Lithium battery mylar film defect detection system, method and electronic device

Abstract

The application provides a lithium battery mylar film defect detection system, method and device and electronic equipment, and relates to the field of battery manufacturing.The lithium battery mylar film defect detection system comprises a conveying mechanism, an image acquisition mechanism, a first grabbing arm and an image detection mechanism.The conveying mechanism is used for moving a detection object to a first target position.The first grabbing arm is used for moving the detection object from the first target position to a second target position.The image acquisition mechanism is used for acquiring a first target image corresponding to a first surface when the detection object is located at the first target position, and acquiring a second target image corresponding to a second surface when the detection object is located at the second target position.The image detection mechanism is used for detecting whether the first surface and the second surface have defects according to the first target image and the second target image.The lithium battery mylar film defect detection system provided by the application is used for detecting lithium battery mylar defects, can save equipment space, and can accurately and efficiently detect lithium battery mylar defects.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of battery manufacturing, in particular to a lithium battery mylar film defect detection system, method and electronic device. BACKGROUND

[0002] Power battery is a key component of new energy vehicles. The advantages and disadvantages of power battery greatly affect the endurance mileage, charging efficiency and vehicle driving stability of new energy vehicles. At present, square battery is the most common structure of lithium ion battery. In the manufacturing process of square lithium battery, after the completion of the core manufacturing, the core needs to be packed into a hard square aluminum shell to complete the assembly. Because the aluminum shell is hard, there is a risk of scratching the core. Therefore, before the core is packed into the aluminum shell, the core needs to be wrapped with a mylar film which is soft and has good flexibility, so as to prevent the aluminum shell from damaging the core.

[0003] However, in the production process of wrapping the core with the mylar film, defects such as mylar damage, incomplete mylar wrapping, falling off, mispositioning of the adhesive, wrinkling and the like are prone to occur. The most common detection method for the mylar film wrapping defects is manual visual inspection. This method not only has low detection efficiency, but also has low detection accuracy. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a lithium battery mylar film defect detection system, method and electronic device. The defect detection system is used to detect the mylar defects of the lithium battery pack, which can not only save equipment space, but also accurately and efficiently detect the mylar defects of the lithium battery.

[0005] In a first aspect, the embodiments of the present application provide a lithium battery mylar film defect detection system, which comprises a conveying mechanism, an image acquisition mechanism, a first grabbing arm and an image detection mechanism. The conveying mechanism is used to move a detection object to a first target position. The first grabbing arm is used to move the detection object from the first target position to a second target position. The image acquisition mechanism is used to acquire a first target image corresponding to a first surface when the detection object is located at the first target position. The image acquisition mechanism is also used to acquire a second target image corresponding to a second surface when the detection object is located at the second target position. The image detection mechanism is used to detect whether the first surface and the second surface have defects according to the first target image and the second target image.

[0006] In the implementation process, the embodiment of the present application provides a lithium battery mylar film defect detection system, which comprises a conveying mechanism for moving a detection object, a first grabbing arm for transferring the detection object, an image acquisition mechanism for acquiring a target image, and an image detection mechanism for detecting the target image. The surface of the target object is detected by using the lithium battery mylar film defect detection system provided by the embodiment of the present application. The space occupied by the device is not large, and the detection efficiency of the detection object is high.

[0007] Optionally, in the embodiment of the present application, the image acquisition mechanism comprises a first image acquisition unit; the first target position comprises a position at which the first surface of the detection object faces the first image acquisition unit and / or a position after the conveying mechanism moves by a first preset distance; and in the process of moving the detection object to the first target position, the conveying mechanism is specifically configured to: carry the detection object and drive the detection object to move to the position at which the first surface of the detection object faces the first image acquisition unit and / or the position after the conveying mechanism moves by the preset distance.

[0008] In the implementation process, the first target position in the embodiment of the present application can be a position at which the first image detection unit detects that the first surface of the detection object faces the first image detection unit, or a position at which the conveying mechanism detects that the conveying mechanism has moved by a preset distance. The lithium battery mylar film defect detection system provided by the embodiment of the present application triggers the first image acquisition unit to acquire the image of the detection object through the first target position, so that the image can be accurately acquired and the corresponding surface of the detection object can be efficiently detected.

[0009] Optionally, in the embodiment of the present application, the first image acquisition unit comprises a highlight annular light source and a camera; and in the process of acquiring the first target image corresponding to the first surface when the detection object is located at the first target position: the highlight annular light source is configured to irradiate the first surface; and the camera is configured to shoot the first surface to obtain the first target image.

[0010] In the implementation process, in the optional implementation manner of the embodiment of the present application, the highlight annular light source is used in cooperation with the camera to acquire the image of the first surface; the highlight annular light source can provide high brightness and uniform light; and the cooperation of the camera can realize image acquisition of a fast-moving object, and high-quality images are beneficial to the detection of surface defects of the detection object.

[0011] Optionally, in the embodiment of the present application, the image acquisition mechanism further comprises a second image acquisition unit; the second image acquisition unit comprises a light source and a camera; the second target position comprises a position at which the second surface faces the second image acquisition unit and / or a position after the first grabbing arm moves by a second preset distance; in the case that the detection object is located at the second target position, in the process of acquiring the second target image corresponding to the second surface: the light source is configured to irradiate the second surface in the case that the detection object is located at the position at which the second surface faces the second image acquisition unit and / or the position after the first grabbing arm moves by the second preset distance; and the camera is configured to acquire the second target image corresponding to the second surface.

[0012] In the above implementation process, after the first grabbing arm clamps the detection object to the second target position, the image acquisition of the second surface is realized under the cooperation of the light source and the camera; therefore, the lithium battery mylar film defect detection system provided by the embodiment of the present application can quickly acquire the second surface image of the detection object through the cooperation of the first grabbing arm and the second image acquisition unit.

[0013] Optionally, in the embodiment of the present application, the first surface comprises a forward first surface and a reverse first surface; the second surface comprises a forward second surface and a reverse second surface; in the process of moving the detection object from the first target position to the second target position by the first grabbing arm, the first grabbing arm is specifically configured to: clamp and move the detection object to the second target position after the first image acquisition unit completes the shooting of the forward first surface; clamp and rotate the detection object by 180 degrees horizontally after the second image acquisition unit completes the shooting of the forward second surface at the second target position; and move the detection object to the first target position after the detection object is rotated by 180 degrees and the second image acquisition unit completes the shooting of the reverse second surface, so that the first image acquisition unit shoots the reverse first surface.

[0014] In the above implementation process, after the first image acquisition unit acquires the first target image, the first grabbing arm clamps the target object and moves to the second target position, and the forward second surface image is acquired by the second image acquisition unit; further, the first grabbing arm clamps the detection object and rotates, so that the reverse second surface faces the second image acquisition unit, and the second image acquisition unit performs the image acquisition operation on the second surface of the detection object; after the reverse second surface image acquisition is completed, the first grabbing arm clamps the detection object to the first target position, and the reverse first surface image of the detection object is acquired. That is, the lithium battery mylar film defect detection system provided by the embodiment of the present application can efficiently realize the image acquisition of the four surfaces of the target object under the cooperation of the first grabbing arm, thereby improving the defect detection efficiency of the detection object.

[0015] Optionally, in the embodiment of the present application, the lithium battery mylar film defect detection system further comprises a second grabbing arm; the second grabbing arm is used for grabbing the detection object with defects and moving to the recycling area.

[0016] In the implementation process, the lithium battery mylar film defect detection system provided by the embodiment of the present application further comprises a second grabbing arm, the defect detection device outputs the result of defect detection after detecting the defects of the first surface and the second surface; when the result of defect detection shows that the detection object has defects, the second grabbing arm can grab the detection object with defects and move it to the recycling area, thereby successfully removing the detection object with defects.

[0017] In the second aspect, the embodiment of the present application provides a lithium battery mylar film defect detection method, which is used for detecting the surface of a battery cell wrapped with a mylar film. The lithium battery mylar film defect detection method comprises the following steps: moving the battery cell to a first target position by a conveying mechanism; acquiring, by a first image acquisition unit, a first target image corresponding to a front wide surface of the battery cell at the first target position; moving the battery cell from the first target position to a second target position by a first grabbing arm; acquiring, by a second image acquisition unit, a second target image corresponding to a front narrow surface of the battery cell at the second target position; horizontally flipping the battery cell by 180° by the first grabbing arm; acquiring, by the second image acquisition unit, a second target image corresponding to a reverse narrow surface of the battery cell; moving the battery cell from the second target position to the first target position by the first grabbing arm; and acquiring, by the first image acquisition unit, a first target image corresponding to a reverse wide surface of the battery cell; and detecting, by an image detection mechanism, whether the front wide surface, the reverse wide surface, the front narrow surface and the reverse narrow surface have defects according to the first target image and the second target image.

[0018] In the implementation process, the lithium battery mylar film defect detection method provided by the embodiment of the present application first moves the detection object to the first target position by the conveying mechanism to acquire the image of the front wide surface; then clamps the battery cell to the second target position by the first grabbing arm, and acquires the image of the front narrow surface by the second image acquisition unit at the second target position; then rotates the battery cell clamped by the first grabbing arm, so that the reverse narrow surface of the battery cell faces the second image acquisition unit, to acquire the image of the reverse narrow surface; finally, clamps the battery cell to the first target position by the first grabbing arm, and then acquires the image of the reverse wide surface. Therefore, the lithium battery mylar film defect detection method provided by the embodiment of the present application can efficiently detect whether the four side surfaces of the battery cell have defects based on the lithium battery mylar film defect detection system.

[0019] Optionally, in the embodiment of the present application, the detection of whether the positive wide face, the negative wide face, the positive narrow face and the negative narrow face have defects according to the first target image and the second target image comprises: detecting whether the positive wide face and the negative wide face have defects according to the first target image; and inputting the second target image into the first preset network model and determining whether the positive narrow face and the negative narrow face have defects.

[0020] In the above implementation process, in order to detect whether the positive wide face, the negative wide face, the positive narrow face and the negative narrow face have defects according to the first target image and the second target image, whether the positive wide face and the negative wide face have defects is detected according to the first target image respectively, and whether the positive narrow face and the negative narrow face have defects is detected according to the second target image. Since the defects that may exist in the wide face and the narrow face of the battery cell are different, the lithium battery mylar film defect detection method provided by the embodiment of the present application can effectively distinguish the defects corresponding to the wide face and the narrow face of the battery cell.

[0021] Optionally, in the embodiment of the present application, the detection of whether the positive wide face and the negative wide face have defects according to the first target image comprises: inputting the first target image into the second preset network model to obtain the welding mark positions of the positive wide face and the negative wide face; obtaining the size and area of the welding mark according to the welding mark positions; and determining that the positive wide face and / or the negative wide face have defects if the size and area of the welding mark do not meet the preset requirements of the welding mark.

[0022] In the above implementation process, in the process of detecting whether the positive wide face and the negative wide face of the battery cell have defects according to the first target image, the welding mark positions on the positive wide face and the negative wide face are first obtained; further, the actual size and area of the welding mark are obtained, and the actual size and area of the welding mark are compared with the parameters of the standard welding mark to accurately determine whether the mylar film on the surface of the battery cell has defects.

[0023] In a third aspect, an embodiment of the present application provides an electronic device, which comprises a memory and a processor, the memory stores program instructions, and the processor reads and runs the program instructions to execute the steps in any of the above implementation manners.

[0024] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores computer program instructions, and the computer program instructions are read and run by a processor to execute the steps in any of the above implementation manners. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those of ordinary skill in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0026] Figure 1 The first schematic diagram of the module of the lithium battery mylar film defect detection system provided by the embodiments of the present application;

[0027] Figure 2 The structural schematic diagram of the lithium battery mylar film defect detection system provided by the embodiments of the present application;

[0028] Figure 3 The second schematic diagram of the module of the lithium battery mylar film defect detection system provided by the embodiments of the present application;

[0029] Figure 4 The schematic diagram of the battery provided by the embodiments of the present application;

[0030] Figure 5 The first flow chart of the lithium battery mylar film defect detection method provided by the embodiments of the present application;

[0031] Figure 6 The second flow chart of the lithium battery mylar film defect detection method provided by the embodiments of the present application;

[0032] Figure 7 The third flow chart of the lithium battery mylar film defect detection method provided by the embodiments of the present application;

[0033] Figure 8 The structural schematic diagram of the electronic device provided by the embodiments of the present application.

[0034] Icon: lithium battery mylar film defect detection system-100; conveying mechanism-110; image acquisition mechanism-120; first image acquisition unit-121; highlight annular light source-1211; camera-1; second image acquisition unit-122; light source-1221; first grabbing arm-130; image detection mechanism-140; first target position-A; second target position-B; first surface-a; positive first surface-aa; reverse first surface-ab; second surface-b; positive second surface-ba; reverse second surface-bb; second grabbing arm-150; recycling area-C; electronic device-300; processor-301; memory-302. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. For example, the flowcharts and block diagrams in the drawings show the possible implementation architecture, functions and operations of the systems, methods and computer program products according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders from those noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present application can be integrated together to form a separate part, or each module can exist independently, or two or more modules can be integrated to form a separate part.

[0036] With the rapid development of China's new energy automobile industry, green and environmentally friendly new energy electric vehicles have become the choice of more and more consumers. From the development trend, carbon dioxide and sulfides emitted by traditional fuel vehicles are the main source of greenhouse gases, and green low-carbon economy is rising, and new energy vehicles are expected to become the first choice of more consumers.

[0037] The power battery is a key component of the new energy vehicle, and the advantages and disadvantages of the power battery greatly affect the endurance mileage, charging efficiency and vehicle driving stability of the new energy vehicle. The Mylar refers to the lithium battery, especially in the production process of the square lithium battery, before the cell enters the shell, a layer of Mylar film is coated on the five surfaces, which prevents the risk of contact between the cell, the tab and the aluminum shell, thereby seriously affecting the safety of the battery.

[0038] The applicant found in the research process that in the Mylar production process, defects such as Mylar damage, incomplete Mylar coating, falling off, mispositioning of the adhesive, and wrinkles are easily produced, and the factory still needs to consume a large amount of manpower to perform quality inspection on the Mylar by manual visual inspection.

[0039] Based on this, the embodiments of the present application provide a lithium battery Mylar film defect detection system, method and electronic equipment; wherein the lithium battery Mylar film defect detection system adopts a complementary structure of a face array camera double work station, which can save equipment space and improve the efficiency and accuracy of the Mylar film defect detection on the surface of the battery.

[0040] Referring to Figure 1 and Figure 2 , Figure 1 A first schematic diagram of a module of a lithium battery mylar film defect detection system provided by an embodiment of the present application is shown in FIG. 1. Figure 2 A structural schematic diagram of a lithium battery mylar film defect detection system provided by an embodiment of the present application is shown in FIG. 2. Figure 1 As shown in FIG. 2, the lithium battery mylar film defect detection system 100 provided by the embodiment of the present application includes a conveying mechanism 110, an image acquisition mechanism 120, a first grabbing arm 130, and an image detection mechanism 140.

[0041] The conveying mechanism 110 is used to move the detection object to a first target position A (shown in FIG. 1). It can be understood that the first target position A is a position at which the photographing detection can be implemented or one of the positions at which the photographing detection can be implemented; and the conveying mechanism 110 is used to move the detection object to be detected to the first target position A. The conveying mechanism 110 can be a conveying belt, a chain mechanism, or a rope mechanism, etc. Figure 2

[0042] The first grabbing arm 130 is used to move the detection object from the first target position A to a second target position B. The lithium battery mylar film defect detection system 100 provided by the embodiment of the present application not only includes the conveying mechanism 110, but also includes the grabbing arm capable of quickly moving the detection object, for example, the first grabbing arm 130. The first grabbing arm 130 can move the detection object from the first target position A to the second target position B; wherein the first target position A and the second target position B are positions at which the surface image of the detection object can be acquired for detection.

[0043] The image acquisition mechanism 120 is used to acquire a first target image corresponding to a first surface a when the detection object is located at the first target position A; and the image acquisition mechanism 120 is also used to acquire a second target image corresponding to a second surface b when the detection object is located at the second target position B. Exemplarily, the image acquisition mechanism 120 provided by the lithium battery mylar film defect detection system 100 provided by the embodiment of the present application can be used to acquire the first surface a image and the second surface b image corresponding to the first surface a and the second surface b of the detection object. It should be noted that the first surface a and the second surface b can each include one or more specific surfaces, for example, the first surface a can refer to two wider surfaces or two narrower surfaces of the square-shaped battery cell; similarly, the second surface b can also refer to two narrower surfaces or two wider surfaces of the square-shaped battery cell; and Figure 2 The optional positions of the first target position A and the second target position B are only exemplarily shown in FIG. 1, which is not a restrictive display.

[0044] ​The image detection mechanism 140 is configured to detect whether the first surface a and the second surface b have defects according to the first target image and the second target image. The lithium battery mylar film defect detection system 100 provided in the embodiments of the present application can detect whether the first surface a and the second surface b have defects according to the first target image and the second target image after the first target image and the second target image are acquired.

[0045] It should be noted that the number of the first target image and the second target image is variable, and is often adjusted according to actual needs.

[0046] Taking a square cell as an example, the square cell is moved to the first target position A by the conveying mechanism 110 of the lithium battery mylar film defect detection system 100 provided in the embodiments of the present application; further, the image acquisition mechanism 120 acquires the first target image corresponding to the first surface a at the first target position A; after the first target image is acquired, the first grabbing arm 130 moves the square cell from the first target position A to the second target position B; similarly, the image acquisition mechanism 120 further acquires the second target image corresponding to the second surface b at the second target position B. Finally, the image detection mechanism 140 detects the first surface a and the second surface b of the square cell according to the first target image and the second target image. Wherein, at the first target position A, the hot melting point of the surface of the cell is generally photographed by moving the image acquisition mechanism 120; for example, three hot melting points are acquired, and three corresponding first target images are acquired. At the second target position B, the cell is moved by the first grabbing arm 130, and is photographed, and two second target images can be acquired; for example, two second target images are acquired, and the images of the hot melting point corresponding area and the highlight of the adhesive part corresponding area are acquired.

[0047] By Figure 1 It can be known that the embodiments of the present application provide a lithium battery mylar film defect detection system, which comprises a conveying mechanism for moving a detection object, a first grabbing arm for transferring the detection object, an image acquisition mechanism for acquiring a target image, and an image detection mechanism for detecting the target image. The surface of the target object is detected by using the lithium battery mylar film defect detection system provided in the embodiments of the present application, so that the space occupation of the equipment is not large, and the detection efficiency of the detection object is high.

[0048] Please continue to refer to Figure 2 , and refer to Figure 3 . Figure 3This is a second schematic diagram of the modules of the lithium battery mylar film defect detection system provided in the embodiments of this application; the image acquisition mechanism 120 in the lithium battery mylar film defect detection system 100 provided in the embodiments of this application includes a first image acquisition unit 121.

[0049] The first target position includes the position where the first surface a is directly opposite the first image acquisition unit 121 and / or the position after the conveying device has moved a first preset distance. That is, in this embodiment of the application, the first target position can be the position where the first surface a of the object being detected is directly opposite the first image acquisition unit 121, or it can be the position where the conveying mechanism 110 has moved a preset distance. In actual operation, in order to improve the accuracy of detection, the lithium battery mylar film defect detection system 100 can simultaneously meet the two conditions of the first surface a of the object being detected being directly opposite the first image acquisition unit 121 and the conveying mechanism 110 having moved a preset distance before triggering the first image acquisition unit 121; for example, it can be preset that the first image acquisition unit 121 takes a picture of the first surface a of the object being detected after the conveying mechanism 110 moves a meters.

[0050] During the process of moving the detection object to the first target position A, the conveying mechanism 110 is specifically used to: carry the detection object and drive the detection object to move in the direction of the image acquisition mechanism 120 to the position where the first surface a of the detection object is directly opposite the first image acquisition unit 121 and / or the position after the conveying device has moved a preset distance.

[0051] by Figure 2 For example, in Figure 2 In the process, after the square battery cell moves to the first target position on the conveyor belt 110, the first image acquisition unit 121 takes a picture of the side of the battery cell facing the first image acquisition unit 121. It is understood that the side facing the first image acquisition unit 121 is related to the orientation in which the battery cell is placed, except... Figure 2 Alternatively, the narrow side of the battery cell can be positioned directly opposite the first image acquisition unit 121.

[0052] pass Figure 2 As can be seen, the first target position in this embodiment can be either the first image detection unit detecting that the first surface of the object to be detected is facing the first image detection unit, or the conveying mechanism detecting that the conveying mechanism itself has moved a preset distance. The lithium battery mylar film defect detection system provided in this embodiment triggers the first image acquisition unit to acquire an image of the object to be detected through the first target position, thereby accurately acquiring the image and efficiently detecting the corresponding surface of the object to be detected.

[0053] Please continue reading. Figure 2In an optional implementation of the embodiment of the present application, the first image acquisition unit 121 comprises a highlight ring light source 1211 and a camera 1.

[0054] In the case where the detection object is located at the first target position A, in the process of acquiring the first target image corresponding to the first surface a: the highlight ring light source 1211 is configured to irradiate the first surface a; and the camera 1 is configured to capture the first surface a to obtain the first target image.

[0055] It should be noted that when the working distance of the highlight ring light source 1211 is 80-100 mm, the light source 1221 can highlight the changes in the edge and height of the measured object and highlight the parts that are originally difficult to see, and is an ideal choice for edge detection, metal surface lettering and damage detection. The ring light source 1221 can adopt a lamp bead particle angle of 60-90 degrees, and is used in cooperation with a stroboscopic controller to improve the instantaneous brightness of the ring light source by more than 400%, and in a very short exposure time, the required brightness is achieved.

[0056] Therefore, in the optional implementation of the embodiment of the present application, the highlight ring light source is used in cooperation with the camera to acquire images in the process of acquiring images of the first surface a; the highlight ring light source can provide high brightness and uniform light; and the cooperation with the camera can realize image acquisition of fast-moving objects, and high-quality images are conducive to the detection of surface defects of the detection object.

[0057] Please continue to read Figure 2 In an optional implementation of the embodiment of the present application, the image acquisition mechanism 120 further comprises a second image acquisition unit 122; the second image acquisition unit 122 comprises a light source 1221 and a camera 1. It should be noted that the cameras used in the first image acquisition unit 121 and the second image acquisition unit 122 can be the same.

[0058] The second target position comprises a position at which the second surface b faces the second image acquisition unit 122 and / or a position after the first grabbing arm 130 moves by a second preset distance.

[0059] It can be understood that the second target position is a position for image acquisition of the second surface b; in an optional implementation of the embodiment of the present application, triggering the second image acquisition unit 122 to acquire the second target image can be that the second surface b of the detection object faces the second image acquisition unit 122, or that the first grabbing arm 130 moves by a preset distance; in actual operation, in order to improve the accuracy of detection, the two conditions that the second surface b of the detection object faces the second image acquisition unit 122 and the first grabbing arm 130 moves by a preset distance are simultaneously met, and then the second image acquisition unit 122 is triggered.

[0060] In the case that the detection object is located at the second target position B, in the process of acquiring the second target image corresponding to the second surface b: the light source 1221 is configured to irradiate the second surface b in the case that the detection object is located at a position where the second surface b directly faces the second image acquisition unit 122 and / or a position where the first grabbing arm 130 has moved by a second preset distance; and the camera 1 is configured to acquire the second target image corresponding to the second surface b.

[0061] In the above process of acquiring the second target image corresponding to the second surface b of the detection object, taking a square-shaped battery as an example, the light source 1221 triggers the second image acquisition unit 122 to acquire the image of the second surface b of the detection object in the case that the second surface b of the detection object directly faces the second image acquisition unit 122 or the first grabbing arm 130 has moved by a preset distance, or both.

[0062] It can be understood by those skilled in the art that, in the embodiments of the present application, the manner of determining whether the first surface a or the second surface b directly faces the image acquisition unit or the second image acquisition unit 122 can be that: the center of the first surface a and / or the second surface b of the battery is marked, and when the first image acquisition unit 121 and / or the second image acquisition unit 122 detects that the mark is located at the center of the image, it can be determined that the first surface a or the second surface directly faces the first image acquisition unit 121 or the second image acquisition unit 122.

[0063] Therefore, after the first grabbing arm clamps the detection object to the second target position, the image acquisition of the second surface is realized under the cooperation of the light source and the camera. Therefore, the lithium battery mylar film defect detection system provided in the embodiments of the present application can quickly acquire the second surface image of the detection object through the cooperation of the first grabbing arm and the second image acquisition unit.

[0064] Please refer to Figure 4 , Figure 4 the schematic diagram of the battery provided in the embodiments of the present application; please refer to Figure 2 , in the optional implementation manner of the embodiments of the present application, as Figure 4 shown, the first surface a includes a forward first surface aa and a reverse first surface ab; and the second surface b includes a forward second surface ba and a reverse second surface bb.

[0065] In the process of moving the detection object from the first target position A to the second target position B by the first grabbing arm 130, the first grabbing arm 130 is specifically configured to: in Figure 2 , after the first image acquisition unit 121 completes the shooting of the forward first surface aa, the detection object is clamped and moved to the second target position B.

[0066] At the second target position B, after the second image acquisition unit 122 finishes photographing the positive second surface ba, the clamping detection object is horizontally rotated by 180°. Exemplarily, as shown in FIG. 2B, the detection object can be rotated from the positive second surface ba to the negative second surface bb, or from the negative second surface bb to the positive second surface ba. It should be noted that the rotation angle 180° in the embodiment of the present application is not an absolute angle, and in some cases, 180°±5° can be regarded as that the first grabbing arm 130 clamps the detection object and realizes the rotation of the detection object. Figure 4

[0067] After the detection object is horizontally rotated by 180° and the second image acquisition unit 122 finishes photographing the negative second surface bb, the clamping detection object is moved to the first target position A, so that the first image acquisition unit 121 photographs the negative first surface ab.

[0068] That is to say, after the rotation of the detection object, the second image acquisition unit 122 acquires the second target image at the second target position B; if the image acquired by the first photographing at the second target position B is the positive second surface ba, then the image of the negative second surface bb is continuously acquired by the second image acquisition unit 122 after the rotation.

[0069] It can be known from FIG. 2B that after the first image acquisition unit acquires the first target image, the first grabbing arm clamps the detection object and moves to the second target position, and the second image acquisition unit acquires the positive second surface image; further, the first grabbing arm clamps the detection object and rotates it, so that the negative second surface is opposite to the second image acquisition unit, and the second image acquisition unit acquires the image of the second surface of the detection object; after the acquisition of the image of the negative second surface is completed, the first grabbing arm clamps the detection object and moves to the first target position, and acquires the image of the negative first surface of the detection object. That is to say, the lithium battery mylar film defect detection system provided in the embodiment of the present application can realize the acquisition of the images of four surfaces of the target object efficiently under the cooperation of the first grabbing arm, thereby improving the defect detection efficiency of the detection object. Figure 4 Figure 2 It can be known from FIG. 2B that after the first image acquisition unit acquires the first target image, the first grabbing arm clamps the detection object and moves to the second target position, and the second image acquisition unit acquires the positive second surface image; further, the first grabbing arm clamps the detection object and rotates it, so that the negative second surface is opposite to the second image acquisition unit, and the second image acquisition unit acquires the image of the second surface of the detection object; after the acquisition of the image of the negative second surface is completed, the first grabbing arm clamps the detection object and moves to the first target position, and acquires the image of the negative first surface of the detection object. That is to say, the lithium battery mylar film defect detection system provided in the embodiment of the present application can realize the acquisition of the images of four surfaces of the target object efficiently under the cooperation of the first grabbing arm, thereby improving the defect detection efficiency of the detection object.

[0070] Please continue to refer to FIG. 2B, in the optional implementation manner of the embodiment of the present application, the lithium battery mylar film defect detection system 100 further comprises a second grabbing arm 150. Figure 2 The second grabbing arm 150 is used for grabbing the detection object with defects and moving to the recycling area C.

[0071] The second grabbing arm 150 is used for grabbing the detection object with defects and moving to the recycling area C.

[0072] ​​Therefore, the lithium battery mylar film defect detection system provided by the embodiment of the application further comprises a second grabbing arm, and after the first surface and the second surface are detected for defects by the defect detection device, the result of the defect detection is output; when the result of the defect detection shows that the detection object has defects, the second grabbing arm can be used to grab the detection object having defects and move the detection object to a recycling area, so that the detection object having defects is successfully removed.

[0073] Please refer to Figure 5 , Figure 5 The first flowchart of the lithium battery mylar film defect detection method provided by the embodiment of the application; the embodiment of the application further provides a lithium battery mylar film defect detection method, which is used for detecting the surface of a battery cell wrapped with a mylar film; the lithium battery mylar film defect detection method can be realized through the following steps:

[0074] Step S100: conveying the battery cell to a first target position by a conveying mechanism.

[0075] Step S101: acquiring, by a first image acquisition unit, a first target image corresponding to a wide face of the battery cell in a forward direction at the first target position.

[0076] In the above step S101, after the battery cell to be detected is conveyed to the first target position by the conveying mechanism, the first target image corresponding to the wide face of the battery cell in the forward direction is acquired by the first image acquisition unit. It should be noted that the first target position can be a position where the battery cell moves to be directly opposite the first image acquisition unit or a position where the conveying device moves by a preset distance.

[0077] Step S102: moving, by a first grabbing arm, the battery cell from the first target position to a second target position; and acquiring, by a second image acquisition unit, a second target image corresponding to a narrow face of the battery cell in a forward direction at the second target position.

[0078] In the above step S102, after the image acquisition of the wide face of the battery cell in the forward direction is completed, the first grabbing arm moves the battery cell from the first target position to the second target position; then, the second image acquisition unit acquires the second target image corresponding to the narrow face of the battery cell in the forward direction. It should be noted that the second target position can be a position where the first grabbing arm moves by a preset distance or a position where the narrow face of the battery cell in the forward direction is directly opposite the second image acquisition unit.

[0079] Step S103: horizontally flipping, by the first grabbing arm, the battery cell by 180°; and acquiring, by the second image acquisition unit, a second target image corresponding to a narrow face of the battery cell in a reverse direction.

[0080] In step S103, after the second target image corresponding to the forward narrow surface is acquired, the first grabbing arm flips the battery 180° horizontally, and then the second image acquisition unit continues to acquire the image of the reverse narrow surface. It should be noted that the 180° flip in the embodiment of the present application does not mean an absolute 180°, but can be 180°±5°.

[0081] Step S104: The first grabbing arm moves the battery from the second target position to the first target position, and the first image acquisition unit acquires the first target image corresponding to the reverse wide surface.

[0082] In step S104, after the second target image is acquired, the first grabbing arm holds the battery to the first target position, and the first image acquisition unit continues to acquire the first target image corresponding to the reverse wide surface.

[0083] Step S105: The image detection mechanism detects whether the forward wide surface, the reverse wide surface, the forward narrow surface, and the reverse narrow surface have defects according to the first target image and the second target image.

[0084] By Figure 5 It can be seen that the lithium battery mylar film defect detection method provided by the embodiment of the present application first moves the detection object to the first target position by the conveying mechanism to acquire the image of the forward wide surface; then the first grabbing arm clamps the battery to the second target position, and the second image acquisition unit acquires the image of the forward narrow surface at the second target position; then the first grabbing arm clamps the battery to rotate, so that the reverse narrow surface of the battery faces the second image acquisition unit, and the image of the reverse narrow surface is acquired; finally, the first grabbing arm clamps the battery to the first target position, and then the image of the reverse wide surface is acquired. Therefore, using the lithium battery mylar film defect detection method provided by the embodiment of the present application can efficiently detect whether the four sides of the battery have defects based on the lithium battery mylar film defect detection system.

[0085] Please refer to Figure 6 , Figure 6 The second flowchart of the lithium battery mylar film defect detection method provided by the embodiment of the present application; in the optional embodiment of the present application, detecting whether the forward wide surface, the reverse wide surface, the forward narrow surface, and the reverse narrow surface have defects according to the first target image and the second target image can include the following steps:

[0086] Step S200: Detecting whether the forward wide surface and the reverse wide surface have defects according to the first target image.

[0087] In step S200, according to the above, the positive wide face and the negative wide face of the battery cell correspond to the first surface and the first target image; therefore, whether the positive wide face and the negative wide face have defects can be detected according to the first target image.

[0088] Step S201: input the second target image into the first preset network model, and determine whether the positive narrow face and the negative narrow face have defects.

[0089] In step S201, on the other hand, or input the second target image into the first preset network model, and determine whether the positive narrow face and the negative narrow face have defects. For example, the first preset network model can be a resnet152 classification model.

[0090] For example, taking the resnet152 classification model as an example, in the state detection of the narrow mylar film, in order to quickly distinguish wrinkles from normal and improve the accuracy of the distinction, a deep learning resnet152 classification model is used. About 2000 pictures of mylar film wrinkle defect in different states can be collected, 2000 pictures of mylar film without wrinkles, and after training with the resnet152 classification model, the state is distinguished and the result is output.

[0091] By Figure 6 It can be seen that in order to detect whether the positive wide face, the negative wide face, the positive narrow face and the negative narrow face have defects according to the first target image and the second target image, whether the positive wide face and the negative wide face have defects is detected according to the first target image, and whether the positive narrow face and the negative narrow face have defects is detected according to the second target image. Because the defects that may exist in the wide face and the narrow face of the battery cell are different; therefore, the lithium battery mylar film defect detection method provided by the application can effectively distinguish the defects corresponding to the wide face and the narrow face of the battery cell.

[0092] Please refer to Figure 7 , Figure 7 The third flow chart of the lithium battery mylar film defect detection method provided by the application; in the optional embodiment of the application, according to the first target image, whether the positive wide face and the negative wide face have defects can include the following steps:

[0093] Step S300: input the first target image into the second preset network model, and obtain the welding position of the positive wide face and the negative wide face.

[0094] In the step S300, the first target image, i.e., the images corresponding to the forward wide face and the reverse wide face, are input into the second preset network model, so as to obtain the welding mark positions of the forward wide face and the reverse wide face. It should be noted that after the mylar is wrapped on the battery cell, there are welding marks on the front and back surfaces; in the welding mark detection, there is a certain reflection and wrinkle on the welding mark boundary, and in some cases, whether the welding mark meets the requirements symbolizes whether the mylar film wrapped on the surface of the battery cell has a problem; therefore, the welding mark needs to be positioned.

[0095] Exemplarily, the second preset model can be a yolov5 deep learning model. Using the yolov5 deep learning model, 100 pictures of welding marks with different morphological characteristics are collected, a total of more than 500 pictures are labeled and trained, and then the rough positioning position of the welding mark is obtained through the parameters of the training. Further, the Blob Analysis is used to analyze the connected domain of the same pixels in the image, so as to determine the connected domain of the welding mark; finally, the welding mark connected domain is obtained, and the position of the connected domain is the position of the welding mark.

[0096] Step S301: According to the welding mark position, the size and area of the welding mark are obtained.

[0097] Step S302: If the size and area of the welding mark do not meet the preset requirements of the welding mark, it is determined that the forward wide face and / or the reverse wide face has a defect.

[0098] In the steps S301-S302, according to the position of the connected domain representing the welding mark position, the size and area of the welding mark are obtained according to the position information. The calculated area and size are compared with the standard welding mark value, and if the calculated area and size are within the standard range, it can be determined that the mylar film on the surface of the battery cell has no defect.

[0099] Through Figure 7 It can be known that in the process of detecting whether the forward wide face and the reverse wide face of the battery cell have a defect according to the first target image, the welding mark positions on the forward wide face and the reverse wide face are first obtained; further, the actual size and area of the welding mark are obtained, and the actual size and area of the welding mark are compared with the parameters of the standard welding mark, so as to accurately determine whether the mylar film on the surface of the battery cell has a defect.

[0100] Please refer to Figure 8 , Figure 8 A structural schematic diagram of an electronic device provided by the embodiment of the application. The electronic device 300 provided by the embodiment of the application comprises a processor 301 and a memory 302, the memory 302 stores machine readable instructions executable by the processor 301, and the machine readable instructions are executed by the processor 301 to perform the method as above.

[0101] Based on the same inventive concept, the embodiment of the present application further provides a computer readable storage medium, wherein computer program instructions are stored in the computer readable storage medium, and the computer program instructions are read and run by a processor to execute the steps in any of the above-mentioned implementation manners.

[0102] The computer readable storage medium can be random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) and the like various media that can store program codes. The storage medium is used to store programs, and the processor executes the programs after receiving execution instructions. The method executed by the electronic terminal defined by the processes disclosed in any of the embodiments of the present application can be applied to the processor, or implemented by the processor.

[0103] In the embodiments provided by the present application, it should be understood that the disclosed device and method 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, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0104] In addition, the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the present embodiment.

[0105] Furthermore, each functional module in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0106] Alternatively, all or a portion of the application can be implemented by software, hardware, firmware, or any combination of them. When implemented in software, all or a portion of the application can be implemented as a computer program product, which can include one or more computer program elements. When the computer program elements include computer program instructions they all or a portion of a computer program that can be loaded onto a computer, a computer system, or another programmable apparatus to produce an specific apparatus for testing or measuring, such that the program instructions which execute on the computer or computer system implement the functions / acts specified by the computer program instructions. Program code can be stored in any appropriate data storage medium that is accessible by a computer, computer system, or another programmable apparatus, such as for example but not limited to: memory devices including both volatile and non-volatile memory storage elements; floppy disks, optical disks, hard disk drives, solid state drives, or any other storage devices or mediums.

[0107] The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus or devices. The computer program instructions can be stored in a computer readable storage medium, or transmitted from one computer readable storage medium to another by a computer readable transmission medium, such as a wireless, wireline, optical fiber cable, R.F., etc., over the Internet, extranet, etc.

[0108] In this document, relational terms such as first and second, and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0109] The embodiments of the application described hereinabove are implemented as software, hardware, firmware, or any combination of them. The foregoing description of the embodiments of the application has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the application to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the application be limited not with this detailed description, but rather by the claims appended hereto.

Claims

1. A method for detecting defects in the mylar film of a lithium battery, characterized in that, The defect detection method is used to detect the surface of a battery cell wrapped with a mylar film; the surface includes a forward wide surface, a reverse wide surface, a forward narrow surface, and a reverse narrow surface; The defect detection method includes: The battery cell is transported to the first target location by a conveying mechanism; At the first target location, the first image acquisition unit acquires the first target image corresponding to the positive wide surface; The first gripping arm moves the battery cell from the first target position to the second target position; and the second image acquisition unit acquires a second target image corresponding to the positive narrow surface at the second target position. The first gripping arm flips the battery cell horizontally by 180°; and the second image acquisition unit acquires the second target image corresponding to the reverse narrow face. The first gripping arm moves the battery cell from the second target position to the first target position; and the first image acquisition unit acquires the first target image corresponding to the reverse wide surface. An image detection agency detects whether there are defects in the forward wide face, reverse wide face, forward narrow face, and reverse narrow face based on the first target image and the second target image; The step of detecting whether the forward wide face, reverse wide face, forward narrow face, and reverse narrow face have defects based on the first target image and the second target image includes: detecting whether the forward wide face and reverse wide face have defects based on the first target image; and inputting the second target image into a first preset network model and determining whether the forward narrow face and reverse narrow face have defects. The step of detecting whether there are defects in the forward and reverse wide surfaces based on the first target image includes: inputting the first target image into a second preset network model to obtain the solder mark positions of the forward and reverse wide surfaces; obtaining the size and area of ​​the solder mark based on the solder mark positions; and determining that there are defects in the forward and / or reverse wide surfaces if the size and area of ​​the solder mark do not meet the preset requirements for the solder mark.

2. The defect detection method according to claim 1, characterized in that, The method employs a lithium battery mylar film defect detection system, which includes: the conveying mechanism, the image acquisition mechanism, the first gripping arm, and the image detection mechanism. The conveying mechanism is used to move the detection object to the first target position; The first gripping arm is used to move the object to be detected from the first target position to the second target position; The image acquisition mechanism is used to acquire the first target image corresponding to the first surface when the detected object is located at the first target position; the image acquisition mechanism is also used to acquire the second target image corresponding to the second surface when the detected object is located at the second target position. The image detection mechanism is used to detect whether there are defects on the first surface and the second surface based on the first target image and the second target image.

3. The defect detection method according to claim 2, characterized in that, The image acquisition mechanism includes a first image acquisition unit; the first target position includes the position of the first surface directly opposite the first image acquisition unit and / or the position after the transmission mechanism has moved a first preset distance; The conveying mechanism is specifically used for: during the process of moving the detected object to the first target position. The device carries the object to be detected and moves it toward the image acquisition mechanism until the first surface of the object is directly opposite the first image acquisition unit and / or the position after the conveying mechanism has moved the first preset distance.

4. The defect detection method according to claim 3, characterized in that, The first image acquisition unit includes a high-brightness ring light source and a camera; In the process of acquiring the first target image corresponding to the first surface when the detected object is located at the first target position: The high-brightness ring light source is used to illuminate the first surface; The camera is used to photograph the first surface to obtain an image of the first target.

5. The defect detection method according to claim 3, characterized in that, The image acquisition mechanism further includes a second image acquisition unit; the second image acquisition unit includes a light source and a camera; the second target position includes the position of the second surface facing the second image acquisition unit and / or the position after the first gripper arm has moved a second preset distance; In the process of acquiring the second target image corresponding to the second surface when the detected object is located at the second target position: The light source is used to illuminate the second surface when the detected object is located at the position of the second surface directly opposite the second image acquisition unit and / or at the position after the first gripper arm has moved the second preset distance; The camera is used to acquire the image of the second target corresponding to the second surface.

6. The defect detection method according to claim 5, characterized in that, The first surface includes a forward first surface and a reverse first surface; the second surface includes a forward second surface and a reverse second surface; During the process of moving the object to be detected from the first target position to the second target position, the first gripping arm is specifically used for: After the first image acquisition unit completes the image capture of the first surface, the detected object is clamped and moved to the second target position; At the second target location, after the second image acquisition unit completes capturing the image of the positive second surface, it clamps the detection object and rotates it horizontally by 180°; and After the detection object is rotated horizontally by 180° and the second image acquisition unit has finished capturing the reverse second surface, the detection object is clamped and moved to the first target position so that the first image acquisition unit can capture the reverse first surface.

7. The defect detection method according to claim 2, characterized in that, The defect detection system also includes a second gripping arm; The second gripping arm is used to grip the defective inspection object and move it to the recycling area.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores program instructions, and when the processor executes the program instructions, it performs the steps of the method according to any one of claims 1-7.

Images