale images are the most commonly used image format in image processing. They simplify image representation and reduce data dimensionality, enabling many algorithms to process and analyze images more efficiently.

[0035] In a preferred embodiment of the present invention, step 115 performs convolution operations on the Gaussian filtered image using the Sobel operator in the horizontal and vertical directions, respectively, to obtain the gradient components of each pixel in the horizontal and vertical directions, including: Step 1151, starting from the upper left corner of the image, select a pixel as the current processing point; overlay the Sobel horizontal kernel on the current pixel and its surrounding pixels, and perform a convolution operation: multiply the upper left corner element of the horizontal kernel by the value of the corresponding image pixel; multiply the upper middle element of the horizontal kernel by the value of the corresponding image pixel, and repeat this process until all elements of the horizontal kernel are multiplied by the corresponding image pixels; add all the products to obtain the gradient component of the current pixel in the horizontal direction, which specifically includes the following steps: Starting from the upper left corner of the image, select the first pixel as the current processing point and determine the size of the Sobel horizontal kernel, which is usually 3×3. Ensure that there are enough pixels around the current processing point for the kernel to cover (i.e., avoid pixels outside the boundary). Align the center of the Sobel horizontal kernel with the current processing point. Ensure that the rest of the kernel covers the pixels surrounding the current processing point. Perform the convolution operation: Starting from the upper left corner element of the Sobel horizontal kernel, multiply its value by the value of the corresponding image pixel; then, multiply the value of the upper middle element of the horizontal kernel by the value of the image pixel it covers, and continue this process from left to right, from top to bottom, multiplying each element in the kernel with the corresponding image pixel one by one. The sum is the gradient component: Add all the products obtained; this sum is the horizontal gradient component of the current pixel. Record or store the calculated gradient component and move the current processing point one pixel to the right. If it reaches the end of the image row, move the processing point to the beginning of the next row. Repeat this step until the horizontal gradient components of all pixels in the image have been calculated.

[0036] Step 1152: Use the Sobel vertical kernel to perform a convolution operation on the same pixel and its surrounding pixels: multiply the upper left corner element of the vertical kernel by the value of the corresponding image pixel; multiply the upper middle element of the vertical kernel by the value of the corresponding image pixel, and repeat this process until all elements of the vertical kernel are multiplied by the corresponding image pixels. All products are added together to obtain the vertical gradient component of the current pixel; the current processing point is shifted one pixel to the right until the horizontal and vertical gradient components of all pixels in the image are calculated. Specifically, the steps include: Continue using the current processing point selected in step 1151 as the starting point; ensure that there are enough pixels around the current processing point for the kernel to cover. Perform the convolution operation: Align the center of the Sobel vertical kernel with the current processing point; starting from the upper left corner element of the Sobel vertical kernel, multiply its value by the value of the corresponding image pixel; then, multiply the value of the upper middle element of the vertical kernel by the value of the image pixel it covers, and continue this process, multiplying each element in the kernel by the image pixel value it covers. Calculate the vertical gradient component: Add all the products obtained; this sum is the vertical gradient component of the current pixel. Record or store the calculated vertical gradient component and move the current processing point one pixel to the right. If the processing point reaches the end of an image row, move it to the beginning of the next row. Repeat this step until the vertical gradient components of all pixels in the image are calculated.

[0037] Step 1153, generating a gradient component image based on the gradient components of all pixels in the image in the horizontal and vertical directions, specifically includes the following steps: Steps 1151 and 1152 calculate the horizontal and vertical gradient components of all pixels in the image. These gradient components are stored in numerical form, with each pixel corresponding to a pair of horizontal gradient components (Gx) and vertical gradient components (Gy). Create a gradient component image: Initialize a new image with the same size as the original image to store and display the gradient component. This new image can be a grayscale image, where the brightness or color of each pixel represents the gradient strength or direction at that location. Calculate the gradient magnitude: For each pixel, the gradient magnitude can be calculated using its horizontal gradient component (Gx) and vertical gradient component (Gy). Assigned to the gradient component image: If the gradient magnitude is calculated, the gradient magnitude value of each pixel can be assigned to the corresponding position in the new image. Alternatively, the horizontal gradient component (Gx) and the vertical gradient component (Gy) can be used as two channels of the new image (for example, red and green channels), thereby simultaneously representing the direction and intensity of the gradient through color. In this case, the new image may be a color image, where the hue of the color represents the direction of the gradient, and the brightness or saturation of the color represents the intensity of the gradient.

[0038] Because the value range of gradient components can be large, they may need to be normalized or scaled to better highlight edge information when displayed. Normalization can map the gradient component values ​​to the range of 0 to 255 (for 8-bit grayscale images) or to a color space suitable for display (for color images). Finally, the resulting gradient component image can be displayed using an image processing library or software.

[0039] In this embodiment of the present invention, the Sobel operator is an effective edge detection algorithm that detects edges by calculating the first or second derivative of the image's grayscale. In step 115, by applying the Sobel operator to the Gaussian-filtered image, the image's edge information can be more accurately detected. Gaussian filtering can smooth the image and remove noise, while the Sobel operator further enhances edge features. Steps 1151 and 1152 calculate the horizontal and vertical gradient components, respectively. By first Gaussian filtering the image and then applying the Sobel operator, the robustness of edge detection can be improved. Gaussian filtering can reduce noise interference in the image, making the Sobel operator more stable during processing and less susceptible to noise. The convolution operation in step 115 is performed across the entire image using a sliding window. This processing method leverages the optimization algorithms and parallel computing capabilities of computer vision libraries, thereby increasing processing speed and achieving efficient edge detection.

[0040] In a preferred embodiment of the present invention, in step 11, the variety produced by each wire drawing machine is bound to the machine vision system, and a visible barcode is printed on the wire cake as a unique identifier of the wire cake, which corresponds to the number recognized by the machine vision system. The following steps may also be included: Step 1190, assigning a unique number to each wire drawing machine's product; Step 1191, print the assigned number in the form of a barcode on the silk cake as the unique identification of the silk cake, specifically including: ensuring that each variety produced by the wire drawing machine has been assigned a unique number. This number can be generated sequentially or according to a specific rule. The key is to ensure its uniqueness. Use professional barcode generation software or library to convert the assigned number into a barcode image. The type of barcode (such as EAN-13, Code128, etc.) should be selected according to actual application requirements and printing conditions. Prepare a printer for printing barcodes and corresponding printing materials (such as label paper, carbon ribbon, etc.). Ensure that the printer can print out the barcode clearly for subsequent scanning and identification. At the appropriate stage in the silk cake production process, print the generated barcode on the silk cake or affix it to the label of the silk cake. The printing position should be convenient for subsequent scanning operations and will not be damaged by the handling or storage of the silk cake; Step 1192, establish a database or lookup table to store the correspondence between varieties and numbers, specifically including: selecting a suitable database system (such as MySQL, SQL Server, etc.) according to needs, and designing a database table containing variety information and corresponding numbers. The table should contain at least fields such as variety name (or description) and number. Enter the information of each variety and its corresponding number into the database. Ensure the accuracy and completeness of the data. In order to improve query efficiency, an index can be set for the number field. In this way, when you subsequently look up variety information based on the number, you can locate the relevant data more quickly. Establish a mechanism for regular database backup and prepare corresponding data recovery plans to prevent data loss or damage; Step 1193 uses image processing technology to preprocess the captured image, scans and analyzes the preprocessed image, and extracts the serial number information on the silk cake. Specifically, the process includes: using a camera or scanner to capture an image containing the silk cake barcode. The captured image is preprocessed, including denoising, binarization, and contrast enhancement, to improve the barcode's recognizability. An image processing algorithm (such as edge detection and morphological transformation) is used to locate the barcode region in the image. A barcode recognition library or algorithm is used to scan and analyze the located barcode to extract the serial number information. The accuracy of the analysis results is ensured. Step 1194 searches for the corresponding variety information based on the extracted number information and binds the variety information and number information. This specifically involves extracting the number information on the silk cake from the previous step. Using the extracted number information as a query condition, the database is searched for the corresponding variety information. This ensures the accuracy and efficiency of the query operation. The retrieved variety information is bound to the extracted number information. This can be achieved by creating a data structure (such as a dictionary or object) in memory, or by directly storing the binding result back in a database or file.

[0041] In an embodiment of the present invention, a machine vision system automatically identifies barcodes on silk cakes, enabling quick and accurate acquisition of each cake's variety information. This avoids the errors and delays associated with traditional manual identification and recording, thereby improving production efficiency. The barcode on each silk cake serves as its unique identifier, enabling information from every stage of the production process to be recorded and tracked. This helps quickly identify the cause of problems and take timely action, thereby improving product quality control. A database or lookup table stores the correspondence between varieties and serial numbers, making inventory management more convenient and efficient. By querying the database, the inventory status of various silk cake varieties can be quickly determined. The entire process enables automated data collection, storage, and processing, enhancing the enterprise's level of informatization. The introduction of automation and informatization reduces labor costs, avoids losses and waste caused by human factors, and thus lowers the enterprise's overall operating costs.

[0042] In a preferred embodiment of the present invention, the step 1190 of assigning a unique number to each product produced by the wire drawing machine includes: Step 11901, determine the basic rules for numbering, including the length of the number and the character set to be used, specifically including: setting an appropriate number length. For example, if the number of varieties to be represented is between thousands and tens of thousands, a number of moderate length, such as 6-8 digits, can be selected. Select an appropriate character set based on actual needs. Common character sets include numbers (0-9), uppercase letters (AZ), lowercase letters (az), or a combination thereof. If readability and input convenience need to be considered, pure numbers or a combination of numbers and uppercase letters may be preferred; Step 11902, obtains the variety information of all wire drawing machines, including variety name, specifications and characteristics, specifically including: determining the data source that stores the variety information of wire drawing machines; according to the type of data source, using appropriate query statements or API interfaces to extract the variety information of all wire drawing machines, including key fields such as variety name, specifications, and characteristics. Clean and organize the extracted data to ensure the accuracy and completeness of the data. This includes removing duplicate records, processing missing values, correcting erroneous data, etc. Store the cleaned and organized data in a data structure that is convenient for subsequent processing, such as a list, data frame, or database table; Step 11903, represent the number of each variety as a gene code, randomly generate an initial population based on the defined gene code, and each individual in the population represents a number allocation scheme, specifically including: defining a suitable gene coding scheme based on the numbering rule determined in step 11901. For example, if the number length is 8 bits and only numeric characters are used, the code of each gene can be a number between 0 and 9. Set a suitable initial population size, which will determine the search space and convergence speed of the algorithm; use a random number generator to randomly generate an initial population according to the defined gene coding scheme. Each individual (i.e., each number allocation scheme) should meet the number length and character set requirements. Represent the generated initial population as an appropriate data structure, such as a list, array, or matrix, and store it in memory for subsequent processing. Ensure that each individual (number allocation scheme) is associated with its corresponding variety information; Step 11904: determine the fitness function used to evaluate the quality of each individual. The specific calculation formula corresponding to the fitness function is: ; in, Indicates the number of number conflicts, indicating that How many numbers are repeated? Indicates that the length does not meet the expected number of numbers, indicating that in the individual How many numbers have lengths not equal to the expected value? Step 11905: According to the fitness function, select the corresponding individuals from the current population to enter the next generation, perform a crossover operation on the selected individuals to generate new individuals, and perform a mutation operation on the newly generated individuals until the preset number of iterations is reached to obtain the final number allocation scheme, which specifically includes: Using a roulette wheel selection mechanism, a portion of individuals are selected from the current population to enter the next generation based on the individual fitness values ​​calculated by the fitness function. During the selection process, individuals with higher fitness should have a greater probability of being selected. For the selected individuals, random pairing and crossover operations are performed to generate new individuals. The crossover operation can use methods such as single-point crossover, multi-point crossover, or uniform crossover. According to the defined gene encoding scheme, crossover points are selected in the gene sequences of the paired individuals and some gene fragments are exchanged. The newly generated individuals are mutated with a certain mutation probability to increase the diversity of the population. Mutation operations can include random replacement, insertion, or deletion of gene sites to ensure that the mutated individuals still meet the basic numbering rules. Repeat the above selection, crossover, and mutation operations to form a new generation of population; evaluate the fitness of the new generation of population, and record the best individual (i.e., the numbering scheme with the highest fitness); determine whether the preset number of iterations has been reached or other termination conditions (such as fitness threshold, population diversity reduction, etc.) have been met. If so, the iteration is stopped, otherwise the evolution of the next generation continues; after the iteration is completed, the best individual is output as the final numbering scheme; Step 11906, assigns a unique number to each variety produced by the wire drawing machine according to the final number allocation plan, specifically including: obtaining the final number allocation plan from the output of step 11905; matching each number with the corresponding variety produced by the wire drawing machine according to the final number allocation plan; ensuring that each variety is assigned one and only one unique number.

[0043] In an embodiment of the present invention, by establishing basic numbering rules, such as length and character set, and using genetic encoding, it is possible to ensure that the numbers assigned to each variety are unique, avoiding number conflicts or duplications. This approach also makes the numbering system more standardized and systematic, making it easier to manage and maintain. The genetic encoding method allows for the consideration of multiple factors during the numbering process, such as variety name, specifications, and characteristics. This flexibility enables the system to easily adapt to the addition or change of different varieties while maintaining the consistency and scalability of the numbering system. By evaluating the numbering scheme using a fitness function, the more optimal individuals can be selected for the next generation, thereby gradually optimizing the numbering scheme. This optimization process not only improves the efficiency of numbering, but also helps to rationally allocate resources, such as ensuring that important or high-frequency varieties have numbers that are easier to identify and remember. The automated numbering method based on genetic encoding reduces human involvement and intervention, thereby reducing errors and delays caused by human factors. This improves the efficiency and accuracy of the production process while reducing the burden on staff.

[0044] In another preferred embodiment of the present invention, in step 12, after the drawing is completed, the yarn cakes are transported to the twisting area through a transfer channel. A camera is installed in the transfer channel to use machine vision technology to identify and record the barcode information on the passing yarn cakes to ensure uninterrupted tracking of the yarn cakes during the transfer process. The process may include: Processing of the yarn cake after drawing: Once the drawing process is completed, the yarn cake will be removed from the drawing machine; workers or automated equipment will place the yarn cake on the transfer channel, ready to be sent to the twisting area; the transfer channel is designed as an automated conveying system with conveyor belts or rollers to ensure the smooth and continuous movement of the yarn cake; high-resolution cameras are installed at key locations in the transfer channel, such as entrances, exits and turns; an integrated machine vision system is used to capture images of the yarn cake on the conveyor belt in real time; the machine vision system automatically recognizes the barcode on the yarn cake and records relevant information, such as the yarn cake number, production time, etc.; the recognized data is recorded in real time and transmitted to the central management system to ensure that the tracking information of the yarn cake is not interrupted during the transfer process.

[0045] Step 13: In the twisting area, each twisting machine is equipped with a unique machine number and displayed in the form of a QR code. When the yarn cake arrives at the twisting area, a scanning device is used to scan the QR code of the twisting machine and the barcode of the yarn cake to bind the information, which may include: Twisting machine numbering and QR code generation: Each twisting machine is assigned a unique machine number, and these numbers are converted into QR code format using a QR code generation tool; the generated QR code labels are affixed to a conspicuous location on each twisting machine for easy scanning and identification; after the silk cakes arrive at the twisting area through the transfer channel, workers prepare to place them on the corresponding twisting machines; the workers' handheld or fixed-position scanning devices are ready to scan QR codes and barcodes; the workers first scan the twisting machine's QR code and then scan the silk cake's barcode, and the system binds these two pieces of information together to record which silk cake is processed on which twisting machine; the bound information is recorded and updated in real time to the central management system to ensure transparency and traceability of the production process.

[0046] The specific implementation process of step 14: After the twisting process is complete, the operator removes the yarn (now in cop form) from the twisting machine and places it on a dedicated transfer cart or conveyor belt. This transports the yarn smoothly to the packaging area, ensuring it remains undamaged during transport.

[0047] The packaging area is equipped with high-precision robotic arms equipped with a vision recognition system that accurately identifies the QR codes on the bobbins. The robotic arms scan incoming bobbins using the vision system, quickly locating and identifying the bobbins bearing the QR codes. Once successfully identified, the robotic arms, following pre-programmed algorithms, precisely grasp the bobbins and place them in designated locations for inspection or packaging.

[0048] The captured bobbins first undergo quality inspection, where inspectors check key indicators such as yarn quality, appearance, and twist. The inspection results are recorded in the information management system and linked to the bobbin's QR code to ensure traceability. Before packaging, a QR code scanner in the packaging area scans the bobbin's QR code again to confirm its identity and previous production process records. The scanning device is connected to the company's information management system, uploading scanned data in real time to ensure that every operation is accurately recorded and tracked.

[0049] After verification, the bobbins are fed into a baler for automatic or semi-automatic packaging, including bagging, sealing, and labeling. The packaged yarn products are also labeled with a label or QR code containing production information and quality inspection results for subsequent logistics and sales. Data generated throughout the entire process (including shipping records, inspection results, and packaging information) is integrated into the company's information management system. Through this system, the entire production process of any yarn product can be queried and traced at any time.

[0050] like Figure 2 As shown, an embodiment of the present invention further provides a superfine yarn non-sensing operation quality tracing system 20, comprising: The encoding module 21 is used to automatically identify and number the wire bobbins and wire cakes on the wire drawing machine in the wire drawing area through a camera and a machine vision system. The variety produced by each wire drawing machine is bound to the machine vision system. A visible barcode is printed on the wire cake as a unique identifier of the wire cake, which corresponds to the number recognized by the machine vision system. Tracking module 22, used to transport the yarn cakes to the twisting area through a transfer channel after the yarn drawing is completed; a camera is installed in the transfer channel, which uses machine vision technology to identify and record the barcode information on the passing yarn cakes, so that the tracking of the yarn cakes is uninterrupted during the transfer process; Scanning module 23 is used in the twisting area. Each twisting machine is equipped with a unique machine number and displayed in the form of a QR code. When the yarn cake arrives at the twisting area, the QR code of the twisting machine and the barcode of the yarn cake are scanned by a scanning device to bind the information. The processing module 24 is used to transport the yarn to the packaging area for inspection and packaging after twisting. The robotic arm in the packaging area identifies and grabs the bobbins with QR codes. The QR code scanning equipment in the packaging area scans and confirms the bobbins to be packaged, so that each step of the operation can be traced and the entire yarn production process can be managed in a digital way.

[0051] It should be noted that this system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effects.

[0052] An embodiment of the present invention further provides a computing device comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the above-described method. All implementations in the above-described method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0053] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the above-described method. All implementations in the above-described method embodiment are applicable to this embodiment and can achieve the same technical effects.

Claims

1. A method for tracing the quality of ultra-fine yarn without feeling operation, characterized in that: The method comprises the following steps: In the wire drawing area, the wire tubes and wire cakes on the wire drawing machine are automatically identified and numbered through cameras and machine vision systems. The varieties produced by each wire drawing machine are bound to the machine vision system, and a visible barcode is printed on the wire cake as the unique identification of the wire cake, which corresponds to the number identified by the machine vision system. After the wire drawing is completed, the silk cake is sent to the twisting area through the transfer channel. A camera is installed in the transfer channel to use machine vision technology to identify and record the barcode information on the silk cake passing by, so that the tracking of the silk cake is not interrupted during the transfer process. In the twisting area, each twisting machine is equipped with a unique machine number, which is displayed in the form of a QR code. When the silk cake arrives at the twisting area, a scanning device is used to scan the QR code of the twisting machine and the barcode of the silk cake to bind the information. After twisting, the yarn is transported to the packaging area for inspection and packaging. The robotic arm in the packaging area identifies and grabs the bobbin with a QR code. The QR code scanning device in the packaging area scans and confirms the bobbin to be packaged, so that each step of the operation can be traced and the entire yarn production process can be managed in a digital way.

2. The ultra-fine yarn non-sensing operation quality tracing method according to claim 1 is characterized in that: Automatically identify and number the wire tubes and wire cakes on the wire drawing machine through cameras and machine vision systems, including: The camera is installed at a preset position on the wire drawing machine to capture images of the wire tube and wire cake on the wire drawing machine in real time through the camera; Preprocess the collected images, perform image segmentation, and separate the silk tube and silk cake from the background; Get a color image from the camera, and calculate the gray value of each pixel in the color image; Generate a grayscale image based on the grayscale value, and calculate the new value of each pixel through the convolution operation of the Gaussian function to obtain a Gaussian filtered image; Use the Sobel operator's horizontal and vertical kernels to perform convolution operations on the Gaussian filtered image to obtain the horizontal and vertical gradient components of each pixel. For each pixel, the gradient magnitude is calculated according to the gradient components of each pixel in the horizontal and vertical directions to obtain a gradient image containing the gradient magnitude and direction of each pixel; Traverse the gradient image of the gradient magnitude and direction of each pixel point to identify and extract the continuous edge contours in the image; For each extracted contour, calculate the number of pixels on the contour, the radius of curvature or the angle of curvature of each point on the contour, and the overall direction of the contour or the direction of each segment; The edge features of the silk tube and silk cake are screened out according to the number of pixel points on the contour, the curvature radius or curvature angle of each point on the contour, and the overall direction of the contour or the direction of each segment; According to the edge features of the silk tube and the silk cake, the silk tube and the silk cake in the image are identified, and the positions and postures of the silk tube and the silk cake are determined; Each identified bobbin and cake is assigned a unique number that is associated with the image, location and time of the bobbin and cake.

3. The ultra-fine yarn non-sensing operation quality tracing method according to claim 2 is characterized in that: Generate a grayscale image based on the grayscale value, and calculate the new value of each pixel through the convolution operation of the Gaussian function to obtain the image after Gaussian filtering, including: Calculate the grayscale values ​​of all pixels to create a new image, in which the value of each pixel is a grayscale value, wherein the new image is a grayscale image; Define the Gaussian kernel, which is a two-dimensional matrix whose values ​​are calculated according to the Gaussian function; Starting from the upper left corner of the image, select the first pixel, multiply the first pixel and its surrounding pixels by the value of the corresponding position of the Gaussian kernel; align the center of the Gaussian kernel to the selected pixel, and do the following: Multiply the upper left corner value of the Gaussian kernel by the pixel value at the corresponding position in the image; Multiply the upper median value of the Gaussian kernel by the pixel value at the corresponding position in the image until all values ​​of the Gaussian kernel are multiplied by the pixel value at the corresponding position in the image, add up all the products, and the result is the new pixel value at the corresponding position of the filtered image; Move the Gaussian kernel one pixel to the right until the new values ​​of all pixels in the image are calculated, and use the calculated new pixel values ​​to create a new image. The new image is the image after Gaussian filtering.

4. The ultra-fine yarn non-sensing operation quality tracing method according to claim 3 is characterized in that: The horizontal and vertical kernels of the Sobel operator are used to perform convolution operations on the Gaussian filtered image to obtain the horizontal and vertical gradient components of each pixel, including: Starting from the upper left corner of the image, select a pixel as the current processing point; cover the Sobel horizontal kernel on the current pixel and its surrounding pixels, and perform a convolution operation: Multiply the upper left corner element of the horizontal kernel by the value of the corresponding image pixel; multiply the upper middle element of the horizontal kernel by the value of the corresponding image pixel, and repeat this process until all elements of the horizontal kernel are multiplied by the corresponding image pixels; add all the products to get the gradient component of the current pixel in the horizontal direction; Use Sobel's vertical kernel to perform convolution on the same pixel and its surrounding pixels: Multiply the upper left corner element of the vertical kernel by the value of the corresponding image pixel; multiply the upper middle element of the vertical kernel by the value of the corresponding image pixel, and repeat this process until all elements of the vertical kernel are multiplied by the corresponding image pixels. Add all the products together to get the gradient component of the current pixel in the vertical direction. Move the current processing point one pixel to the right until the gradient components of all pixels in the image in the horizontal and vertical directions are calculated; A gradient component image is generated based on the gradient components of all pixels in the image in the horizontal and vertical directions.

5. The ultra-fine yarn non-sensing operation quality tracing method according to claim 4 is characterized in that: The camera is installed at a preset position on the wire drawing machine to capture the images of the wire tube and wire cake on the wire drawing machine in real time through the camera, including: Determine the set of all potential locations where the camera can be installed. The location points are fixed points around the wire drawing machine. Define the properties of each location point, including coordinates and viewing angle range. Randomly select a portion of all potential locations as the ant's initial location; assign a memory table to each ant to record the locations it has visited and the corresponding pheromone concentrations; Determine the initial concentration and volatilization rate of pheromones, and each ant chooses the next location to move to based on the pheromone concentration and heuristic information around its current location; After a certain number of iterations, the final position point is determined based on the memory tables and path evaluation results of all ants; The camera is installed according to the final position point, and the image of the wire tube and wire cake on the wire drawing machine is captured in real time by the camera.

6. The ultra-fine yarn non-sensing operation quality tracing method according to claim 5 is characterized in that: Each wire drawing machine produces a variety of products that are bound to the machine vision system. A visible barcode is printed on the wire cake as the unique identifier of the wire cake, which corresponds to the number recognized by the machine vision system, including: Assign a unique number to each type of wire drawing machine; Print the assigned number on the silk cake in the form of a barcode as a unique identifier of the silk cake; Establish a database or lookup table to store the corresponding relationship between varieties and numbers; The collected images are preprocessed by using image processing technology, and the preprocessed images are scanned and analyzed to extract the number information on the silk cakes; According to the extracted number information, the corresponding variety information is searched, and the variety information and number information are bound.

7. The ultra-fine yarn non-sensing operation quality tracing method according to claim 6 is characterized in that: Each wire drawing machine is assigned a unique number, including: Determine basic rules for numbering, including number length and character set to be used; Obtain information on all varieties produced by wire drawing machines, including variety name, specifications and characteristics; The number of each variety is represented as a gene code. According to the defined gene code, an initial population is randomly generated. Each individual in the population represents a number allocation scheme. Determine the fitness function used to evaluate the quality of each individual; According to the fitness function, the corresponding individuals are selected from the current population to enter the next generation, the selected individuals are crossover operated to generate new individuals, and the newly generated individuals are mutated until the preset number of iterations is reached to obtain the final number allocation scheme; According to the final numbering allocation plan, a unique number is assigned to each variety produced by the wire drawing machine.

8. A superfine yarn non-sensing operation quality tracing system, characterized in that: Applied to the method according to any one of claims 1 to 6, comprising: The encoding module is used to automatically identify and number the wire tubes and wire cakes on the wire drawing machine in the wire drawing area through the camera and machine vision system; the variety produced by each wire drawing machine is bound to the machine vision system, and a visible barcode is printed on the wire cake as the unique identification of the wire cake, which corresponds to the number recognized by the machine vision system; Tracking module: After the wire drawing is completed, the silk cake is sent to the twisting area through the transfer channel; a camera is installed in the transfer channel, which uses machine vision technology to identify and record the barcode information on the passing silk cake, so that the tracking of the silk cake is not interrupted during the transfer process; The scanning module is used in the twisting area. Each twisting machine is equipped with a unique machine number and displayed in the form of a QR code. When the silk cake arrives at the twisting area, the scanning device is used to scan the QR code of the twisting machine and the barcode of the silk cake to bind the information. The processing module is used to transport the yarn to the packaging area for inspection and packaging after the twisting is completed; the robot in the packaging area identifies and grabs the bobbin with a QR code; the QR code scanning device in the packaging area scans and confirms the bobbin to be packaged, so that each step of the operation can be traced and the whole process of yarn production can be managed in a digital way.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images