Intelligent positioning method, device, memory and electronic device for defective wafer

Abstract

The present application discloses a method, device, memory and electronic device for intelligently locating defective pieces, the method comprising projecting an electronic marker onto the tabletop of a cloth-pulling machine; identifying defective points of the cloth during the cloth-pulling process, obtaining the defective points and defective cloth piece information; laminating the surface of the cloth after the cloth-pulling process, printing the electronic marker on the laminating film according to the size of the marker image to obtain a laminating marker, and printing the relevant information of each piece and the defective cloth piece information on the corresponding laminating piece surface; cutting the cloth according to the shape of each laminating piece of the laminating marker and obtaining each group of cloth pieces, and obtaining the location of the defective cloth in the group of cloth pieces according to the defective cloth piece information recorded on the laminating piece surface on each group of cloth pieces. The method can quickly obtain defective pieces in each group of cloth pieces, thereby improving the efficiency of finding defective pieces.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing, and in particular to an intelligent positioning method, device, memory and electronic device for defective wafers. Background Art

[0002] In the production process of the cutting room, the inspection link is often indispensable. The cloth inspection machine is a set of necessary special equipment for the garment industry to inspect large-format, double-width and single-width cloth such as cotton, wool, linen, silk, and chemical fiber before production. The operation method of the cloth inspection machine: provide the hardware environment for cloth inspection, continuously unfold the fabric in sections, provide sufficient light source, and the operator relies on visual observation to find surface defects and color differences. The cloth inspection machine automatically completes the length recording and roll arrangement work. The cloth inspection machine with good performance is equipped with an electronic defect detection device. After detecting defects, the cloth inspection machine will mark the defects, and then spread the cloth on the cloth stretching machine for flattening and cutting. Finally, the inspector will search for the pieces with defective marks piece by piece.

[0003] However, when there is no cloth inspection machine in this process, the inspectors also have to search for defective pieces one by one, so the workload of finding defective pieces after cutting is still relatively large. Summary of the invention

[0004] The embodiments of the present application provide a method, device, memory and electronic device for intelligently locating defective pieces, which are used to solve the technical problem of large workload in finding defective pieces in the prior art.

[0005] The first aspect of the present application provides an intelligent positioning method for defective sheets, comprising:

[0006] Projecting the electronic marker onto the table of the cloth spreading machine to form a marker image, wherein the size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth;

[0007] Identify the defective points of the cloth during the cloth pulling process, obtain the first position information of the defective points and the second position information of the defective points to form the defective cloth piece information; wherein the first position information is the position of the layer of the defective point in the cloth on the table, and the second position information is the specific piece information of the defective point in the image of the marker;

[0008] Laminating the surface of the cloth after the cloth is stretched, printing the electronic marker on the laminating film according to the size of the marker image to obtain a laminating marker, and printing the relevant information of each piece and the defective fabric piece information on the corresponding laminating piece surface on the laminating marker, wherein the defective fabric piece information is printed on the corresponding laminating piece surface according to the piece information indicated in the second position information;

[0009] The cloth is cut according to the shapes of the respective coated pieces of the coated marker diagram to obtain groups of cloth pieces, and the positions of the defective cloth pieces in the group of cloth pieces are obtained according to the defective cloth piece information recorded on the surfaces of the coated pieces on each group of cloth pieces.

[0010] Furthermore, the step of identifying defective points of the cloth during the cloth pulling process, obtaining first position information of the defective points and second position information of the defective points to form defective cloth piece information includes:

[0011] During the fabric inspection stage, the locations of the defects detected are marked on the fabric;

[0012] During the cloth pulling process, each time a layer of cloth is pulled, a first image of the current layer is obtained, wherein the first image includes the topmost layer of cloth stretched straight on the table and the image of the marker;

[0013] In response to identifying the presence of the mark in the first image, obtaining layer information of the current top layer of fabric, and a relative position relationship between the mark and a specific piece in the marker image;

[0014] The first position information is obtained according to the layer information, and the second position information is obtained according to the relative position relationship.

[0015] Furthermore, each time a layer of cloth is pulled, a first image of the current layer is obtained, including:

[0016] In response to the cloth pulling machine starting the cloth pulling process of the current layer, the table image of the current cloth pulling front position in the cloth pulling process is continuously photographed from top to bottom with a camera position relatively fixed to the head of the cloth pulling machine until the cloth pulling process of the current layer is completed and the shooting is terminated. The visual range of a single frame during the shooting is at least greater than or equal to a single image of the marker frame.

[0017] Further, in response to identifying the existence of the mark in the first image, obtaining the layer information of the current top layer of cloth and the relative position relationship between the mark and the specific piece in the marker image includes:

[0018] According to the number of marker image images on the table of the cloth spreading machine, the first image is divided into a corresponding number of sub-images, each of which is a set of video frames containing all pictures of a corresponding marker image;

[0019] After the drawing is completed, all sub-images corresponding to a certain marker image are combined into a sub-image set, where each sub-image has the marker image information and the corresponding layer information as a label;

[0020] Using a pre-trained machine vision model to perform defect recognition on the sub-image set, and obtaining defect points in each of the sub-images and specific piece information of the defect points in the sub-images;

[0021] Different defect points, layer information, cutting piece information, and marker map information in the sub-image set are grouped according to different specific cutting piece information of the defect points in the sub-images.

[0022] Furthermore, each time a layer of cloth is pulled, a first image of the current layer is obtained, including:

[0023] During the cloth pulling process, in response to the sensor capable of detecting the mark detecting the mark, the cloth pulling machine is paused;

[0024] According to the mark position currently detected by the sensor, a photo including the defect corresponding to the mark is taken from top to bottom, wherein the visual range of the photo at least includes a complete image of the defect and a complete image of the cut piece where the defect is located;

[0025] Each photo taken on this layer is cut according to the complete cut-out image recorded thereon to obtain a silhouette photo, and all the silhouette photos on this layer that belong to the same cut-out image are deduplicated, and all the remaining silhouette photos constitute the first image.

[0026] Furthermore, the method further comprises:

[0027] Complete the cutting of all fabrics under the current production task according to the production quantity, and obtain the types and quantities of all defective fabric pieces generated under the current production task according to the defective fabric piece information of each piece;

[0028] According to the types and quantities of all the defective fabric pieces, a supplementary electronic marker diagram is designed with the minimum required fabric quantity as the optimization goal, and corresponding fabric pieces are cut according to the supplementary electronic marker diagram to make up for the shortage of fabric pieces under the current production scheduling task.

[0029] A second aspect of the present application provides an intelligent positioning device for defective sheets, comprising:

[0030] A projection module is used to project the electronic marker image onto the table top of the cloth spreading machine to form a marker image, wherein the size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth;

[0031] A defective fabric piece information acquisition module is used to identify defective points of the fabric during the fabric pulling process, and obtain the first position information of the defective point and the second position information of the defective point to form defective fabric piece information; wherein the first position information is the position of the defective point in the layer of the fabric on the table, and the second position information is the specific piece information of the defective point in the image of the marker, wherein the defective fabric piece information is printed on the corresponding laminated piece surface according to the piece information indicated in the second position information;

[0032] A printing module, used for laminating the surface of the cloth after the cloth is stretched, printing the electronic marker on the laminating film according to the size of the marker image to obtain a laminating marker, and printing the relevant information of each cut piece and the defective cloth cut piece information on the corresponding laminating cut piece surface on the laminating marker;

[0033] The cutting module is used to cut cloth according to the shapes of each coated piece of the coated marker diagram and obtain each group of cloth pieces, and obtain the position of the defective cloth in the group of cloth pieces according to the defective cloth piece information recorded on the surface of the coated piece on each group of cloth pieces.

[0034] The third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method described in the first aspect of the present application.

[0035] The fourth aspect of the present application provides a computer-readable storage medium, which is used to store a computer program. When the computer program runs on a computer, the computer executes the method described in the first aspect of the present application.

[0036] A fifth aspect of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect of the present application.

[0037] In an embodiment of the present application, an intelligent positioning method for defective pieces is adopted, including: projecting an electronic marker image onto the table top of a cloth-pulling machine to form a marker image, wherein the size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth; identifying defective points of the cloth during the cloth-pulling process, obtaining first position information of the defective point and second position information of the defective point to form defective cloth cut piece information; wherein the first position information is the position of the defective point in the layer of the cloth on the table top, and the second ... The specific cutting piece information in the label image; laminating the surface of the cloth after the cloth is pulled, printing the electronic label on the laminating film according to the size of the label image to obtain the laminating label, and printing the relevant information of each cutting piece and the defective fabric cutting piece information on the corresponding laminating cutting piece surface on the laminating label; cutting the cloth according to the shape of each laminating cutting piece of the laminating label and obtaining each group of fabric cutting pieces, and obtaining the location of the defective fabric in the group of fabric cutting pieces according to the defective fabric cutting piece information recorded on the laminating cutting piece surface on each group of fabric cutting pieces. This application solves the problem of large workload in finding defective cutting pieces, thereby saving labor costs and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 It is a flow chart of a method for intelligently locating a defective piece according to an embodiment of the present application.

[0040] Figure 2 is a structural schematic diagram of an intelligent positioning device for defective sheets according to an embodiment of the present application;

[0041] Figure 3 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0043] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] like Figure 1FIG. 1 is a flow chart of a method for intelligently locating defective sheets according to an embodiment of the present application. Figure 1 It can be seen that the intelligent positioning method for defective sheets comprises the following steps:

[0045] Step S101, projecting the electronic marker onto the table top of the cloth spreading machine to form a marker image, wherein the size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth.

[0046] Markers refer to the process of laying out patterns on a cutting bed paper that is the same width as the fabric being cut before cutting clothes in batches during industrial production of clothing. When designing clothing, designers usually use clothing CAD software, which is a computer-aided design software specifically designed for clothing. It supports clothing design, sample making, pattern design, typesetting, markers, pattern making and other functions, and is suitable for production management and design development work of clothing companies. Commonly used design software includes but is not limited to common clothing CAD software such as Gemini, Lectra, Gerber, etc.

[0047] Therefore, by projecting the electronic marker image obtained in the clothing CAD software onto the table top of the cloth spreading machine to form a marker image, the marker image can be seen on the table top of the cloth spreading machine or on the surface of the cloth when the cloth is laid on the table top of the cloth spreading machine. The number and distribution of the electronic marker images projected during projection are adapted to the cloth width of the cloth spreading machine table. For example, if a marker image formed after projection just fits a layer of cloth width, only one electronic marker image is projected; if a marker image formed after projection only occupies a part of a layer of cloth width, for example, the width fits the cloth width, but the length only occupies 1 / 5 of the cloth width, then 5 of the above electronic marker images are arranged in the length direction to form an electronic marker image combination and projected simultaneously so that the formed marker image fits the cloth width as a whole. The electronic marker images can be a combination of electronic marker images of the same set of clothing, or a combination of electronic marker images of different clothing. The principle is to make full use of as much fabric as possible.

[0048] Step S102, identifying defective points of the cloth during the cloth pulling process, obtaining first position information of the defective points and second position information of the defective points to form defective cloth piece information; wherein the first position information is the position of the layer of the defective point in the cloth on the table, and the second position information is the specific piece information of the defective point in the marker image.

[0049] The cloth pulling machine can count the information of the current cloth pulling layer when pulling the cloth. Therefore, the first position information of the defect point in the top layer of cloth in the current state is the number of layers of the current top layer of cloth in the current round of cloth pulling by the cloth pulling machine. For example, if the current top layer of cloth is the 5th layer, the first position information of the defect point is recorded as 5.

[0050] Since the marker image is also presented on the surface of the top layer of cloth, the relative position relationship between the defect point on this layer of cloth and the specific piece in the marker image can be obtained through the surface of the top layer of cloth, including multiple different position relationships such as not being located on any piece, being completely located in one of the pieces, and being located on multiple pieces at the same time.

[0051] Therefore, the above relative position relationship can be converted into the second information, for example:

[0052] When the defect point is not located on any cut piece, the second position information recording the defect point is empty;

[0053] When the defect point is completely located in one of the cut pieces X1, the second position information of the defect point is recorded as X1;

[0054] When the defect point is located in a plurality of cut pieces X2 and X3 at the same time, the second position information of the defect point is recorded as X2 and X3.

[0055] Step S103, laminating the surface of the cloth after the cloth is stretched, printing the electronic marker on the laminating film according to the size of the marker image to obtain a laminating marker, and printing the relevant information of each piece and the defective fabric piece information on the corresponding laminated piece surface on the laminating marker, wherein the defective fabric piece information is printed on the corresponding laminated piece surface according to the piece information indicated in the second position information.

[0056] For example, after the cloth is stretched to form 50 layers, the cloth is transferred to the cutting table, the top layer of the cloth is covered with a film for protection, and the marker image is directly printed on the film using a printing device to replace the traditional marker paper.

[0057] The relevant information of the corresponding pieces and the defective fabric piece information are recorded on different laminated pieces. For example, two different laminated pieces X1 and X2 belonging to the same clothing model A have the following information recorded on the surface of the laminated pieces:

[0058] The relevant information recorded on the laminated piece X1 is: piece X1---model A of the garment it belongs to, location B;

[0059] The defective fabric piece information recorded on the laminated piece X1 is: the 5th layer, X1; the 8th layer, X1; the 35th layer, X1.

[0060] The relevant information recorded on the laminated piece X2 is: piece X2---model A of the garment it belongs to, location C;

[0061] The defective fabric piece information recorded on the laminated piece X2 is: the 5th layer, X2; the 13th layer, X2; the 27th layer, X2.

[0062] Step S104, cutting cloth according to the shapes of each coated piece of the coated marker diagram to obtain each group of cloth pieces, and obtaining the location of the defective cloth in the group of cloth pieces according to the defective cloth piece information recorded on the surface of the coated piece on each group of cloth pieces.

[0063] After cutting the fabric according to the shape of the above-mentioned laminated pieces, the specific location of the defective fabric in the group of fabric pieces can be obtained. For example, according to the "5th layer, X2; 13th layer, X2; 27th layer, X2" recorded on the above-mentioned laminated piece X2, the corresponding defective pieces can be directly found from the 5th layer, 13th layer and 27th layer.

[0064] Through the above method, the defective cut pieces are conveniently and quickly located, which greatly saves the time of searching for the defective cut pieces and improves the labor efficiency.

[0065] In some preferred embodiments, in order to obtain defective fabric piece information more intelligently, the defective point of the fabric is identified during the cloth pulling process, and the first position information of the defective point and the second position information of the defective point are obtained to form the defective fabric piece information, including:

[0066] During the cloth inspection stage, the locations of the detected defects are marked on the cloth.

[0067] The marking here can be realized in various ways according to the functions of different cloth inspection machines, for example, the defect can be marked by pasting, embossing, etc.; or a marking element can be configured on the cloth inspection machine, for example, a marking element is configured at the cloth outlet end of the detection chamber of the cloth inspection machine, and the marking element faces the first surface of the cloth obliquely so that the marking element can produce a mark on the first surface of the cloth obliquely. Specifically, the marking element can be, for example, an element that can automatically replenish ink or toner and other coatings, and the coating replenished by the marking element is in initial contact with the first surface of the cloth obliquely. In some embodiments, the angle θ1 between the marking element and the first surface of the cloth can be between 15 degrees and 45 degrees, so that the cloth can move forward smoothly during the marking period without pausing its conveyance, thereby improving the detection efficiency, and can reduce the thrust strength applied to the cloth by the marking element during the marking period to avoid excessive pulling of the cloth, thereby ensuring that the cloth remains flat until the detection, positioning and marking of the defect are completely completed.

[0068] During the cloth pulling process, each time a layer of cloth is pulled, a first image of the current layer is obtained, wherein the first image includes the topmost layer of cloth stretched straight on the table and the image of the marker.

[0069] Since the positions of defects in each layer are different, it is necessary to obtain corresponding image information by layer in units to traverse the defects in each layer. This process is synchronized with the working process of the cloth pulling machine and determines the ability to quickly count the positions of defective pieces in each group of cloth pieces.

[0070] In response to identifying that the mark exists in the first image, layer information of the current top layer of cloth is obtained, as well as a relative position relationship between the mark and a specific cut piece in the marker image.

[0071] The first position information is obtained according to the layer information, and the second position information is obtained according to the relative position relationship.

[0072] Therefore, after the above information is counted for each layer of cloth, the defective cloth piece information on each layer of cloth can be obtained. Based on this, when all layers are counted, the defective cloth piece information can be reclassified to the corresponding piece according to the piece dimension, thereby realizing the integration of the defective piece information in a group of cloth pieces.

[0073] In some preferred embodiments, in order to be able to capture the first image relatively stably, a camera device is fixed on the head of the cloth-pulling machine so that the camera device and the head of the cloth-pulling machine move synchronously, and the lens of the camera device is located directly above the table of the cloth-pulling machine. Based on this, each time a layer of cloth is pulled, the first image of the current layer is obtained, including:

[0074] In response to the cloth pulling machine starting the cloth pulling process of the current layer, the camera device is started, and the camera device continuously shoots the table image of the current cloth pulling front position in the cloth pulling process in a top-down direction and at a relatively fixed position until the cloth pulling process of the current layer is completed and the shooting is ended. The visual range of a single frame during the shooting is at least greater than or equal to a single image of the marker frame.

[0075] In the above scheme, the camera device completely records the process of pulling the cloth of each layer to form a continuous image, and the viewing angle remains relatively fixed, so that the defect points and the marker image in this layer of cloth are recorded one by one in the image according to the order of appearance of the cloth pulling process. The start and stop of this process responds to the start and stop of the cloth pulling machine, and does not affect the work of the cloth pulling machine, and can be completed at the same time as the cloth pulling machine.

[0076] Since the length of the same layer of cloth may be very long, it may include multiple marker image images. As described in the above embodiments, in order to more accurately distinguish defects based on the images, in some preferred embodiments, in response to recognizing the presence of the mark in the first image, obtaining the layer information of the current top layer of cloth, and the relative position relationship between the mark and the specific cut piece in the marker image, includes:

[0077] The first image is divided into a corresponding number of sub-images according to the number of marker image images on the table of the cloth-pulling machine, and each sub-image is a set of video frames containing all pictures of a corresponding marker image. For example, if the number of marker images is 5 and they are arranged in sequence according to the cloth-pulling direction, the image is divided into 5 sub-images, and the first sub-image is from the time when the first marker image enters the screen to the time when the first marker image completely disappears from the screen, the second sub-image is from the time when the second marker image enters the screen to the time when the second marker image completely disappears from the screen, and so on. The Nth sub-image and the N+1th or N-1th sub-image obtained by the above-mentioned segmentation method partially overlap in time sequence, but it can ensure that each sub-image completely records the appearance process of the corresponding marker image.

[0078] After the cloth is pulled, all sub-images corresponding to a certain marker image are combined into a sub-image set, where each sub-image has the marker image information and the corresponding layer information as a label. For example, if the number of marker image images per layer is 5, then 5 sub-images are generated per layer; when a total of 50 layers of cloth are pulled, 50 sub-images are formed for each marker image to form a sub-image set.

[0079] In order to quickly identify the position of defective pieces in each group of fabric pieces, it is also necessary to process the above-mentioned sub-image set, that is: use a pre-trained machine vision model to perform defect recognition on the sub-image set to obtain the defect points in each sub-image and the specific piece information of the defect points in the sub-image; according to the different specific piece information of the defect points in the sub-image, the different defect points, layer information, piece information, and marker map information in the sub-image set are grouped.

[0080] In certain optional embodiments, the use of a pre-trained machine vision model to perform defect recognition on the sub-image set includes: for each sub-image, selecting a key frame from the sub-image, wherein the key frame satisfies that the geometric center of the defect in the frame is located on the horizontal or vertical center dividing line of the frame image, identifying the piece information where the key frame is located based on multiple frame images with a predetermined time sequence distance before and after the key frame, and identifying the type of defect points on the key frame based on the key frame.

[0081] In an optional embodiment, the machine vision model uses the YOLO4 model and uses CSPdarknet53 as the feature extraction backbone network, including 23 CSP modules, each of which includes a residual component deepening network. In order to better count the defect categories, in some preferred embodiments, the machine vision model can also identify 13 defect categories such as parallel wire, thread knot, hooked wire, and grade.

[0082] The above-mentioned method based on continuous images for recognition requires a large storage space and computing power. Therefore, when the storage space or computing power is limited, in some other preferred embodiments, each time a layer of cloth is pulled, the first image of the current layer is obtained, including:

[0083] During the cloth pulling process, in response to the sensor capable of detecting the mark detecting the mark, the cloth pulling machine is paused;

[0084] According to the mark position currently detected by the sensor, a photo including the defect corresponding to the mark is taken from top to bottom, wherein the visual range of the photo at least includes a complete image of the defect and a complete image of the cut piece where the defect is located;

[0085] Each photo taken on this layer is cut according to the complete cut-out image recorded thereon to obtain a silhouette photo, and all the silhouette photos on this layer that belong to the same cut-out image are deduplicated, and all the remaining silhouette photos constitute the first image.

[0086] Through the above method, the defect mark is directly identified by the sensor, and the camera can be quickly and accurately moved to aim at the defect to shoot. This method needs to appropriately sacrifice the smoothness of the cloth pulling process of the cloth pulling machine, but it can reduce the number of image frames exponentially, greatly reducing the storage space, and then according to the cutting method based on the complete piece, each independent piece corresponds to an image, which facilitates the subsequent work of identifying defects based on the first image.

[0087] In certain preferred embodiments, the method further comprises:

[0088] Complete the cutting of all fabrics under the current production task according to the production quantity, and obtain the types and quantities of all defective fabric pieces generated under the current production task according to the defective fabric piece information of each piece;

[0089] According to the types and quantities of all the defective fabric pieces, a supplementary electronic marker diagram is designed with the minimum required fabric quantity as the optimization goal, and corresponding fabric pieces are cut according to the supplementary electronic marker diagram to make up for the shortage of fabric pieces under the current production scheduling task.

[0090] For example, suppose that the types and quantities of all defective fabric pieces obtained after cutting this batch of fabric are as follows:

[0091] Piece X1: 35 pieces; Piece X2: 105 pieces; Piece X3: 70 pieces.

[0092] Taking the minimum required amount of fabric as the optimization goal, it was found that 1 piece X1, 3 pieces X2, and 2 pieces X3 were arranged in a supplementary electronic marker diagram that is equivalent to the width of the fabric and the most compact in length. After the corresponding fabrics were stretched into 35 layers, the fabrics were cut according to the supplementary electronic marker diagram to obtain 35 pieces X1, 105 pieces X2, and 70 pieces X3.

[0093] This embodiment also provides an intelligent positioning device for defective sheets, including:

[0094] The projection module is used to project the electronic marker image onto the table top of the cloth stretching machine to form a marker image. The size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth.

[0095] The defective fabric piece information acquisition module is used to identify the defective points of the fabric during the fabric pulling process, and obtain the first position information of the defective point and the second position information of the defective point to form the defective fabric piece information; wherein the first position information is the position of the layer of the defective point in the fabric on the table, and the second position information is the specific piece information of the defective point in the marker image.

[0096] The printing module is used to coat the surface of the cloth after the cloth is stretched, and the electronic marker is printed on the coating according to the size of the marker image to obtain a coated marker, and the relevant information of each piece and the defective cloth piece information are printed on the corresponding coated piece surface on the coated marker.

[0097] The cutting module is used to cut cloth according to the shapes of each coated piece of the coated marker diagram and obtain each group of cloth pieces, and obtain the position of the defective cloth in the group of cloth pieces according to the defective cloth piece information recorded on the surface of the coated piece on each group of cloth pieces.

[0098] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0099] By means of the above-mentioned intelligent positioning device for defective pieces, the positioning of defective pieces is realized conveniently and quickly, which greatly saves the time for searching for defective pieces and improves labor efficiency.

[0100] Based on the same inventive concept as the above-mentioned method embodiment, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method in the above-mentioned embodiment.

[0101] In one embodiment, the electronic device may be a server. In this embodiment, the structure of the electronic device may be as follows: Figure 3 As shown, it includes a memory 2001 , a communication module 2003 and one or more processors 2002 .

[0102] The memory 2001 is used to store computer programs executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and programs required for running the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0103] The memory 2001 may be a volatile memory, such as a random-access memory (RAM); the memory 2001 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 2001 may be any other medium that can be used to carry or store a desired computer program in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2001 may be a combination of the above memories.

[0104] The processor 2002 may include one or more central processing units (CPU) or a digital processing unit, etc. The processor 2002 is used to implement the above-mentioned intelligent positioning method for defective slices when calling the computer program stored in the memory 2001 .

[0105] The communication module 2003 is used to communicate with terminal devices and other servers.

[0106] The specific connection medium between the memory 2001, the communication module 2003 and the processor 2002 is not limited in the embodiment of the present application. Figure 3 In the embodiment, the memory 2001 and the processor 2002 are connected via a bus 2004. The bus 2004 is Figure 3The thick arrows in the figure are used to describe the connection between other components, which is only for illustrative purposes and is not intended to be limiting. The bus 2004 can be divided into an address bus, a data bus, a control bus, etc. For ease of description, Figure 3 Only one thick arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0107] Based on the same inventive concept as the above method embodiment, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium is used to store a computer program, when the computer program is run on a computer, the electronic device implements the intelligent positioning method of the defective piece in the above embodiment. The computer-readable storage medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0108] Based on the same inventive concept as the above-mentioned method embodiment, an embodiment of the present invention further provides a computer program product, the computer program product including a computer program. When the program product is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the control method according to various exemplary embodiments of the present application described above in this specification. The program product may adopt any combination of one or more readable media. These computer program commands may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the commands executed by the processor of the computer or other programmable data processing device generate commands for implementing the steps in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

Claims

1. An intelligent positioning method for defective sheets, characterized in that: include: Projecting the electronic marker onto the table of the cloth spreading machine to form a marker image, wherein the size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth; Identify the defective points of the cloth during the cloth pulling process, obtain the first position information of the defective points and the second position information of the defective points to form the defective cloth piece information; wherein the first position information is the position of the layer of the defective point in the cloth on the table, and the second position information is the specific piece information of the defective point in the image of the marker; Laminating the surface of the cloth after the cloth is stretched, printing the electronic marker on the laminating film according to the size of the marker image to obtain a laminating marker, and printing the relevant information of each piece and the defective fabric piece information on the corresponding laminating piece surface on the laminating marker, wherein the defective fabric piece information is printed on the corresponding laminating piece surface according to the piece information indicated in the second position information; The cloth is cut according to the shapes of the respective coated pieces of the coated marker diagram to obtain groups of cloth pieces, and the positions of the defective cloth pieces in the group of cloth pieces are obtained according to the defective cloth piece information recorded on the surfaces of the coated pieces on each group of cloth pieces.

2. The method according to claim 1, characterized in that: The method of identifying defective points of the cloth during the cloth pulling process, obtaining first position information of the defective points and second position information of the defective points to form defective cloth piece information includes: During the fabric inspection stage, the locations of the defects detected are marked on the fabric; During the cloth pulling process, each time a layer of cloth is pulled, a first image of the current layer is obtained, wherein the first image includes the topmost layer of cloth stretched straight on the table and the image of the marker; In response to identifying the presence of the mark in the first image, obtaining layer information of the current top layer of fabric, and a relative position relationship between the mark and a specific piece in the marker image; The first position information is obtained according to the layer information, and the second position information is obtained according to the relative position relationship.

3. The method according to claim 2, characterized in that: The first image of the current layer is obtained each time a layer of cloth is pulled, including: In response to the cloth pulling machine starting the cloth pulling process of the current layer, the table image of the current cloth pulling front position in the cloth pulling process is continuously photographed from top to bottom with a camera position relatively fixed to the head of the cloth pulling machine until the cloth pulling process of the current layer is completed and the shooting is terminated. The visual range of a single frame during the shooting is at least greater than or equal to a single image of the marker frame.

4. The method according to claim 3, characterized in that: In response to recognizing that the mark exists in the first image, obtaining the layer information of the current top layer of cloth, and the relative position relationship between the mark and the specific piece in the marker image, includes: According to the number of marker image images on the table of the cloth spreading machine, the first image is divided into a corresponding number of sub-images, each of which is a set of video frames containing all pictures of a corresponding marker image; After the drawing is completed, all sub-images corresponding to a certain marker image are combined into a sub-image set, where each sub-image has the marker image information and the corresponding layer information as a label; Using a pre-trained machine vision model to perform defect recognition on the sub-image set, and obtaining defect points in each of the sub-images and specific piece information of the defect points in the sub-images; Different defect points, layer information, cutting piece information, and marker map information in the sub-image set are grouped according to different specific cutting piece information of the defect points in the sub-images.

5. The method according to claim 2, characterized in that: The first image of the current layer is obtained each time a layer of cloth is pulled, including: During the cloth pulling process, in response to the sensor capable of detecting the mark detecting the mark, the cloth pulling machine is paused; According to the mark position currently detected by the sensor, a photo including the defect corresponding to the mark is taken from top to bottom, wherein the visual range of the photo at least includes a complete image of the defect and a complete image of the cut piece where the defect is located; Each photo taken on this layer is cut according to the complete cut-out image recorded thereon to obtain a silhouette photo, and all the silhouette photos on this layer that belong to the same cut-out image are deduplicated, and all the remaining silhouette photos constitute the first image.

6. The method according to claim 5, characterized in that: The method further comprises: Complete the cutting of all fabrics under the current production task according to the production quantity, and obtain the types and quantities of all defective fabric pieces generated under the current production task according to the defective fabric piece information of each piece; According to the types and quantities of all the defective fabric pieces, a supplementary electronic marker diagram is designed with the minimum required fabric quantity as the optimization goal, and corresponding fabric pieces are cut according to the supplementary electronic marker diagram to make up for the shortage of fabric pieces under the current production scheduling task.

7. An intelligent positioning device for defective sheets, characterized in that: include: A projection module is used to project the electronic marker image onto the table top of the cloth spreading machine to form a marker image, wherein the size of each cut piece image in the marker image is consistent with the size of the cut piece that actually needs to be cut from the cloth; A defective fabric piece information acquisition module is used to identify defective points of the fabric during the fabric pulling process, and obtain the first position information of the defective point and the second position information of the defective point to form defective fabric piece information; wherein the first position information is the position of the defective point in the layer of the fabric on the table, and the second position information is the specific piece information of the defective point in the image of the marker, wherein the defective fabric piece information is printed on the corresponding laminated piece surface according to the piece information indicated in the second position information; A printing module, used for laminating the surface of the cloth after the cloth is stretched, printing the electronic marker on the laminating film according to the size of the marker image to obtain a laminating marker, and printing the relevant information of each cut piece and the defective cloth cut piece information on the corresponding laminating cut piece surface on the laminating marker; The cutting module is used to cut cloth according to the shapes of each coated piece of the coated marker diagram and obtain each group of cloth pieces, and obtain the position of the defective cloth in the group of cloth pieces according to the defective cloth piece information recorded on the surface of the coated piece on each group of cloth pieces.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product is run on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 6.

Images