A large circular weaving needle wear detection method and system

Abstract

The application discloses a circular knitting needle wear detection method and system, and relates to the field of machine vision.The method comprises the following steps: acquiring an image of a to-be-detected knitting needle, obtaining a needle hook image, a needle latch image and a needle foot image of the to-be-detected knitting needle by using an image segmentation method; respectively determining the wear conditions of the needle hook, the needle latch and the needle foot based on the needle hook image, the needle latch image and the needle foot image; and comprehensively determining the wear conditions of the needle hook, the needle latch and the needle foot to accurately determine the wear degree of the to-be-detected knitting needle.The application realizes automatic and accurate detection of the wear of the circular knitting needle, effectively overcomes the low efficiency and errors of manual detection, and can quickly and accurately provide a wear degree detection result of the knitting needle, thereby providing a reliable basis for timely replacement and maintenance of the knitting needle in textile production, and helping to improve the quality and production efficiency of textiles.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of machine vision, in particular to a circular knitting machine needle wear detection method and system. BACKGROUND

[0002] With the rapid development of the textile industry, higher requirements are put forward for the quality and production efficiency of textiles. In the textile production process, the needle is a key component, and its state directly affects the quality of the cloth surface and the production efficiency. The needle of the circular knitting machine, as an important equipment in the textile machinery, is prone to wear during long-term operation. The wear of the needle not only affects the service life of the needle, but also may cause defects on the cloth surface, such as yarn breakage, cloth surface holes, etc., and even cause the loom to stop running, affecting the production efficiency. Therefore, during the daily inspection, pre-operation check or fault analysis of the needle, careful wear evaluation of its key parts (especially the needle hook, needle tongue and needle foot) is needed.

[0003] However, the needle defect detection in the related art mainly relies on manual visual inspection, and the manual detection efficiency is extremely low, and visual fatigue and omissions are easy to occur when facing a large number of needles. Moreover, the subjective judgment of the defect position is strong, which will greatly affect the accuracy of the judgment of the usability of the needle, leading to the damage of the needle due to misuse, causing cloth defects, or increasing the cost by prematurely scrapping the still usable needle.

[0004] Therefore, there is an urgent need for a circular knitting machine needle wear detection method to solve the problems of low efficiency, strong subjectivity, easy visual fatigue and omissions in manual visual inspection, leading to inaccurate judgment of the wear state of the needle, and thus affecting the quality and production efficiency of textiles. SUMMARY

[0005] The purpose of the present application is to provide a circular knitting machine needle wear detection method and system, which can realize automatic, fast and accurate detection of the wear state of the key parts (needle hook, needle tongue and needle foot) of the circular knitting machine needle, solve the problems of low efficiency, strong subjectivity, easy visual fatigue and omissions in manual visual inspection in the prior art, and thus improve the accuracy and efficiency of needle wear detection, reduce the risk of cloth defects and production downtime caused by misjudgment, reduce production costs, and ensure the quality and production efficiency of textiles.

[0006] To achieve the above-mentioned purpose, the present application provides the following solutions:

[0007] In a first aspect, the present application provides a circular knitting machine needle wear detection method, comprising:

[0008] obtaining an image of a needle to be detected;

[0009] segmenting the image of the needle to be detected by using an image segmentation method to obtain a needle hook image, a needle tongue image and a needle foot image of the needle to be detected;

[0010] determine a hook wear detection result based on the hook image of the to-be-detected knitting needle;

[0011] determine a latch wear detection result based on the latch image of the to-be-detected knitting needle;

[0012] determine a stitch wear detection result based on the stitch image of the to-be-detected knitting needle;

[0013] determine a wear degree detection result of the to-be-detected knitting needle according to the hook wear detection result, the latch wear detection result and the stitch wear detection result.

[0014] In a second aspect, the present application provides a circular knitting machine knitting needle wear detection system, comprising:

[0015] an image acquisition module configured to acquire an image of a to-be-detected knitting needle;

[0016] an image segmentation module configured to segment the image of the to-be-detected knitting needle by using an image segmentation method to obtain a hook image, a latch image and a stitch image of the to-be-detected knitting needle;

[0017] a hook wear detection module configured to determine a hook wear detection result based on the hook image of the to-be-detected knitting needle;

[0018] a latch wear detection module configured to determine a latch wear detection result based on the latch image of the to-be-detected knitting needle;

[0019] a stitch wear detection module configured to determine a stitch wear detection result based on the stitch image of the to-be-detected knitting needle;

[0020] a knitting needle wear degree detection module configured to determine a wear degree detection result of the to-be-detected knitting needle according to the hook wear detection result, the latch wear detection result and the stitch wear detection result.

[0021] In a third aspect, the present application provides 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 implement the steps of the circular knitting machine knitting needle wear detection method according to any one of the above.

[0022] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the steps of the circular knitting machine knitting needle wear detection method according to any one of the above.

[0023] In a fifth aspect, the present application provides a computer program product comprising a computer program, wherein the computer program is executable by a processor to implement the steps of the circular knitting machine knitting needle wear detection method according to any one of the above.

[0024] According to the specific embodiments provided in the application, the application has the following technical effects:

[0025] The application provides a circular knitting needle wear detection method and system, which acquires an image of a to-be-detected knitting needle, and accurately segments a needle hook, a needle latch and a needle foot image by using an image segmentation method, solves the problem that a traditional manual detection cannot accurately acquire a clear image of each part of the knitting needle, and realizes fast and lossless collection and separation of the image of the key part of the knitting needle; the needle hook wear detection result, the needle latch wear detection result and the needle foot wear detection result are determined based on the needle hook image, the needle latch image and the needle foot image respectively, the problem that manual judgment of the wear position is highly subjective and cannot accurately quantify the wear degree is solved, and objective and accurate evaluation of the wear state of each part of the knitting needle is realized; the wear degree detection result of the to-be-detected knitting needle is determined according to the needle hook wear detection result, the needle latch wear detection result and the needle foot wear detection result, the problem that manual comprehensive judgment is low in efficiency and prone to errors is solved, and fast and reliable determination of the overall wear degree of the knitting needle is realized, thereby providing a scientific basis for timely replacement and maintenance of the knitting needle. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description only constitute some embodiments of the application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0027] Figure 1 It is an application environment diagram of a circular knitting needle wear detection method according to an embodiment of the application.

[0028] Figure 2 It is a flowchart of a circular knitting needle wear detection method according to an embodiment of the application.

[0029] Figure 3 It is a intercepted needle hook image provided by an embodiment of the application; wherein, Figure 3 (a) in the figure represents a normal needle hook part diagram; Figure 3 (b) in the figure represents a needle hook part diagram after wear occurs.

[0030] Figure 4 It is a intercepted needle latch image provided by an embodiment of the application; wherein, Figure 4 (a) in the figure represents a normal needle latch part diagram of a circular knitting needle; Figure 4 (b) in the figure represents a needle latch part diagram of a circular knitting needle after wear occurs.

[0031] Figure 5 It is a intercepted needle foot image provided by an embodiment of the application; wherein,Figure 5 (a) in the diagram represents a normal circular knitting needle position; Figure 5 (b) in the diagram represents the needle foot of a circular knitting machine after wear.

[0032] Figure 6 This application provides an image of a needle hook after image processing, as shown in one embodiment. Figure 6 (a) in the image represents a schematic diagram of the normal hook area after image processing; Figure 6 (b) in the image represents a schematic diagram of the worn hook area after image processing.

[0033] Figure 7 This application provides an image of a needle tongue after image processing, as shown in one embodiment. Figure 7 (a) in the image represents a schematic diagram of the normal needle tongue area after image processing; Figure 7 (b) in the image represents a schematic diagram of the worn needle tongue area after image processing.

[0034] Figure 8 This is an image of a pin after image processing, provided in one embodiment of this application; wherein, Figure 8 (a) in the image represents a schematic diagram of the normal pin location after image processing; Figure 8 (b) in the image represents a schematic diagram of the worn pin area after image processing.

[0035] Figure 9 This is a schematic diagram of the functional modules of a circular knitting machine needle wear detection system provided in one embodiment of this application.

[0036] Figure 10 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0039] The method for detecting needle wear on a circular knitting machine provided in this application embodiment can be applied to, for example... Figure 1The terminal 101 communicates with the server 102 through the network. The data storage system can store the data required by the server 102 to process. The data storage system can be separately arranged, integrated on the server 102, or placed on the cloud or other servers. The terminal 101 can send the image of the knitting needle to be detected to the server 102. After receiving the image of the knitting needle to be detected, the server 102 uses an image segmentation method to segment the image of the knitting needle to be detected to obtain the hook image, the latch image and the stitch image of the knitting needle to be detected. Based on the hook image of the knitting needle to be detected, the hook wear detection result is determined. Based on the latch image of the knitting needle to be detected, the latch wear detection result is determined. Based on the stitch image of the knitting needle to be detected, the stitch wear detection result is determined. According to the hook wear detection result, the latch wear detection result and the stitch wear detection result, the wear degree detection result of the knitting needle to be detected is determined. The server 102 can feed back the obtained wear degree detection result of the knitting needle to be detected to the terminal 101. In addition, in some embodiments, the circular knitting needle wear detection method can also be implemented by the server 102 or the terminal 101 alone, such as directly performing wear detection processing on the image of the knitting needle to be detected by the terminal 101, or obtaining the image of the knitting needle to be detected from the data storage system and performing wear detection processing on the image of the knitting needle to be detected by the server 102.

[0040] The terminal 101 can be, but is not limited to, various desktop computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The server 102 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0041] In an exemplary embodiment, as Figure 2 shown, a circular knitting needle wear detection method is provided, which is executed by a computer device, specifically can be executed by a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to the server 102 in Figure 1 , which includes the following steps 201 to 206. Wherein:

[0042] Step 201, obtaining the image of the knitting needle to be detected. An industrial camera is used to shoot the overall image of the knitting needle.

[0043] Step 202, using an image segmentation method to segment the image of the knitting needle to be detected to obtain the hook image, the latch image and the stitch image of the knitting needle to be detected. The image is segmented to obtain the corresponding part images of the hook, the latch and the stitch, respectively, as Figure 3 、 Figure 4 、 Figure 5 shown.

[0044] As an optional implementation, the ROI is obtained according to the relative positions of the hook, the latch and the needle foot in the whole needle image and is saved. The image in the ROI is intercepted and saved respectively. Different parts of the needle can be separated, so that the wear detection of each part is carried out independently, and the accuracy and efficiency of the detection are improved.

[0045] In step 203, the hook wear detection result is determined based on the hook image of the needle to be detected.

[0046] In step 204, the latch wear detection result is determined based on the latch image of the needle to be detected.

[0047] In step 205, the needle foot wear detection result is determined based on the needle foot image of the needle to be detected.

[0048] In step 206, the wear degree detection result of the needle to be detected is determined according to the local wear detection results.

[0049] By implementing the steps 201 to 206, the present application can provide automatic detection of the needle wear of the circular knitting machine, which can accurately and quickly realize the automatic detection of the wear of the key parts of the needle, and further improve the automation degree.

[0050] In another exemplary embodiment of the present application, step 203 specifically includes:

[0051] The hook image of the needle to be detected is preprocessed to obtain a hook preprocessed image; the preprocessing operation includes Gaussian blur processing, binaryzation processing and median filter processing. Through these image processing operations, the features of the hook image can be enhanced, the noise can be removed, and the hook region can be made more clear, so as to facilitate the judgment of whether the hook is worn.

[0052] The hook preprocessed image is subjected to a large kernel (12x12) erosion operation, so that the normal hook center black region is fully eroded and broken to form a fault, and the worn hook center has no black region and is basically not affected, thereby obtaining a hook erosion image. The wear features of the hook can be further highlighted, and the wear region can be made more obvious.

[0053] All hook erosion image connected domains of the hook erosion image are identified, and the pixel with the smallest row number in each hook erosion image connected domain is determined respectively to obtain a hook minimum pixel set.

[0054] The hook minimum pixel set is traversed, and the hook erosion image connected domain corresponding to the pixel with the smallest row number is selected as the main hook region.

[0055] determine the total number of rows of pixels in the needle hook body region, and determine the needle hook wear detection result according to a preset needle hook wear condition; the preset needle hook wear condition includes that if the total number of rows of pixels in the needle hook body region is greater than or equal to a preset needle hook wear row threshold, the needle hook has wear; and if the total number of rows of pixels in the needle hook body region is less than the preset needle hook wear row threshold, the needle hook has no wear. As shown in Figure 3 provides a captured needle hook image; wherein, Figure 3 (a) in FIG. 1 shows a normal needle hook part (i.e. the needle hook has no wear) schematic diagram; Figure 3 (b) in FIG. 1 shows a worn needle hook part (i.e. the needle hook has wear) schematic diagram.

[0056] As shown in Figure 6 provides a needle hook image after image processing, Figure 6 (a) in FIG. 2 shows a normal needle hook part schematic diagram after image processing; Figure 6 (b) in FIG. 2 shows a worn needle hook part schematic diagram after image processing.

[0057] In this embodiment, first, the uppermost (i.e. the smallest row number) connected domain of the eroded image is found.

[0058] The total number of rows of the connected domain is found, and if it is greater than or equal to 70 rows, it means that the needle hook region remains connected, and it is determined that there is wear, otherwise, if it is less than 70 rows, it means that there is no wear.

[0059] In another exemplary embodiment of the present application, step 204 specifically includes:

[0060] The needle hook image to be detected is subjected to a filtering operation to obtain a needle hook filtered image.

[0061] The needle hook filtered image is subjected to a morphological operation to obtain a needle hook morphological image; the morphological operation includes a small core (3x3) erosion operation and a small core (3x3) expansion operation to fully break the small connections. As shown in Figure 7 provides a needle hook image after image processing, Figure 7 (a) in FIG. 3 shows a normal needle hook part schematic diagram after image processing; Figure 7 (b) in FIG. 3 shows a worn needle hook part schematic diagram after image processing.

[0062] All needle hook morphological image connected domains of the needle hook morphological image are identified, and the pixel with the largest row number in each needle hook morphological image connected domain is determined to obtain a needle hook pixel set.

[0063] The needle hook pixel set is traversed, and the needle hook morphological image connected domain corresponding to the pixel with the largest row number in the needle hook pixel set is selected as the needle hook body region. The image after the morphological operation is extracted and the connected domain at the bottom (i.e. the largest row number) is found.

[0064] determining a total number of rows of pixels in the latch body region, and determining a latch wear detection result according to a preset latch wear condition; the preset latch wear condition includes that if the total number of pixels in the latch body region is greater than a preset latch wear number threshold, the latch has wear; and if the total number of pixels in the latch body region is less than or equal to the preset latch wear number threshold, the latch has no wear. If greater than 150 pixels, the latch has wear, otherwise, no wear, as shown in Figure 4 provides a latched image intercepted; wherein, Figure 4 (a) in FIG. 1 indicates a normal latch part (i.e. the latch has no wear) schematic diagram; Figure 4 (b) in FIG. 1 indicates a latched part after wear (i.e. the latch has wear) schematic diagram.

[0065] In another exemplary embodiment of the present application, step 205 specifically includes:

[0066] performing a preprocessing operation on the stitch image of the needle to be detected to obtain a stitch preprocessing image; the preprocessing operation includes Gaussian blur processing, binaryzation processing and median filter processing.

[0067] In the stitch preprocessing image, a stitch preprocessing image connected domain is identified and calculated, and the largest area is selected as a stitch body region.

[0068] The distance between the white pixel with the smallest column number in each row in the stitch body region and the pixel with the smallest column number in the corresponding row of the stitch preprocessing image is calculated respectively to obtain a stitch pixel distance set. The distance between the white pixel with the smallest column number in each row in the connected domain and the pixel with the smallest column number (right side boundary) is calculated and saved.

[0069] Based on the stitch pixel distance set, the stitch straightness state is determined.

[0070] Based on the stitch straightness state, and according to a preset stitch wear condition, a stitch wear detection result is determined; the preset stitch wear condition includes that if the stitch straightness state is a non-straight state, the stitch has wear; and if the stitch straightness state is a straight state, the stitch has no wear. As shown in Figure 5 provides a stitch image intercepted; wherein, Figure 5 (a) in FIG. 1 indicates a normal stitch part (i.e. the stitch has no wear) schematic diagram; Figure 5 (b) in FIG. 1 indicates a stitch part after wear (i.e. the stitch has wear) schematic diagram.

[0071] In another exemplary embodiment of the present application, based on the stitch pixel distance set, the stitch straightness state is determined, specifically including:

[0072] Sort the data in the stitch pixel distance set in descending order.

[0073] Delete the data in the sorted stitch pixel distance set according to the preset quantity threshold value to obtain a stitch pixel distance screening set. The last third of the data is removed.

[0074] Select the data in the stitch pixel distance screening set that is greater than the preset average distance threshold value to obtain a first data set. In this implementation, the average value and the standard deviation of the stitch pixel distance screening set can be calculated first, and then the data points in the stitch pixel distance screening set that are within 5 standard deviations of the average value are retained.

[0075] Select the data in the stitch pixel distance screening set that is less than or equal to the preset average distance threshold value to obtain a second data set, and calculate the average value of all data in the second data set to obtain a reference distance value.

[0076] Calculate the absolute value of the difference between each data in the first data set and the reference distance value to obtain a difference data set.

[0077] Based on the difference data set, the distance mean square error value is obtained through the mean square error formula.

[0078] According to the distance mean square error value, the matching degree of the stitch flatness state of the to-be-detected knitting needle is calculated. The matching degree formula is 10 / (10+distance mean square error value).

[0079] If the matching degree is greater than the preset matching threshold value, the stitch flatness state is flat.

[0080] If the matching degree is less than or equal to the preset matching threshold value, the stitch flatness state is not flat.

[0081] In this implementation, when the matching degree is greater than 80%, it is considered that the right boundary of the connected domain is flat, and otherwise it is not flat. As shown in FIG. 8, Figure 8 provides a stitch image after image processing, Figure 8 (a) a schematic diagram of a normal stitch part after image processing in FIG. 8; Figure 8 (b) a schematic diagram of a worn stitch part after image processing in FIG. 8.

[0082] In another exemplary embodiment of the present application, step 206 specifically includes:

[0083] If the needle hook wear detection result of the to-be-detected knitting needle is that the needle hook has no wear, the latch wear detection result is that the latch has no wear, and the stitch wear detection result is that the stitch has no wear, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle has no wear.

[0084] If the hook wear detection result of the to-be-detected knitting needle is that the hook is not worn, the latch wear detection result is that the latch is not worn, the stitch wear detection result is that the stitch is worn, and the stitch straightness state is straight, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle is slightly worn.

[0085] If the hook wear detection result of the to-be-detected knitting needle is that the hook is not worn, the latch wear detection result is that the latch is not worn, the stitch wear detection result is that the stitch is worn, and the stitch straightness state is not straight, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle is severely worn.

[0086] If the hook wear detection result is that the hook is worn, or the latch wear detection result is that the latch is worn, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle is severely worn.

[0087] As an optional implementation, when the wear degree detection result of the to-be-detected knitting needle is that the knitting needle is not worn, the knitting needle is classified as A level. When the wear degree detection result of the to-be-detected knitting needle is that the knitting needle is slightly worn, the knitting needle is classified as B level. When the wear degree detection result of the to-be-detected knitting needle is that the knitting needle is severely worn, the knitting needle is classified as C level. The A level can be directly used, the B level can be used together with other B levels, and the C level cannot be used.

[0088] The application also provides an application scenario of the circular knitting machine knitting needle wear detection method. Specifically, the circular knitting machine knitting needle wear detection method provided in the embodiment can be applied in a textile production quality monitoring scenario. The textile production quality monitoring scenario includes a pre-machine checking link, a production process sampling link, and a fault analysis link. The knitting needle enters the pre-machine checking link from the procurement or storage link, is subjected to preliminary appearance inspection, and then is subjected to accurate detection by using the circular knitting machine knitting needle wear detection method provided in the embodiment, so as to obtain the wear conditions of each part of the knitting needle and the overall classification result, and then enters a subsequent classified storage or use decision link. In the production process, the knitting needle is periodically sampled from the circular knitting machine and enters the production process sampling link, and is also subjected to detection by using the detection method, so as to timely find the wear change of the knitting needle. When a fault such as a fabric surface defect occurs, the related knitting needle enters the fault analysis link, and the detection method is used to determine whether the wear of the knitting needle is the cause of the fault. The circular knitting machine knitting needle wear detection method provided in the embodiment belongs to the knitting needle state detection link in the textile production quality monitoring. Specifically, it captures the image of the knitting needle by using an industrial camera, and provides an accurate basis for the quality evaluation and use decision of the knitting needle in the textile production through the steps of image segmentation, part wear detection, and comprehensive classification judgment, which helps to improve the quality and production efficiency of the textile product and reduce the production cost.

[0089] Based on the same inventive concept, the application further provides a circular knitting needle wear detection system for implementing the above-mentioned circular knitting needle wear detection method. The system provides a solution to the problem similar to the implementation scheme described in the above method, so the specific limitations in one or more embodiments of the circular knitting needle wear detection system provided below can refer to the limitations of the circular knitting needle wear detection method described above, which will not be repeated here.

[0090] In one exemplary embodiment, as shown in Figure 9 A circular knitting needle wear detection system is provided, comprising:

[0091] An image acquisition module 301 is configured to acquire an image of a needle to be detected.

[0092] An image segmentation module 302 is configured to segment the image of the needle to be detected using an image segmentation method to obtain a needle hook image, a needle latch image and a needle foot image of the needle to be detected.

[0093] A needle hook wear detection module 303 is configured to determine a needle hook wear detection result based on the needle hook image of the needle to be detected.

[0094] A needle latch wear detection module 304 is configured to determine a needle latch wear detection result based on the needle latch image of the needle to be detected.

[0095] A needle foot wear detection module 305 is configured to determine a needle foot wear detection result based on the needle foot image of the needle to be detected.

[0096] A needle wear degree detection module 306 is configured to determine a wear degree detection result of the needle to be detected according to the needle hook wear detection result, the needle latch wear detection result and the needle foot wear detection result.

[0097] As an optional implementation, the circular knitting needle wear detection system further comprises:

[0098] A sample carrying module is configured to fix the needle to be detected and provide a suitable background color to highlight the defect features.

[0099] An image pickup module is configured to capture an image of the sample using an industrial camera after the needle to be detected enters the field of view of the industrial camera and stabilizes.

[0100] In summary, the application solves the problems of low efficiency of manual detection, visual fatigue and omission when facing a large number of needles, strong subjectivity of manual judgment of defect positions, inability to estimate wear area, resulting in misuse of damaged needles to cause fabric defects, or premature scrapping of still usable needles to increase costs. The application further classifies and judges the needles while detecting the wear of each part of the needles, can accurately and quickly realize automatic detection of needle wear, and further improve the automation degree of the needle defect detection equipment.

[0101] In an exemplary embodiment, a computer device, which can be a server or a terminal, is provided, and an internal structure diagram of the computer device can be as shown in Figure 10 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store processing data in the process of detecting needle wear. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a circular knitting machine needle wear detection method.

[0102] Those skilled in the art can understand that Figure 10 the structure shown in the above description is only a block diagram of part of the structure related to the scheme of the application, and does not constitute a limitation on the computer device to which the scheme of the application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.

[0103] In an exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to implement the steps in the above method embodiments.

[0104] In an exemplary embodiment, a computer program product is provided, including a computer program, which is executed by a processor to implement the steps in the above method embodiments.

[0105] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0106] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0107] The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on blockchain, etc., without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0108] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described above, however, it should be understood that the application encompasses all possible combinations of the technical features unless such a combination is not technically possible.

[0109] The principles and implementation manners of the present application are described herein by using specific examples, and the above embodiments are only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, the specific implementation manners and application range can be changed according to the idea of the present application. In conclusion, the content of the present specification should not be understood as a limitation of the present application.

Claims

1. A method of detecting wear of a large circular weaving needle, characterized in that, The large circular weaving needle wear detection method comprises: acquiring an image of a needle to be detected; segmenting the image of the needle to be detected by using an image segmentation method to obtain a needle hook image, a needle latch image and a needle foot image of the needle to be detected; based on the needle hook image of the needle to be detected, determining a needle hook wear detection result, specifically comprising: performing a preprocessing operation on the needle hook image of the needle to be detected to obtain a needle hook preprocessing image; the preprocessing operation comprises Gaussian blur processing, binaryzation processing and median filter processing; performing a large kernel corrosion operation on the needle hook preprocessing image to obtain a needle hook corrosion image; identifying all needle hook corrosion image connected domains of the needle hook corrosion image, and respectively determining the pixel with the smallest row number in each needle hook corrosion image connected domain to obtain a needle hook minimum pixel set; traversing the needle hook minimum pixel set, and selecting the needle hook corrosion image connected domain corresponding to the pixel with the smallest row number as a needle hook main body region; determining the total number of rows of pixels in the needle hook main body region, and determining the needle hook wear detection result according to a preset needle hook wear condition; the preset needle hook wear condition comprises that if the total number of rows of pixels in the needle hook main body region is greater than or equal to a preset needle hook wear row number threshold, the needle hook has wear; if the total number of rows of pixels in the needle hook main body region is less than the preset needle hook wear row number threshold, the needle hook has no wear; based on the needle latch image of the needle to be detected, determining a needle latch wear detection result, specifically comprising: performing a filtering operation on the needle latch image of the needle to be detected to obtain a needle latch filtering image; performing a morphological operation on the needle latch filtering image to obtain a needle latch morphological image; the morphological operation comprises a small kernel corrosion operation and a small kernel dilation operation; identifying all needle latch morphological image connected domains of the needle latch morphological image, and respectively determining the pixel with the largest row number in each needle latch morphological image connected domain to obtain a needle latch pixel set; traversing the needle latch pixel set, and selecting the needle latch morphological image connected domain corresponding to the pixel with the largest row number in the needle latch pixel set as a needle latch main body region; determining the total number of rows of pixels in the needle latch main body region, and determining the needle latch wear detection result according to a preset needle latch wear condition; the preset needle latch wear condition comprises that if the total number of rows of pixels in the needle latch main body region is greater than a preset needle latch wear row number threshold, the needle latch has wear; if the total number of rows of pixels in the needle latch main body region is less than or equal to the preset needle latch wear row number threshold, the needle latch has no wear; Based on the stitch image of the to-be-detected knitting needle, a stitch wear detection result is determined, specifically including: performing a preprocessing operation on the stitch image of the to-be-detected knitting needle to obtain a stitch preprocessing image; the preprocessing operation includes Gaussian blur processing, binaryzation processing and median filter processing; on the stitch preprocessing image, a stitch preprocessing image connected domain is identified and calculated, and the largest area is selected as a stitch main body area; the distance between the white pixel with the smallest column number in each row in the stitch main body area and the pixel with the smallest column number in the corresponding row of the stitch preprocessing image is calculated respectively to obtain a stitch pixel distance set; based on the stitch pixel distance set, a stitch flatness state is judged; based on the stitch flatness state and according to a preset stitch wear condition, a stitch wear detection result is determined; the preset stitch wear condition includes that if the stitch flatness state is a non-flat state, the stitch has wear; if the stitch flatness state is a flat state, the stitch has no wear; According to the needle hook wear detection result, the needle tail wear detection result and the stitch wear detection result, the wear degree detection result of the to-be-detected knitting needle is determined.

2. The flat knitting needle wear detection method according to claim 1, characterized by, Based on the stitch pixel distance set, the stitch flatness state is judged, specifically including: Traverse the stitch pixel distance set, and sort the data in the stitch pixel distance set in descending order; Delete the data of the preset number threshold in the sorted stitch pixel distance set in sequence to obtain a stitch pixel distance filtered set; Select the data greater than the preset average distance threshold in the stitch pixel distance filtered set to obtain a first data set; Select the data less than or equal to the preset average distance threshold in the stitch pixel distance filtered set to obtain a second data set, and calculate the average value of all data in the second data set to obtain a reference distance value; Calculate the absolute value of the difference between each data in the first data set and the reference distance value to obtain a difference data set; Based on the difference data set, the distance mean square error value is obtained through the mean square error formula; According to the distance mean square error value, the matching degree of the stitch flatness state of the to-be-detected knitting needle is calculated; If the matching degree is greater than a preset matching threshold, the stitch flatness state is flat; If the matching degree is less than or equal to the preset matching threshold, the stitch flatness state is non-flat.

3. The flat knitting needle wear detection method according to claim 1, characterized by, According to the needle hook wear detection result, the needle tail wear detection result and the stitch wear detection result, the wear degree detection result of the to-be-detected knitting needle is determined, specifically including: If the needle hook wear detection result of the to-be-detected knitting needle is that the needle hook has no wear, the needle tail wear detection result is that the needle tail has no wear, and the stitch wear detection result is that the stitch has no wear, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle has no wear; If the needle hook wear detection result of the to-be-detected knitting needle is that the needle hook has no wear, the needle tail wear detection result is that the needle tail has no wear, the stitch wear detection result is that the stitch has wear, and the stitch flatness state is flat, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle has light wear; If the needle hook wear detection result of the to-be-detected knitting needle is that the needle hook has no wear, the needle tail wear detection result is that the needle tail has no wear, the stitch wear detection result is that the stitch has wear, and the stitch flatness state is non-flat, the wear degree detection result of the to-be-detected knitting needle is that the knitting needle has heavy wear; If the needle hook wear detection result is that the needle hook is worn, or the needle latch wear detection result is that the needle latch is worn, the wear degree detection result of the to-be-detected needle is that the needle is severely worn.

4. A large circular weaving needle wear detection system characterized by, The circular knitting machine needle wear detection system applies the circular knitting machine needle wear detection method of any one of claims 1-3, and the circular knitting machine needle wear detection system comprises: an image acquisition module configured to acquire an image of a to-be-detected needle; an image segmentation module configured to segment the image of the to-be-detected needle by using an image segmentation method to obtain a needle hook image, a needle latch image, and a needle stitch image of the to-be-detected needle; a needle hook wear detection module configured to determine a needle hook wear detection result based on the needle hook image of the to-be-detected needle, specifically comprising: performing a preprocessing operation on the needle hook image of the to-be-detected needle to obtain a needle hook preprocessed image; the preprocessing operation comprises Gaussian blur processing, binaryzation processing, and median filter processing; performing a large kernel corrosion operation on the needle hook preprocessed image to obtain a needle hook corrosion image; identifying all needle hook corrosion image connected domains of the needle hook corrosion image, and respectively determining a pixel with the smallest row number in each needle hook corrosion image connected domain to obtain a needle hook minimum pixel set; traversing the needle hook minimum pixel set, and selecting a needle hook corrosion image connected domain corresponding to a pixel with the smallest row number as a needle hook main body region; determining a total number of rows of pixels in the needle hook main body region, and determining the needle hook wear detection result according to a preset needle hook wear condition; the preset needle hook wear condition comprises that if the total number of rows of pixels in the needle hook main body region is greater than or equal to a preset needle hook wear row number threshold, the needle hook is worn; and if the total number of rows of pixels in the needle hook main body region is less than the preset needle hook wear row number threshold, the needle hook is not worn; a needle latch wear detection module configured to determine a needle latch wear detection result based on the needle latch image of the to-be-detected needle, specifically comprising: performing a filtering operation on the needle latch image of the to-be-detected needle to obtain a needle latch filtered image; performing a morphological operation on the needle latch filtered image to obtain a needle latch morphological image; the morphological operation comprises a small kernel corrosion operation and a small kernel dilation operation; identifying all needle latch morphological image connected domains of the needle latch morphological image, and respectively determining a pixel with the largest row number in each needle latch morphological image connected domain to obtain a needle latch pixel set; traversing the needle latch pixel set, and selecting a needle latch morphological image connected domain corresponding to a pixel with the largest row number in the needle latch pixel set as a needle latch main body region; determining a total number of rows of pixels in the needle latch main body region, and determining the needle latch wear detection result according to a preset needle latch wear condition; the preset needle latch wear condition comprises that if the total number of rows of pixels in the needle latch main body region is greater than a preset needle latch wear row number threshold, the needle latch is worn; and if the total number of rows of pixels in the needle latch main body region is less than or equal to the preset needle latch wear row number threshold, the needle latch is not worn; The stitch wear detection module is configured to determine a stitch wear detection result based on a stitch image of the needle to be detected, and specifically includes: performing a preprocessing operation on the stitch image of the needle to be detected to obtain a stitch preprocessing image; the preprocessing operation includes Gaussian blur processing, binaryzation processing and median filter processing; identifying and calculating a stitch preprocessing image connected domain on the stitch preprocessing image, and selecting the largest area as a stitch main body region; calculating the distance between the white pixel with the smallest column number in each row in the stitch main body region and the pixel with the smallest column number in the corresponding row of the stitch preprocessing image to obtain a stitch pixel distance set; determining a stitch flatness state based on the stitch pixel distance set; determining a stitch wear detection result based on the stitch flatness state and according to a preset stitch wear condition; the preset stitch wear condition includes that if the stitch flatness state is a non-flat state, the stitch has wear; and if the stitch flatness state is a flat state, the stitch has no wear; The needle wear degree detection module is configured to determine a wear degree detection result of the needle to be detected based on the needle hook wear detection result, the needle tail wear detection result and the stitch wear detection result.

Images