Low-power yarn breakage detection methods, devices, equipment, media and products

Abstract

This application provides a low-power yarn breakage detection method, apparatus, device, medium, and product. When an inspection device follows a preset inspection route to the first spinning station and detects a target component at the first spinning station, the device's acquisition component is triggered to acquire the target image corresponding to the first spinning station. Based on yarn feature information, edge detection is performed on the target image to obtain an initial region of interest. The yarn feature information characterizes the physical and image features of the yarn processed by the spinning equipment. Using the yarn feature information as a reference, non-yarn areas within the initial region of interest are filtered to obtain the target area. Based on the texture features and yarn feature information of the target area, yarn identification is performed on the target area to obtain an identification result. If the identification result indicates that no yarn exists in the target area, a yarn breakage is determined at the first spinning station. This application's embodiments can improve the accuracy of yarn breakage identification.

Description

Technical Field

[0001] This application relates to the field of detection technology, and in particular to a low-power yarn breakage detection method, apparatus, equipment, medium, and product. Background Technology

[0002] In the textile industry, spinning machines and twisting machines, as core upstream processes in weaving, directly determine the overall production capacity and quality performance of the production line through their operational efficiency and stability. Yarn breakage, a common problem, not only leads to production interruptions and reduced efficiency but also requires workers to expend considerable effort locating and repairing broken yarns, significantly increasing their labor intensity. Therefore, automating inspections using robots to replace manual yarn breakage detection has become an urgent need for industry development. Current yarn breakage detection methods rely on image acquisition systems to determine yarn breakage. However, the textile production environment is complex and variable. To ensure timely and accurate detection, these methods require continuous image data acquisition, resulting in prolonged operation of the image acquisition equipment and related processing units. This leads to high power consumption in the entire yarn breakage detection system, resulting in high power consumption for yarn breakage identification in these technologies. Summary of the Invention

[0003] This application provides a low-power yarn breakage detection method, apparatus, equipment, medium, and product that can reduce the power consumption of yarn breakage identification.

[0004] In a first aspect, embodiments of this application provide a low-power yarn breakage detection method, applied to an inspection device. The inspection device is used to inspect spinning equipment, which includes multiple spinning stations. The method includes:

[0005] When the inspection device inspects the first spinning station according to the preset inspection route and detects the target component on the first spinning station, the acquisition component of the inspection device is triggered to acquire the target image corresponding to the first spinning station. The first spinning station is any one of multiple spinning stations, and the preset inspection route is an S-shaped route.

[0006] Based on yarn feature information, edge detection is performed on the target image to obtain the initial region of interest. The yarn feature information is used to characterize the yarn physical features and yarn image features of the yarn processed by the spinning equipment.

[0007] Based on yarn feature information, non-yarn regions in the initial region of interest are filtered to obtain the target region;

[0008] Based on the texture and yarn features of the target area, yarn identification is performed in the target area to obtain the identification result;

[0009] If the identification result indicates that there is no yarn in the target area, it is determined that there is a yarn breakage at the first spinning station.

[0010] Secondly, this application provides a low-power yarn breakage detection device applied to an inspection device. The inspection device is used to inspect spinning equipment, which includes multiple spinning stations. The device includes:

[0011] The acquisition module is used to trigger the acquisition component of the inspection device to acquire the target image corresponding to the first spinning station when the inspection device inspects the first spinning station according to the preset inspection route and detects the target component on the first spinning station. The first spinning station is any one of the plurality of spinning stations, and the preset inspection route is an S-shaped route.

[0012] The detection module is used to perform edge detection on the target image based on yarn feature information to obtain an initial region of interest. The yarn feature information is used to characterize the yarn physical features and yarn image features of the yarn processed by the spinning equipment.

[0013] The filtering module is used to filter non-yarn regions in the initial region of interest based on the yarn feature information to obtain the target region;

[0014] The identification module is used to identify the yarn in the target area based on the texture features of the target area and the yarn feature information, and obtain the identification result;

[0015] The determination module is used to determine that there is a yarn breakage at the first spinning station when the identification result indicates that there is no yarn in the target area.

[0016] Thirdly, embodiments of this application provide an electronic device, which includes: a processor and a memory storing computer program instructions;

[0017] When the processor executes computer program instructions, it implements the low-power yarn breakage detection method as described in any of the embodiments of the first aspect.

[0018] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the low-power yarn breakage detection method as described in any of the embodiments of the first aspect.

[0019] Fifthly, embodiments of this application provide a computer program product in which instructions are executed by the processor of an electronic device, causing the electronic device to perform a low-power yarn breakage detection method as described in any of the embodiments of the first aspect above.

[0020] In the low-power yarn breakage detection method, apparatus, device, medium, and product provided in this application embodiment, the inspection device adopts a specific triggering mechanism. It only activates the acquisition component to acquire the target image when it reaches the first spinning station and detects the target component along a preset S-shaped inspection route. This avoids or reduces the meaningless continuous operation of the image acquisition device, significantly reducing unnecessary energy consumption. Furthermore, the S-shaped inspection route is the optimal route for inspection, allowing it to traverse each spinning station in an orderly, efficient, and energy-saving manner according to the layout of the spinning equipment. This, combined with the triggering acquisition mechanism, effectively reduces the power consumption for yarn breakage detection. In the subsequent image processing stage, yarn breakage identification is performed based on pre-determined yarn feature information. First, edge detection is performed on the target image to obtain an initial region of interest. Then, based on this, non-yarn areas are precisely filtered to obtain the target area. Finally, yarn identification is performed based on the texture features and yarn feature information of the target area. The entire process closely revolves around precise analysis of yarn features, eliminating the need for large amounts of redundant image data and complex calculations to ensure accuracy, as is done in related technologies. This not only reduces the runtime of the image acquisition device, but also reduces the computational burden on the processing unit, making the entire yarn breakage detection method more efficient and energy-saving. It avoids or reduces the high power consumption problem caused by continuous image acquisition in related technologies, and significantly reduces the power consumption of yarn breakage identification. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the low-power yarn breakage detection method provided in an embodiment of this application;

[0023] Figure 2 This is a schematic diagram of the inspection device provided in the embodiments of this application;

[0024] Figure 3 This is one of the schematic diagrams illustrating the principle of the low-power yarn breakage detection method provided in the embodiments of this application;

[0025] Figure 4 This is the second schematic diagram of the principle of the low-power yarn breakage detection method provided in the embodiments of this application;

[0026] Figure 5 This is the third schematic diagram illustrating the principle of the low-power yarn breakage detection method provided in the embodiments of this application;

[0027] Figure 6 This is the fourth schematic diagram illustrating the principle of the low-power yarn breakage detection method provided in this application embodiment.

[0028] Figure 7 This is the fifth schematic diagram illustrating the principle of the low-power yarn breakage detection method provided in this application.

[0029] Figure 8 This is a schematic diagram of the structure of a low-power yarn breakage detection device provided in an embodiment of this application;

[0030] Figure 9 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application.

[0031] Explanation of reference numerals in the attached figures:

[0032] 1. Inspection device; 2. Spinning equipment; 3. Sensor; 4. Light source; 5. Camera; 6. Overfeed roller; 7. Yarn; 8. Motion system; 9. Navigation system;

[0033] 801. Acquisition module; 802. Detection module; 803. Filtering module; 804. Identification module; 805. Determination module; 901. Processor; 902. Memory; 903. Communication interface; 910. Bus. Detailed Implementation

[0034] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0035] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0036] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0037] At the forefront of the weaving process, yarn breakage frequently occurs on spinning machines and twisting machines during operation. This requires workers to continuously patrol and inspect to locate broken yarns and reconnect them. However, the harsh environment of the workshop, characterized by high dust, high noise, and high temperature, seriously threatens the health of the inspection workers. Therefore, developing a robot that can replace manual inspection is particularly urgent.

[0038] Currently, most inspection robots on the market are battery-powered, and are replaced when the battery is low to ensure 24-hour uninterrupted inspection. In order to reduce energy consumption, extend inspection time, and maximize battery efficiency, more stringent requirements have been placed on the hardware usage strategy, software computing power requirements, and inspection algorithms of inspection equipment.

[0039] Although engineers have experimented with various yarn inspection solutions over the years to improve automation in the textile industry and have developed some practical improvements, most of these solutions have not adequately considered energy consumption. For example, the inspection device is mounted on top of a mobile cart, and the image sensor is rotary, continuously driven to rotate by a control unit to collect images of the workstations on both sides. However, this active detection method results in the camera and light source running continuously, which not only increases power consumption but also fails to ensure that each acquired image accurately captures the target location.

[0040] For example, a pre-programmed inspection robot can film the working state of a twisting machine, acquiring video footage, and then extracting all frames as the first frame for analysis. However, this method requires continuous operation of the camera and light source to record video. While the convolutional neural network algorithm used can improve image recognition accuracy, its computationally intensive nature necessitates high-performance computing hardware acceleration, increasing the device's power consumption. Furthermore, some algorithm designs fail to adequately consider the physical and image characteristics of the yarn, making it difficult to effectively distinguish the yarn from the background when the yarn color is similar to the environment or when the yarn is moving rapidly, resulting in false alarms or missed alarms. Therefore, improving the accuracy of yarn breakage detection and reducing power consumption remain pressing issues for automated inspection technology in the textile industry.

[0041] To address the problems existing in related technologies, embodiments of this application provide a low-power yarn breakage detection method, apparatus, device, medium, and product.

[0042] This application provides a low-power yarn breakage detection method, apparatus, device, medium, and product. The low-power yarn breakage detection method provided in this application will be described first. For example... Figure 1 As shown, this method is applied to an inspection device 1, which is used to inspect a spinning equipment 2. The spinning equipment 2 includes multiple spinning stations. The method specifically includes the following steps:

[0043] S100, when the inspection device 1 inspects the first spinning station according to the preset inspection route and detects the target component on the first spinning station, the acquisition component of the inspection device 1 is triggered to acquire the target image corresponding to the first spinning station. The first spinning station is any one of the plurality of spinning stations, and the preset inspection route is an S-shaped route.

[0044] Optionally, the inspection device 1 refers to a device capable of automatically inspecting the spinning equipment 2 and detecting whether there are yarn breaks. Specifically, this inspection device 1 can be a robot integrating multiple sensors 3, cameras 5, light sources 4, and a motion system 8. This robot can move within the spinning workshop and inspect each spinning station one by one. In this application, as... Figure 2 As shown, the core components of the inspection device 1 include a host computer (for controlling the entire system), a mobile system 8 (enabling the robot to move within the workshop), a navigation system 9 (helping the robot find the correct path and spinning station), a camera 5 (for capturing images of the spinning station), a light source 4 (for illuminating the yarn so that the camera 5 can take pictures), and a sensor 3 (for detecting the spinning station and triggering the camera 5 and the light source 4).

[0045] Specifically, the host computer is the control center of the entire inspection device 1. It is responsible for receiving and processing information from various components and issuing control commands based on this information. The host computer can display the working status, location information, and detected yarn status of the inspection device 1 in real time; it can also control the movement path and speed of the inspection device 1 in the workshop by sending commands to the mobile system 8; it can also process and analyze the image data collected by the camera 5 to determine whether there is yarn breakage; and it can record important events and detection results during the detection process for subsequent analysis and improvement.

[0046] The mobile system 8 enables the inspection device 1 to move freely within the spinning workshop to inspect various spinning stations. The mobile system 8 may specifically include components such as a drive motor, wheels, or tracks. The mobile system 8 can adjust its direction and speed according to instructions from the host computer and, guided by the navigation system 9, automatically avoid obstacles and find the correct inspection path. The mobile system 8 can also maintain the stability of the inspection device 1 during movement to ensure the camera 5 and the light source 4 function properly.

[0047] The navigation system 9 helps the inspection device 1 find the correct travel path and spinning station within the spinning workshop. Based on environmental information collected by the sensor 3, the navigation system 9 constructs a workshop map and determines the real-time position of the inspection device 1. Subsequently, based on the workshop map and the inspection target, it plans the optimal movement path for the inspection device 1. The navigation system 9 can also monitor obstacles in real time during movement and guide the inspection device 1 to avoid them.

[0048] Camera 5 and light source 4 together constitute the acquisition component of inspection device 1. Camera 5 is used to acquire images of the spinning station. Light source 4 is used to illuminate the yarn so that camera 5 can capture clear images.

[0049] Sensor 3 is used to detect the spinning station and trigger camera 5 and light source 4. Specifically, sensor 3 can locate the position of the yarn by identifying specific components (such as overfeed roller 6) at the spinning station.

[0050] Optionally, spinning equipment 2 refers to a machine or device used to process fiber raw materials into yarn. In this application, spinning equipment 2 can be a doubling machine or a spinning frame. A doubling machine includes multiple spinning stations, each with one or more yarn processing units. A spinning station is a specific area or location on spinning equipment 2 used for processing yarn. On a doubling machine, each spinning station includes one or more yarn processing components, such as overfeed rollers 6, which work together to complete the yarn processing process. In this application, the spinning station is the target that the inspection device 1 needs to inspect and detect. The inspection device 1 locates the position of the yarn by identifying specific components (such as overfeed rollers 6) on the spinning station, and then performs yarn breakage detection.

[0051] Optionally, the target component refers to a specific component on the spinning station used to locate the yarn position or trigger the acquisition component. In this application, the target component can be one or more identifying components on the spinning station, such as the overfeed roller 6, the yarn guide, etc. These components have a fixed relationship with the position or movement trajectory of the yarn, so the position of the yarn can be indirectly located by identifying these components.

[0052] The acquisition component refers to the part of the inspection device 1 used to acquire image information of the spinning station. The acquisition component mainly consists of a camera 5 and possibly a matching light source 4. When the inspection device 1 inspects a spinning station and detects a target component at that station, the acquisition component is triggered and begins acquiring image information of that station. This image information is then used for subsequent yarn identification and yarn breakage detection.

[0053] Optionally, in one feasible implementation of this application, such as Figure 3As shown, when the inspection device 1 moves to any spinning station (i.e., the first spinning station) according to the preset inspection route, the inspection device 1 will first use the built-in sensor 3 to identify the target component at that station. For example, this target component can be the overfeed roller 6 at the twisting station. Since the relative position of the overfeed roller 6 and the yarn is fixed, once the sensor 3 successfully identifies the overfeed roller 6, it means that the inspection device 1 has indirectly located the position of the yarn.

[0054] It should be noted that setting the preset inspection route to an S-shaped path allows for better adaptation to the layout of spinning equipment in textile workshops without significantly increasing travel distance. This ensures that the inspection device 1 can approach each spinning station in a relatively even manner, thereby promptly detecting yarn breaks. Furthermore, the S-shaped path planning provides a stable foundation for subsequent targeted image acquisition and yarn breakage detection processes, making the entire detection process more orderly and helping to reduce overall power consumption. Because the S-shaped path reduces unnecessary movement and waiting time for the inspection device 1, detection resources can be more accurately allocated to the actual spinning stations requiring inspection, thus improving the performance and energy efficiency of the entire yarn breakage detection system.

[0055] Next, sensor 3 triggers camera 5 and light source 4 to start working via an electrical signal link. This triggering mechanism ensures that camera 5 and light source 4 are only activated when needed, thereby reducing power consumption and improving system response speed. After camera 5 and light source 4 are triggered, light source 4 starts working before camera 5, illuminating the yarn to ensure that camera 5 can capture clear and accurate images. Subsequently, camera 5 acquires images according to a preset callback image acquisition mode.

[0056] In callback-based image acquisition mode, by setting callback functions, camera 5 only acquires images when truly needed. The significant advantage of this method is that it greatly reduces the power consumption of camera 5, because camera 5 no longer performs endless image data acquisition tasks, but instead triggers image acquisition events based on the specific needs of the actual application. This is drastically different from the traditional inspection mode, which often continuously acquires images, requiring the application layer to use multi-threading technology to process this continuous stream of image data. This not only leads to fierce competition for system CPU resources but also incurs high image data processing costs. In contrast, callback-based image acquisition mode cleverly avoids frequent switching between multiple threads, thereby reducing the system burden.

[0057] Each time camera 5 passes the inspected station and is identified by sensor 3, it is hard-triggered to acquire an image. This hard-triggered method ensures that camera 5 acquires the target image at the correct time, thereby improving the accuracy and reliability of image acquisition. At the same time, since each station only needs to process one image, the system's response speed and real-time performance are also significantly improved.

[0058] Optionally, in one feasible implementation of this application, the inspection device 1 can utilize various sensors 3 to achieve precise detection in order to identify the target component. For example, since the position of the overfeed roller 6 on the twisting machine is fixed, the sensor 3 can determine its identity by measuring the distance or angle relative to the overfeed roller 6. Specifically, a high-precision position sensor 3 can be used, such as a photoelectric switch, a laser rangefinder 3, etc. When the sensor 3 detects a distance or angle matching a preset position, the overfeed roller 6 can be confirmed as identified.

[0059] In other embodiments, the overfeed roller 6 has specific physical characteristics such as shape, size, or material. The sensor 3 can determine whether it is an overfeed roller 6 by recognizing these characteristics. For example, an image recognition sensor 3 can capture an image of the overfeed roller 6 and compare it with a preset image template; or a shape sensor 3 can detect the contour and size of the overfeed roller 6 and match it with preset parameters.

[0060] In some implementations, to simplify the identification process, specific markings, such as QR codes, barcodes, or magnetic tags, can be added to the overfeed roller 6. The sensor 3 can quickly identify the overfeed roller 6 by reading these markings. For example, a QR code reader can be used to scan the QR code on the overfeed roller 6, or the magnetic sensor 3 can be used to detect the presence of a magnetic tag. In summary, the method by which the sensor 3 identifies whether it is an overfeed roller 6 depends on the physical characteristics of the overfeed roller 6, the operating environment, and the application requirements. By selecting appropriate location identification, feature identification, or tag identification methods, and a suitable sensor type 3, accurate and reliable identification can be achieved.

[0061] S200, Based on the yarn feature information, edge detection is performed on the target image to obtain an initial region of interest. The yarn feature information is used to characterize the yarn physical features and yarn image features of the yarn processed by the spinning equipment 2.

[0062] Optionally, yarn feature information can be used to describe the physical state of the yarn or its representation in an image. Yarn physical features refer to the inherent physical properties of the yarn itself, such as diameter, material, elasticity, and strength. Yarn image features are the representation of the yarn in an image, including color, brightness, texture, and shape. These yarn image features are extracted from images using image processing techniques and reflect the visual characteristics of the yarn within the image.

[0063] Optionally, in one feasible implementation of this application, in order to improve the image quality of the target image, reduce noise interference, and enhance the clarity of the yarn edges, the inspection device 1 can perform Gaussian filtering preprocessing on the acquired target image.

[0064] Specifically, a 3x3 Gaussian kernel can be constructed first. Each element of this kernel can be calculated using a Gaussian function, ensuring that the value of the central element is the largest, while the values ​​of surrounding elements gradually decrease with distance from the center, forming a weighted distribution with a high center and low periphery. This design allows the Gaussian kernel to assign higher weights to central pixels when processing images, while also considering the influence of its neighboring pixels; however, the weights of neighboring pixels decrease with increasing distance.

[0065] In practice, the inspection device 1 performs a convolution operation between the constructed Gaussian kernel and each pixel in the target image and its neighborhood. Specifically, each element of the Gaussian kernel is multiplied by the corresponding pixel value in the target image, and these products are summed. The sum is then assigned to the center pixel of the current sliding matrix in the target image. This convolution process is performed pixel by pixel in the target image until the entire target image is covered. In this way, each pixel in the target image is affected by its surrounding pixels (according to the weight distribution of the Gaussian kernel), thereby achieving image smoothing.

[0066] It should be noted that the smoothing effect of Gaussian filtering is closely related to the size of the Gaussian kernel and the standard deviation parameter. In this application, a 3x3 Gaussian kernel is chosen to achieve a moderate smoothing effect while ensuring computational efficiency. The standard deviation parameter determines the weight distribution range of the Gaussian kernel, that is, the neighborhood range that affects the center pixel. By reasonably setting these parameters, the inspection device 1 can remove image noise while preserving the sharpness and detail features of the yarn edges.

[0067] After Gaussian filtering preprocessing, noise in the target image is effectively suppressed, and the yarn edges become smoother and clearer. This lays a solid foundation for subsequent steps such as yarn edge detection, contour extraction, and yarn breakage identification. Therefore, Gaussian filtering preprocessing is an indispensable part of the inspection device 1 to achieve accurate yarn breakage detection, and it is also the key to improving detection efficiency and accuracy. Through the meticulous implementation of this step, the inspection device 1 can more accurately capture changes in the yarn state and issue timely yarn breakage warnings, providing strong technical support for the automation and intelligentization of spinning production.

[0068] After Gaussian filtering the target image, the inspection device 1 can employ one or more edge detection algorithms to accurately identify subtle changes in the yarn edges within the image. These edge detection algorithms meticulously analyze the grayscale or color values ​​of each pixel in the target image, searching for points where values ​​undergo significant transitions; these points typically indicate the location of object edges. To more accurately locate the yarn edges, the inspection device 1 dynamically adjusts the edge detection algorithms based on the physical and image characteristics of the yarn, such as adjusting detection sensitivity, gradient thresholds, or applying specific filters, to ensure that the algorithm accurately captures the yarn edges while effectively suppressing image noise and background interference.

[0069] Furthermore, the inspection device 1 can further optimize the edge detection results using morphological operations (such as dilation, erosion, opening, and closing operations). These operations enhance the coherence of the yarn edges, fill in minor breaks on the edges, and remove irrelevant fine structures. Through these refined edge detection steps, the inspection device 1 can accurately extract edge regions matching the yarn feature information from the target image. These regions are the initial regions of interest (ROIs), which not only contain the main outline of the yarn in the image but also cover some related areas around the yarn, providing image data for subsequent non-yarn region filtering and yarn recognition steps. It should be noted that although various image processing techniques and algorithms are mentioned in the above description, in practical applications, the inspection device 1 will flexibly select and combine these techniques and algorithms according to factors such as the specific characteristics of the yarn, image quality, and detection requirements to achieve the best edge detection effect. At the same time, the parameter settings for edge detection (such as gradient threshold, size and intensity of morphological operations, etc.) can also be dynamically adjusted and optimized according to the actual situation.

[0070] S300: Based on the yarn feature information, filter out the non-yarn regions in the initial region of interest to obtain the target region.

[0071] Optionally, in one feasible implementation of this application, after successfully obtaining the initial region of interest containing the yarn edge, the inspection device 1 will further utilize predefined yarn feature information to accurately distinguish the yarn region from other non-yarn regions in the initial region of interest.

[0072] Specifically, the inspection device 1 can employ one or more advanced image processing and classification techniques, such as color space conversion, threshold segmentation, machine learning classifiers (such as support vector machines, random forests, or deep learning models), or morphological operations, to analyze and compare the degree of matching between each pixel or pixel block in the initial region of interest and the yarn feature information.

[0073] During processing, the inspection device 1 can first apply color space conversion technology to transform the initial region of interest from the original color space (such as RGB) to a color space more suitable for yarn feature extraction and classification (such as hue, saturation, lightness (HSV), Lab, etc.) to better capture the color features of the yarn. Next, using threshold segmentation technology, the initial region of interest is divided into foreground (which can be yarn) and background based on features such as yarn brightness or color contrast. To further improve classification accuracy, the inspection device 1 can also employ machine learning classifiers. These classifiers have been trained and optimized using a large amount of training data containing both yarn and non-yarn samples, enabling them to accurately identify yarn and non-yarn regions within the initial region of interest. Furthermore, morphological operations (such as dilation, erosion, opening, and closing operations) are also used to optimize the classification results, further improving the accuracy and robustness of yarn recognition by enhancing the coherence of yarn regions, filling in minor breaks at edges, and removing irrelevant fine structures.

[0074] Ultimately, through this series of meticulous image processing and classification steps, the inspection device 1 successfully filters out non-yarn areas from the initial region of interest, obtaining a target region containing only the yarn and its surrounding key features. This target region not only provides clearer and more accurate input data for subsequent yarn identification steps but also significantly reduces computational load, improving the efficiency and accuracy of the entire yarn breakage detection process.

[0075] S400, based on the texture features of the target area and the yarn feature information, yarn identification is performed on the target area to obtain the identification result.

[0076] Optionally, in one feasible implementation of this application, yarn recognition in the target area is specifically achieved by comparing and matching the texture features of the target area with predefined yarn feature information. First, the inspection device 1 extracts the texture features of the target area. These features include, but are not limited to, local variation patterns of pixel values, edge density, texture directionality, and periodicity. These features reflect the unique characteristics of the yarn in the image, such as yarn thickness, texture density, and gloss. To extract these features, the inspection device 1 can employ texture analysis techniques such as Gray-Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP), Gabor filters, or convolutional neural networks in deep learning.

[0077] After extracting the texture features of the target area, the inspection device 1 compares and matches these texture features with a predefined yarn feature information database. This database, trained and learned from a large amount of sample data, contains typical texture features of various yarn types in the image. The comparison and matching process involves calculating feature vectors, converting the extracted texture features into mathematical vector form for quantitative comparison. Next, a suitable distance metric, such as Euclidean distance, Manhattan distance, or cosine similarity, is selected to measure the similarity or difference between the texture feature vector and the yarn feature vector. Based on this, classification algorithms, such as K-nearest neighbors, support vector machines, or decision trees, are applied to classify the texture features of the target area and determine its yarn type or state.

[0078] It should be noted that relying solely on comparison and matching may not be accurate enough, as noise, lighting variations, and other factors in the image can interfere with the recognition results. Therefore, the inspection device 1 can also employ some optimization strategies to improve the accuracy and robustness of the recognition. These strategies include using machine learning or deep learning models to further abstract and combine texture features to form more discriminative feature representations; and considering the contextual information of the yarn in the image, such as its position and orientation, which can help the inspection device 1 more accurately identify the yarn.

[0079] Ultimately, through the application of comparison, matching, and optimization strategies, the inspection device 1 can obtain an identification result indicating whether yarn exists in the target area and the type or state of the yarn. If the identification result indicates that no yarn exists in the target area, the inspection device 1 will further determine whether the situation is a yarn breakage, that is, whether the yarn failed to appear in the target area for some reason (such as breakage, detachment, or blockage). If a yarn breakage is confirmed, the inspection device 1 will issue a corresponding alarm or signal so that the operator can take timely measures to handle the situation.

[0080] S500, if the identification result indicates that there is no yarn in the target area, it is determined that there is a yarn breakage at the first spinning station.

[0081] Optionally, in one feasible implementation of this application, if the identification result clearly indicates that there is no yarn in the target area, the inspection device 1 will immediately initiate a series of subsequent judgment logic.

[0082] First, the inspection device 1 will conduct further analysis based on the operating logic of the spinning equipment 2. The spinning equipment 2 has a complex control system used to monitor and manage the operating status of each spinning station. The inspection device 1 will communicate with this control system to obtain the current operating status information of the spinning station, such as spinning speed and tension. If the identification result indicates that there is no yarn in the target area, but the spinning station is in normal operating condition (such as normal spinning speed and stable tension), then the inspection device 1 will preliminarily determine that there may be a yarn breakage at that spinning station.

[0083] To further improve the accuracy of the judgment, the inspection device 1 can also use other auxiliary means for verification. For example, the inspection device 1 can also use data from the sensors 3 of the spinning equipment 2, such as the yarn tension sensor 3 and the yarn breakage sensor 3, to assist in the judgment. If information from multiple sources points to a yarn breakage situation, then the inspection device 1 will ultimately confirm that there is a yarn breakage problem at that spinning station.

[0084] Once a yarn breakage is confirmed, the inspection device 1 will immediately issue an alarm or signal to notify the operator or the control system of the spinning equipment 2. This ensures that the operator can respond quickly and take necessary measures to resolve the problem, such as stopping the machine for inspection or replacing the yarn. Simultaneously, the inspection device 1 will also record the yarn breakage in a log for subsequent analysis and tracking.

[0085] In the low-power yarn breakage detection method provided in this application embodiment, the inspection device 1 adopts a specific triggering mechanism. It only activates the acquisition component to acquire the target image when it reaches the first spinning station along the S-shaped preset inspection route and detects the target component. This avoids or reduces the meaningless continuous operation of the image acquisition device, significantly reducing unnecessary energy consumption. Furthermore, the S-shaped inspection route is the optimal route for inspection. Based on the layout of the spinning equipment, the S-shaped inspection route can traverse each spinning station in an orderly, efficient, and energy-saving manner, effectively reducing the power consumption of yarn breakage detection in conjunction with the triggering acquisition mechanism. In the subsequent image processing stage, yarn breakage identification is performed based on predetermined yarn feature information. First, edge detection is performed on the target image to obtain the initial region of interest. Then, based on this, non-yarn areas are accurately filtered to obtain the target area. Finally, yarn identification is performed based on the texture features and yarn feature information of the target area. The entire process closely revolves around precise analysis of yarn features, eliminating the need for large amounts of redundant image data and complex calculations to ensure accuracy, as is the case in related technologies. This not only reduces the runtime of the image acquisition device, but also reduces the computational burden on the processing unit, making the entire yarn breakage detection method more efficient and energy-saving. It avoids or reduces the high power consumption problem caused by continuous image acquisition in related technologies, and significantly reduces the power consumption of yarn breakage identification.

[0086] In one embodiment, the step of performing edge detection on the target image based on yarn feature information to obtain an initial region of interest includes:

[0087] Obtain the gradient value corresponding to each pixel in the target image;

[0088] The pixel corresponding to the first value is determined as the edge point. The first value is the gradient value that is greater than a preset gradient threshold among the gradient values ​​corresponding to each pixel. The preset gradient threshold is determined according to the yarn feature information.

[0089] If the distance between two target points is less than a first preset threshold, the two target points are determined as connected edge points. The two target points are two edge points located in the same connected neighborhood. The first preset threshold is determined based on the yarn feature information.

[0090] Based on the contour shape of the processed yarn, contour fitting is performed on the connected edge points to form the initial region of interest.

[0091] Optionally, in one specific implementation of this application, the inspection device 1 first utilizes image processing techniques, such as the Sobel operator and the Canny edge detector, to calculate the gradient value of each pixel in the target image. The gradient value reflects the rate of change in pixel brightness in the image and is a crucial basis for edge detection. These gradient values ​​are then used to determine which pixels might be located on the edge of the yarn.

[0092] Next, the inspection device 1 presets a gradient threshold based on yarn characteristic information (such as yarn thickness, color contrast, etc.). This gradient threshold is used to distinguish which pixels have gradient values ​​large enough to be considered edge points. Specifically, the inspection device 1 iterates through the gradient values ​​of all pixels and marks the pixels with gradient values ​​greater than the preset gradient threshold as edge points. These edge points initially outline the contour of the yarn in the image.

[0093] However, relying solely on gradient values ​​to determine edge points may result in isolated edge points or broken edge lines. To address this issue, the inspection device 1 can further analyze the connectivity between these edge points. Specifically, it iterates through each edge point in the edge image, checking other edge points in its neighborhood. If the distance between two edge points is less than a preset distance threshold (this threshold is related to the yarn thickness), they are considered connected edge points, meaning they reside in the same connected neighborhood. In this way, the inspection device 1 can connect isolated edge points to form continuous edge lines. Subsequently, morphological operations (such as dilation and filling voids) are used to refine the edge contour, forming a continuous yarn contour. Finally, the initial region of interest suspected to be yarn is determined based on the bounding rectangle or minimum bounding rectangle of this contour.

[0094] In these alternative embodiments, the edges of the yarn are extracted from the target image based on yarn feature information, thereby forming an initial region of interest. By calculating gradient values ​​and setting a reasonable gradient threshold, the yarn can be effectively distinguished from the background, reducing noise interference. Simultaneously, connecting adjacent edge points and fitting contours accurately reflects the actual shape of the yarn, improving the accuracy of the region of interest. This process not only improves the accuracy of edge detection but also lays a solid foundation for subsequent yarn breakage analysis steps, contributing to improved overall processing efficiency and accuracy.

[0095] In one embodiment, the step of filtering non-yarn regions in the initial region of interest based on the yarn feature information to obtain the target region includes:

[0096] Connected pixel region identification is performed on the initial region of interest to obtain multiple identified regions;

[0097] If the boundary curvature of the first region is greater than a preset curvature threshold, or the area of ​​the first region is greater than a preset area threshold, or the aspect ratio of the first region is less than a second preset threshold, the first region is filtered out from the initial region of interest to obtain the target region. The first region is any one of the plurality of identification regions. The preset curvature threshold, the preset area threshold, and the second preset threshold are determined based on the yarn feature information.

[0098] Optionally, in one specific implementation of this application, firstly, a connected pixel region identification operation is performed on the initial region of interest. This operation can identify and segment all connected pixel sets to obtain a Blob region (i.e., the identification region). Each Blob region represents a potential yarn or interference region.

[0099] Subsequently, for each identified blob region, key features such as boundary curvature, area, and aspect ratio are calculated. Boundary curvature reflects the smoothness of the region's boundary, area measures the region's size, and aspect ratio reveals the region's shape characteristics. Next, based on the known characteristics of the yarn, a series of preset thresholds are established, including curvature threshold, area threshold, and aspect ratio threshold. These thresholds are used to evaluate whether each blob region conforms to the typical characteristics of the yarn.

[0100] Specifically, if the boundary curvature of a blob region is too large, it may indicate that its edges are irregular and do not conform to the smooth characteristics of yarn, since the ends of the working yarn are straight. If the area exceeds the preset range, it may mean that the region contains non-yarn interference. If the aspect ratio is too small, it may indicate that the region's shape is too flat and does not match the slender shape of the yarn. Based on these evaluation criteria, blob regions that do not meet the conditions are filtered out from the initial region of interest, and only those blob regions that conform to the yarn characteristics are retained as target regions. This process not only improves the accuracy of target region extraction but also effectively reduces noise and interference in subsequent processing, providing a reliable foundation for further yarn analysis and processing.

[0101] In these alternative implementations, the accuracy of target region extraction is significantly improved by precisely identifying and filtering non-yarn regions within the initial region of interest. Utilizing connected pixel region recognition technology, combined with curvature, area, and aspect ratio thresholds set based on yarn feature information, interfering regions with rugged edges, abnormal areas, or mismatched shapes are effectively eliminated. This process not only reduces noise and false detections but also ensures a close match between the target region and yarn features, providing more reliable data support for subsequent yarn analysis, defect detection, and other steps, thereby improving the overall processing efficiency and accuracy.

[0102] In one embodiment, the step of performing yarn identification on the target region based on the texture features of the target region and the yarn feature information to obtain an identification result includes:

[0103] By traversing each pixel in the target region at a preset distance and a preset direction, multiple pixel pairs are obtained, wherein the distance between the two pixels in a pixel pair is the preset distance, and the direction between the two pixels in a pixel pair is the preset direction;

[0104] The gray-level co-occurrence matrix of the target region is determined based on the gray values ​​of the plurality of pixel pairs;

[0105] If the texture features of the gray-level co-occurrence matrix meet the target preset conditions, the recognition result is determined to indicate that there is yarn in the target area. The texture features of the gray-level co-occurrence matrix include energy value, contrast value, correlation value, and entropy value. The target preset conditions are determined based on the yarn feature information.

[0106] If the texture features of the gray-level co-occurrence matrix do not meet the target preset conditions, the recognition result is determined to be that there is no yarn in the target area.

[0107] Optionally, in one specific implementation of this application, firstly, a set of preset distances and preset directions are set. The selection of these parameters can be based on the characteristic information of the yarn to ensure that key information about the yarn texture can be captured. Subsequently, each pixel in the target area is traversed, and the corresponding pixel pair is found according to the preset distance and direction. These pixel pairs constitute the basic data for analyzing texture features.

[0108] After acquiring all pixel pairs, the grayscale value of each pair is calculated, and a grayscale co-occurrence matrix (GCM) for the target region is constructed based on these grayscale values. The GCM is a two-dimensional array whose elements represent the frequency of pixel pairs with specific grayscale value combinations occurring at a specific direction and distance. This GCM provides detailed statistical information about the image texture and forms the basis for subsequent texture feature extraction.

[0109] Next, four key texture features are extracted from the gray-level co-occurrence matrix: energy value, contrast value, correlation value, and entropy value. The energy value reflects the uniformity of the image's gray-level distribution and the coarseness of the texture; a high energy value indicates a relatively uniform and coarse texture. Contrast value reveals the rate of local gray-level changes in the image; high contrast indicates significant variations in brightness. The correlation value measures the degree of linearity in the gray-level values ​​of the image; high correlation means that the gray-level changes in the image have stronger regularity. Entropy value reflects the randomness of the gray-level distribution in the image; a high entropy value indicates a more complex and chaotic image texture.

[0110] To determine the presence of yarn in the target area, a series of preset conditions are set for the four texture features mentioned above, based on known yarn characteristic information. These conditions are derived from the analysis and experimental data of a large number of yarn images, aiming to ensure the accuracy and reliability of the recognition results. For example, for energy values, a range can be set, where energy values ​​within this range are considered to represent the uniformity of the yarn texture; for contrast, a threshold can also be set, where contrast values ​​exceeding this threshold are considered to indicate significant changes in brightness and darkness in the yarn; similarly, corresponding judgment criteria are set for correlation and entropy values.

[0111] During the yarn identification stage, the texture features of the target area are compared one by one with the preset target conditions. If all texture features meet the conditions, it is determined that yarn exists in the target area, and the identification result is marked as "yarn exists". Conversely, if any texture feature does not meet the conditions, or if there is a significant deviation between the texture features of the target area and the yarn feature information, it is determined that yarn does not exist in the target area, and the identification result is marked as "yarn does not exist".

[0112] Alternatively, in another feasible implementation of this application, in addition to the gray-level co-occurrence matrix method, a deep learning-based yarn recognition method can also be used. This method utilizes deep learning algorithms, such as convolutional neural networks, to extract features and classify the image of the target region. Compared to the gray-level co-occurrence matrix, deep learning algorithms can automatically learn and extract high-level semantic features from the image without the need for manually designed feature extraction rules. This means that deep learning algorithms can more flexibly adapt to different yarn types and texture features, thereby improving the accuracy and generalization ability of recognition.

[0113] In deep learning solutions, the first step is to annotate and preprocess a large number of yarn images to construct a training dataset. Then, this dataset is used to train a convolutional neural network (CNN) to learn the texture features and classification rules of yarn. During training, the algorithm continuously optimizes the network parameters to improve the accuracy of yarn recognition. Once training is complete, the CNN can quickly and accurately identify yarn in new target region images.

[0114] Besides deep learning, yarn recognition can also be based on multi-scale feature fusion. This method combines image features at different scales to capture yarn texture information more comprehensively. In practice, the target region image can first be decomposed into sub-images at different scales. Then, features are extracted from each sub-image and fused to obtain a richer description of yarn texture features. This method can more effectively handle the complexity and diversity of yarn textures, improving the accuracy and robustness of recognition.

[0115] In these alternative embodiments, by capturing the texture features of the target area and utilizing the gray-level co-occurrence matrix and its texture feature parameters such as energy value, contrast, correlation value, and entropy value, accurate yarn identification is effectively achieved. This not only improves the accuracy and stability of identification but also has strong adaptability and robustness, enabling it to meet the yarn detection needs under complex environments with varying lighting and noise levels. Furthermore, this method is relatively simple to implement, computationally efficient, and reduces the power consumption of yarn breakage detection.

[0116] In one embodiment, before the inspection device 1 detects a target component at the first spinning station and triggers the acquisition component of the inspection device 1 to acquire the target image corresponding to the first spinning station, the method further includes:

[0117] The inspection device 1 is controlled to move and inspect along a preset path according to a preset inspection route. The preset path includes multiple main paths and multiple branch paths. The multiple main paths are connected to the multiple branch paths. The main paths are composed of the channels between the spinning equipment 2. The branch paths are composed of the passages between the first and second ends of the spinning equipment 2 along a preset direction. The inspection device 1 moves along the main path to any branch path.

[0118] Optionally, in one specific implementation of this application, the inspection strategy of the inspection device 1 is carefully designed as an efficient and flexible path planning scheme, aiming to ensure full coverage of the spinning station while maximizing inspection efficiency and minimizing path movement. For example... Figure 4 and Figure 5 As shown, the preset path is clearly divided into branch paths and main paths. Branch paths mainly consist of spacious passages between spinning equipment 2 (such as doubling equipment). These passages ensure that the inspection device 1 can smoothly move between various spinning stations for close-range, detailed inspection. The main path utilizes the passages of the spinning equipment 2 along preset directions (such as the front and rear ends of the equipment). These passages act as bridges connecting the various branch paths, enabling the inspection device 1 to efficiently switch between different branch paths.

[0119] In terms of inspection route (i.e., preset inspection route) planning, inspection device 1 adopts an S-shaped module movement strategy. The implementation process of this strategy is as follows: Figure 6As shown, the inspection device 1 starts from a preset starting point (or origin) and first moves along the main path to the front end of the nearest branch path. After entering the branch path, the inspection device 1 inspects each spinning station within the branch path in the order of entering from the front end and exiting from the back end. After completing the inspection of the current branch path, the inspection device 1 does not return directly to the main path, but continues along the S-shaped route, entering from the back end of the next adjacent branch path and exiting from the front end, and so on, until the inspection task of all branches is completed. This S-shaped movement mode not only avoids unnecessary path repetition, but also ensures that the inspection device 1 can evenly cover each spinning station, improving the efficiency and comprehensiveness of the inspection.

[0120] In these optional embodiments, by controlling the inspection device 1 to move and inspect along a preset path containing multiple main paths and multiple branch paths, the device can flexibly enter any branch path along the main path. This step ensures that the inspection device 1 can comprehensively and efficiently cover all spinning stations. This not only improves the automation level of the inspection but also optimizes the inspection path, reduces the possibility of missed inspections, and enhances inspection efficiency and accuracy, providing strong support for the stability and quality control of spinning production.

[0121] In one embodiment, controlling the inspection device 1 to move and inspect along a preset path according to a preset inspection route includes:

[0122] When the inspection device 1 moves to the first branch road and detects the first obstacle on the first branch road, the inspection device 1 is controlled to exit the first branch road in the opposite direction of the current driving direction and move to the next branch road of the first branch road in the preset inspection route. The first branch road is any one of the multiple branch road paths.

[0123] When the inspection device 1 moves to the first main road and detects a second obstacle on the first main road, the feasibility of the inspection device 1 bypassing the second obstacle according to the preset inspection route is obtained, where the first main road is any one of the multiple main road paths;

[0124] If the feasibility is greater than or equal to a third preset threshold, the inspection device 1 is controlled to bypass the second obstacle according to a supplementary route, the supplementary route being used to bypass the second obstacle;

[0125] If the feasibility is less than the third preset threshold, the inspection device 1 is controlled to return to the branch path of the last movement of the inspection device 1, and move from the target entrance of the branch path of the last movement to the next branch path, the next branch path being the branch path of the next movement of the inspection device 1 according to the preset inspection route.

[0126] Optionally, in one specific implementation of this application, such as Figure 7 As shown, firstly, when the inspection device 1 moves to the first branch of the preset path (here, "first branch" refers to any one of multiple branch paths) for inspection, the inspection device 1 uses its own sensors 3 or cameras to perceive the surrounding environment. If a first obstacle is detected on the first branch, it may hinder the normal progress of the inspection device 1. At this time, a reverse movement command is immediately triggered, controlling the inspection device 1 to gradually retreat in the opposite direction of the current travel direction until it completely exits the first branch. This step ensures that the inspection device 1 will not force its way through when encountering obstacles, avoiding or reducing possible collisions or damage. After exiting the first branch, the inspection device 1 will automatically adjust its direction according to the navigation information in the preset inspection route and move to the next branch of the preset inspection route.

[0127] However, as Figure 7 As shown, when the inspection device 1 moves along the main road path (here, "first main road" refers to any one of multiple main road paths), the situation becomes more complicated if a second obstacle is detected. In this case, the inspection device 1 needs to rely on its built-in navigation system 9 to assess the feasibility of bypassing the obstacle. This assessment process specifically involves a comprehensive consideration of the obstacle's location, size, shape, as well as the inspection device 1's own moving speed and turning capabilities.

[0128] If the navigation system 9 determines that the feasibility of bypassing the obstacle is greater than or equal to a third preset threshold (this threshold is preset based on the actual situation and inspection requirements), then the inspection device 1 will bypass the obstacle according to a supplementary route. This supplementary route is pre-planned to ensure that the inspection device 1 can continue inspection along the preset inspection route after bypassing the obstacle. During the obstacle bypass process, the inspection device 1 can adopt a smooth and efficient path planning strategy to minimize detour time and distance.

[0129] However, if the navigation system 9 determines that the feasibility of bypassing the obstacle is less than a third preset threshold, i.e., the bypass is too difficult or impossible, the inspection device 1 will adopt another strategy: return to the branch path of the previous movement and move to the next branch path from the other exit of that branch (i.e., the target entrance). This strategy ensures that the inspection device 1 can continue its inspection task even when it encounters an obstacle that cannot be bypassed, but simply by choosing a different path to bypass the obstacle. During the process of returning to the previous branch path and moving to the next branch path from the other exit, the inspection device 1 can use its own navigation system 9 to update its location information in real time and plan the optimal path.

[0130] In these alternative embodiments, when an obstacle is encountered on the first branch, the inspection device 1 can quickly reverse and turn to the next branch, avoiding stagnation. When an obstacle is encountered on the main road, by assessing the feasibility of detours, the inspection device 1 can intelligently choose to detour or return to the previous branch and enter the next branch from another entrance, effectively coping with complex environments. This strategy not only improves inspection efficiency but also reduces inspection interruptions caused by obstacles, providing a reliable guarantee for continuous monitoring of the spinning station.

[0131] Figure 8 A schematic diagram of a low-power yarn breakage detection device provided in another embodiment of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0132] Reference Figure 8 A low-power yarn breakage detection device is applied to an inspection device used to inspect spinning equipment. The spinning equipment includes multiple spinning stations, and the low-power yarn breakage inspection device may include:

[0133] The acquisition module 801 is used to trigger the acquisition component of the inspection device to acquire the target image corresponding to the first spinning station when the inspection device inspects the first spinning station according to the preset inspection route and detects the target component on the first spinning station. The first spinning station is any one of the plurality of spinning stations, and the preset inspection route is an S-shaped route.

[0134] Detection module 802 is used to perform edge detection on the target image based on yarn feature information to obtain an initial region of interest. The yarn feature information is used to characterize the yarn physical features and yarn image features of the yarn processed by the spinning equipment.

[0135] Filtering module 803 is used to filter non-yarn regions in the initial region of interest based on the yarn feature information to obtain the target region;

[0136] The identification module 804 is used to identify the yarn in the target area based on the texture features of the target area and the yarn feature information, and obtain the identification result.

[0137] The determination module 805 is used to determine that there is a yarn breakage at the first spinning station when the identification result indicates that there is no yarn in the target area.

[0138] In one embodiment, the detection module 802 may include:

[0139] The first acquisition submodule is used to acquire the gradient value corresponding to each pixel in the target image;

[0140] The first determining submodule is used to determine the pixel corresponding to the first value as the edge point, wherein the first value is the gradient value among the gradient values ​​corresponding to each pixel that is greater than a preset gradient threshold, and the preset gradient threshold is determined according to the yarn feature information.

[0141] The second determining submodule is used to determine the two target points as connected edge points when the distance between the two target points is less than a first preset threshold. The two target points are two edge points located in the same connected neighborhood. The first preset threshold is determined based on the yarn feature information.

[0142] The fitting submodule is used to fit the contour of the connected edge points based on the contour shape of the processed yarn to form the initial region of interest.

[0143] In one embodiment, the filtering module 803 may include:

[0144] The first recognition submodule is used to perform connected pixel region recognition on the initial region of interest to obtain multiple recognition regions;

[0145] The filtering submodule is used to filter the first region from the initial region of interest to obtain the target region when the boundary curvature of the first region is greater than a preset curvature threshold, or the area of ​​the first region is greater than a preset area threshold, or the aspect ratio of the first region is less than a second preset threshold. The first region is any one of the plurality of recognition regions. The preset curvature threshold, the preset area threshold, and the second preset threshold are determined according to the yarn feature information.

[0146] In one embodiment, the identification module 804 may include:

[0147] The third determining submodule is used to traverse each pixel in the target area at a preset distance and a preset direction to obtain multiple pixel pairs, wherein the distance between the two pixels in a pixel pair is the preset distance, and the direction between the two pixels in a pixel pair is the preset direction;

[0148] The fourth determining submodule is used to determine the gray-level co-occurrence matrix of the target region based on the gray-level values ​​of the plurality of pixel pairs;

[0149] The fifth determining submodule is used to determine the recognition result as indicating the presence of yarn in the target area when the texture features of the gray-level co-occurrence matrix meet the target preset conditions. The texture features of the gray-level co-occurrence matrix include energy value, contrast value, correlation value, and entropy value. The target preset conditions are determined based on the yarn feature information.

[0150] The sixth determining submodule is used to determine the recognition result as indicating that there is no yarn in the target area when the texture features of the gray-level co-occurrence matrix do not meet the target preset conditions.

[0151] In one embodiment, the low-power yarn breakage detection device may further include:

[0152] The control module is used to control the inspection device to move and inspect along a preset path according to a preset inspection route. The preset path includes multiple main paths and multiple branch paths. The multiple main paths are connected to the multiple branch paths. The main paths are composed of channels between the spinning equipment. The branch paths are composed of passages between the first and second ends of the spinning equipment along a preset direction. The inspection device moves along the main paths to any branch path.

[0153] In one embodiment, the control module may include:

[0154] The first control submodule is used to control the inspection device to exit the first branch in the opposite direction of the current travel direction and move to the next branch of the first branch in the preset inspection route when the inspection device moves to the first branch and detects the first obstacle on the first branch. The first branch is any one of the multiple branch paths.

[0155] The second acquisition submodule is used to acquire the feasibility of the inspection device bypassing the second obstacle according to the preset inspection route when the inspection device moves to the first main road and detects the second obstacle on the first main road. The first main road is any one of the multiple main road paths.

[0156] The second control submodule is used to control the inspection device to bypass the second obstacle by following a supplementary route when the feasibility is greater than or equal to a third preset threshold. The supplementary route is used to bypass the second obstacle.

[0157] The third control submodule is used to control the inspection device to return to the branch path of the last movement of the inspection device when the feasibility is less than the third preset threshold, and to move from the target entrance of the branch path of the last movement to the next branch path, wherein the next branch path is the branch path of the next movement of the inspection device according to the preset inspection route.

[0158] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application, and are devices corresponding to the above-mentioned methods. All implementation methods in the above-mentioned method embodiments are applicable to the embodiments of this device. For details on its specific functions and the technical effects it brings, please refer to the method embodiment section, which will not be repeated here.

[0159] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0160] Figure 9 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0161] The device may include a processor 901 and a memory 902 storing program instructions.

[0162] When processor 901 executes the program, it implements the steps in any of the above method embodiments.

[0163] For example, the program can be divided into one or more modules / units, one or more of which are stored in memory 902 and executed by processor 901 to complete this application. One or more modules / units can be a series of program instruction segments capable of performing a specific function, which describe the program's execution process in the device.

[0164] Specifically, the processor 901 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0165] Memory 902 may include mass storage for data or instructions. For example, and not limitingly, memory 902 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 902 may include removable or non-removable (or fixed) media. Where appropriate, memory 902 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 902 is non-volatile solid-state memory.

[0166] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0167] The processor 901 implements any of the methods described in the above embodiments by reading and executing program instructions stored in the memory 902.

[0168] In one example, the electronic device may also include a communication interface 903 and a bus 910. The processor 901, memory 902, and communication interface 903 are connected via the bus 910 and communicate with each other.

[0169] The communication interface 903 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0170] Bus 910 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 910 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0171] Furthermore, in conjunction with the methods in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium stores program instructions; when these program instructions are executed by a processor, they implement any of the methods in the above embodiments.

[0172] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0173] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0174] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above method embodiments and achieve the same technical effects. To avoid repetition, it will not be described again here.

[0175] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0176] The functional modules shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on machine-readable media or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer grids such as the Internet, intranets, etc.

[0177] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0178] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to create a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0179] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A low-power yarn breakage detection method, characterized in that, The method is applied to an inspection device used for inspecting spinning equipment, the spinning equipment including multiple spinning stations, and includes: When the inspection device inspects the first spinning station according to the preset inspection route and detects the target component on the first spinning station, the acquisition component of the inspection device is triggered to acquire the target image corresponding to the first spinning station. The first spinning station is any one of the plurality of spinning stations, and the preset inspection route is an S-shaped route. Based on yarn feature information, edge detection is performed on the target image to obtain an initial region of interest. The yarn feature information is used to characterize the yarn physical features and yarn image features of the yarn processed by the spinning equipment. Based on the yarn feature information, the non-yarn regions in the initial region of interest are filtered to obtain the target region; Based on the texture features of the target area and the yarn feature information, yarn identification is performed on the target area to obtain the identification result; If the identification result indicates that there is no yarn in the target area, it is determined that there is a yarn breakage at the first spinning station; The step of performing edge detection on the target image based on yarn feature information to obtain an initial region of interest includes: Obtain the gradient value corresponding to each pixel in the target image; The pixel corresponding to the first value is determined as the edge point. The first value is the gradient value that is greater than a preset gradient threshold among the gradient values ​​corresponding to each pixel. The preset gradient threshold is determined according to the yarn feature information. If the distance between two target points is less than a first preset threshold, the two target points are determined as connected edge points. The two target points are two edge points located in the same connected neighborhood. The first preset threshold is determined based on the yarn feature information. Based on the contour shape of the processed yarn, contour fitting is performed on the connected edge points to form the initial region of interest; The step of filtering non-yarn regions in the initial region of interest based on the yarn feature information to obtain the target region includes: Connected pixel region identification is performed on the initial region of interest to obtain multiple identified regions; If the boundary curvature of the first region is greater than a preset curvature threshold, or the area of ​​the first region is greater than a preset area threshold, or the aspect ratio of the first region is less than a second preset threshold, the first region is filtered out from the initial region of interest to obtain the target region. The first region is any one of the plurality of identification regions. The preset curvature threshold, the preset area threshold, and the second preset threshold are determined based on the yarn feature information. The step of identifying yarn in the target region based on the texture features and yarn feature information of the target region to obtain an identification result includes: By traversing each pixel in the target region at a preset distance and a first preset direction, multiple pixel pairs are obtained, wherein the distance between the two pixels in a pixel pair is the preset distance, and the direction between the two pixels in a pixel pair is the first preset direction; The gray-level co-occurrence matrix of the target region is determined based on the gray values ​​of the plurality of pixel pairs; If the texture features of the gray-level co-occurrence matrix meet the target preset conditions, the recognition result is determined to indicate that there is yarn in the target area. The texture features of the gray-level co-occurrence matrix include energy value, contrast value, correlation value, and entropy value. The target preset conditions are determined based on the yarn feature information. If the texture features of the gray-level co-occurrence matrix do not meet the target preset conditions, the recognition result is determined to be that there is no yarn in the target area.

2. The low-power yarn breakage detection method according to claim 1, characterized in that, Before the inspection device, following a preset inspection route, inspects the first spinning station and detects a target component at the first spinning station, and before triggering the acquisition component of the inspection device to acquire the target image corresponding to the first spinning station, the method further includes: The inspection device is controlled to move and inspect along a preset path according to the preset inspection route. The preset path includes multiple main paths and multiple branch paths. The multiple main paths are connected to the multiple branch paths. The main paths are composed of passages between the spinning equipment. The branch paths are composed of passages between the first and second ends of the spinning equipment along a second preset direction. The inspection device moves along the main path to any branch path.

3. The low-power yarn breakage detection method according to claim 2, characterized in that, The control of the inspection device to move and inspect along a preset path according to the preset inspection route includes: When the inspection device moves to the first branch road and detects the first obstacle on the first branch road, the inspection device is controlled to exit the first branch road in the opposite direction of the current travel direction and move to the next branch road of the first branch road in the preset inspection route. The first branch road is any one of the multiple branch road paths. When the inspection device moves to the first main road and detects a second obstacle on the first main road, the feasibility of the inspection device bypassing the second obstacle according to the preset inspection route is obtained, where the first main road is any one of the multiple main road paths; If the feasibility is greater than or equal to a third preset threshold, the inspection device is controlled to bypass the second obstacle according to a supplementary route, the supplementary route being used to bypass the second obstacle; If the feasibility is less than the third preset threshold, the inspection device is controlled to return to the branch path of the last movement of the inspection device, and move from the target entrance of the branch path of the last movement to the next branch path, the next branch path being the branch path of the next movement of the inspection device according to the preset inspection route.

4. A low-power yarn breakage detection device, characterized in that, An inspection device is used to inspect spinning equipment, which includes multiple spinning stations. The device includes: The acquisition module is used to trigger the acquisition component of the inspection device to acquire the target image corresponding to the first spinning station when the inspection device inspects the first spinning station according to the preset inspection route and detects the target component on the first spinning station. The first spinning station is any one of the plurality of spinning stations, and the preset inspection route is an S-shaped route. The detection module is used to perform edge detection on the target image based on yarn feature information to obtain an initial region of interest. The yarn feature information is used to characterize the yarn physical features and yarn image features of the yarn processed by the spinning equipment. The filtering module is used to filter non-yarn regions in the initial region of interest based on the yarn feature information to obtain the target region; The identification module is used to identify the yarn in the target area based on the texture features of the target area and the yarn feature information, and obtain the identification result; The determination module is used to determine that there is a yarn breakage at the first spinning station when the identification result indicates that there is no yarn in the target area; The step of performing edge detection on the target image based on yarn feature information to obtain an initial region of interest includes: Obtain the gradient value corresponding to each pixel in the target image; The pixel corresponding to the first value is determined as the edge point. The first value is the gradient value that is greater than a preset gradient threshold among the gradient values ​​corresponding to each pixel. The preset gradient threshold is determined according to the yarn feature information. If the distance between two target points is less than a first preset threshold, the two target points are determined as connected edge points. The two target points are two edge points located in the same connected neighborhood. The first preset threshold is determined based on the yarn feature information. Based on the contour shape of the processed yarn, contour fitting is performed on the connected edge points to form the initial region of interest; The step of filtering non-yarn regions in the initial region of interest based on the yarn feature information to obtain the target region includes: Connected pixel region identification is performed on the initial region of interest to obtain multiple identified regions; If the boundary curvature of the first region is greater than a preset curvature threshold, or the area of ​​the first region is greater than a preset area threshold, or the aspect ratio of the first region is less than a second preset threshold, the first region is filtered out from the initial region of interest to obtain the target region. The first region is any one of the plurality of identification regions. The preset curvature threshold, the preset area threshold, and the second preset threshold are determined based on the yarn feature information. The step of identifying yarn in the target region based on the texture features and yarn feature information of the target region to obtain an identification result includes: By traversing each pixel in the target region at a preset distance and a first preset direction, multiple pixel pairs are obtained, wherein the distance between the two pixels in a pixel pair is the preset distance, and the direction between the two pixels in a pixel pair is the first preset direction; The gray-level co-occurrence matrix of the target region is determined based on the gray values ​​of the plurality of pixel pairs; If the texture features of the gray-level co-occurrence matrix meet the target preset conditions, the recognition result is determined to indicate that there is yarn in the target area. The texture features of the gray-level co-occurrence matrix include energy value, contrast value, correlation value, and entropy value. The target preset conditions are determined based on the yarn feature information. If the texture features of the gray-level co-occurrence matrix do not meet the target preset conditions, the recognition result is determined to be that there is no yarn in the target area.

5. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the low-power yarn breakage detection method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the low-power yarn breakage detection method as described in any one of claims 1-3.

Images