A large circular weaving needle latch quality detection method and system

Abstract

This invention discloses a method for detecting the quality of needle latches on a circular knitting machine, comprising: segmenting a frontal image of the needle to be tested using an image segmentation method to obtain a frontal image of the needle latch; determining the degree of skewness of the needle latch relative to the needle body based on the frontal image of the needle latch; applying force to the closed needle latch along the opening direction; segmenting an image of the needle to be tested using an image segmentation method to obtain a side image of the needle latch; determining the opening state of the needle latch based on the side image; and determining the quality detection result of the needle latch based on the detection results of the opening state and the degree of skewness. This invention discloses a method and system for detecting the quality of needle latches on a circular knitting machine, which can quickly and accurately provide the quality detection results of the needle latch, providing a reliable basis for the timely replacement and maintenance of knitting needles in textile production, and helping to improve the quality of textiles and production efficiency.

Description

Technical Field

[0001] This invention relates to the fields of machine vision and mechanical design technology, specifically to a method and system for detecting the quality of needle latches on a large circular knitting machine. Background Technology

[0002] In the textile manufacturing industry, the circular knitting machine is a key piece of equipment for the production of knitted fabrics. The operational stability and efficiency of the circular knitting machine directly determine the output and quality of textile products. As the actuating component of the circular knitting machine, the needle is responsible for knitting the yarn into shape. During long-term high-speed operation, it is affected by multiple factors such as yarn friction, mechanical impact, and material wear, making the quality problems of the needle tongue part particularly prominent.

[0003] As the main structure controlling yarn feed and ensuring knitting continuity, the quality of the needle latch directly affects the lifespan of the knitting needle and the stability of the knitting process. Defects such as wear, deformation, jamming, and gaps in the needle latch not only accelerate the overall wear of the knitting needle and shorten its replacement cycle, but also directly lead to various defects during knitting, such as yarn breakage, fabric holes, missed stitches, and skipped stitches. In severe cases, it can even cause knitting needle jamming and loom shutdowns, significantly reducing production efficiency and increasing production costs and product rework rates. Therefore, inspecting the quality of the needle latch is an indispensable and crucial step in textile production. Whether it's routine maintenance and inspection of the knitting needle, pre-operation quality verification, or troubleshooting and analysis, the key components of the needle latch must be quality assessed to ensure that the knitting needle meets production and usage standards.

[0004] Currently, the quality inspection of knitting needle latches in the textile industry still largely relies on traditional manual inspection methods. This involves inspectors visually observing and tactilely sensing the needle latch to determine if it has defects or is ready for normal use. However, this traditional inspection method has many insurmountable drawbacks: On the one hand, manual inspection is extremely inefficient and cannot meet the batch inspection needs of a large number of knitting needles in large-scale textile production. After working for a long time, the inspectors are prone to visual fatigue, which leads to inspection omissions and makes it impossible to fully cover all needle tongue defects. On the other hand, the judgment results of manual inspection are greatly affected by factors such as the experience, sense of responsibility, and subjective judgment of the inspectors. There is a lack of unified and objective inspection standards, and the accuracy of judgment is difficult to guarantee. This may result in defective knitting needles being used on the machine due to misjudgment, which may lead to fabric defects and equipment damage. It may also result in knitting needles that are still usable being scrapped prematurely due to overjudgment, which may increase the cost of knitting needle consumables and is not conducive to the company's refined production and cost control. Summary of the Invention

[0005] This invention overcomes the shortcomings of the prior art and provides a method and system for detecting the quality of needle latches on circular knitting machines. It can quickly and accurately provide the detection results of needle latch quality, providing a reliable basis for timely replacement and maintenance of knitting needles in textile production, and helping to improve the quality of textiles and production efficiency. It realizes the detection of needle latch quality on circular knitting machines, effectively overcoming the shortcomings of low efficiency and easy error in manual detection.

[0006] To achieve the above objectives, the present invention provides a method for quality inspection of the latch of a circular knitting machine needle, comprising the following steps: acquiring a front image of the needle to be inspected; segmenting the front image of the needle to be inspected using an image segmentation method to obtain a front image of the latch of the needle to be inspected; determining the degree of skewness of the latch of the needle to be inspected relative to the needle body based on the front image of the latch of the needle to be inspected; applying force to the closed latch along the opening direction of the latch; acquiring a side image of the needle to be inspected; segmenting the image of the needle to be inspected using an image segmentation method to obtain a side image of the latch of the needle to be inspected; determining the opening state of the latch based on the side image of the latch; and determining the quality inspection result of the latch of the needle to be inspected based on the detection results of the opening state and the degree of skewness.

[0007] In a preferred embodiment of the present invention, before acquiring a frontal image of the needle to be tested, the needle to be tested is selected, the needle tongue is closed, and the needle is clamped on the device by a needle fixing clamp.

[0008] In a preferred embodiment of the present invention, obtaining the degree of skewness includes the following steps: The image of the latch of the knitting needle to be detected is preprocessed to obtain a preprocessed image of the latch; the preprocessing operation includes grayscale conversion, Gaussian blurring, binarization and median filtering. The needle tongue preprocessed image is subjected to a small kernel erosion operation to obtain a needle tongue erosion image; On the etched image of the needle tongue, the connected regions of the preprocessed image of the needle tongue are identified and calculated, and the region with the largest area is selected as the main region Ω. Record the maximum row index in the main region Ω. Corresponding feature pixel set ; Calculate the set of feature pixels Minimum value of column index Maximum value of column index The arithmetic mean of the reference center column is used as the reference center column index. : ; Iterate through the column indices C of all feature region pixels in the main region Ω and obtain the minimum global column index. Maximum value of global column index and calculate respectively and Columns with reference center The absolute value of the difference is used to obtain the left deviation distance. Distance from the right : ; ; Calculate the absolute value of the difference in deviation distance between the two sides, and use it as the asymmetric deviation value. ; When the asymmetric deviation value greater than the preset needle type skew threshold At that time, it was determined to be a needle tongue deviation; When the asymmetric deviation value Less than or equal to the preset needle type skew threshold At that time, the needle tongue was judged to be normal.

[0009] In a preferred embodiment of the present invention, a mechanical air blowing device is used to blow air at a certain angle and force along the normal opening direction of the needle tongue to close the needle tongue, including the following steps: Fix the mechanical air blowing device to the knitting needle fixing clamp below the needle tongue; Position the nozzle of the air blowing device at a certain angle, tilting it upwards towards the direction in which the needle tongue normally opens; The airflow is blown evenly onto the needle tongue with just enough force to make it open.

[0010] In a preferred embodiment of the present invention, the blowing control method includes: Establish a three-dimensional spatial coordinate system with the knitting needle fixing clamp as the origin, and set the center of the nozzle of the mechanical air blowing device at a preset coordinate point below the needle tongue rotation axis. ; Adjust the nozzle's spray direction vector So that the angle between it and the axis of the needle body satisfy This ensures that the airflow is directed obliquely upwards towards the force-bearing edge of the needle tongue; The instantaneous airflow pressure P generated by the air blowing device satisfies The pressure range is set to a critical value that just overcomes the normal frictional force of the needle tongue rotation without causing the needle body to vibrate. It adopts a pulsed air blowing method with a blowing time t of 100ms-300ms, and uses the instantaneous inertia of the airflow impact force to make the needle tongue completely flip to the maximum opening position.

[0011] In a preferred embodiment of the present invention, obtaining the open state of the needle tongue includes the following steps: The image of the side of the needle tongue of the knitting needle to be inspected is preprocessed and morphologically operated to obtain the connected component Ω of the main region; Obtain the bounding box of the connected component Ω and record the maximum column index of the top of the hook. The maximum value of the row index at the bottom of the needle body and the minimum row index at the top ; Calculate the characteristic height of the hook region And set a dynamic detection benchmark based on H: First benchmark line ,in This is the height coefficient, with a value range of 1.1-1.3; Second benchmark column ,in This is the width coefficient, with a value ranging from 0.2 to 0.3. Statistical row standard equals Feature pixel set Number of pixels Get column index equal to The set of row numbers of all feature pixels ; If satisfied If the values ​​within the set of row numbers K are not continuous, it is determined that the needle is not flexible. If satisfied If the values ​​inside the row number set K are a continuous integer sequence, then it is determined to be a flexible needle tongue.

[0012] In a preferred embodiment of the present invention, the quality inspection result of the probe to be inspected is determined based on the detection results of the open state and the degree of skewness, including: If the needle tongue deviation test result is no deviation and the needle tongue flexibility test result is flexible, then the quality test result of the needle is qualified and the needle can continue to be used. If the needle tongue deviation test result is needle tongue deviation, or the needle tongue flexibility test result is needle tongue inflexibility, then the quality test result of the needle is that the needle is unqualified and the needle should be replaced.

[0013] In a preferred embodiment of the present invention, a circular knitting machine needle latch quality detection system is provided. The system employs a circular knitting machine needle latch quality detection method and includes: Front image acquisition module, used to acquire a front image of the needle to be detected; The side image acquisition module is used to acquire the side image of the needle to be detected; The frontal image segmentation module is used to segment the image of the knitting needle to be detected using image segmentation methods to obtain the frontal image of the needle's tab. The side image segmentation module is used to segment the image of the knitting needle to be detected using image segmentation methods to obtain the side image of the knitting needle to be detected. The needle tongue skew detection module is used to determine the needle tongue skew detection result based on the image of the needle tongue of the needle to be detected. The needle tongue flexibility detection module is used to determine the needle tongue flexibility detection result based on the needle tongue image of the knitting needle to be tested; The needle quality inspection module determines the quality level of the needle to be inspected based on the needle tongue skew detection results and the needle tongue flexibility detection results.

[0014] In a preferred embodiment of the present invention, a computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for detecting the quality of needle latches on a circular knitting machine.

[0015] In a preferred embodiment of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a method for detecting the quality of the needle latch of a circular knitting machine.

[0016] In a preferred embodiment of the present invention, a computer program product includes a computer program that, when executed by a processor, implements a method for detecting the quality of the needle latch of a circular knitting machine.

[0017] This invention addresses the deficiencies in the technical background, and the beneficial technical effects of this invention are: A method and system for detecting the quality of needle latches on circular knitting machines is provided, which can quickly and accurately provide the detection results of needle latch quality, providing a reliable basis for timely replacement and maintenance of knitting needles in textile production, and helping to improve the quality of textiles and production efficiency; it realizes the detection of needle latch quality on circular knitting machines, effectively overcoming the shortcomings of low efficiency and easy error in manual detection.

[0018] 1. By acquiring images of the knitting needle to be inspected and using image segmentation methods to accurately segment the front and side images of the needle tab, the problem of difficulty in accurately acquiring clear images of various parts of the knitting needle in traditional manual inspection is solved, and rapid, non-destructive acquisition and separation of images of key parts of the knitting needle is achieved. 2. By basing assessments on the degree of needle tongue skew and the open state, the problem of subjective judgment and inability to accurately quantify needle tongue quality is solved, thus enabling objective and accurate evaluation of the quality of various parts of the knitting needle. 3. The quality of the needle latch of the knitting needle to be tested is determined by comprehensively considering the degree of needle latch skew and the open state. This solves the problems of low efficiency and easy error in manual comprehensive judgment, and realizes a rapid and reliable judgment of the overall quality of the knitting needle, providing a scientific basis for the timely replacement and maintenance of the knitting needle. Attached Figure Description

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] Figure 1 This is an application environment diagram of a method for detecting the quality of needle latches on a circular knitting machine according to an embodiment of this application; Figure 2 A flowchart illustrating a method for detecting the quality of needle latches on a circular knitting machine, provided in an embodiment of this application; Figure 3 A frontal view of the needle tongue provided in one embodiment of this application; wherein, Figure 3 (a1) represents a frontal view of a normal needle tongue area; Figure 3 (b1) shows a frontal view of the tongue area after it has become misaligned; Figure 4 A side view of the needle tongue provided in one embodiment of this application; wherein, Figure 4 (a2) shows a side view of the needle tongue area of ​​a normal circular knitting machine needle; Figure 4 (b2) shows a side view of the latch area of ​​a non-flexible circular knitting needle; Figure 5 This is an image of a frontal pin tongue after image processing, provided in one embodiment of this application; wherein, Figure 5 Image (a3) ​​shows a schematic diagram of the normal frontal pin tongue area after image processing; Figure 5 (b3) shows a schematic diagram of the frontal pin tongue area after image processing, which has become skewed; Figure 6 This application provides an image of a processed side view of a needle tongue according to an embodiment of the present application; wherein, Figure 6 Image (a4) shows a schematic diagram of the normal side view of the needle tongue after image processing; Figure 6 (b4) shows a schematic diagram of the inflexible side needle tongue after image processing; Figure 7 This is a schematic diagram illustrating the air blowing device nozzle blowing air obliquely upwards toward the normal opening direction of the needle latch in a method for detecting the quality of the needle latch on a large circular knitting machine according to an embodiment of this application, thereby providing an airflow force for opening the needle latch. Figure 8 This is a schematic diagram of the structure of a circular knitting needle latch quality detection system provided in an embodiment of this application. Detailed Implementation

[0021] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. These drawings are simplified schematic diagrams, which are only used to illustrate the basic structure of the present invention and therefore only show the components relevant to the present invention.

[0022] It should be noted that if directional indicators (such as up, down, bottom, top, etc.) are involved in the embodiments of the present invention, these directional indicators are only used to explain the relative positional relationship and movement of the components in a specific posture. If the specific posture changes, the directional indicators will also change accordingly. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of that feature. Unless otherwise explicitly specified and limited, the terms "set," "connected," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal connection of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0023] Example 1, as Figures 1-3 As shown, a method for detecting the quality of the needle latch of a circular knitting machine includes the following steps; Obtain the front image of the knitting needle to be detected.

[0024] The front image of the needle to be detected is segmented using an image segmentation method to obtain the front image of the needle tab of the needle to be detected; Based on the frontal image of the needle latch of the needle to be detected, the degree of skewness of the needle latch relative to the needle body is determined. Further, the determination of the skewness includes the following steps: preprocessing the frontal image of the needle latch to obtain a preprocessed image; the preprocessing operations include grayscale conversion, Gaussian blurring, binarization, and median filtering; performing a little-kernel erosion operation on the preprocessed image to obtain an eroded image; identifying and calculating the connected components of the preprocessed image on the eroded image, selecting the largest area as the main region Ω; and recording the maximum row index value within the main region Ω. The corresponding set of feature pixels (in this implementation, the bright area). ; Calculate the set of feature pixels Minimum value of column index Maximum value of column index The arithmetic mean of the reference center column is used as the reference center column index. : ; Traverse the column indices C of all feature region pixels in the main region Ω and obtain the minimum global column index. Maximum value of global column index and calculate respectively and Columns with reference center The absolute value of the difference is used to obtain the left deviation distance. Distance from the right : ; Calculate the absolute value of the difference between the left and right deviation distances, and use it as the asymmetric deviation value. When the asymmetric deviation value greater than the preset needle type skew threshold When the asymmetric deviation value is [value missing], it is determined to be needle tongue deviation; when the asymmetric deviation value is [value missing], it is determined to be needle tongue deviation. Less than or equal to the preset needle type skew threshold At that time, the needle tongue was judged to be normal.

[0025] Apply force to the closed needle tongue along the opening direction. Further, use a mechanical air blowing device to blow air at a certain angle and force along the normal opening direction of the needle tongue to close it.

[0026] Obtain a side image of the needle to be inspected; An image segmentation method is used to segment the image of the knitting needle to be detected, thereby obtaining a side image of the needle's tab. Based on the side image of the needle latch, the open state of the needle latch is determined. Further, obtaining the open state of the needle latch includes the following steps: preprocessing and morphological operations on the side image of the needle latch of the needle to be detected, wherein the preprocessing includes grayscale conversion, Gaussian blurring, binarization, and median filtering of the side image of the needle latch of the needle to be detected. On the side image of the needle latch, the connected components of the preprocessed image are identified and calculated, and the largest area is selected as the main region, obtaining the connected component Ω of the main region; the bounding box of the connected component Ω is obtained, and the maximum value of the column index at the top of the needle hook is recorded. The maximum value of the row index at the bottom of the needle body and the minimum row index at the top ; Calculate the characteristic height of the hook region And based on H, a dynamic detection benchmark is set: the first benchmark row ,in This is the height coefficient, with a value range of 1.1-1.3; second benchmark column. ,in This is the width coefficient, ranging from 0.2 to 0.3; the statistical row index is equal to... Feature (bright area in this embodiment) pixel set Number of pixels Get column index equal to The set of row numbers for all feature pixels (bright areas in this implementation). If satisfied If the values ​​within the row number set K are not consecutive, then the needle is determined to be inflexible; if the following conditions are met... If the set of row numbers K contains a continuous sequence of integers, then it is determined to be a flexible needle tongue.

[0027] Based on the test results of the open state and degree of skewness, the quality test result of the needle latch to be tested is determined, including: if the needle latch skewness test result is that the needle latch is not skewed and the needle latch flexibility test result is that the needle latch is flexible, then the quality test result of the needle to be tested is that the needle quality is qualified and the needle can continue to be used; if the needle latch skewness test result is that the needle latch is skewed, or the needle latch flexibility test result is that the needle latch is not flexible, then the quality test result of the needle to be tested is that the needle quality is unqualified and the needle is replaced.

[0028] In Example 2, based on Example 1, before acquiring the frontal image of the needle to be tested, the needle to be tested is selected, and the needle's latch is closed. The needle is then clamped onto the device using a needle fixing clamp. Specifically, the clamping structure and clamping spacing of the needle fixing clamp are set according to the shoulder position and body thickness of different needle models. The corresponding needle model is placed into the clamp for clamping and fixing.

[0029] Furthermore, the mechanical air blowing device is fixed below the needle clamp near the needle tongue; the nozzle of the air blowing device is tilted upwards at a certain angle towards the normal opening direction of the needle tongue; and the airflow force is evenly blown onto the needle tongue so that the needle tongue can be just blown open.

[0030] Example 3, based on Example 1 or Example 2, such as Figure 2 As shown, a method for detecting the quality of needle latches on a circular knitting machine is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps: Step 201: The needle to be tested is clamped onto the device using a needle fixing clamp. The entire image sampling process for the test is static.

[0031] Step 202: Obtain an image of the knitting needle to be inspected. An industrial camera is used to capture an overall image of the knitting needle.

[0032] Step 203: The image of the needle to be detected is segmented using an image segmentation method to obtain a frontal image of the needle latch, such as... Figure 3 As shown.

[0033] Step 204: Based on the image of the needle tongue on the front of the needle to be detected, determine the degree of skewness of the needle tongue relative to the needle body.

[0034] Step 205: Using a mechanical air blowing device, blow air at a certain angle and force along the normal opening direction of the needle tongue to the closed needle tongue.

[0035] Step 206: Obtain a side view image of the needle to be detected.

[0036] Step 207: The side image of the needle to be detected is segmented using an image segmentation method to obtain the side image of the needle tab of the needle to be detected, such as... Figure 4 .

[0037] Step 208: Determine the open state of the needle latch based on the side image of the needle to be detected.

[0038] Step 209: Determine the quality inspection result of the needle tongue to be inspected based on the detection results of the open state and the degree of tilt.

[0039] By implementing steps 201 to 209 above, this application can provide quality detection for the needle latch of a circular knitting machine, which can accurately and quickly realize automatic detection of the quality of key parts of the needle, thereby improving the degree of automation.

[0040] In another exemplary embodiment of this application, step 204 specifically includes: A preprocessing operation is performed on the front image of the needle latch of the knitting needle to be inspected, resulting in a preprocessed needle latch image. This preprocessing includes grayscale conversion, Gaussian blurring, binarization, and median filtering. These image processing operations enhance image features, remove noise, and make the needle latch area clearer, facilitating the determination of whether the needle latch is misaligned.

[0041] A small-kernel (3×3) erosion operation is performed on the preprocessed needle latch image to make the needle edges clearer, resulting in an eroded image of the front of the needle latch. This further highlights the skewed features of the needle latch, making the skewed area more obvious.

[0042] Identify all connected components of the pinhole erosion image, select the largest area as the main region, and record the maximum row index of the main region Ω. Corresponding feature pixel set ; Calculate the set of feature pixels Minimum value of column index Maximum value of column index The arithmetic mean of the reference center column is used as the reference center column index. : ; Traverse the column indices C of all feature region pixels in the main region Ω and obtain the minimum global column index. Maximum value of global column index and calculate respectively and Columns with reference center The absolute value of the difference is used to obtain the left deviation distance. Distance from the right : ; Calculate the absolute value of the difference between the left and right deviation distances, and use it as the asymmetric deviation value. When the asymmetric deviation value greater than the preset needle type skew threshold When the asymmetric deviation value is [value missing], it is determined to be needle tongue deviation; when the asymmetric deviation value is [value missing], it is determined to be needle tongue deviation. Less than or equal to the preset needle type skew threshold At that time, the needle tongue was judged to be normal.

[0043] like Figure 5 As shown, a frontal image of the needle tongue after image processing is provided. Figure 5 (a3) Schematic diagram of the normal needle tongue area after image processing; Figure 5 (b3) Schematic diagram of the skewed needle tongue after image processing.

[0044] In another exemplary embodiment of this application, step 205 specifically includes: Fix the mechanical air blowing device below the needle clamp near the needle tongue to ensure that the needle and the air blowing position are fixed and to prevent the air from blowing off to one side.

[0045] Position the nozzle of the air blowing device at a certain angle, tilting it upwards towards the direction in which the needle tongue normally opens.

[0046] An airflow of just enough force to open the needle latch is evenly directed at it, allowing the latch to open naturally due to the inertia of the airflow. Specifically, a three-dimensional coordinate system is established with the knitting needle clamp as the origin, and the center of the nozzle of the mechanical air blowing device is set at a preset coordinate point below the needle latch rotation axis. Adjust the nozzle's spray direction vector. So that the angle between it and the axis of the needle body satisfy Ensure the airflow is directed obliquely upwards towards the force-bearing edge of the needle tongue; control the instantaneous airflow pressure P generated by the blowing device to meet the requirements. The pressure range is set to a critical value that just overcomes the normal friction of the needle tongue rotation without causing the needle body to vibrate; a pulse blowing method is adopted, and the blowing time t is 100ms-300ms. The instantaneous inertia of the airflow impact force is used to make the needle tongue completely flip to the maximum open position. In this embodiment, the blowing time t is 200ms.

[0047] like Figure 7As shown, in the method for detecting the quality of the needle latch of a circular knitting machine, the nozzle of the air blowing device blows air obliquely upward toward the normal opening direction of the needle latch, providing an airflow force for opening the needle latch.

[0048] In another exemplary embodiment of this application, step 208 specifically includes: The preprocessing and morphological operations on the side image of the needle latch of the knitting needle to be inspected include: preprocessing the side image of the needle latch of the knitting needle to be inspected, including grayscale conversion, Gaussian blurring, binarization, and median filtering; identifying and calculating the connected components of the preprocessed needle latch image on the side image, and selecting the largest area as the connected component Ω of the main region. Morphological operations include a small kernel (3×3) erosion operation to remove noise interference and make the edges of the needle latch area clear, thus obtaining the needle latch image.

[0049] On the needle tongue image, identify and calculate the connected components of the preprocessed needle tongue image, and select the region with the largest area as the main body region; obtain the bounding box of the connected component Ω, and record the maximum column index value of the top of the needle hook. The maximum value of the row index at the bottom of the needle body and the minimum row index at the top ; Calculate the characteristic height of the hook region And based on H, a dynamic detection benchmark is set: the first benchmark row ,in This is a height coefficient, ranging from 1.1 to 1.3. In one embodiment, a preferred value is 1.2. Second reference column. ,in This is the width coefficient, ranging from 0.2 to 0.3. In one embodiment, a preferred value is 0.25. The statistical row index equals... bright pixel set Number of pixels Get column index equal to The set of row numbers for all bright pixels If satisfied If the values ​​within the row number set K are not consecutive, then the needle is determined to be inflexible; if the following conditions are met... If the set of row numbers K contains a continuous sequence of integers, then it is determined to be a flexible needle tongue. For example... Figure 6 As shown, a side view image of the needle tongue after image processing is provided. Figure 6 (a4) Schematic diagram of the normal needle tongue area after image processing; Figure 6 (b4) Schematic diagram of the skewed needle tongue after image processing.

[0050] In another exemplary embodiment of this application, step 209 specifically includes: If the needle tongue deviation test result shows no deviation and the needle tongue flexibility test result shows flexible, then the quality test result of the needle is qualified and it can continue to be used.

[0051] If the needle tongue deviation test result is needle tongue deviation, or the needle tongue flexibility test result is needle tongue inflexibility, then the quality test result of the needle is that the needle is unqualified and should be replaced.

[0052] This application also provides an application scenario in which the above-mentioned circular knitting machine needle latch quality inspection method is applied. Specifically, the circular knitting machine needle latch quality inspection method provided in this embodiment can be applied in textile production quality monitoring scenarios. Textile production quality monitoring scenarios include a pre-machine calibration stage for knitting needles, a production process sampling inspection stage, and a fault analysis stage. Knitting needles enter the pre-machine calibration stage from the procurement or storage stage. After a preliminary visual inspection, the circular knitting machine needle latch quality inspection method of this embodiment is used for precise inspection, obtaining the results of needle latch skewness and flexibility detection, and then proceeding to the subsequent classification, storage, or usage decision stage. During the production process, knitting needles are periodically sampled from the circular knitting machine for the production process sampling inspection stage, and the same inspection method is used to detect changes in needle latch quality in a timely manner. When fabric defects or other faults occur, the relevant knitting needles enter the fault analysis stage, where this inspection method is used to determine whether the quality problem with the needle latch is the cause of the fault. The circular knitting machine needle latch quality inspection method provided in this embodiment belongs to the needle status detection stage in textile production quality monitoring. Specifically, it uses industrial cameras to capture images of knitting needles from different angles, and performs steps such as needle tongue skew and flexibility detection through image segmentation. This provides an accurate basis for quality assessment and usage decisions of knitting needles in textile production, which helps to improve the quality and production efficiency of textiles and reduce production costs.

[0053] Example 4: A method for detecting the quality of the needle latch on a circular knitting machine, which can be applied to, for example... Figure 1In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be set up independently, integrated into server 102, or placed in the cloud or on another server. Terminal 101 can send an image of the needle to be inspected to server 102. After receiving the image, server 102 uses an image segmentation method to segment the image of the needle to obtain front and side images of the needle latch. Based on the front image of the needle latch, the server determines the needle latch skew detection result; based on the side image of the needle latch, the server determines the needle latch flexibility detection result; and based on the needle latch skew and flexibility detection results, the server determines the quality detection result of the needle latch. Server 102 can then feed back the obtained needle latch quality detection result to terminal 101. In addition, in some embodiments, the method for detecting the quality of the needle tongue of a circular knitting machine can also be implemented by the server 102 or the terminal 101 separately. For example, the terminal 101 can directly perform detection processing on the image of the needle to be detected, or the server 102 can obtain the image of the needle to be detected from the data storage system and perform detection processing on the image of the needle to be detected.

[0054] The terminal 101 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. The server 102 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0055] Example 5: Based on the same inventive concept, this application also provides a circular knitting machine needle latch quality inspection system for implementing the aforementioned circular knitting machine needle latch quality inspection method. The solution provided by this system is similar to the implementation described in the above method. Therefore, the specific limitations of one or more circular knitting machine needle latch quality inspection system embodiments provided below can be found in the limitations of the circular knitting machine needle latch quality inspection method described above, and will not be repeated here.

[0056] In one exemplary embodiment, such as Figure 8 As shown, a quality inspection system for the needle latch of a large circular knitting machine is provided, comprising: The front image acquisition module 301 is used to acquire the front image of the knitting needle to be detected.

[0057] The side image acquisition module 302 is used to acquire the side image of the needle to be detected.

[0058] The front image segmentation module 303 is used to segment the image of the needle to be detected using an image segmentation method to obtain the front image of the needle's tab.

[0059] The side image segmentation module 304 is used to segment the image of the knitting needle to be detected using an image segmentation method to obtain a side image of the knitting needle to be detected.

[0060] The needle tongue skew detection module 305 is used to determine the needle tongue skew detection result based on the needle tongue image of the needle to be detected.

[0061] The needle tongue flexibility detection module 306 is used to determine the needle tongue flexibility detection result based on the needle tongue image of the needle to be detected.

[0062] The needle latch quality detection module 307 determines the quality level detection result of the needle to be tested based on the needle latch skew detection result and the needle latch flexibility detection result.

[0063] As an optional implementation, the circular knitting machine needle latch quality inspection system also includes: The sample carrier module is used to fix the knitting needle to be tested and provide a suitable background color to highlight the feature.

[0064] The image acquisition module is used to capture images of the sample using an industrial camera after the knitting needle to be inspected has entered and stabilized within the field of view of the industrial camera.

[0065] Example 6: A computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the method for detecting the quality of the needle latch of a circular knitting machine as described in any one of Examples 1 to 5.

[0066] Example 7: A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor using the method for detecting the quality of the needle latch of a circular knitting machine as described in any one of Examples 1 to 5.

[0067] Example 8: A computer program product, comprising a computer program that is executed by a processor using the method for detecting the quality of the needle latch of a circular knitting machine as described in any one of Examples 1 to 5.

[0068] Working principle: A method and system for detecting the quality of needle latches on circular knitting machines is disclosed. This method provides rapid and accurate needle latch quality detection results, offering a reliable basis for timely needle replacement and maintenance in textile production, thus improving textile quality and production efficiency. It effectively overcomes the shortcomings of manual inspection, such as low efficiency and susceptibility to errors. The invention acquires images of the needle to be inspected and uses image segmentation methods to accurately segment the front and side images of the needle latch, solving the problem of traditional manual inspection's difficulty in accurately obtaining clear images of various parts of the needle. This enables rapid and non-destructive acquisition and separation of images of key parts of the needle. Furthermore, by basing the method on the degree of needle latch skewness and open state, the invention addresses the issues of subjective judgment and the inability to accurately quantify needle latch quality in manual assessment, achieving objective and accurate evaluation of the quality of various parts of the needle. Finally, the invention comprehensively determines the needle latch quality of the needle to be inspected based on the results of the degree of needle latch skewness and open state, solving the problems of low efficiency and susceptibility to errors in manual comprehensive judgment, and achieving rapid and reliable determination of the overall quality of the needle.

[0069] The above specific embodiments are specific support for the concept proposed in this invention, and should not be used to limit the scope of protection of this invention. Any equivalent changes or modifications made on the basis of this technical solution in accordance with the technical concept proposed in this invention shall still fall within the scope of protection of this invention.

Claims

1. A method for detecting the quality of the needle latch of a large circular knitting machine, characterized in that, Includes the following steps; Obtain the front image of the knitting needle to be detected; The front image of the needle to be detected is segmented using an image segmentation method to obtain the front image of the needle tab of the needle to be detected; Based on the frontal image of the needle tongue of the needle to be tested, the degree of skewness of the needle tongue relative to the needle body of the needle to be tested is determined. Apply force to the closed needle tongue in the direction of its opening; Obtain a side image of the needle to be inspected; An image segmentation method is used to segment the image of the knitting needle to be detected, thereby obtaining a side image of the needle's tab. Determine the open state of the needle tongue based on the side image of the needle tongue; Based on the test results of the open state and degree of tilt, the quality test result of the needle tongue to be tested is determined.

2. The method for detecting the quality of the needle latch of a large circular knitting machine according to claim 1, characterized in that: Before acquiring a frontal image of the needle to be inspected, select the needle to be inspected and close the needle's latch. The needle is then clamped onto the device by the needle fixing clamp.

3. The method for detecting the quality of the needle latch of a large circular knitting machine according to claim 2, characterized in that: Obtaining the degree of skewness includes the following steps: The image of the latch of the knitting needle to be detected is preprocessed to obtain a preprocessed image of the latch; the preprocessing operation includes grayscale conversion, Gaussian blurring, binarization and median filtering. The needle tongue preprocessed image is subjected to a small kernel erosion operation to obtain a needle tongue erosion image; On the etched image of the needle tongue, the connected regions of the preprocessed image of the needle tongue are identified and calculated, and the region with the largest area is selected as the main region Ω. Record the maximum row index in the main region Ω. Corresponding feature pixel set ; Calculate the set of feature pixels Minimum value of column index Maximum value of column index The arithmetic mean of the reference center column is used as the reference center column index. : ； Iterate through the column indices C of all feature region pixels in the main region Ω and obtain the minimum global column index. Maximum value of global column index and calculate respectively and Columns with reference center The absolute value of the difference is used to obtain the left deviation distance. Distance from the right : ； ； Calculate the absolute value of the difference in deviation distance between the two sides, and use it as the asymmetric deviation value. ; When the asymmetric deviation value greater than the preset needle type skew threshold At that time, it was determined to be a needle tongue deviation; When the asymmetric deviation value Less than or equal to the preset needle type skew threshold At that time, the needle tongue was judged to be normal.

4. The method for detecting the quality of the needle latch of a large circular knitting machine according to claim 3, characterized in that: The mechanical air blowing device is used to blow air at a certain angle and force along the normal opening direction of the needle latch to close the needle latch, including the following steps: Fix the mechanical air blowing device to the knitting needle fixing clamp below the needle tongue; Position the nozzle of the air blowing device at a certain angle, tilting it upwards towards the direction in which the needle tongue normally opens; The airflow is blown evenly onto the needle tongue with just enough force to make it open.

5. The method for detecting the quality of the needle latch of a large circular knitting machine according to claim 4, characterized in that: Blow-up control methods include: Establish a three-dimensional spatial coordinate system with the knitting needle fixing clamp as the origin, and set the center of the nozzle of the mechanical air blowing device at a preset coordinate point below the needle tongue rotation axis. ; Adjust the nozzle's spray direction vector So that the angle between it and the axis of the needle body satisfy This ensures that the airflow is directed obliquely upwards towards the force-bearing edge of the needle tongue; The instantaneous airflow pressure P generated by the air blowing device satisfies The pressure range is set to a critical value that just overcomes the normal frictional force of the needle tongue rotation without causing the needle body to vibrate. It adopts a pulsed air blowing method with a blowing time t of 100ms-300ms, and uses the instantaneous inertia of the airflow impact force to make the needle tongue completely flip to the maximum opening position.

6. The method for detecting the quality of the needle latch of a circular knitting machine according to claim 5, characterized in that: Obtaining the open state of the needle tongue includes the following steps: The image of the side of the needle tongue of the knitting needle to be inspected is preprocessed and morphologically operated to obtain the connected component Ω of the main region; Obtain the bounding box of the connected component Ω and record the maximum column index of the top of the hook. The maximum value of the row index at the bottom of the needle body and the minimum row index at the top ; Calculate the characteristic height of the hook region And set a dynamic detection benchmark based on H: First benchmark line ,in This is the height coefficient, with a value range of 1.1-1.3; Second benchmark column ,in This is the width coefficient, with a value ranging from 0.2 to 0.

3. Statistical row standard equals Feature pixel set Number of pixels Get column index equal to The set of row numbers of all feature pixels ; If satisfied If the values ​​within the set of row numbers K are not continuous, it is determined that the needle is not flexible. If satisfied If the values ​​inside the row number set K are a continuous integer sequence, then it is determined to be a flexible needle tongue.

7. The method for detecting the quality of the needle latch of a circular knitting machine according to claim 6, characterized in that: Based on the test results of the open state and degree of tilt, the quality test results of the needle tongue to be tested are determined, including: If the needle tongue deviation test result is no deviation and the needle tongue flexibility test result is flexible, then the quality test result of the needle is qualified and the needle can continue to be used. If the needle tongue deviation test result is needle tongue deviation, or the needle tongue flexibility test result is needle tongue inflexibility, then the quality test result of the needle is that the needle is unqualified and the needle should be replaced.

8. A quality inspection system for the needle latch of a large circular knitting machine, characterized in that, The circular knitting machine needle latch quality detection system uses the circular knitting machine needle latch quality detection method as described in any one of claims 1-7, and the circular knitting machine needle latch quality detection system includes: Front image acquisition module, used to acquire a front image of the needle to be detected; The side image acquisition module is used to acquire a side image of the needle to be detected. The frontal image segmentation module is used to segment the image of the knitting needle to be detected using image segmentation methods to obtain the frontal image of the needle's tab. The side image segmentation module is used to segment the image of the knitting needle to be detected using image segmentation methods to obtain the side image of the knitting needle to be detected. The needle tongue skew detection module is used to determine the needle tongue skew detection result based on the image of the needle tongue of the needle to be detected. The needle tongue flexibility detection module is used to determine the needle tongue flexibility detection result based on the needle tongue image of the knitting needle to be tested; The needle quality inspection module determines the quality level of the needle to be inspected based on the needle tongue skew detection results and the needle tongue flexibility detection results.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for detecting the quality of the needle latch of a circular knitting machine according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for detecting the quality of the needle tongue of a large circular knitting machine as described in any one of claims 1-7.

Images