Battery tab defect visual identification method and system

Abstract

The invention relates to a battery tab defect visual identification method and system. The method comprises the following steps: acquiring a tab group image of a battery tab group through an image acquisition device; the tab group comprises one or more layers of tabs which are stacked, the tab group at least comprises a top surface, a first side surface, a second side surface and a bottom surface, the bottom surface is located at the root of the tab group and is connected with a battery pole piece, the top surface and the bottom surface are oppositely arranged, the tab group image comprises at least part of the top surface and all the first side surface, and the first side surface and the second side surface are opposite to each other. Or comprises at least part of the top surface and all the second side surfaces; carrying out image identification on the tab group image, and identifying defects in the tab group; therefore, the effect of accurately and rapidly detecting the defects of the tabs is achieved, cooperation of a mechanical moving device is not needed, and the production and manufacturing cost is greatly reduced.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and in particular to a method and system for visually identifying battery tab defects. Background Art

[0002] Lithium ions usually include positive electrodes, negative electrodes, separators, and electrolytes. The positive electrode sheet usually uses aluminum foil as a conductor, and the positive electrode active material is coated on the aluminum foil, and the positive electrode tab is set on the positive electrode sheet; the negative electrode sheet uses copper foil as a conductor, and the negative electrode active material is coated on the copper foil, and the negative electrode tab is set on the negative electrode sheet; the separator is set between the positive electrode sheet and the negative electrode sheet, and the charging and discharging process is carried out through the movement of lithium ions in the electrolyte, and the electric energy is transferred to the positive electrode tab and the negative electrode tab to achieve the storage and release of electric energy. With the development of industrial technology, the thickness of aluminum foil and copper foil has gradually decreased. At present, the aluminum foil of the conventional battery production process reaches 12um, and the copper foil reaches 6um.

[0003] During the battery production process, the positive and negative electrode materials need to be stacked layer by layer to form a three-layer structure of negative electrode, separator and positive electrode materials. During the production of the roll core, due to the fast transportation speed, the positive and negative electrode aluminum foils are easily folded due to wind resistance or the influence of the equipment structure. The folded positive and negative electrode ears are prone to overlap of the positive and negative electrodes, resulting in internal short circuits. Internal short circuits can easily cause the battery to catch fire and explode, affecting the safety of the battery.

[0004] In order to avoid battery quality and safety issues caused by the folding of the battery tabs, the battery factory needs to arrange quality inspectors to conduct a full inspection of the tab condition of each battery after winding or stacking. However, during the implementation process, due to fatigue and negligence, missed inspections often occur. In addition, each person's operating techniques and seriousness are different, and it is impossible to do a 100% inspection of the tab folding, which poses a serious safety hazard. At the same time, the existing manual full inspection requires multiple quality inspectors to be deployed on each production line, resulting in high manufacturing costs. Summary of the invention

[0005] The main purpose of the present application is to provide a method and system for visually identifying battery tab defects, so as to solve the problems in the prior art of easy missed detection and high detection cost of tab defects.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides a method for visually identifying battery tab defects, the method comprising:

[0007] Acquire a tab group image of a battery tab group by an image acquisition device; the tab group includes one or more layers of tabs stacked together, the tab group includes at least a top surface, a first side surface, a second side surface and a bottom surface, the bottom surface is located at the root of the tab group and connected to the battery pole piece, the top surface is arranged opposite to the bottom surface, and the tab group image includes at least a portion of the top surface and all of the first side surface, or includes at least a portion of the top surface and all of the second side surface;

[0008] Image recognition is performed on the image of the tab group to identify defects in the tab group.

[0009] Furthermore, the step of acquiring the image of the battery tab group by the image acquisition device includes:

[0010] Adjusting the focal position of the image acquisition device, and acquiring a single image of the battery tab group at each focal position;

[0011] The single images at each focus position are fused using a multi-focus fusion algorithm to obtain the tab group image.

[0012] Furthermore, the image acquisition device includes a liquid lens, and the step of adjusting the focal position of the image acquisition device and acquiring a single image of the battery tab group at each focal position includes:

[0013] Obtaining a liquid lens photographing voltage range, wherein a first voltage corresponding to when the farthest end of the collected image of the tab group is clearly imaged and a second voltage corresponding to when the closest end of the collected image of the tab group is clearly imaged are both within the photographing voltage range;

[0014] Determining a preset number of adjustment voltage values ​​from the photographing voltage range, wherein different adjustment voltage values ​​are set in a gradient manner;

[0015] The respective adjustment voltage values ​​are applied to the liquid lens in sequence, and the single images corresponding to the respective adjustment voltage values ​​are acquired respectively.

[0016] Furthermore, the step of determining a preset number of adjustment voltage values ​​from the photographing voltage range includes:

[0017] Obtaining the object depth between the plane where the farthest end of the tab group image is located and the plane where the closest end is located, and obtaining the depth of field of the single image;

[0018] Divide the object depth by the depth of field of the single image to obtain a first value, and set the preset number to ≥ the first value;

[0019] Determine the preset number of gradient-distributed adjustment voltage values ​​distributed in the photographing voltage range.

[0020] Furthermore, the image acquisition device includes an optical lens, an optical axis of the optical lens forms a first angle with the top surface, and an optical axis of the optical lens forms a second angle with the first side surface or the second side surface, and the first angle and the second angle are not equal to 90°.

[0021] Furthermore, the image acquisition device includes an optical lens and a prism, wherein the prism is arranged between the optical lens and the top surface and is located on the optical axis of the optical lens, and the prism deflects the incident light path of the optical lens to form an angle not equal to 90° with the first side surface or the second side surface of the tab group.

[0022] Furthermore, the image acquisition device includes a light source, and the light source is used to illuminate the tab group. Before the step of acquiring the tab group image of the battery tab group through the image acquisition device, the step includes:

[0023] Acquiring the relative position of the tab group and the image acquisition device;

[0024] According to the relative position, the irradiation angle of the light source is adjusted so that the light source directly irradiates the tab group.

[0025] Furthermore, the step of performing image recognition on the tab group image to identify defects in the tab group includes:

[0026] In a direction perpendicular to the tab stacking direction, the tab group image is divided into a main area and a root area, wherein the root area is an area with a preset width from the bottom surface;

[0027] Identifying the number of root tab layers included in the root region;

[0028] Compare the number of root tab layers with the preset number of tab layers to determine whether the number of root tab layers is less than the preset number of tab layers;

[0029] If so, it is determined that there is a defect, and the defect is a missing pole piece, a missing pole ear, or a completely folded pole ear.

[0030] A second aspect of the present application provides a battery tab defect visual recognition system, the system comprising an image recognition device and an image acquisition device,

[0031] The image acquisition device is used to obtain a tab group image of a battery tab group; the tab group includes one or more layers of tabs stacked together, the tab group includes at least a top surface, a first side surface, a second side surface and a bottom surface, the bottom surface is located at the root of the tab group and connected to the battery pole piece, the top surface is arranged opposite to the bottom surface, and the tab group image includes at least a portion of the top surface and all of the first side surface, or includes at least a portion of the top surface and all of the second side surface;

[0032] The image recognition device is used to perform image recognition on the image of the tab group to identify defects in the tab group.

[0033] Further, for a single battery, the number of the image acquisition devices is 4, including a first image acquisition device, a second image acquisition device, a third image acquisition device and a fourth image acquisition device; the tab group includes a positive tab group and a negative tab group;

[0034] The first image acquisition device is used to obtain a first angle image of the positive electrode tab group, wherein the first angle image of the positive electrode tab group includes at least a portion of the top surface and all of the first side surfaces of the positive electrode tab group;

[0035] The second image acquisition device is used to obtain a second angle image of the positive electrode tab group, wherein the second angle image of the positive electrode tab group includes at least a portion of the top surface and all of the second side surface of the positive electrode tab group;

[0036] The third image acquisition device is used to obtain a tab group image of the negative electrode tab group at a third angle, wherein the tab group image of the negative electrode tab group at the third angle includes at least a portion of the top surface of the negative electrode tab group and all of the first side surface;

[0037] The fourth image acquisition device is used to obtain a fourth angle image of the negative electrode tab group, and the fourth angle image of the negative electrode tab group includes at least a portion of the top surface and all of the second side surface of the negative electrode tab group.

[0038] The battery tab defect visual recognition method and system provided in the present application can achieve 100% inspection of battery tab defects through the above method. At the same time, a set of image acquisition devices can be used to clearly capture the image of the tab group from the top surface to the root in a side view, and combined with the image recognition algorithm, the tab defects can be accurately detected without the cooperation of mechanical moving devices, which greatly reduces the production cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the process of a method for visually identifying battery tab defects in one embodiment of the present application;

[0040] Figure 2 is a schematic diagram of an image of a tab group in an embodiment of the present application;

[0041] Figure 3 It is a schematic diagram of the position of the image acquisition device when the positive electrode tab group and the negative electrode tab group are arranged on the same side in one embodiment of the present application;

[0042] Figure 4 It is a schematic diagram of the position of the image acquisition device when the positive electrode tab group and the negative electrode tab group are arranged on different sides in one embodiment of the present application;

[0043] Figure 5 is a schematic diagram of the position of the image acquisition device when the optical axis of the optical lens of the image acquisition device in one embodiment of the present application is perpendicular to the top surface;

[0044] Figure 6 is a structural schematic diagram of an image acquisition device in one embodiment of the present application;

[0045] Figure 7 is a schematic diagram of a partial folding of a tab group in an embodiment of the present application;

[0046] Figure 8 is a schematic diagram of a battery tab defect visual recognition system in one embodiment of the present application;

[0047] Fig. 9 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0048] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] Reference Figure 1 , an embodiment of the present application provides a method for visually identifying battery tab defects, the method comprising:

[0051] S1. Acquire a tab group image of a battery tab group by an image acquisition device; the tab group includes one or more layers of tabs stacked together, the tab group includes at least a top surface 11, a first side surface 12, a second side surface 13 and a bottom surface 14, the bottom surface 14 is located at the root of the tab group and connected to the battery pole piece 15, the top surface 11 is arranged opposite to the bottom surface 14, and the tab group image includes at least a portion of the top surface 11 and the entire first side surface 12, or includes at least a portion of the top surface 11 and the entire second side surface 13;

[0052] S2. Perform image recognition on the image of the tab group to identify defects in the tab group.

[0053] In this embodiment, the tabs are generally roughly rectangular, and the tab group formed by stacking multiple tabs is roughly cubic. Figure 2 As shown, it includes a top surface 11, a first side surface 12, a second side surface 13 and a bottom surface 14. Optionally, a first top corner 16 for transition is set between the top surface 11 and the second side surface 12, and a second top corner 17 for transition is also set between the top surface 11 and the second side surface 13.

[0054] The above-mentioned image acquisition device preferably adopts a high-precision camera with a high focusing effect, so that the tab group can form a clear, sharp, and detail-rich image, providing a reliable basis for subsequent image recognition.

[0055] In the above step S1, by adjusting the image acquisition angle of the image acquisition device, the acquired image of the tab group is not directly facing the top surface 11, the first side surface 12 or the second side surface 13, but at a certain angle. Figure 2 At least part of the top surface 11 and all of the first side surface 12 as shown, or at least part of the top surface 11 and all of the second side surface 13.

[0056] In this way, for a pole piece group, only two image acquisition devices need to be set, one for acquiring images of the pole lug group of at least part of the top surface 11 and all of the first side surface 12, and the other for acquiring images of the pole lug group of at least part of the top surface 11 and all of the second side surface 13. The cooperation of the two image acquisition devices can achieve the effect of acquiring the overall morphology of a pole lug group, so there is no need to set image acquisition devices on the top surface 11, the first side surface 12, and the second side surface 13, respectively, which reduces the number of image acquisition devices used for defect detection of the battery pole lug group and saves manufacturing costs. In addition, if image acquisition devices are set on the top surface 11, the first side surface 12, and the second side surface 13 of the pole lug group, then there must be an image acquisition device that needs to be set in the battery conveying direction of the production line. When the battery is conveyed, a mechanical moving device needs to be used to drive the image acquisition device to move to avoid blocking the battery conveying. In this embodiment, by setting two image acquisition devices to capture the pole lug group at a certain angle (non-front view), it is possible to avoid setting the image acquisition device in the battery conveying direction of the production line, so there is no need to use a mechanical moving device, which further reduces the manufacturing cost.

[0057] In the above step S2, the image features of the tab group image collected in step 1 are extracted and compared through an image recognition algorithm to further identify whether there are tab defects in the tab group image. Common tab defects include, for example: a) tab folding, the morphology of the tab is irregularly deformed, such as folding, bending, warping, wrinkling and other deformation defects; b) tab tearing, tab tearing means that one or more layers of the tab have destructive defects such as damage, tearing, and boundary fracture; c) tab missing, the overall tab folding means that the tab is folded into the battery pack as a whole. It can be understood that the types of tab defects that need to be detected in the manual full inspection step not listed in this application should also be included in the range of tab defects that can be identified in this application.

[0058] Through the above method, this embodiment can achieve 100% inspection of battery tab defects. At the same time, a set of image acquisition devices can be used to clearly capture the image of the tab group from the top surface to the root in a side view, and combined with the image recognition algorithm, the tab defects can be accurately detected, and no mechanical moving device is required, which greatly reduces the production cost. For batteries with defects in the tab group, they can be marked, and the defective batteries can be removed by the mechanical gripper in the subsequent process step, thereby ensuring the stable quality of the shipped batteries.

[0059] In a specific embodiment, the step S1 of acquiring the image of the tab group of the battery tab group by the image acquisition device includes:

[0060] S11, adjusting the focal position of the image acquisition device, and acquiring a single image of the battery tab group at each focal position;

[0061] S12, fusing the single images at each focus position using a multi-focus fusion algorithm to obtain the tab group image.

[0062] In this embodiment, since the collected image of the tab group is not a plane, but a stereoscopic image with a certain object depth, the object depth is the object depth between the plane where the farthest end of the tab group image is located and the plane where the closest end is located. Specifically, the farthest end is the root area of ​​the tab group, and the closest end is the junction area between the top surface 11 and the first side surface 12 or the second side surface 13. Conventional lenses have a small depth of field and cannot clearly capture all images of the tab group at different depths at one time. In order to more clearly illustrate the technical problem solved by this embodiment, Figure 2 The image of the tab group including at least the top surface 11 and all the first side surfaces 12 is used as an example. Figure 2In a single image, when the first top corner 16 is clearly imaged, the area of ​​the first side 12 close to the battery pole piece 15 is blurred; when the area of ​​the first side 12 close to the battery pole piece 15 is clear, the first top corner 16 becomes blurred. Using a conventional lens to shoot, it is impossible to detect defects on the top surface 11 and the root of the tab at the same time.

[0063] Therefore, this embodiment performs rapid focusing on the image acquisition device to adjust the focal position of the image acquisition device, and respectively acquires single images of the battery tab group at multiple focal positions, and then uses a multi-focus fusion algorithm to fuse the images, so that multiple single images with local clarity focused on different positions can be fused into an image of the tab group with clear imaging within the entire object depth range.

[0064] The multi-focus fusion algorithm can be implemented illustratively by the following steps:

[0065] 1) Initialization: Create an empty image imgResults to store the final result, and create an image imageGradient to store the gradient calculation result. Perform gradient calculation on the first single image and store the result in imageGradient. Copy the first single image as the initial image and store it in imgResults.

[0066] 2) Image merging: Traverse each of the above single images in the image list and calculate their gradients respectively. For each pixel, compare the gradient value in the current image and imageGradient. If the gradient value of the current image is higher, update the values ​​in imageGradient and imgResults.

[0067] 3) Output results: Output the final merged imgResults image as the above-mentioned tab group image.

[0068] The multi-focus fusion algorithm of this embodiment may also adopt other algorithms that have been disclosed or not disclosed in the prior art to achieve the above-mentioned purpose of the embodiment of the present application.

[0069] In a specific embodiment, the image acquisition device includes a liquid lens, and the step S11 of adjusting the focal position of the image acquisition device and acquiring a single image of the battery tab group at each focal position includes:

[0070] S111, obtaining a liquid lens photographing voltage range, wherein a first voltage corresponding to when the farthest end of the collected image of the tab group is clearly imaged and a second voltage corresponding to when the closest end of the collected image of the tab group is clearly imaged are both within the photographing voltage range;

[0071] S112, determining a preset number of adjustment voltage values ​​from the photographing voltage range, wherein different adjustment voltage values ​​are set in a gradient manner;

[0072] S113, applying each of the adjustment voltage values ​​to the liquid lens in sequence, and acquiring the single image corresponding to each of the adjustment voltage values ​​respectively.

[0073] In this embodiment, since the battery conveyor on the production line is very fast, the time to take multiple single pictures at different focal positions cannot be too long, otherwise it will affect the detection efficiency. The liquid lens can quickly zoom multiple times in a short time, so it can well achieve fast focusing in a short time and complete the collection of single images at different focal positions.

[0074] The above-mentioned liquid lens includes but is not limited to optical lenses such as telecentric lenses and FA lenses, which use liquid lenses. The specific optical design parameters of the liquid lens are not the innovation of this application, and this application does not make special restrictions here, as long as it can capture clear, sharp, and detailed images with high precision. Two liquids are arranged inside the liquid lens, and the two liquids are separated by a transparent film. By inputting voltage to the positive and negative electrodes of the liquid lens, the surface tension of the liquid lens changes, and the middle transparent diaphragm is deformed, which eventually changes the optical focal length of the liquid lens, thereby adjusting the imaging focus position. The liquid lens has a very fast response speed to voltage, so that by adjusting the voltage applied to the liquid lens, the focus position of the image acquisition device can be quickly adjusted, thereby achieving high depth of field shooting.

[0075] In the above step S111, by presetting the first voltage corresponding to the nearest end of the image of the pole ear group to be imaged, and the second voltage corresponding to the farthest end, specifically, the farthest end is the root area of ​​the pole ear group, and the nearest end is the boundary area between the top surface 11 and the first side surface 12 or the second side surface 13. According to the voltage interval corresponding to the first voltage and the second voltage, the photographing voltage range is determined so that the photographing voltage range at least includes the above voltage interval. The photographing voltage range can be slightly larger than the above voltage interval, so as to avoid the unclear local shooting caused by the offset of the battery placement. The above first voltage and the second voltage can be set by manual pre-debugging. It can also be directly and automatically obtained by adaptive adjustment during the focusing process of the liquid lens. In one example, the above photographing voltage range is 0V-70V. In other specific usage scenarios, the photographing voltage range can be adaptively adjusted according to specific needs, and this application does not make special restrictions on this.

[0076] In the above step S112, the preset number of adjustment voltage values ​​may be manually input or determined by the following method.

[0077] In a specific embodiment, the step S112 of determining a preset number of adjustment voltage values ​​from the photographing voltage range includes:

[0078] S1121, obtaining the object depth between the plane where the farthest end of the tab group image is located and the plane where the nearest end is located, and obtaining the depth of field of the single image; wherein the depth of field of the single image is the clear depth range captured by the liquid lens when the voltage remains unchanged.

[0079] S1122: Divide the object depth by the depth of field of the single image to obtain a first value, and set the preset number to ≥ The first value.

[0080] S1123, determining the preset number of gradient-distributed adjustment voltage values ​​distributed in the photographing voltage range. Each adjustment voltage value may be evenly distributed or unevenly distributed, and those skilled in the art may make adaptive adjustments according to specific usage scenarios, so that images of different object depths can be completely captured through each adjustment voltage value, so that a complete and clear image of the tab group can be fused.

[0081] In the above step S113, when the battery is transported to the inspection station through the logistics belt, the battery is paused for a period of time, and the liquid lens collects multiple single images during the pause time, and completes the image fusion and defect determination. Due to the rapid focusing capability of the liquid lens, the liquid lens is used to take multiple single images, and then further complete the image fusion of the above S12, which can be completed within 2 seconds, greatly improving the detection efficiency of the online detection of battery tab defects.

[0082] In a specific embodiment, Figure 3 , Figure 4 As shown, the image acquisition device includes an optical lens 2, the optical axis of the optical lens 2 forms a first angle with the top surface 11, the optical axis of the optical lens 2 forms a second angle with the first side surface 12 or the second side surface 13, and the first angle and the second angle are not equal to 90°.

[0083] In this embodiment, Figure 3 The corresponding battery is a battery in which the positive electrode tab group 301 and the negative electrode tab group 302 are arranged on the same side. Figure 4 The corresponding battery is a battery in which the positive pole tab group 301 and the negative pole tab group 302 are arranged on different sides. By setting the first angle and the second angle not equal to 90°, the optical axis of the optical lens 2 is oblique to the pole tab group, so that a clear image of the whole from the top surface 11 to the root of the pole tab group can be collected. For a pole tab group, two image acquisition devices are provided to realize the overall image acquisition of the entire pole tab group. Specifically, the optical lens 2 is the liquid lens in the aforementioned embodiment.

[0084] In a specific embodiment, Figure 5 As shown, the image acquisition device includes an optical lens 2 and a prism 3, wherein the prism 3 is arranged between the optical lens 2 and the top surface 11 and is located on the optical axis of the optical lens 2, and the prism 3 deflects the incident light path of the optical lens 2 to form an angle not equal to 90° with the first side surface 12 or the second side surface 13 of the tab group.

[0085] This embodiment is particularly suitable for the case where the optical axis of the optical lens 2 is perpendicular to the top surface 11. By arranging a prism 3 between the optical lens 2 and the top surface 11, the incident light path is deflected, so that the optical lens 2 can achieve image acquisition of the first side surface 12 or the second side surface 13 of the tab group when it is located at a position perpendicular to the top surface 11. The specific optical parameters of the prism 3 are not the main invention protection point of this application, and this application does not make any special restrictions here, as long as it can achieve the effect of deflecting the incident light path to an angle not equal to 90° with the first side surface 12 or the second side surface 13 of the tab group. Those skilled in the art can design the optical parameters of the prism 3 according to the inventive concept of this application, and all should be covered within the protection scope of this application.

[0086] In a specific embodiment, referring to Figure 6 The image acquisition device includes a light source 4, and the light source 4 is used to illuminate the tab group. Before the step S1 of acquiring the tab group image of the battery tab group through the image acquisition device, the method includes:

[0087] S01, obtaining the relative position of the tab group and the image acquisition device;

[0088] S02. According to the relative position, adjust the irradiation angle of the light source 4 so that the light source 4 directly irradiates the tab group.

[0089] Figure 5 This is an example of a light source setting of the present embodiment. The light source 4 forms a depression angle with the optical lens 2. The light source 4 can be connected to the optical lens 2 of the image acquisition device through a connector 5. A camera body 6 is set behind the optical lens 2. Specifically, the light source 4 includes but is not limited to plane light, strip light, ring light, line light, etc. By setting the light source 4, the imaging clarity of the tab group can be improved, thereby improving the accuracy of defect identification. The connector 5 can realize the angle adjustment of the light source 3. Specifically, the angle adjustment mechanism can be set on the connector 5 structure, and the optimal angle position of the light source can be adjusted by controlling the angle adjustment mechanism.

[0090] In a specific embodiment, the step S2 of performing image recognition on the tab group image to identify defects in the tab group includes:

[0091] S201, dividing the tab group image into a main area and a root area in a direction perpendicular to the tab stacking direction, wherein the root area is an area with a preset width from the bottom surface;

[0092] S202, identifying the number of root tab layers contained in the root area;

[0093] S203, comparing the number of root tab layers with a preset number of tab layers to determine whether the number of root tab layers is less than the preset number of tab layers;

[0094] S204: If yes, it is determined that there is a defect, and the defect is a missing electrode piece, a missing electrode tab, or a completely folded electrode tab.

[0095] In this embodiment, in the above step S201, the above preset width can be several millimeters, several hundred micrometers or more than ten millimeters, which can be determined according to the specific battery specifications. The area other than the root area is used as the main area.

[0096] In the above step S202, the stacking method of the battery pole pieces is a multi-layer positive electrode-diaphragm-negative electrode-diaphragm stacking structure. Taking the positive electrode tab group as an example, each layer of positive electrode tabs is connected to a layer of positive electrode. Since the diaphragm and negative electrode at the corresponding positions in the vertical direction of the positive electrode tabs are not led out, a certain gap is formed between the two layers of positive electrode tabs in the vertical direction. Since the positive electrode tabs themselves are very thin and the material is relatively soft, as the tab group extends from the root to the top surface 11, the multi-layer positive electrode tabs are stacked more and more closely, and the gaps between layers are getting smaller and smaller. Therefore, for the positive electrode tab group formed by stacking multiple layers of positive electrode tab groups, the stratification is most significant in the root area of ​​the tab group. It is based on the analysis of this key technical point that the embodiment of the present application preferably identifies the number of root tab layers in the root area of ​​the tab group image.

[0097] The specific method for identifying the number of tab layers can be determined by an image recognition algorithm, which can be achieved by feature comparison, contrast comparison, etc. The present application does not limit the specific algorithm process of the image recognition algorithm, and it can be achieved by using mature technologies in the prior art, which will not be described in detail here.

[0098] In the above steps S203-S204, the preset number of tab layers is manually preset. If the number of tab layers at the root is less than the preset number of tab layers, it is determined that there is a missing pole piece, a missing tab, or a tab is completely folded into the battery pack. If the number of tab layers at the root is greater than the preset number of tab layers, it is possible that the tab is partially folded to the root.

[0099] In another specific embodiment, the number of main body tab layers in the main body region can also be identified, and the number of tab layers can be compared with the preset number of tab layers to determine whether the number of main body tab layers is less than the preset number of tab layers; if so, it is determined that there is a defect. The number of root tab layers can also be further identified to determine whether the number of main body tab layers is consistent with the number of root tab layers. If they are consistent, the defect is determined to be missing pole pieces, missing tabs, or a tab is completely folded into the battery pack; if they are inconsistent, the defect is determined to be partially folded pole pieces, and partially folded pole pieces are, for example, one or more layers of pole pieces are folded.

[0100] In a specific embodiment, after step S201 of dividing the tab group image into a main area and a root area in a direction perpendicular to the tab stacking direction, wherein the root area is an area with a preset width from the bottom surface, the method further includes:

[0101] S205, determining whether there is an area exceeding a preset brightness by performing image recognition on the subject area;

[0102] S206. If yes, it is determined that there is a defect, and the defect is a partial folding defect.

[0103] In this embodiment, Figure 7 As shown in the figure, when the tab group has a partial tab folding, there will be a highlight in an area on the tab group image, and there will be a very obvious contrast difference compared with the normal qualified product image. If the contrast difference exceeds the preset range, it is determined that there is a defect, and the defect is a partial folding defect. The preset brightness can be obtained by collecting the brightness of the normal qualified product image.

[0104] In a specific embodiment, the step S2 of performing image recognition on the tab group image to identify defects in the tab group includes:

[0105] S211, extracting the edges of each layer of tabs from the tab group image;

[0106] S212, determining whether the edge of each layer of tabs is continuous from the top surface to the bottom surface;

[0107] S213. If not, it is determined that there is a defect, and the defect is a tab tear defect.

[0108] In this embodiment, the algorithm for extracting the edge of the tab from the tab group image can adopt an image recognition algorithm in the prior art, such as contrast-based feature recognition, etc. The present application does not limit the specific algorithm process of the image recognition algorithm, which can be implemented using mature technologies in the prior art and will not be described in detail here.

[0109] like Figure 8As shown, the embodiment of the present application also provides a battery tab defect visual recognition system, the system comprising an image recognition device 200 and an image acquisition device 100,

[0110] The image acquisition device 100 is used to obtain an image of a battery tab group (e.g. Figure 2 The tab group includes one or more layers of stacked tabs, the tab group includes at least a top surface 11, a first side surface 12, a second side surface 13 and a bottom surface 14, the bottom surface 14 is located at the root of the tab group and is connected to the battery pole piece 15, the top surface 11 is arranged opposite to the bottom surface 14, and the tab group image includes at least part of the top surface 11 and all of the first side surface 12, or includes at least part of the top surface 11 and all of the second side surface 13;

[0111] The image recognition device 200 is used to perform image recognition on the tab group image to identify defects in the tab group.

[0112] In a specific embodiment, the system includes an image recognition device 200 and a plurality of image acquisition devices 100 .

[0113] In a specific embodiment, Figure 3 and Figure 4 As shown, for a single battery, the number of the image acquisition devices 100 is 4, including a first image acquisition device 101, a second image acquisition device 102, a third image acquisition device 103 and a fourth image acquisition device 104; the tab group includes a positive tab group 301 and a negative tab group 302;

[0114] The first image acquisition device 101 is used to obtain a first angle image of the positive electrode tab group 301, wherein the first angle image of the positive electrode tab group 301 includes at least a portion of the top surface 11 and all of the first side surface 12 of the positive electrode tab group;

[0115] The second image acquisition device 102 is used to obtain a second angle image of the positive electrode tab group 301, wherein the second angle image of the positive electrode tab group 301 includes at least a portion of the top surface 11 and all of the second side surface 13 of the positive electrode tab group;

[0116] The third image acquisition device 103 is used to obtain a tab group image of the negative electrode tab group 302 at a third angle, wherein the tab group image of the negative electrode tab group 302 at the third angle includes at least a portion of the top surface 11 of the negative electrode tab group and all of the first side surface 12;

[0117] The fourth image acquisition device 104 is used to obtain a fourth angle image of the negative electrode tab group 302 , wherein the fourth angle image of the negative electrode tab group 302 includes at least a portion of the top surface 11 and all of the second side surface 13 of the negative electrode tab group.

[0118] In a specific embodiment, when the positive and negative tabs are set on the same side, refer to Figure 3 The specific process of the tab defect detection is as follows: a workstation is set at the positive tab group 301, and a workstation is set at the negative tab group 302. One workstation includes two groups of image acquisition devices, wherein the workstation of the positive tab group 301 is set with two groups of mirror-oblique image acquisition devices consisting of an optical lens 2, a camera body 6, a light source 4, and a connector 5. One group of image acquisition devices detects the first side surface 12 (left side surface) and at least the left area of ​​the top surface 11 of the positive tab group 301, and the other group of image acquisition devices detects the second side surface 13 (right side surface) and at least the right area of ​​the top surface 11 of the positive tab group 301. Similarly, two groups of mirror-oblique image acquisition devices consisting of an optical lens 2, a camera body 6, a light source 4, and a connecting part 5 are set at the work station of the negative electrode tab group 302. One group of image acquisition devices detects the first side surface 12 (left side surface) of the negative electrode tab group 302 and at least the left area of ​​the top surface 11, and the other group of image acquisition devices detects the second side surface 13 (right side surface) of the negative electrode tab group 302 and at least the right area of ​​the top surface 11.

[0119] In another specific embodiment, when the positive and negative electrode tabs are set on both sides, refer to Figure 4 , the specific process of the tab defect detection is as follows: the detection of the positive and negative tab groups is completed in one station, and one station has four sets of image acquisition devices. At this station, two sets of image acquisition devices consisting of an optical lens 2, a camera body 6, a light source 4, and a connector 5 are set corresponding to the positive tab group 301, one set of image acquisition devices detects the first side 12 (left side) of the positive tab group 301 and at least the left area of ​​the top surface 11, and the other set of image acquisition devices detects the second side 13 (right side) of the positive tab group 301 and at least the right area of ​​the top surface 11; at the same time, at this station, two sets of image acquisition devices consisting of an optical lens 2, a camera body 6, a light source 4, and a connector 5 are set corresponding to the negative tab group 302, one set of image acquisition devices detects the first side 12 (left side) of the negative tab group 302 and at least the left area of ​​the top surface 11, and the other set of image acquisition devices detects the second side 13 (right side) of the negative tab group 302 and at least the right area of ​​the top surface 11.

[0120] In a specific embodiment, the step of acquiring the image of the tab group of the battery tab group by the image acquisition device comprises:

[0121] Adjusting the focal position of the image acquisition device, and acquiring a single image of the battery tab group at each focal position;

[0122] The single images at each focus position are fused using a multi-focus fusion algorithm to obtain the tab group image.

[0123] In a specific embodiment, the image acquisition device includes a liquid lens, the liquid lens adjusts the focus position, and the steps of respectively acquiring a single image of the battery tab group at each focus position include:

[0124] Obtaining a liquid lens photographing voltage range, wherein a first voltage corresponding to when the farthest end of the collected image of the tab group is clearly imaged and a second voltage corresponding to when the closest end of the collected image of the tab group is clearly imaged are both within the photographing voltage range;

[0125] Determining a preset number of adjustment voltage values ​​from the photographing voltage range, wherein different adjustment voltage values ​​are set in a gradient manner;

[0126] The respective adjustment voltage values ​​are applied to the liquid lens in sequence, and the single images corresponding to the respective adjustment voltage values ​​are acquired respectively.

[0127] In a specific embodiment, the step of determining a preset number of adjustment voltage values ​​of the liquid lens from the photographing voltage range includes:

[0128] Obtaining the object depth between the plane where the farthest end of the tab group image is located and the plane where the closest end is located, and obtaining the depth of field of the single image;

[0129] Divide the object depth by the depth of field of the single image to obtain a first value, and set the preset number to ≥ the first value;

[0130] Determine the preset number of gradient-distributed adjustment voltage values ​​distributed in the photographing voltage range.

[0131] In a specific embodiment, the image acquisition device includes an optical lens 2, the optical axis of the optical lens 2 forms a first angle with the top surface 11, the optical axis of the optical lens 2 forms a second angle with the first side surface 12 or the second side surface 13, and the first angle and the second angle are not equal to 90°.

[0132] In a specific embodiment, the image acquisition device includes an optical lens 2 and a prism 3, wherein the prism 3 is disposed between the optical lens 2 and the top surface 11 and is located on the optical axis of the optical lens 2, and the prism 3 deflects the incident light path of the optical lens 2 to an angle not equal to 90° with the first side surface 12 or the second side surface 13 of the tab group.

[0133] In a specific embodiment, the image acquisition device includes a light source 4, and the light source 4 is used to illuminate the tab group. Before the step of acquiring the tab group image of the battery tab group through the image acquisition device, the step includes:

[0134] Acquiring the relative position of the tab group and the image acquisition device;

[0135] According to the relative position, the irradiation angle of the light source is adjusted so that the light source directly irradiates the tab group.

[0136] In a specific embodiment, the image recognition device 200 performs image recognition on the tab group image to identify defects in the tab group, including:

[0137] In a direction perpendicular to the tab stacking direction, the tab group image is divided into a main area and a root area, wherein the root area is an area with a preset width from the bottom surface;

[0138] Identifying the number of root tab layers included in the root region;

[0139] Compare the number of root tab layers with the preset number of tab layers to determine whether the number of root tab layers is less than the preset number of tab layers;

[0140] If yes, it is determined that there is a defect, and the defect is the missing pole piece, missing pole ear, or the pole ear is completely folded.

[0141] In another specific embodiment, the number of main body tab layers in the main body region can also be identified, and the number of tab layers can be compared with the preset number of tab layers to determine whether the number of main body tab layers is less than the preset number of tab layers; if so, it is determined that there is a defect. The number of root tab layers can also be further identified to determine whether the number of main body tab layers is consistent with the number of root tab layers. If they are consistent, the defect is determined to be missing pole pieces, missing tabs, or a tab is completely folded into the battery pack; if they are inconsistent, the defect is determined to be partially folded pole pieces, and partially folded pole pieces are, for example, one or more layers of pole pieces are folded.

[0142] In a specific embodiment, after the step of dividing the tab group image into a main area and a root area in a direction perpendicular to the tab stacking direction, wherein the root area is an area with a preset width from the bottom surface, the method further includes:

[0143] By performing image recognition on the subject area, determining whether there is an area exceeding a preset brightness;

[0144] If yes, it is determined that there is a defect, and the defect is a partial folding defect.

[0145] In a specific embodiment, the image recognition device 200 performs image recognition on the tab group image to identify defects in the tab group, including:

[0146] Extracting the edges of each layer of tabs from the tab group image;

[0147] Determine whether the edge of each layer of tabs is continuous from the top surface to the bottom surface;

[0148] If not, it is determined that there is a defect, and the defect is a tab tear defect.

[0149] For the specific implementation of each device in the above-mentioned system embodiments, please refer to the above-mentioned method embodiments, which will not be repeated here.

[0150] Reference Fig. 9 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected via a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above-mentioned battery tab defect visual recognition method is implemented.

[0151] Those skilled in the art will understand that Fig. 9 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0152] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0154] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0155] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for visually identifying battery tab defects, characterized in that: The method comprises: Acquire a tab group image of a battery tab group by an image acquisition device; the tab group includes one or more layers of tabs stacked together, the tab group includes at least a top surface, a first side surface, a second side surface and a bottom surface, the bottom surface is located at the root of the tab group and connected to the battery pole piece, the top surface is arranged opposite to the bottom surface, and the tab group image includes at least a portion of the top surface and all of the first side surface, or includes at least a portion of the top surface and all of the second side surface; Image recognition is performed on the image of the tab group to identify defects in the tab group.

2. The battery tab defect visual recognition method according to claim 1, characterized in that: The step of acquiring the image of the battery tab group by the image acquisition device comprises: Adjusting the focal position of the image acquisition device, and acquiring a single image of the battery tab group at each focal position; The single images at each focus position are fused using a multi-focus fusion algorithm to obtain the tab group image.

3. The battery tab defect visual recognition method according to claim 2, characterized in that: The image acquisition device includes a liquid lens, and the step of adjusting the focal position of the image acquisition device and acquiring a single image of the battery tab group at each focal position includes: Obtaining a liquid lens photographing voltage range, wherein a first voltage corresponding to when the farthest end of the collected image of the tab group is clearly imaged and a second voltage corresponding to when the closest end of the collected image of the tab group is clearly imaged are both within the photographing voltage range; Determining a preset number of adjustment voltage values ​​from the photographing voltage range, wherein different adjustment voltage values ​​are set in a gradient manner; The respective adjustment voltage values ​​are applied to the liquid lens in sequence, and the single images corresponding to the respective adjustment voltage values ​​are acquired respectively.

4. The battery tab defect visual recognition method according to claim 3, characterized in that: The step of determining a preset number of adjustment voltage values ​​from the photographing voltage range includes: Obtaining the object depth between the plane where the farthest end of the tab group image is located and the plane where the closest end is located, and obtaining the depth of field of the single image; Divide the object depth by the depth of field of the single image to obtain a first value, and set the preset number to ≥ the first value; Determine the preset number of gradient-distributed adjustment voltage values ​​distributed in the photographing voltage range.

5. The battery tab defect visual recognition method according to claim 1, characterized in that: The image acquisition device includes an optical lens, wherein the optical axis of the optical lens forms a first angle with the top surface, and the optical axis of the optical lens forms a second angle with the first side surface or the second side surface, and the first angle and the second angle are not equal to 90°.

6. The battery tab defect visual recognition method according to claim 1, characterized in that: The image acquisition device includes an optical lens and a prism, wherein the prism is arranged between the optical lens and the top surface and is located on the optical axis of the optical lens, and the prism deflects the incident light path of the optical lens to form an angle not equal to 90° with the first side surface or the second side surface of the tab group.

7. The battery tab defect visual recognition method according to claim 1, characterized in that: The image acquisition device includes a light source, and the light source is used to illuminate the tab group. Before the step of acquiring the tab group image of the battery tab group through the image acquisition device, include, Acquiring the relative position of the tab group and the image acquisition device; According to the relative position, the irradiation angle of the light source is adjusted so that the light source directly irradiates the tab group.

8. The battery tab defect visual recognition method according to claim 1, characterized in that: The step of performing image recognition on the tab group image to identify defects in the tab group includes: In a direction perpendicular to the tab stacking direction, the tab group image is divided into a main area and a root area, wherein the root area is an area with a preset width from the bottom surface; Identifying the number of root tab layers included in the root region; Compare the number of root tab layers with the preset number of tab layers to determine whether the number of root tab layers is less than the preset number of tab layers; If so, it is determined that there is a defect, and the defect is a missing pole piece, a missing pole ear, or a completely folded pole ear.

9. A battery tab defect visual recognition system, characterized in that: The system comprises an image recognition device and an image acquisition device. The image acquisition device is used to obtain a tab group image of a battery tab group; the tab group includes one or more layers of tabs stacked together, the tab group includes at least a top surface, a first side surface, a second side surface and a bottom surface, the bottom surface is located at the root of the tab group and connected to the battery pole piece, the top surface is arranged opposite to the bottom surface, and the tab group image includes at least a portion of the top surface and all of the first side surface, or includes at least a portion of the top surface and all of the second side surface; The image recognition device is used to perform image recognition on the image of the tab group to identify defects in the tab group.

10. The battery tab defect visual recognition system according to claim 9, characterized in that: For a single battery, the number of the image acquisition devices is 4, including a first image acquisition device, a second image acquisition device, a third image acquisition device and a fourth image acquisition device; the tab group includes a positive tab group and a negative tab group; The first image acquisition device is used to obtain a first angle image of the positive electrode tab group, wherein the first angle image of the positive electrode tab group includes at least a portion of the top surface and all of the first side surfaces of the positive electrode tab group; The second image acquisition device is used to obtain a second angle image of the positive electrode tab group, wherein the second angle image of the positive electrode tab group includes at least a portion of the top surface and all of the second side surface of the positive electrode tab group; The third image acquisition device is used to obtain a tab group image of the negative electrode tab group at a third angle, wherein the tab group image of the negative electrode tab group at the third angle includes at least a portion of the top surface of the negative electrode tab group and all of the first side surface; The fourth image acquisition device is used to obtain a fourth angle image of the negative electrode tab group, and the fourth angle image of the negative electrode tab group includes at least a portion of the top surface and all of the second side surface of the negative electrode tab group.

Images