CN118209561A - Coil stock detection method and system - Google Patents

Abstract

The embodiment of the application discloses a detection method and a detection system for coiled materials, wherein the detection method for coiled materials is applied to a visual upper computer and comprises the following steps: respectively acquiring line scanning images acquired by at least two line scanning cameras on a detection station for the coil stock; at least two line scanning cameras have intersection areas in the acquisition visual field range of the coil stock, and the range of the union areas is larger than the width of the coil stock; and respectively carrying out defect detection on the line scanning images acquired by each line scanning camera, correspondingly obtaining a defect detection result of each line scanning image, and sending the defect detection result to the controller. In the embodiment of the application, the intersection area exists in the acquisition visual field range of the coil stock by at least two line scanning cameras on the detection station, and the range of the union area is larger than the width of the coil stock, so that the line scanning images acquired by the at least two line scanning cameras can be ensured to completely cover the coil stock, and the condition of missing shooting in partial areas of the coil stock can be avoided.

Description

Coil material detection method and system

Technical Field

The present application relates to but is not limited to the field of battery technology, and in particular to a coil material detection method and system.

Background technique

For coils, a black and white line scan camera is usually used to take pictures of the coils after being illuminated by a light source to inspect the coils. Due to the uneven coating or missing coating of the base material and coating material of the anode coils, it is difficult to distinguish the copper foil base and film area from the line scan image, making it difficult to detect defects in the coils.

Summary of the invention

In view of this, an embodiment of the present application provides a method and system for detecting a coil.

The technical solution of this application is implemented as follows:

In a first aspect, an embodiment of the present application provides a method for detecting a coil of material, which is applied to a visual host computer, and the detection method includes: respectively acquiring line scan images of the coil of material captured by at least two line scan cameras on the detection station; the capture fields of view of the coil of material by the at least two line scan cameras have an intersection area and the range of the union area is greater than the width of the coil of material; respectively performing defect detection on the line scan images captured by each of the line scan cameras, obtaining corresponding defect detection results for each of the line scan images, and sending the defect detection results to a controller.

In the embodiment of the present application, on the one hand, by detecting that there is an intersection area between the collecting field of view of the at least two line scan cameras on the detection station and the range of the union area is greater than the width of the coil, it can be ensured that the line scan images collected by the at least two line scan cameras can completely cover the coil, thereby avoiding the situation where some areas of the coil are missed; on the other hand, by performing defect detection on the line scan images collected by each line scan camera through the visual host computer, it can be ensured that some areas of the coil are missed.

In some embodiments, line scan images of the material roll captured by at least two line scan cameras on the inspection station are respectively obtained, including: in response to a trigger signal, controlling the light source on the inspection station to illuminate the material roll in a moving state; controlling at least two line scan cameras on the inspection station to take photos of the material roll at the same time; when the number of photos taken is greater than a preset number, controlling the at least two line scan cameras to output line scan images at the same time.

In the embodiments of the present application, on the one hand, by controlling at least two line scan cameras on the inspection station to take pictures of the moving roll material at the same time through a visual host computer, it is possible to avoid missing some areas of the roll material; on the other hand, when the number of pictures is greater than a preset number, the visual host computer controls at least two line scan cameras to output line scan images at the same time, thereby providing conditions for the line scan cameras to stop collecting line scan images of the roll material.

In some embodiments, each of the inspection stations includes a line scan camera and a light source; wherein the long side of the field of view of the line scan camera is parallel to the width of the roll; there is a first preset angle between the field of view direction of the line scan camera and the normal of the roll; and there is a second preset angle between the lighting direction of the light source and the normal of the roll.

In the embodiment of the present application, by setting the long side of the field of view of the line scan camera to be parallel to the width of the coil, it can be ensured that the line scan image captured by the line scan camera can completely cover the coil.

In some embodiments, the coiled material is a lithium electrode sheet, and the inspection station includes a front inspection station and a back inspection station; the front inspection station is used to inspect the front side of the lithium electrode sheet; the back inspection station is used to inspect the back side of the lithium electrode sheet; wherein, each of the inspection stations is provided with two brackets; each of the brackets is provided with two line scan cameras, and there is a space of a preset area between the two line scan cameras, and the area of the line scan camera is larger than the area of the space; the four line scan cameras on each of the inspection stations are arranged in an alternating manner.

In the embodiment of the present application, on the one hand, by adopting the front inspection station and the back inspection station to respectively inspect the front and back sides of the lithium electrode sheet, a comprehensive inspection of the lithium electrode sheet is achieved, thereby improving the performance and safety of the battery; on the other hand, by respectively setting four line scan cameras on the front inspection station and the back inspection station and arranging them in a staggered manner, it can be ensured that the line scan images captured by the four line scan cameras can completely cover the coil.

In some embodiments, the front inspection station includes a first front inspection station and a second front inspection station; controlling at least two line scan cameras on the inspection station to take pictures of the roll material at the same time, including: controlling the two line scan cameras on the first front inspection station to take pictures of the roll material at the same time; controlling the two line scan cameras on the second front inspection station to take pictures of the roll material at the same time.

In the embodiment of the present application, the visual host computer controls two line scan cameras on two front inspection stations to take pictures of the coil at the same time, which can avoid missing some areas of the coil.

In some embodiments, the defect detection includes metal leakage detection of the lithium electrode sheet; defect detection is performed on each line scan image captured by the line scan camera respectively, and a defect detection result corresponding to each line scan image is obtained, including: binarization processing is performed on each line scan image captured by the line scan camera respectively, and a binary image corresponding to each line scan image is obtained; a first connected area in which white pixels in each binary image are connected to each other is determined; the white pixels represent the pixels corresponding to the membrane area in the binary image; an expansion operation is performed on the first connected area corresponding to each binary image, and a second connected area is obtained; the position of each second connected area in the corresponding line scan image is determined; a third connected area is screened out from the second connected area; the third connected area represents an area where metal leakage defects may exist; and the defect detection result of the third connected area corresponding to the area larger than the preset metal leakage area is determined as metal leakage.

In the embodiment of the present application, on the one hand, by using a visual host computer to determine the first connected area based on white pixels in the binary image corresponding to the line scan image, the accuracy of the first connected area can be improved; on the other hand, by using a dilation operation, the image features in the first connected area can be enhanced and the white highlight area in the image can be expanded so as to more accurately locate and identify defects.

In some embodiments, filtering out a third connected area from the second connected area includes: determining the number of pixel points in each of the second connected areas and the pixel value corresponding to each pixel point; when the number of pixel points is greater than a first preset value, determining the pixel points in the second connected area whose pixel values are greater than the second preset value as target pixel points; and determining the third connected area based on the target pixel points.

In the embodiment of the present application, by combining the two conditions of the number of pixel points and the pixel value for screening, the second connected regions that do not meet the conditions can be excluded, thereby improving the accuracy of the third connected regions.

In some embodiments, the defect detection includes detecting concave and convex points of the lithium electrode sheet; performing defect detection on each line scan image captured by the line scan camera respectively, and obtaining a defect detection result corresponding to each line scan image, and also includes: classifying each line scan image by a pre-trained classifier, and obtaining a fourth connected area; the fourth connected area represents an area where concave and convex points may exist; if the confidence of the fourth connected area is greater than a preset threshold, determining that the defect detection result of the line scan image corresponding to the fourth connected area is a concave and convex point.

In the embodiment of the present application, on the one hand, the visual host computer classifies each line scan image through a pre-trained classifier to obtain a fourth connected area where concave and convex points may exist, thereby achieving effective classification of line scan images in areas where concave and convex points may exist; on the other hand, the visual host computer determines the defect detection results of the line scan images corresponding to the confidence levels greater than a preset threshold as concave and convex points, thereby improving the accuracy and efficiency of concave and convex point recognition.

In some embodiments, each of the line scan images is classified by a pre-trained classifier to obtain a corresponding fourth connected area, including: performing semantic segmentation on each of the line scan images to obtain a corresponding segmented area of each of the line scan images; performing feature extraction on each segmented area of the line scan images to obtain a corresponding feature of each segmented area; classifying the features of each segmented area by the pre-trained classifier to obtain a classification result; when the classification result indicates that the lithium electrode sheet has concave-convex point defects, the segmented area corresponding to the classification result is determined as the fourth connected area.

In the embodiment of the present application, by combining semantic segmentation and a pre-trained classifier, it is possible to more accurately identify the concave-convex point defects on the lithium electrode sheet and determine the range of the concave-convex point defects.

In some embodiments, the defect detection result includes a first result for characterizing that the coil material is qualified and a second result for characterizing that the coil material is unqualified. The detection method also includes: when the defect detection result characterizes that the coil material does not have defects, sending the first result to the controller; when the defect detection result characterizes that the coil material has defects, sending the second result to the controller.

In the embodiment of the present application, the visual host computer sends the qualified or unqualified result of the coil to the controller, thereby realizing the quality control and traceability of the coil on the automated production line.

In a second aspect, an embodiment of the present application provides a coil material detection system, the detection system comprising at least two line scan cameras and a visual host computer; wherein the at least two line scan cameras are used to collect line scan images of the coil material; the collection field of view of the at least two line scan cameras for the coil material has an intersection area and the range of the union area is greater than the width of the coil material; the visual host computer is used to respectively obtain the line scan images of the coil material collected by the at least two line scan cameras on the detection station; respectively perform defect detection on the line scan images collected by each of the line scan cameras, obtain corresponding defect detection results for each of the line scan images, and send the defect detection results to a controller.

In some embodiments, the detection system further includes a controller; the controller is configured to mark a region of the coil where the defect is located in the line scan image when a defect detection result of the line scan image indicates the presence of a defect.

It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application.

BRIEF DESCRIPTION OF THE DRAWINGS

The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

FIG1 is a schematic diagram of an overall hardware layout for detecting a coil provided in an embodiment of the present application;

FIG2 is a schematic diagram of a process flow of implementing a coil material detection method provided in an embodiment of the present application;

FIG3 is a schematic diagram of the hardware layout of a single inspection station provided in an embodiment of the present application;

FIG4 is a top view of an installation of a line scan camera of a front visual inspection station provided by an embodiment of the present application;

FIG5 is a schematic diagram of the distribution of the front and back camera fields of view of a web of a visual inspection station provided in an embodiment of the present application;

FIG6 is a front view of an overall solution of a visual inspection station provided in an embodiment of the present application;

FIG. 7 is a schematic diagram of the hardware configuration and installation structure of a front vision station for a coil provided in an embodiment of the present application;

FIG8 is a schematic diagram of an implementation flow of another coil material detection method provided in an embodiment of the present application;

FIG. 9 is a schematic diagram of the composition structure of a coil material detection system provided in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the specific technical scheme of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this application are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

In the following description, reference is made to “some embodiments”, “this embodiment”, “embodiments of the present application” and examples, etc., which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

If similar descriptions of "first/second" appear in the application documents, the following instructions are added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

In order to facilitate understanding of the embodiments of the present application, an anode coil in the battery field is taken as an example for explanation.

(1) In the battery field, anode coil is a rolled anode material that needs to be further processed to become an anode plate. For example, the anode coil is cut into anode plates of a certain shape and size using a punching process.

(2) Laminating battery electrodes is an important step in the manufacturing process of lithium batteries. It mainly involves dividing the coated positive and negative electrodes into required sizes and stacking them in a specific order (usually positive electrode, separator, negative electrode, separator) to form a "sandwich" structure. Multiple such "sandwich" structures are further stacked to form a battery cell that can be packaged.

(3) Unwinding is a key step in the production process of lithium batteries, especially in the production of laminated battery electrodes. Unwinding is mainly to release the coated positive and negative electrode materials from the roll for subsequent punching, lamination and other processes.

At present, in the front process of power battery production, for example, before punching the anode coil, it is necessary to detect defects such as metal leakage, edge wrinkles and pinhole damage of the anode coil. On the one hand, due to manual misoperation, production equipment failure or process design defects, the coating material on the surface of the anode pole piece may fall off and the base metal material may leak out; on the other hand, due to the different manufacturing processes of laminated battery pole pieces, as the unwinding speed of the anode coil increases, the metal leakage area on the front and back of the anode coil continues to decrease, and it is difficult to identify the metal leakage area by human eyes; on the other hand, due to the different nucleation barriers on the surface of the metal leakage area and the membrane area of the anode pole piece, it will affect the growth trend of deposits (for example, lithium metal or other active substances) in subsequent electrochemical reactions, the decomposition of the electrolyte on the surface of the base and membrane area, and the consistency of the thickness of the cell micro-area, thereby reducing the overall stability and reliability of the battery. The current optical solution does not have the detection capability of the relevant detection items before punching, especially the high detection area accuracy of the metal leakage detection item, and cannot guarantee a 100% detection rate. Therefore, detecting the metal leakage problem of the anode coil is the key and difficulty in the front process of power battery production.

Based on this, an embodiment of the present application provides a method and system for detecting a coil of material, wherein the method for detecting a coil of material is applied to a visual host computer. On the one hand, by detecting that there is an intersection area in the collection field of view of the coil of material by at least two line scan cameras on the detection station and the range of the union area is greater than the width of the coil of material, it can be ensured that the line scan images collected by at least two line scan cameras can completely cover the coil of material, thereby avoiding the situation where some areas of the coil of material are missed; on the other hand, by performing defect detection on the line scan images collected by each line scan camera by the visual host computer, it can be ensured that some areas of the coil of material are missed.

The embodiment of the present application provides an overall hardware layout for detecting a coil, as shown in FIG1 , the overall hardware includes a light source 11, a line scan camera 12, an industrial computer 13, a central control display 14, a controller 15, an encoder 16 and a marking machine 17, wherein:

The size of the light source 11 can be selected according to the needs. Selecting a light source with high brightness and very good uniformity can effectively ensure the consistency of imaging; the line scan camera 12 is used to expose line by line according to the running speed and beat of the coil 18 to form a complete line scan image that meets the size requirements.

The industrial computer 13 is an image processing terminal in the system, which has a core computing model and can adapt to various operating systems to meet the needs of running host computer software in various development languages.

The central control display 14 is used to organize and summarize the processing results output by the industrial computer 13, arrange and display them after graphical operations, link various integrated functions, and interact with user operations on the front-end interface.

The controller 15 can exchange data with the industrial computer 13, for example, the control instructions of the industrial computer can be loaded into the memory for storage and execution at any time. It is mainly responsible for distance calculation. After receiving the alarm signal from the industrial computer, it controls the marking machine to mark the coil after a certain distance. The controller 15 can be a programmable logic controller (PLC).

The encoder 16 is generally press-mounted on the unwinding roller. During the movement of the coil, it will drive the rice pressing wheel to rotate together. Every time the encoder rotates a certain angle, it will output a pulse signal, triggering the line scan camera to capture a line of image data of the coil, thereby driving the line scan camera's shooting frequency and the coil's movement speed to be unified, ensuring that the line scan camera can stably output line scan images at different speeds.

The marking machine 17 can be driven by a motor to stick a sticker on a defective position of the coil material to mark the defect and remind subsequent processes to avoid and handle the defect.

The embodiment of the present application provides a coil material detection method, which is applied to a visual host computer. As shown in FIG2 , the coil material detection method may include the following steps S101 and S102, wherein:

Step S101, respectively acquiring line scan images of the coil collected by at least two line scan cameras on the inspection station; the collection field of view of the coil by the at least two line scan cameras has an intersection area and the range of the union area is greater than the width of the coil;

Here, the line scan images of the coils captured by at least two line scan cameras at the inspection station are obtained by the visual host computer. The visual host computer is an important component of the machine vision system. It is usually a computer or a special device (for example, an industrial computer) used to control and manage the entire machine vision system. It can receive image data from image acquisition devices (for example, line scan cameras) and perform image processing and analysis on them. Among them, the working mode of the line scan camera is different from that of an ordinary area array camera. It scans the coil in a moving state line by line, and only collects one line of image data each time. These image data are spliced to form a complete line scan image.

In some embodiments, at least two line scan cameras at the detection station take pictures of the coil and obtain corresponding line scan images. The visual host computer splices the line scan images of the at least two line scan cameras to obtain an image that completely covers the coil, wherein the line scan images corresponding to two adjacent line scan cameras have an intersecting area.

It should be noted that the at least two line scan cameras in the embodiment of the present application may be two line scan cameras, three line scan cameras, four line scan cameras, etc. The number of line scan cameras can be determined by the width of the coil. For example, if the width of the coil is 240 millimeters (mm), four line scan cameras with a total field of view of 320 mm (each line scan camera has a field of view of 80 mm) are used to take pictures of the coil. In this way, the total field of view of the four line scan cameras is greater than the width of the coil, which can ensure that the line scan images captured by the four line scan cameras can completely cover the coil, thereby avoiding the situation where some areas of the coil are missed.

Step S102 , performing defect detection on each line scan image captured by the line scan camera, obtaining a corresponding defect detection result for each line scan image, and sending the defect detection result to a controller.

Here, PLC is a digital operation electronic system, which uses a programmable memory to store instructions for performing logical operations, sequential control, timing, counting and arithmetic operations, and controls various types of mechanical equipment or production processes through digital or analog input and output. The working principle of PLC is based on input, output and central processing, and works in a "sequential scanning, continuous cycle" manner. It can monitor, adjust and optimize the automated production process through programming, thereby improving production efficiency and quality.

The defect detection result of the line scan image can be that the coil has defects or no defects. Regardless of whether the visual host computer detects that the line scan image has defects, the defect detection result of the line scan image will be sent to the PLC. For example, if the visual host computer detects that the line scan image has no defects, the visual host computer sends the defect detection result of no defects in the coil to the PLC; if the visual host computer detects that the line scan image has defects, the visual host computer sends the defect detection result of defective coil to the PLC.

In some embodiments, since each line scan camera captures a different area of the roll material, it is necessary to perform defect detection on the line scan image corresponding to the roll material area captured by each line scan camera to avoid missing detection of some areas of the roll material.

In some embodiments, after step S102, after the PLC receives the defect detection result of the line scan image sent by the visual host computer, the PLC first determines the defective line scan image, and then marks the coil area where the defect is located in the line scan image, thereby achieving quality control and traceability of the coil on the automated production line.

In the embodiment of the present application, on the one hand, by detecting that there is an intersection area between the collecting field of view of the at least two line scan cameras on the detection station and the range of the union area is greater than the width of the coil, it can be ensured that the line scan images collected by the at least two line scan cameras can completely cover the coil, thereby avoiding the situation where some areas of the coil are missed; on the other hand, by performing defect detection on the line scan images collected by each line scan camera through the visual host computer, it can be ensured that some areas of the coil are missed.

In some embodiments, the implementation of step S101 of "respectively acquiring line scan images of the web captured by at least two line scan cameras at the inspection station" may include the following steps S1011 to S1013, wherein:

Step S1011, in response to a trigger signal, controlling the light source on the detection station to illuminate the web in a moving state;

Here, the light source includes a bar light source and an array light source. Taking a light emitting diode (LED) lamp as an example, in some embodiments, a bar light source may be a plurality of LED lamps arranged in a straight line; an array light source may include a plurality of bar light sources, and the plurality of bar light sources are sequentially connected end to end to form a square frame structure. Both the bar light source and the array light source can generate high-intensity light, and the light distribution is uniform, so that the coil obtains a clear and bright lighting effect. This uniform lighting helps to reduce shadows and reflections, thereby improving image quality. It should be noted that the light source in the embodiment of the present application may be any of the above-mentioned light sources.

The trigger signal can be a pulse signal sent by a PLC or a pulse signal sent by an encoder. The following is an example in which the trigger signal is a pulse signal sent by a PLC.

In some embodiments, first, the unwinding roller will drive the encoder on its shaft end to move synchronously during its movement, and the encoder will send a pulse signal generated during the movement to the visual host computer; then, after receiving the pulse signal, the visual host computer controls the light source on the inspection station to illuminate the coil in a moving state (for example, a moving speed of 80 meters per minute (m/min)) in response to the pulse signal, so that the light source provides a suitable ambient brightness for the line scan camera to take pictures of the coil.

Step S1012, controlling at least two line scan cameras on the inspection station to take pictures of the coil simultaneously;

In some embodiments, since at least two line scan cameras are taking pictures of the moving roll material, and each line scan camera is arranged at a different position of the inspection station and photographs different areas of the roll material, it is necessary to use a visual host computer to control at least two line scan cameras at the inspection station to take pictures of the roll material at the same time, so as to avoid missing some areas of the roll material.

Step S1013, when the number of photographing times is greater than a preset number, controlling the at least two line scan cameras to output line scan images simultaneously.

Here, the preset number of times may be a value preset according to the size of the coil, for example, 500 times, 600 times, 800 times, and 1000 times, etc. Given the coil size and the scanning width of the line scan camera, the number of pictures taken by the line scan camera is proportional to the length of the coil. Therefore, when the number of pictures taken by the line scan camera is greater than the preset number of times, it can be ensured that the line scan camera outputs a complete line scan image of the coil.

In some implementations, if the preset number of times is equal to 500 times, after each line scan camera collects 500 lines of image data, the visual host computer controls each line scan camera to simultaneously output a line scan image containing 500 lines of image data.

In the embodiments of the present application, on the one hand, by controlling at least two line scan cameras on the inspection station to take pictures of the moving roll material at the same time through a visual host computer, it is possible to avoid missing some areas of the roll material; on the other hand, when the number of pictures is greater than a preset number, the visual host computer controls at least two line scan cameras to output line scan images at the same time, thereby providing conditions for the line scan cameras to stop collecting line scan images of the roll material.

In some embodiments, each of the inspection stations includes a line scan camera and a light source; wherein the long side of the field of view of the line scan camera is parallel to the width of the roll; there is a first preset angle between the field of view direction of the line scan camera and the normal of the roll; and there is a second preset angle between the lighting direction of the light source and the normal of the roll.

The positional relationship between the line scan camera and the light source of a single inspection station is described below in conjunction with FIG3 and FIG4. As shown in FIG3, there is a first preset angle 25 between the field of view direction of the line scan camera 21 and the normal 24 of the web 22; there is a second preset angle 26 between the lighting direction of the light source 23 and the normal 24 of the web 22, and the first preset angle 25 is smaller than the second preset angle 26. As shown in FIG4, the long side 30 of the field of view of the line scan cameras 31, 32, 33 and 34 is parallel to the width of the web 22.

It should be noted that, as shown in Figure 3, the first preset angle 25 between the field of view of the line scan camera 21 and the normal 24 of the coil 22 is smaller than the second preset angle 26 between the lighting direction of the light source 23 and the normal 24 of the coil 22. Since the angle between the lighting direction of the light source and the normal of the coil is larger, it helps to reduce the shadows generated on the surface of the coil. Since the angle between the field of view of the line scan camera and the normal of the coil is smaller, the illuminated area within the field of view of the line scan camera is more concentrated, thereby improving the quality of the line scan image captured by the line scan camera.

In the embodiment of the present application, by setting the long side of the field of view of the line scan camera to be parallel to the width of the coil, it can be ensured that the line scan image captured by the line scan camera can completely cover the coil.

In some embodiments, the coiled material is a lithium electrode sheet, and the inspection station includes a front inspection station and a back inspection station; the front inspection station is used to inspect the front side of the lithium electrode sheet; the back inspection station is used to inspect the back side of the lithium electrode sheet; wherein, each of the inspection stations is provided with two brackets; each of the brackets is provided with two line scan cameras, and there is a space of a preset area between the two line scan cameras, and the area of the line scan camera is larger than the area of the space; the four line scan cameras on each of the inspection stations are arranged in an alternating manner.

Here, the front inspection station and the back inspection station are respectively provided with two brackets, two line scan cameras are placed on each bracket, and the area of the empty space between the two line scan cameras is smaller than the area of any one of the line scan cameras.

The positional relationship of the four line scan cameras located on two brackets at the front inspection station is described below in conjunction with FIG4. As shown in FIG4, the line scan camera 31 and the line scan camera 33 are located on one bracket of the front inspection station, and the line scan camera 32 and the line scan camera 34 are located on another bracket of the front inspection station. The line scan cameras 31 to 34 at the front inspection station are arranged in an interlaced manner. For example, there is an empty space 35 between the line scan camera 31 and the line scan camera 33, and there is an empty space 36 between the line scan camera 32 and the line scan camera 34, and the area of the empty space 35 or 36 is smaller than the area of any line scan camera at the front inspection station.

In the embodiment of the present application, on the one hand, by adopting the front inspection station and the back inspection station to respectively inspect the front and back sides of the lithium electrode sheet, a comprehensive inspection of the lithium electrode sheet is achieved, thereby improving the performance and safety of the battery; on the other hand, by respectively setting four line scan cameras on the front inspection station and the back inspection station and arranging them in a staggered manner, it can be ensured that the line scan images captured by the four line scan cameras can completely cover the coil.

In some embodiments, the front inspection station includes a first front inspection station and a second front inspection station; the implementation of step S1012 "controlling at least two line scan cameras on the inspection station to take pictures of the coil at the same time" may include the following steps S1121 and S1122, wherein:

Step S1121, controlling two line scan cameras on the first front inspection station to take pictures of the coil simultaneously;

In some embodiments, since the two line scan cameras on the first front inspection station are located on the same bracket and arranged at intervals, the visual host computer is required to control the two line scan cameras on the first front inspection station to take pictures of the roll material at the same time, which can avoid missing some areas of the roll material.

Step S1122, controlling two line scan cameras on the second front inspection station to take pictures of the coil simultaneously.

In some embodiments, since the two line scan cameras on the second front inspection station are located on the same bracket and arranged at intervals, the visual host computer is required to control the two line scan cameras on the second front inspection station to take pictures of the roll material at the same time, which can avoid missing some areas of the roll material.

In the embodiment of the present application, the visual host computer controls two line scan cameras on two front inspection stations to take pictures of the coil at the same time, which can avoid missing some areas of the coil.

In some embodiments, the defect detection includes metal leakage detection of the lithium electrode sheet; the implementation of "performing defect detection on each line scan image acquired by the line scan camera, and obtaining a corresponding defect detection result for each line scan image" in step S102 may include the following steps S1021 to S1026, wherein:

Step S1021, performing binarization processing on each line scan image acquired by the line scan camera to obtain a binary image of each line scan image;

Here, the line scan image can be a red, green, and blue (RGB) color image. Binarization is a process of setting the RGB value of each pixel of a color image to 0 (black) or 255 (white), so that the original color value range is changed from 256 to black and white, so that the binary image after binarization has only black and white.

In some embodiments, before the visual host computer performs binarization processing on the line scan image, the visual host computer can first grayscale the line scan image to obtain a grayscale image; then, scan the pixel values corresponding to each pixel point in the grayscale image, set the pixel values less than a preset threshold to 0, and set the pixel values greater than or equal to the preset threshold to 255, thereby obtaining a binary image of the line scan image.

Step S1022, determining a first connected region in which white pixels in each of the binary images are connected to each other; the white pixels represent pixels corresponding to the membrane area in the binary image;

Here, the first connected region may be an image region composed of white pixels having the same pixel value and adjacent to each other in the binary image.

Step S1023, performing an expansion operation on the first connected region corresponding to each of the binary images to obtain a corresponding second connected region;

Here, the dilation operation can be implemented by the dilate function. In image processing, the dilation operation can expand the range of the white highlight area in the image so as to more accurately locate and identify defects.

In some embodiments, the visual host computer dilates the first connected region corresponding to each binary image, fills the blank part in the first connected region, enhances the image features in the first connected region, and expands the white highlight area in the image, thereby obtaining a corresponding second connected region.

Step S1024, determining a position of each of the second connected regions in the corresponding line scan image;

In some embodiments, since the second connected area is a sub-area in the line scan image, it is necessary to convert the coordinates of the second connected area into the coordinate system of the line scan image through a visual host computer so that the second connected area can correctly correspond to the corresponding position in the line scan image.

Step S1025, selecting a third connected region from the second connected regions; the third connected region represents a region where metal leakage defects may exist;

Here, since the second connected area is the area corresponding to the membrane area of the coil, and metal leakage defects may exist on the membrane area, the visual host computer can remove the noise in the second connected area through corrosion operation, thereby more accurately screening out the third connected area where metal leakage defects may exist, and then more accurately locating whether there is a defect in the third connected area.

Step S1026, determining the defect detection result of the third connected area that is larger than the preset metal leakage area as metal leakage.

In some embodiments, the visual host computer compares the area of the third connected region with a preset metal leakage area. If the area of the third connected region is larger than the preset metal leakage area, it can be determined that a metal leakage defect exists in the third connected region.

In the embodiment of the present application, on the one hand, by using a visual host computer to determine the first connected area based on white pixels in the binary image corresponding to the line scan image, the accuracy of the first connected area can be improved; on the other hand, by using a dilation operation, the image features in the first connected area can be enhanced and the white highlight area in the image can be expanded so as to more accurately locate and identify defects.

In some embodiments, the implementation of step S1025 of "selecting a third connected area from the second connected area" may include the following steps S1251 to S1253, wherein:

Step S1251, determining the number of pixels in each of the second connected regions and the pixel value corresponding to each pixel;

Here, the number of pixels in the second connected region and the pixel value corresponding to each pixel may be determined by traversing all the pixels in the second connected region.

Step S1252, when the number of the pixel points is greater than the first preset value, determining the pixel points in the second connected area whose pixel values are greater than the second preset value as target pixel points;

Here, the first preset value may be any suitable value, such as 25, 40, etc. The second preset value may be any suitable value, such as 205, 234, etc. By setting the first preset value, the second connected areas with too few pixels and possibly composed of noise or irrelevant details may be excluded. By setting the second preset value, pixels with higher pixel values may be screened out.

Step S1253: determining the third connected area based on the target pixel point.

Here, after the target pixels are determined, a connected area may be formed based on the target pixels.

In the embodiment of the present application, by combining the two conditions of the number of pixel points and the pixel value for screening, the second connected regions that do not meet the conditions can be excluded, thereby improving the accuracy of the third connected regions.

In some embodiments, the defect detection includes detection of concave and convex points of the lithium electrode sheet; the implementation of "performing defect detection on each line scan image acquired by the line scan camera, and obtaining defect detection results for each line scan image" in step S102 may also include the following steps S1121 and S1122, wherein:

Step S1121, classifying each of the line scan images by a pre-trained classifier, and obtaining a corresponding fourth connected region; the fourth connected region represents a region where concave and convex points may exist;

Here, the pre-trained classifier may be a deep learning model (e.g., a convolutional neural network) for identifying potential concave and convex point regions. The pre-trained classifier may be obtained by training a classifier using images with concave and convex point annotations.

In some embodiments, the implementation of step S1121 “classifying each of the line scan images by a pre-trained classifier to obtain a corresponding fourth connected region” may also include the following steps S1211 to S1214, wherein:

Step S1211, performing semantic segmentation on each of the line scan images to obtain a corresponding segmented area of each of the line scan images;

Here, each line scan image can be semantically segmented by any of the fully convolutional networks (FCNs), deep learning models (Deeplab), and Transformer-based semantic segmenters (SegFormer), and the corresponding segmented areas of the line scan image can be obtained. Each line scan image may be divided into different areas, and each area may correspond to a different part of the lithium electrode sheet, such as a normal area, an area that may contain defects, etc.

Step S1212, performing feature extraction on each segmented region of the line scan image to obtain corresponding features of each segmented region;

Here, in the detection of lithium electrode sheets, it may be necessary to focus on specific features related to concave and convex point defects, such as local brightness changes, edge irregularities, etc. Therefore, it is necessary to extract features from the segmented areas of each line scan image to obtain the features of each segmented area.

It should be noted that the method of extracting features from the segmented area of the line scan image may include but is not limited to Histogram of Oriented Gradient (HOG), Local Binary Pattern (LBP), etc. For example, by using HOG, the segmented area is divided into small connected areas, and then the gradient or edge direction histograms of each pixel in the connected area are collected, and finally these histograms are combined to obtain multiple features.

Step S1213, classifying the features of each segmented region by the pre-trained classifier to obtain a classification result;

Here, the pre-trained classifier may be a convolutional neural network (Convnext), a residual network (Resnet), etc. In some embodiments, the extracted features of each segmented region are input into the pre-trained classifier, and the pre-trained classifier classifies the features of each segmented region and outputs a classification result. This classification result may be a probability value or a category label, indicating whether the segmented region contains a concave-convex point defect.

Step S1214, when the classification result indicates that the lithium electrode sheet has a concave-convex point defect, the segmented area corresponding to the classification result is determined as the fourth connected area.

In the embodiment of the present application, by combining semantic segmentation and a pre-trained classifier, it is possible to more accurately identify the concave-convex point defects on the lithium electrode sheet and determine the range of the concave-convex point defects.

Step S1122: if the confidence of the fourth connected area is greater than a preset threshold, determine that the defect detection result of the line scan image corresponding to the fourth connected area is a concave-convex point.

Here, the confidence reflects the possibility or credibility of the region being a concave-convex point. In some embodiments, the confidence of the fourth connected region related to the concave-convex point can be calculated by a confidence calculation formula.

In the embodiment of the present application, on the one hand, the visual host computer classifies each line scan image through a pre-trained classifier to obtain a fourth connected area where concave and convex points may exist, thereby achieving effective classification of line scan images in areas where concave and convex points may exist; on the other hand, the visual host computer determines the defect detection results of the line scan images corresponding to the confidence levels greater than a preset threshold as concave and convex points, thereby improving the accuracy and efficiency of concave and convex point recognition.

In some embodiments, the defect detection result includes a first result for characterizing that the coil is qualified and a second result for characterizing that the coil is unqualified, and the detection method further includes the following steps S111 and S112, wherein:

Step S111, when the defect detection result indicates that the coil has no defects, sending the first result to the controller;

Step S112: When the defect detection result indicates that the coil material has defects, the second result is sent to the controller.

In the embodiment of the present application, the visual host computer sends the qualified or unqualified result of the coil to the controller, thereby realizing the quality control and traceability of the coil on the automated production line.

The pole piece of a power battery is one of the important components of a power battery, and its quality and performance directly determine the quality and safety of the power battery. The pole piece of a power battery is composed of a base material and a coating material. The base material of the anode pole piece is a copper foil of about 8 microns (μm), and the coating material is an active medium of about 12 microns. The anode coil is formed by stirring, coating, rolling, and slitting the slurry. During the production process of the above process, the coil may have metal leakage, edge wrinkles, pinhole damage, bumps, wavy edges, negative electrode overhang and other depressions. Therefore, it is very important to conduct quality inspection of the power battery pole piece during the production process to ensure consistency.

For the above-mentioned coil defect detection, visual inspectors were initially arranged to conduct manual spot checks. They would sample the produced coils and inspect the two film areas of a section of coils through an optical microscope. However, with the improvement of production line production efficiency, the disadvantages of low efficiency and high missed detection rate of manual visual inspection became apparent. Therefore, a visual inspection system was introduced, using a black and white line scan camera and a line scan light source to complete the full inspection of the coil pole piece.

The current visual inspection system uses a black and white line scan camera and a line scan light source to complete the full inspection of the coil. However, due to changes in the coiling process, the coating material in the film area of the coil is unevenly coated or leaked, resulting in the general black and white line scan camera being unable to distinguish the grayscale value of the leaked metal in the film area of the coil under the dark field lighting of the line scan light source. In addition, with the improvement of the coiling process, the accuracy required for the detection of leaked metal on the surface of the coil is increased. The current optical inspection solution cannot meet the inspection specification requirements, and it is impossible to distinguish the leaked coating of the copper foil substrate and the film area only by the grayscale value.

The embodiment of the present application is mainly used to solve the problem of detecting the leakage of surface metal materials in the anode electrode film area caused by manual misoperation, production equipment failure or process design defects in the front process of power battery production. Based on industrial visual inspection technology, the embodiment of the present application proposes a visual inspection route for detecting the surface features of the front and back of the coil by splicing multiple cameras, which solves the problem that the current optical vision solution cannot effectively detect the leakage metal on the surface of the coil and distinguish the copper foil substrate and the film area, thereby improving the quality and performance of the battery electrode.

In view of the high-precision detection requirements of the metal leakage area of the power battery pole piece, the embodiment of the present application proposes an optical method of improving the visual inspection accuracy by splicing multiple cameras. By using multiple 16K (K represents the resolution of the line scan camera) color TDI line scan cameras (Time Delay Integration Line Scan Camera, time delay integration line scan camera) at the metal leakage detection visual station at the unwinding of the anode coil, with high-resolution lenses and light sources for lighting and taking pictures. Since the surface of the film area material of the coil is smooth and reflective, and the base copper foil material is rough, under the condition of dark field lighting, the light reflected by the film area does not enter the line scan camera lens image and is shown as a darker black film area, and the diffuse reflection of the base copper foil is shown as a bright red in the image. And by splicing multiple cameras, it is ensured that the camera field of view covers the width of the coil, and the single pixel accuracy of the camera is improved, and the theoretical detection accuracy reaches 0.01 mm/pix. The embodiment of the present application ensures that the line scan camera field of view covers the width of the anode coil by splicing multiple cameras, and improves the single pixel accuracy of the line scan camera. Visual inspection stations are set up on the front and back sides of the anode coil respectively. According to the surface defect detection characteristics of the coil, the metal leakage detection accuracy, the width of the coil and the size of the installation space, it is decided to use a 16K color TDI line scan camera. The focal length of the lens that meets the required field of view and accuracy of the camera is calculated, and the working distance meets the spatial layout and number of cameras on site.

As shown in FIGS. 5 and 6 , four 16K color TDI line scan cameras are respectively arranged on the front and back sides of the anode coil, with a total of eight line scan cameras, wherein the front side 41 of the anode coil is arranged with line scan cameras 401 to 404 (not shown in FIGS. 5 and 6 ) and light sources 411 and 412, wherein the line scan cameras 401 and 403 are placed in the same line scan camera dustproof cover 415, and the line scan cameras 402 and 404 are placed in the same line scan camera dustproof cover 416; the back side 42 of the anode coil is arranged with line scan cameras 405 to 408 (not shown in FIGS. 5 and 6 ) and light sources 413 and 414, wherein the line scan cameras 405 and 407 are placed in the same line scan camera dustproof cover 417, and the line scan cameras 406 and 408 are placed in the same line scan camera dustproof cover 418. Each line scan camera takes a picture of an anode coil area; the line scan image corresponding to each coil area is processed by an algorithm to identify the film area of the line scan image, and then after a series of image processing such as binarization, the metal leakage area and area of the film area are detected.

For anode pole pieces made by different processes, the embodiment of the present application designs two sets of lighting solutions (for example, front side lighting of anode coil and back side lighting of anode coil) to meet the algorithm detection requirements, accurately capture the metal leakage area of the membrane area and detect the area. The embodiment of the present application will effectively solve the problems of difficulty in detecting metal leakage of anode coils in the production process and high labor consumption for detection, thereby greatly reducing the leakage of metal defects, thereby achieving the purpose of reducing product risks, improving defect detection rate and product quality rate.

The following uses the front vision station of the coil as an example to introduce the optical method of multi-camera splicing to improve the visual inspection accuracy. The back vision station is similar, so I will not go into details here.

In the embodiment of the present application, since the width of the coil is large and the detection accuracy is required to be high, the shooting field of view of each line scan camera needs to be allocated in consideration of the large size of the line scan camera used. As shown in FIG4 , the line scan cameras are respectively installed on two brackets (not shown in FIG4 ) according to the field of view. There are two line scan cameras on each bracket. The line scan camera 31 and the line scan camera 33 are photographed on one bracket, and the line scan camera 32 and the line scan camera 34 are photographed on the other bracket. As shown in FIG3 , the angle between the field of view direction of each line scan camera 21 and the normal line 24 of the coil 22 is a first preset angle 25, the long side of the field of view of the line scan camera is parallel to the width of the coil, the angle between the light source 23 and the normal line 24 of the coil 22 is a second preset angle 26, and the first preset angle 25 is smaller than the second preset angle 26. The hardware configuration and installation structure of the front vision station of the coil material are shown in Figure 7. Each vision station is equipped with a line scan camera dust cover 61, a dust-proof air blowing mechanism 62 and a light source 63 (for example, a line scan strip light source). Among them, two line scan cameras are placed in the same line scan camera dust cover 61 at each inspection station. The dust-proof air blowing mechanism 62 is used to prevent dust from accumulating on the lens during the unwinding process of the coil material, which affects the imaging effect of the line scan camera.

The present application embodiment provides another coil material detection method, as shown in FIG8 , the detection method comprises the following steps:

Step S710, the coil moves on the unwinding roller, triggering the line scan camera to collect a line scan image of the coil;

Here, an encoder is installed at the shaft end of the unwinding roller. When the coil moves on the unwinding roller, the encoder sends the generated pulse signal to the line scan camera, and the line scan camera starts to collect the line scan image of the coil in response to the pulse signal.

Step S720: the four line scan cameras on the front visual station take pictures of the four areas on the front side of the coil respectively, and the four line scan cameras on the back visual station take pictures of the four areas on the back side of the coil respectively;

Step S730, the software algorithm on the visual host computer detects the line scan images of the eight coil areas respectively to determine whether there is metal leakage or concave-convex points in the coil; if so, that is, there is metal leakage or concave-convex points, go to step S740; if not, that is, there is no metal leakage or concave-convex points, go to step S760;

Here, determining whether there is metal leakage in the coil includes: first, the algorithm performs image processing on the line scan images of the eight areas of the coil respectively, and identifies the coating material and copper foil substrate of the film area of the image; secondly, the film area of the line scan image is binarized to detect the position and area of the metal leakage area of the film area; then, the metal leakage area is compared with the preset area to determine whether the metal leakage area exceeds the detection requirements; determining whether there are concave and convex points in the coil includes: using deep learning algorithms and traditional algorithms to perform image processing on the line scan images of the eight areas of the coil to locate and determine the positions of the concave and convex points on the surface of the coil.

It should be noted that the detection of the metal leakage area of the membrane area includes: binarizing each line scan image respectively to obtain a binary image of each line scan image. The image area composed of white pixels with the same pixel value and adjacent positions in each binary image is determined as the first connected area. The first connected area corresponding to each binary image is expanded to fill the blank part in the first connected area, enhance the image features in the first connected area and expand the white highlight area in the image, so as to obtain the second connected area. The number of pixels in the second connected area and the pixel value corresponding to each pixel are determined by traversing all the pixels in the second connected area. When the number of pixels is greater than the first preset value, the pixel in the second connected area whose pixel value is greater than the second preset value is determined as the target pixel. After determining the target pixel, the connectivity detection algorithm can be used to find the third connected area formed by these target pixels. The defect detection result of the third connected area corresponding to the preset metal leakage area is determined as metal leakage.

Step S740, the visual host computer sends a coil OK result to the PLC, that is, a coil quality qualified result;

Step S750, the PLC feeds back an OK result to the unwinding roller and controls the unwinding roller to operate normally;

Step S760: the visual host computer sends the coil material NG result, i.e. the coil material quality is unqualified, to the PLC.

Here, if there is metal leakage or concave-convex spots in the coil, the host computer sends the coil NG result to the PLC, and the NG result includes the defect type of the coil (metal leakage or concave-convex spots); if the defect type is metal leakage, the NG result also includes the area and position of the metal leakage area; if the defect type is concave-convex spots, the NG result also includes the position of the concave-convex spots.

Compared with the prior art, the embodiments of the present application have the following advantages:

1. The embodiment of the present application uses a 16K color TDI line scan camera based on the principle of multi-level exposure cumulative line scan imaging on the front and back sides of the coil to shoot the base and film area of the coil to obtain a color image of the surface characteristics of the coil. The color image obtained by traditional algorithm processing can accurately distinguish the position and area size of the copper foil base, film area and the metal leakage area of the film area, and compare the screened metal leakage area with the preset area to determine whether the metal leakage area exceeds the detection requirements.

2. The visual inspection station in the embodiment of the present application can identify surface defects of the coil, distinguish the copper foil substrate, film area material and leaking metal of the coil, and improve the ability to detect leaking metal on the surface of the coil.

3. The embodiment of the present application uses deep learning in the visual inspection station, combines traditional algorithms to process the obtained high-precision images, quickly locates the positions of the concave and convex points on the surface of the coil, and realizes the positioning and judgment of the concave and convex points on the surface of the pole piece.

4. The embodiments of the present application can meet the requirements of real-time detection of surface defects such as metal leakage, concave and convex spots on the surface of the coil without affecting on-site production, obtain the regional position and area information of metal leakage and concave and convex spots on the surface of the coil, and can interact the corresponding NG signal or OK signal with the unwinding equipment to discharge waste in the subsequent process section.

An embodiment of the present application provides a coil material detection system, as shown in Figure 9, the coil material detection system 800 includes at least two line scan cameras 810 and a visual host computer 820; wherein the at least two line scan cameras 810 are used to collect line scan images of the coil material; the at least two line scan cameras have an intersection area in their collection field of view for the coil material and the range of the union area is greater than the width of the coil material; the visual host computer 820 is used to respectively obtain the line scan images of the coil material collected by the at least two line scan cameras on the inspection station; defect detection is performed on each line scan image collected by the line scan camera, and a corresponding defect detection result is obtained for each line scan image, and the defect detection result is sent to a controller.

In some embodiments, the coil material detection system 800 further includes a controller; the controller is configured to mark the coil material region where the defect is located in the line scan image when the defect detection result of the line scan image indicates the presence of a defect.

It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial numbers of the above-mentioned steps/processes does not mean the order of execution, and the execution order of each step/process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

It should be noted that, in the application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the embodiments of the present application may be all integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims (11)

1. The detection method of the coil stock is characterized by being applied to a visual host computer, and comprises the following steps:

Respectively acquiring line scanning images acquired by at least two line scanning cameras on a detection station for the coil stock respectively; the at least two line scanning cameras have intersection areas for the acquisition visual field range of the coil stock, and the range of the union areas is larger than the width of the coil stock;

Performing defect detection on the line scanning images acquired by each line scanning camera respectively, correspondingly obtaining a defect detection result of each line scanning image, and sending the defect detection result to a controller;

the detection station comprises a front detection station and a back detection station;

the front detection station is used for detecting the front of the lithium electrode slice;

the back detection station is used for detecting the back of the lithium electrode slice;

wherein, each detection station is provided with two brackets;

Two line scanning cameras are arranged on each support, a gap with a preset area exists between the two line scanning cameras, and the area of each line scanning camera is larger than that of the gap;

Four line scanning cameras on each detection station are arranged in a staggered mode.

2. The method of claim 1, wherein the step of acquiring respective line scan images of the roll acquired by at least two line scan cameras at the inspection station, respectively, comprises:

Responding to a trigger signal, and controlling a light source on the detection station to polish the coil stock in a moving state;

controlling at least two line scanning cameras on the detection station to simultaneously photograph the coiled material;

and under the condition that the photographing times are larger than the preset times, controlling the at least two line scanning cameras to output line scanning images at the same time.

3. The method of claim 2, wherein each of the inspection stations includes a line scan camera and a light source;

Wherein the long side of the visual field of the line scanning camera is parallel to the width of the coil stock;

A first preset angle exists between the visual field direction of the line scanning camera and the normal line of the coil stock;

A second preset angle exists between the polishing direction of the light source and the normal line of the coil stock.

4. The method of claim 1, wherein the front side inspection station comprises a first front side inspection station and a second front side inspection station;

Controlling at least two line scanning cameras on the detection station to simultaneously photograph the coil stock, comprising:

Controlling two line scanning cameras on the first front detection station to simultaneously photograph the coiled material;

And controlling two line scanning cameras on the second front detection station to simultaneously photograph the coiled material.

5. The method of detecting a web according to claim 1, wherein the defect detection includes a metal leakage detection of the lithium electrode sheet;

Performing defect detection on the line scan image acquired by each line scan camera respectively to correspondingly obtain a defect detection result of each line scan image, including:

respectively carrying out binarization processing on the line scanning images acquired by each line scanning camera to correspondingly obtain a binary image of each line scanning image;

determining a first communication area in which white pixels in each binary image are connected with each other; the white pixel points represent pixel points corresponding to a film region in the binary image;

performing expansion operation on the first communication area corresponding to each binary image to correspondingly obtain a second communication area;

determining the position of each second communication area in the corresponding line scan image;

screening a third communication area from the second communication area; the third communication region characterizes a region possibly having a metal leakage defect;

And determining a defect detection result of the third communication region corresponding to the area larger than the preset metal leakage area as metal leakage.

6. The method of claim 5, wherein selecting a third communication area from the second communication areas, comprises:

Determining the number of pixel points in each second communication area and the pixel value corresponding to each pixel point;

Determining the pixel points with the pixel values larger than a second preset value in the second communication area as target pixel points under the condition that the number of the pixel points is larger than a first preset value;

And determining the third communication area based on the target pixel point.

7. The method of detecting a web material according to claim 1, wherein the defect detection includes a concave-convex point detection of the lithium electrode sheet;

performing defect detection on the line scanning images acquired by each line scanning camera respectively to correspondingly obtain defect detection results of each line scanning image, and further comprising:

classifying each line scanning image through a pre-trained classifier to correspondingly obtain a fourth communication area; the fourth communication region represents a region where an concave-convex point possibly exists;

And if the confidence coefficient of the fourth communication region is larger than a preset threshold value, determining that the defect detection result of the line scan image corresponding to the fourth communication region is concave-convex points.

8. The method of claim 7, wherein classifying each of the line scan images by a pre-trained classifier, the fourth connected region being obtained correspondingly, comprises:

Carrying out semantic segmentation on each line scanning image to correspondingly obtain a segmentation area of each line scanning image;

extracting features of the segmented regions of each line scan image, and correspondingly obtaining the features of each segmented region;

Classifying the characteristics of each segmented region through the pre-trained classifier to obtain a classification result;

And determining a segmentation area corresponding to the classification result as the fourth communication area under the condition that the classification result represents that the lithium electrode plate has the concave-convex point defect.

9. A method of inspecting a web according to any one of claims 2 to 8, wherein the defect inspection results include a first result for characterizing that the web is acceptable and a second result for characterizing that the web is unacceptable, the method further comprising:

sending the first result to a controller under the condition that the defect detection result indicates that the coil stock has no defect;

And sending the second result to the controller when the defect detection result indicates that the coil stock has defects.

10. The detection system for the coiled material is characterized by comprising at least two line scanning cameras and a visual upper computer;

The at least two line scanning cameras are used for collecting line scanning images of the coil stock; the at least two line scanning cameras have intersection areas for the acquisition visual field range of the coil stock, and the range of the union areas is larger than the width of the coil stock;

The visual upper computer is used for respectively acquiring line scanning images of the coil stock respectively acquired by at least two line scanning cameras on the detection station; performing defect detection on the line scanning images acquired by each line scanning camera respectively, correspondingly obtaining a defect detection result of each line scanning image, and sending the defect detection result to a controller; the detection station comprises a front detection station and a back detection station; the front detection station is used for detecting the front of the lithium electrode slice; the back detection station is used for detecting the back of the lithium electrode slice; wherein, each detection station is provided with two brackets; two line scanning cameras are arranged on each support, a gap with a preset area exists between the two line scanning cameras, and the area of each line scanning camera is larger than that of the gap; four line scanning cameras on each detection station are arranged in a staggered mode.

11. The coil stock inspection system of claim 10, further comprising a controller; the controller is used for marking a coil stock area where the defect is located in the line scanning image under the condition that the defect detection result of the line scanning image represents that the defect exists.