Collector plate defect detection method, device, computer equipment, medium and system

Abstract

The invention relates to a collector plate defect detection method, device and system, computer equipment and a medium. The method comprises the following steps: acquiring first illumination image information obtained by performing image acquisition on a collector plate in a first illumination environment; performing preliminary defect detection on the collector plate based on the first illumination image information, and obtaining second illumination image information obtained by performing image acquisition on the collector plate in a second illumination environment under the condition of determining that the collector plate has an undetermined type defect, the first illumination angle of the first illumination environment being higher than the second illumination angle of the second illumination environment; according to the first illumination image information and the second illumination image information, carrying out three-dimensional smudginess defect detection on the class-to-be-determined defects, and determining the defect classes of the class-to-be-determined defects; and determining a defect detection result of the collector plate based on the defect category. By adopting the method, the defect category of the collector plate can be accurately identified, the probability of missing detection or excessive detection is reduced, and the battery production efficiency is improved.

Description

Technical Field

[0001] This application relates to the technical field of battery detection, and in particular, to a method and device for detecting current collector defects, a computer device, a storage medium, a system, and a computer program product. Background Art

[0002] In the production process of cylindrical batteries, the welding of the current collector is a production step to achieve the full connection of the positive and negative electrodes with the current collector. The welding quality of the current collector welding can directly affect the stability and safety of battery use. Metal particles generated during the welding process, such as metal welding slag larger than 100 μm, are not effectively removed, and the battery will have serious self-discharge behavior. Therefore, in order to improve the operating safety of the battery, it is necessary to detect the defects of the welded current collector to reduce the outflow probability of defective batteries.

[0003] Currently, the commonly used method for detecting current collector defects is to collect images of the welded current collector and then use an image recognition model to identify the defects in the current collector image. However, among the defects of the current collector, the morphology of the welding slag and dirt is similar, and it is more difficult to distinguish the two when the size is small. Therefore, the current method for detecting current collector defects cannot accurately distinguish the defect categories of the current collector defects, easily causes misjudgment of defects, resulting in problems of missed detection or over-detection, and affects the production efficiency of cylindrical batteries. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method and device for detecting current collector defects, a computer device, a computer-readable storage medium, a computer program product, and a system that can accurately identify the defect categories of the current collector, reduce the probability of missed detection or over-detection, and improve the production efficiency of batteries.

[0005] In a first aspect, this application provides a method for detecting current collector defects, the method including:

[0006] Obtain first illumination image information obtained by collecting an image of the current collector in a first illumination environment;

[0007] When performing preliminary defect detection on the current collector based on the first illumination image information and determining that the current collector has defects of undetermined category, obtain second illumination image information obtained by collecting an image of the current collector in a second illumination environment; the first illumination angle of the first illumination environment is higher than the second illumination angle of the second illumination environment; the defects of undetermined category refer to defects whose categories cannot be distinguished by using only the first illumination image information;

[0008] Perform three-dimensional soiling defect detection on the defect to be determined in terms of category according to the first illumination image information and the second illumination image information, and determine the defect category of the defect to be determined in terms of category; there are differences in the imaging of three-dimensional soiling defects under the first illumination environment and the second illumination environment;

[0009] Determine the defect detection result of the current collector plate based on the defect category.

[0010] For the method in the above embodiments, only the first illumination environment and the second illumination environment with different illumination angles need to be provided for the current collector plate, and one more image acquisition is added. Then, by using the imaging differences of the current collector plate under the first illumination environment and the second illumination environment, the morphological features of the defects can be highlighted, achieving the effect of accurately identifying three-dimensional soiling defects and non-three-dimensional soiling defects. While effectively improving the defect detection accuracy of the current collector plate and thus improving the battery production efficiency, it can also effectively reduce the detection cost of accurately detecting the defects of the current collector plate.

[0011] In some of the embodiments, the determining the defect detection result of the current collector plate based on the defect category includes:

[0012] When the defect category is the three-dimensional soiling defect, determine the second defect size of the three-dimensional soiling defect according to the second defect contour of the defect to be determined in terms of category in the second illumination image information;

[0013] When the second defect size is smaller than the first qualified size threshold set for the three-dimensional soiling defect, determine that the detection of the three-dimensional soiling defect of the current collector plate is qualified.

[0014] In the above embodiments, determining the defect size of the three-dimensional soiling defect through the second defect contour can make the determined defect size closer to the true size of the three-dimensional soiling defect, effectively improving the detection accuracy of the qualification detection of the three-dimensional soiling defect. At the same time, performing size compliance re-judgment on the three-dimensional soiling defect can also effectively reduce the risk of over-detection of defects, improve the battery production efficiency, and reduce the battery production cost.

[0015] In some of the embodiments, the method further includes:

[0016] When it is determined based on the first illumination image information that there are defects to be detected on the current collector plate, extract the first defect contour of the defect to be detected;

[0017] Determine the first defect size of the defect to be detected according to the first defect contour;

[0018] When the first defect size is less than the second qualified size threshold set for planar dirt defects and greater than or equal to the first qualified size threshold, determine the contour position of the first defect profile; the second qualified size threshold is greater than the first qualified size threshold.

[0019] When it is determined, based on the contour position, that the defect to be detected needs to be detected for three-dimensional dirt defects, determine the defect to be detected as a defect with undetermined category.

[0020] In the above embodiments, by comparing the first defect size of the defect to be detected with the first qualified size threshold and the second qualified size threshold respectively, it can be quickly determined whether the defect to be detected is an obviously unqualified defect or an obviously qualified defect. Only when it is determined that the defect to be detected is not an obviously unqualified defect or an obviously qualified defect, will the contour position of the defect to be detected be further followed up to determine whether the defect to be detected needs to be detected for three-dimensional dirt defects, effectively improving the detection efficiency of the current collector plate defect detection.

[0021] In some of the embodiments, the method further includes:

[0022] For the weld bead area of the current collector plate, perform region recognition on the first illumination image information to obtain the region contour position of the weld bead area;

[0023] Match the contour position of the defect to be detected with the region contour position to obtain a defect position matching result;

[0024] When the defect position matching result indicates that the defect to be detected is not located in the weld bead area, determine that the defect to be detected needs to be detected for three-dimensional dirt defects.

[0025] In the above embodiments, by matching the contour position of the defect to be detected with the region contour position of the weld bead area, it can be quickly determined whether the defect to be detected is a weld bead defect. When it is determined that it is not a weld bead defect, subsequent three-dimensional dirt defect detection can be performed on it, effectively improving the detection efficiency and detection accuracy of the current collector plate defect detection.

[0026] In some of the embodiments, the method further includes:

[0027] When the defect position matching result indicates that the defect to be detected is located in the weld bead area, determine the defect to be detected as a pinhole explosion defect;

[0028] When the size of the first defect is smaller than the third qualified size threshold set for the pinhole explosion defect, it is determined that the detection of the pinhole explosion defect of the current collector plate is qualified; the third qualified size threshold is greater than the first qualified size threshold and smaller than the second qualified size threshold.

[0029] In the above embodiment, for the pinhole explosion defect located in the weld bead area, the corresponding third qualified size threshold is used to perform the qualification detection, which can make the defect qualification detection process have a higher matching degree with the actual defect category, and effectively improve the detection accuracy of the current collector plate defect detection.

[0030] In some embodiments, for the weld bead area of the current collector plate, region recognition is performed on the first illumination image information to obtain the region contour position of the weld bead area, including:

[0031] Use a preset region of interest to frame the initial region information including the weld bead area from the first illumination image information;

[0032] Input the initial region information into a pre-set weld bead width detection model, and intercept and correct the initial region information based on the weld bead width of the weld bead area to obtain the region contour position of the weld bead area.

[0033] In the above embodiment, a relatively large range of the weld bead area is framed from the first illumination image through a preset region of interest, and then the relatively large range of the weld bead area is intercepted and corrected through the recognized weld bead width to obtain the region contour position of the weld bead area, which can effectively improve the recognition accuracy of the region contour position of the weld bead area and provide an accurate data basis for the subsequent judgment of whether the defect to be detected is within the weld bead area.

[0034] In some embodiments, the contour position of the defect to be detected includes the defect contour position coordinates of the defect to be detected, and the region contour position includes the region contour position coordinates of the weld bead area;

[0035] The matching of the contour position of the defect to be detected with the region contour position to obtain the defect position matching result includes:

[0036] Perform region mapping on the defect contour position coordinates of the defect to be detected and the region contour position coordinates of the weld bead area to determine the overlapping area of the defect contour of the defect to be detected and the region contour of the weld bead area;

[0037] Determine the area ratio between the overlapping area and the contour area of the defect contour;

[0038] When the area ratio is greater than a preset area ratio threshold, it is determined that the defect position matching result indicates that the defect to be detected is located in the weld bead area.

[0039] In the above embodiments, by comparing the area ratio of the overlapping area obtained by region mapping the defect contour position coordinates and the region contour position coordinates with the preset area ratio threshold through the preset area ratio threshold, it is possible to quickly and accurately determine whether the defect to be detected is located in the weld bead area, improving the accuracy and detection efficiency of the current collector defect detection.

[0040] In some embodiments, the determining the qualification detection result of the defect of undetermined category based on the defect category includes:

[0041] When the defect category is the planar dirt defect, it is determined that the planar dirt defect is a qualified defect.

[0042] In the above embodiments, when the defect of undetermined category is a planar dirt defect, directly determining the planar dirt defect as a qualified defect can reduce the possibility of over-detection of qualified defects, resulting in an increase in defective products of the battery product, thereby improving the production efficiency of the battery product and reducing the production cost of the battery product.

[0043] In some embodiments, the defect category includes a three-dimensional dirt defect and a planar dirt defect; the first illumination image information includes bright-field image information, and the second illumination image information includes dark-field image information;

[0044] The detecting the three-dimensional dirt defect of the defect of undetermined category according to the first illumination image information and the second illumination image information to determine the defect category of the defect of undetermined category includes:

[0045] Gray-scale features of the bright-field image information and the dark-field image information are respectively extracted to obtain the bright-field gray-scale feature and the dark-field gray-scale feature of the defect of undetermined category;

[0046] When the feature difference degree between the bright-field gray-scale feature and the dark-field gray-scale feature is greater than the three-dimensional dirt difference degree threshold, it is determined that the defect category of the defect of undetermined category is a three-dimensional dirt defect;

[0047] When the feature difference degree is less than or equal to the three-dimensional dirt difference degree threshold, it is determined that the defect category of the defect of undetermined category is a planar dirt defect.

[0048] In the above embodiments, by extracting the bright-field gray-scale features and dark-field gray-scale features of the defects with undetermined categories, the imaging differences of the defects with undetermined categories under the two illumination modes can be accurately and intuitively reflected. Furthermore, the defect types of the defects with undetermined categories can be quickly determined based on the imaging differences, effectively improving the efficiency of determining the defect categories and the recognition accuracy of the defects with undetermined categories.

[0049] In some of the embodiments, the step of respectively extracting the gray-scale features from the first illumination image information and the second illumination image information to obtain the bright-field gray-scale features and dark-field gray-scale features of the defects with undetermined categories includes:

[0050] Extracting the gray-scale features of the bright field of the defects with undetermined categories from the first illumination image information according to the first defect contour of the defects with undetermined categories;

[0051] Using the first defect contour as the region of interest for detection, performing region mapping on the second illumination image information to obtain the second defect contour of the defects with undetermined categories;

[0052] Extracting the gray-scale features of the dark field of the defects with undetermined categories from the second illumination image information based on the second defect contour.

[0053] In the above embodiments, by using the first defect contour as the region of interest for detection, performing region mapping on the second illumination image information to obtain the second defect contour, and then respectively extracting the gray-scale features from the image information according to the first defect contour and the second defect contour, the data processing amount during gray-scale feature extraction can be effectively reduced, and the gray-scale feature extraction efficiency can be improved. At the same time, through the method of region mapping, the feature matching degree between the bright-field gray-scale features and the dark-field gray-scale features can also be improved, thereby improving the accuracy of defect category determination.

[0054] In a second aspect, the present application further provides a current collector plate defect detection device, which includes:

[0055] A first illumination information acquisition module, configured to acquire first illumination image information obtained by image acquisition of the current collector plate in a first illumination environment;

[0056] A second illumination information acquisition module, configured to acquire second illumination image information obtained by image acquisition of the current collector plate in a second illumination environment when it is determined based on the first illumination image information that there are defects with undetermined categories on the current collector plate; the first illumination angle of the first illumination environment is higher than the second illumination angle of the second illumination environment; the defects with undetermined categories refer to defects that cannot be distinguished using only the first illumination image information;

[0057] A defect category determination module, configured to perform three-dimensional dirt defect detection on the defect to be determined in terms of category according to the first illumination image information and the second illumination image information, and determine the defect category of the defect to be determined in terms of category; there are differences in the imaging of three-dimensional dirt defects under the first illumination environment and the second illumination environment;

[0058] A defect detection module, configured to determine the defect detection result of the current collector plate based on the defect category.

[0059] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0060] In a fourth aspect, 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 steps of the above method are implemented.

[0061] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0062] In a sixth aspect, the present application further provides a current collector plate defect detection system, where the system includes a first illumination environment component, a second illumination environment component, an image acquisition component, and a visual defect detection component communicatively connected to the image acquisition component;

[0063] The first illumination environment component is configured to provide a first illumination environment for the current collector plate;

[0064] The second illumination environment component is configured to provide a second illumination environment for the current collector plate; the first illumination angle of the first illumination environment is higher than the second illumination angle of the second illumination environment;

[0065] The image acquisition component is configured to acquire first illumination image information of the current collector plate under the first illumination environment and second illumination image information under the second illumination environment;

[0066] The visual defect detection component is configured to implement the current collector plate defect detection method as described above.

[0067] In some of the embodiments, the system further includes an acquisition control component communicatively connected to the visual defect detection component;

[0068] The acquisition control component is electrically connected to the first lighting environment component, the second lighting environment component, and the image acquisition component respectively. By sending electrical signals to the first lighting environment component or the second lighting environment component, the opening and closing of the first lighting environment component or the second lighting environment component are controlled. By sending electrical signals to the image acquisition component, the image acquisition component is controlled to perform image acquisition on the current collector plate.

[0069] In some embodiments, the first lighting environment component includes a bowl-shaped light source with a first irradiation angle and a coaxial light source;

[0070] The second lighting environment component includes a ring-shaped light source with a second irradiation angle.

[0071] The above current collector plate defect detection method, device, computer device, storage medium, and computer program product perform preliminary defect detection on the current collector plate through the first lighting image information collected by the current collector plate in the first lighting environment with the first lighting angle. When it is determined that there are defects of undetermined categories in the current collector plate, it means that there are defects in the current collector plate that cannot be distinguished by using only the first lighting image at this time, and it is necessary to use the second lighting image information of the current collector plate for auxiliary identification to determine the defect category of the defects of undetermined categories. Continue to provide the current collector plate with the second lighting environment with the second lighting angle, and obtain the second lighting image information obtained by performing image acquisition on the current collector plate in the second lighting environment. Since the first lighting angle is higher than the second lighting angle of the second lighting environment, the imaging of the three-dimensional dirt defect in the first lighting environment and the second lighting environment will be different. Perform three-dimensional dirt defect detection on the defects of undetermined categories according to the first lighting image information and the second lighting image information, determine the defect category of the defects of undetermined categories, and determine the defect detection result of the current collector plate based on the defect category. The above method only needs to provide the current collector plate with the first lighting environment and the second lighting environment with different lighting angles, and add one image acquisition, and then the imaging difference of the current collector plate in the first lighting environment and the second lighting environment can be used to highlight the morphological characteristics of the defects, achieving the effect of accurately identifying three-dimensional dirt defects and non-three-dimensional dirt defects. While effectively improving the defect detection accuracy of the current collector plate and thus improving the battery production efficiency, it can also effectively reduce the detection cost of accurate defect detection of the current collector plate. Description of the Drawings

[0072] Figure 1 It is a schematic structural diagram of a current collector plate defect detection system in some embodiments;

[0073] Figure 2 It is a schematic structural diagram of a current collector plate defect detection system in other embodiments;

[0074] Figure 3 It is a schematic diagram of a bright-field lighting environment in some embodiments;

[0075] Figure 4 Schematic diagram of the dark-field illumination environment in some embodiments;

[0076] Figure 5 Schematic diagram of the process of the current collector plate defect detection method in some embodiments;

[0077] Figure 6 Schematic diagram of the process of performing three-dimensional dirt defect detection on the defect to be determined and determining the defect category of the defect to be determined according to the first illumination image information and the second illumination image information in some embodiments;

[0078] Figure 7 Schematic diagram of the process of respectively extracting the gray-scale features of the bright-field image information and the dark-field image information to obtain the bright-field gray-scale feature and the dark-field gray-scale feature of the defect to be determined in some embodiments;

[0079] Figure 8 Schematic diagram of the process of the current collector plate defect detection method in some other embodiments;

[0080] Figure 9 Schematic diagram of the process of the current collector plate defect detection method in some other embodiments;

[0081] Figure 10 Schematic diagram of the process of performing position matching between the contour position of the defect to be detected and the region contour position to obtain the defect position matching result in some embodiments;

[0082] Figure 11 Schematic diagram of the process of the preliminary defect detection part of the current collector plate defect detection method in some embodiments;

[0083] Figure 12 Schematic diagram of the process of the defect category re-inspection part of the current collector plate defect detection method in some embodiments;

[0084] Figure 13 Schematic block diagram of the current collector plate defect detection device in some embodiments;

[0085] Figure 14 Internal structure diagram of a computer device in some embodiments. Detailed implementation manners

[0086] Next, embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solution of the present application more clearly, so they are only examples and cannot be used to limit the protection scope of the present application.

[0087] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used herein are for the purpose of describing specific embodiments only and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion.

[0088] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least some embodiments of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0089] In the description of the embodiments of this application, the term "plurality" means two or more (including two). Similarly, "multiple groups" means two or more groups (including two groups), and "multiple pieces" means two or more pieces (including two pieces).

[0090] In the description of the embodiments of this application, the orientation or positional relationship indicated by technical terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the embodiments of this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the embodiments of this application.

[0091] In the description of the embodiments of this application, unless otherwise clearly specified and limited, technical terms such as "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can also be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and can be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of this application can be understood according to specific circumstances.

[0092] The welding of the current collector plate is a production step to achieve the full connection between the positive and negative electrodes and the current collector. It refers to the precise connection of the end face of the battery cell of the battery electrode sheet with the current collector plate, thereby achieving the full connection between the positive and negative electrodes of the battery and the current collector, enabling the current to flow smoothly inside the battery. The welding quality of the current collector plate welding can directly affect the stability and safety of battery use. Metal particles generated during the welding process, such as metal welding slag larger than 100μm that are not effectively removed, will cause serious self-discharge behavior in the battery. Therefore, in order to improve the safety of battery operation, it is necessary to perform defect detection on the welded current collector plate to reduce the outflow probability of defective batteries.

[0093] Currently, the commonly used method for defect detection of the current collector plate is to collect images of the welded current collector plate and then identify defects in the current collector plate image through an image recognition model. However, among the defects of the current collector plate, the morphology of the welding slag and dirt is similar, and it is more difficult to distinguish between the two when the size is small. Therefore, the current method for defect detection of the current collector plate cannot accurately distinguish the defect categories of the current collector plate defects, easily causing misjudgment of defects, resulting in problems of missed detection or over-detection, and affecting the production efficiency of cylindrical batteries.

[0094] In order to improve the defect detection accuracy of the current collector plate, the current collector plate can be initially defect-detected by using the first illumination image information collected under the first illumination environment at the first illumination angle of the current collector plate. When it is determined that there are defects of undetermined categories in the current collector plate, it indicates that there are defects in the current collector plate that cannot be distinguished by using only the first illumination image at this time. It is necessary to use the second illumination image information of the current collector plate for auxiliary identification to determine the defect category of the defects of undetermined categories. Continue to provide the current collector plate with the second illumination environment at the second illumination angle, and obtain the second illumination image information obtained by collecting images of the current collector plate under the second illumination environment. Since the first illumination angle is higher than the second illumination angle of the second illumination environment, the imaging of the three-dimensional dirt defect will be different under the first illumination environment and the second illumination environment. Perform three-dimensional dirt defect detection on the defects of undetermined categories according to the first illumination image information and the second illumination image information, determine the defect category of the defects of undetermined categories, and determine the defect detection result of the current collector plate based on the defect category. The above method only needs to provide the current collector plate with the first illumination environment and the second illumination environment at different illumination angles, and increase one image collection. Then, by using the imaging difference of the current collector plate under the first illumination environment and the second illumination environment, the morphological characteristics of the defects can be highlighted, achieving the effect of accurately identifying three-dimensional dirt defects and non-three-dimensional dirt defects. While effectively improving the defect detection accuracy of the current collector plate and thus improving the battery production efficiency, it can also effectively reduce the detection cost of accurate defect detection of the current collector plate.

[0095] The method for defect detection of the current collector plate provided by the embodiments of this application can be applied to, for example Figure 1In the manifold defect detection system 100 shown. Among them, the manifold defect detection system 100 includes a first lighting environment component 101, a second lighting environment component 102, an image acquisition component 103, and a vision defect detection component 104 that is communicatively connected to the first lighting environment component 101, the second lighting environment component 102, and the image acquisition component 103 respectively.

[0096] Among them, the first lighting environment component 101 is a device component for providing a first lighting environment for the manifold, and the second lighting environment component 102 is a device component for providing a second lighting environment for the manifold. The first lighting angle of the first lighting environment is different from the second lighting angle of the second lighting environment, and the first lighting angle is higher than the second lighting angle. By performing image acquisition on the manifold at different lighting angles, there will be a difference in the imaging of the three-dimensional dirt defect in the first lighting environment and the second lighting environment. The imaging difference of the manifold in the first lighting environment and the second lighting environment can be utilized to highlight the morphological characteristics of the defect, achieving the effect of accurately identifying three-dimensional dirt defects and non-three-dimensional dirt defects.

[0097] It can be understood that the first lighting environment component 101 and the second lighting environment component 102 can be any lighting components that can provide lighting environments with different lighting angles, as long as there is an imaging difference between the first imaging of the three-dimensional dirt defect in the category-to-be-determined defect in the first lighting environment and the second imaging in the second lighting environment, and there is no difference between the first imaging and the second imaging of the non-three-dimensional dirt defect in the category-to-be-determined defect.

[0098] In some embodiments, the first lighting environment component 101 can include a device component for providing a bright field lighting environment, and the second lighting environment component 101 can include a device component for providing a dark field lighting environment.

[0099] Among them, the principle of bright field illumination is that the light source directly irradiates the surface of the object to be measured, and a high-contrast image is formed by using the strong light reflected by the object surface. By providing an environment for the manifold, the smooth surface of the manifold will present a bright area due to specular reflection, while the concave, foreign object, or texture area will form a dark area due to scattering or occlusion, thereby highlighting the surface feature differences.

[0100] When the first lighting environment component 101 is a bright field lighting environment component, the light emitted by the first lighting environment component 101 is also called bright field light or high-angle light, and the first lighting environment component 101 can be any device component that can provide bright field light.

[0101] Among them, dark field illumination is an optical imaging technique that highlights the three-dimensional convex features of an object's surface through low-angle scattered light. Its principle is that the light source irradiates the object to be measured at a large incident angle, such as >75°, so that the light reflected by the smooth surface can avoid the image acquisition component 103, while the light signals generated by scattering or refraction at the edges of the surface protrusions enter the image acquisition component 103. Therefore, in dark field imaging, the flat area presents a dark background, while the protruding defects are displayed as bright spots, forming a high-contrast light and dark contrast.

[0102] When the second illumination environment component 102 is a dark field illumination environment component, the light emitted by the second illumination environment component 102 is also called dark field light or low-angle light, and the second illumination environment component 102 can be any device component that can provide dark field light.

[0103] In some embodiments, the first illumination environment component may include a bowl-shaped light source and a coaxial light source with a first irradiation angle. The second illumination environment component may include an annular light source with a second irradiation angle, and the first irradiation angle is higher than the second irradiation angle.

[0104] Among them, the bowl-shaped light source is usually composed of a bowl-shaped reflector and a built-in light source, mainly used to control the direction, focusing or scattering of light. The coaxial light source is an illumination device in which the light direction of the light source is consistent with the optical axis of the camera, which can eliminate shadow and specular reflection interference and achieve high-contrast imaging of the fine features on the object surface. The annular light source is usually composed of multiple light sources arranged along an annular structure, and the light is symmetrically distributed around the axis of the camera lens, so as to form a uniform annular light to irradiate the object surface and achieve effects such as surface texture enhancement and shadow elimination.

[0105] Among them, the first irradiation angle is the irradiation angle of the bowl-shaped light source, and the second irradiation angle is the irradiation angle of the annular light source. The first irradiation angle is higher than the second irradiation angle. The bowl-shaped light source uses a high-angle first irradiation angle for floodlight or spotlight design, which can directly and evenly irradiate the surface of the current collector plate and reduce shadows. The annular light source uses a low-angle second irradiation angle for oblique light incidence, so that the light source entering the camera is scattered light, achieving the effect of a dark background and a bright defect area.

[0106] In some embodiments, the second illumination environment component 102 is a 0° annular light source.

[0107] In some embodiments, the coaxial light source, the bowl-shaped light source or the 0° annular light source can all be stroboscopic light sources.

[0108] In the above embodiments, the current collector tray defect detection system adopts a light source design with high-angle bowl light, coaxial light, and low-angle ring light, providing different-angle light field illumination for the current collector tray. Through dual-light field imaging, the characteristics of the current collector tray defect items can be effectively highlighted, thereby improving the information accuracy of the first illumination image information and the second illumination image information collected subsequently.

[0109] In some other embodiments, the first illumination environment component 101 may include a device component that provides a bright-field illumination environment, and the second illumination environment component 102 may include a device component that provides a 2.5D (two and a half dimensional) imaging illumination environment.

[0110] Among them, 2.5D imaging is a technology between two-dimensional and three-dimensional imaging. By obtaining limited depth information, it adds the ability to perceive the height or depth changes of the object surface on the basis of a two-dimensional image, thus presenting a three-dimensional-like visual effect. Its principle is to illuminate the target object from different angles, collect multiple images with different lighting conditions, and use the changes in the reflected light intensity of the object surface in these images, combined with corresponding algorithms, to estimate the height information of each defect on the target object surface.

[0111] In the case where the second illumination environment component 102 is a 2.5D imaging illumination component, there can be multiple second illumination angles for the second illumination environment component 102. The multiple second illumination angles are different from each other and lower than the first illumination angle. By obtaining the second illumination image information collected under the second illumination environments corresponding to the multiple second illumination angles, together with the first illumination image information collected under the first illumination angle, the three-dimensional characteristics of the defect to be determined can be determined. For example, in the case where the defect to be determined is a three-dimensional dirt defect, the three-dimensional structural characteristics of the three-dimensional dirt defect can be obtained by fitting the first illumination image information and the second illumination image information. In the case where the defect to be determined is a non-three-dimensional dirt defect, such as a planar defect, the defect characteristics obtained by fitting the first illumination image information and the second illumination image information are only planar defect characteristics.

[0112] In some of these embodiments, the second illumination environment component 102 may include bowl-shaped light sources with multiple different illumination angles. Image acquisition is performed on the current collector tray under each bowl-shaped light source to obtain the corresponding image information, and finally the second illumination image information of the current collector tray can be obtained.

[0113] Among them, the image acquisition component 103 is a device component for acquiring the first illumination image information of the current collector tray under the first illumination environment and the second illumination image information under the second illumination environment. It can be understood that the image acquisition component 103 can be any device component capable of implementing image acquisition, such as a camera, a video camera, etc.

[0114] In some of these embodiments, in order to improve the detection accuracy, the image acquisition component 103 can be a high-resolution color full-frame camera. By setting the high-resolution color full-frame camera as the image acquisition component 103, the detection requirements at the μm level can be met.

[0115] Among them, the visual defect detection component 104 is a system component used to detect defects in the current collector tray based on the image information collected by the image acquisition component 103, and to determine the qualification of the current collector tray by detecting the qualification of the defects. The visual defect detection component 104 is equipped with a visual defect detection system generated based on a preset defect detection processing logic and corresponding defect detection algorithms, which can accurately detect the defects of the current collector tray, thereby improving the battery production efficiency and reducing the risk of missed or over-detected defects.

[0116] In some embodiments, when the visual defect detection component 104 determines that the current collector tray has reached the detection station, it can control the first lighting environment component 101 to turn on, provide a first lighting environment for the current collector tray, then control the image acquisition component 103 to collect an image of the current collector tray in the first lighting environment, obtain the first lighting image information of the current collector tray, receive the first lighting image information sent by the image acquisition component 103, and control the first lighting environment component 101 to turn off. Based on the first lighting image information, a preliminary defect detection of the current collector tray is performed. When it is determined that there are defects of undetermined categories in the current collector tray, it means that there are defects in the current collector tray that cannot be distinguished using only the first lighting image information at this time, and the second lighting image information of the current collector tray is required for auxiliary identification to determine the defect category of the defects of undetermined categories. The visual defect detection component 104 can control the second lighting environment component 102 to turn on, provide a second lighting environment for the current collector tray, then control the image acquisition component 103 to collect an image of the current collector tray in the second lighting environment, obtain the second lighting image information of the current collector tray. Receive the second lighting image information sent by the image acquisition component 103, and control the second lighting environment component 102 to turn off. Subsequently, a three-dimensional dirt defect detection is performed on the defects of undetermined categories based on the first lighting image information and the second lighting image information to determine the defect category of the defects of undetermined categories, and the qualification detection result of the defects of undetermined categories is determined based on the defect category.

[0117] In the current collector plate defect detection system in the above embodiments, by setting the first lighting environment component and the second lighting environment component, a first lighting environment and a second lighting environment with different lighting angles can be provided for the current collector plate. Compared with traditional defect detection methods, only one additional image acquisition is required. The imaging differences of the current collector plate in the first lighting environment and the second lighting environment can be utilized to highlight the morphological features of the defects, achieving the effect of accurately identifying three-dimensional dirt defects and non-three-dimensional dirt defects. While effectively improving the defect detection accuracy of the current collector plate and thus the battery production efficiency, the detection cost of accurately detecting current collector plate defects can also be effectively reduced.

[0118] In some embodiments, the current collector plate defect detection system further includes an acquisition control component connected to the visual defect detection component. Among them, the acquisition control component is electrically connected to the first lighting environment component, the second lighting environment component, and the image acquisition component respectively. By sending electrical signals to the first lighting environment component or the second lighting environment component, the startup of the first lighting environment component or the second lighting environment component is controlled. By sending electrical signals to the image acquisition component, the image acquisition component is controlled to perform image acquisition on the current collector plate.

[0119] In some of these embodiments, the acquisition control component can be a programmable logic controller (PLC).

[0120] In the above embodiments, the acquisition control component is electrically connected to the first lighting environment component, the second lighting environment component, and the image acquisition component respectively by using electrical signals, such as IO signals, and then controls the opening and closing of the first lighting environment component or the second lighting environment component, and triggers the image acquisition of the current collector plate, which can effectively save the image acquisition time and improve the detection efficiency of current collector plate defect detection.

[0121] In some embodiments, as Figure 2 shown, a current collector plate defect detection system is provided. The system includes a camera 201, a camera lens 202, a coaxial light source 203, a bowl-shaped light source 204, a 0° ring light 205, and an acquisition controller (not shown in the figure) that is electrically connected to the camera 201, the coaxial light source 203, the bowl-shaped light source 204, and the 0° ring light 205 respectively, and a visual defect detection component (not shown in the figure) that is communicatively connected to the acquisition controller.

[0122] In some of these embodiments, the camera 201 can be a high-resolution color full-frame area array camera.

[0123] In some of these embodiments, the coaxial light source 203, the bowl-shaped light source 204, and the 0° ring light 205 can use stroboscopic light sources. After the acquisition controller sends a hard trigger signal to light up the light sources, the light sources can automatically go out after a preset lighting time without the control of the acquisition controller, which can effectively reduce the resource consumption during the image acquisition process.

[0124] In some embodiments, when the visual defect detection component determines that the battery cell reaches the detection station, it sends a bright-field light source turn-on instruction to the acquisition controller. In response to the bright-field light source turn-on instruction, the acquisition controller sends a in-place signal and the battery cell code to the coaxial light source 203 and the bowl-shaped light source 204, and hard-triggers to light up the light sources to construct a bright-field illumination environment for the current collector plate. The schematic diagram of the bright-field illumination environment is shown as Figure 3 shown.

[0125] The visual defect detection component controls the camera 201 to take a first photo of the surface of the current collector plate, obtains the first illumination image information of the current collector plate, and sends the first illumination image information to the visual defect detection component. The coaxial light source 203 and the bowl-shaped light source 204 automatically turn off after being lit and running for a preset bright-field light source lighting time.

[0126] The visual defect detection component performs a preliminary defect detection on the current collector plate based on the bright-field image information. When it is determined that there are defects of undetermined category in the current collector plate, it means that there are defects in the current collector plate that cannot be distinguished by using only the bright-field image at this time, and it is necessary to assist in identification through the second illumination image information of the current collector plate to determine the defect category of the defects of undetermined category. The visual defect detection component sends a dark-field light source turn-on instruction to the acquisition controller. In response to the dark-field light source turn-on instruction, the acquisition controller sends the battery cell code to the 0° ring light 205, and hard-triggers to light up the light source to construct a dark-field illumination environment for the current collector plate. The schematic diagram of the dark-field illumination environment is shown as Figure 4 shown.

[0127] The visual defect detection component controls the camera 201 to take a second photo of the surface of the current collector plate, obtains the second illumination image information of the current collector plate, and sends the second illumination image information to the visual defect detection component. The 0° ring light 205 automatically turns off after being lit and running for a preset dark-field light source lighting time. It can be understood that the bright-field light source lighting time and the dark-field light source lighting time can be determined by the designer according to actual usage requirements. The bright-field light source lighting time and the dark-field light source lighting time can be the same or different, as long as it can maintain the normal acquisition of the image of the current collector plate under the illumination of the corresponding light source by the image acquisition device.

[0128] The visual defect detection component performs a three-dimensional dirt defect detection on the defects of undetermined category according to the first illumination image information and the second illumination image information, determines the defect category of the defects of undetermined category, and determines the pass / fail detection result of the defects of undetermined category based on the defect category.

[0129] In some embodiments, as Figure 5 shown, a method for detecting defects of a current collector plate is provided. Taking the method applied to the visual defect detection component 104 in Figure 1 as an example, it includes the following steps:

[0130] S502. Obtain first illumination image information obtained by performing image acquisition on the current collector tray in a first illumination environment.

[0131] The first illumination image information is information data used to characterize the imaging features of the surface of the current collector tray in the first illumination environment. For example, the first illumination image information may include each pixel point constituting the first illumination image of the current collector tray and the pixel value corresponding to each pixel point.

[0132] In some embodiments, the visual defect detection component may obtain the first illumination image information of the current collector tray through the image acquisition component when the current collector tray is in the first illumination environment.

[0133] S504. When performing preliminary defect detection on the current collector tray based on the first illumination image information and determining that the current collector tray has defects with undetermined categories, obtain second illumination image information obtained by performing image acquisition on the current collector tray in a second illumination environment.

[0134] Among them, the first illumination angle of the first illumination environment is higher than the second illumination angle of the second illumination environment. The preliminary defect detection is a detection step used to determine whether there are defects on the surface of the current collector tray with undetermined defect categories. By performing preliminary defect detection on the current collector tray through the first illumination image information, it can be determined whether there are defects on the current collector tray that cannot be classified using only the first illumination image and require the use of the second illumination image information for auxiliary identification. At the same time, by performing preliminary defect detection on the current collector tray, obvious unqualified defects on the surface of the current collector tray can be quickly detected, further improving the detection efficiency of the qualification of the current collector tray.

[0135] In some of these embodiments, the preliminary defect detection may be a defect detection operation of using a pre-trained defect detection model to identify defects on the surface of the current collector tray. The visual defect detection component may input the first illumination image information of the current collector tray into the defect detection model, perform defect category detection on the surface of the current collector tray based on the defect detection model, obtain the category detection results of each defect on the surface of the current collector tray, and determine whether there are defects with undetermined categories in the current collector tray according to the category detection results.

[0136] In some of these embodiments, when there are defects on the surface of the current collector tray with undetermined defect categories, it is determined that the current collector tray has defects with undetermined categories.

[0137] In some of these embodiments, it is only when all the defects of the determined categories identified in the preliminary defect detection are qualified defects and there are defects for which the defect category cannot be determined that it is determined that the current collector plate has defects of undetermined category. If unqualified defects have been detected on the surface of the current collector plate during the preliminary defect detection process, such as planar contamination defects with large dimensions, three-dimensional contamination defects, etc., it can be directly determined that the inspection of the current collector plate is unqualified, and the battery cell to which the current collector plate belongs is transferred to the defective product area for processing. If all the defects of the determined categories that can be detected on the surface of the current collector plate through the preliminary defect detection are qualified defects, such as planar contamination defects with compliant dimensions, pinhole explosion point defects, etc., then the preliminary defect detection results can be further followed up to determine whether there are still defects for which the defect category cannot be identified. If so, it can be considered that the current collector plate has defects of undetermined category, and it is necessary to further detect the defects of undetermined category, and determine the pass / fail inspection result of the current collector plate according to the pass / fail inspection result of the defects of undetermined category, so as to determine the next flow direction of the battery cell product.

[0138] Among them, the second illumination image information is information data used to characterize the imaging characteristics of the surface of the current collector plate in the second illumination environment. For example, the second illumination image information may include each pixel point constituting the second illumination image of the current collector plate and the pixel value corresponding to each pixel point.

[0139] In some embodiments, the visual defect detection component can perform preliminary defect detection on the current collector plate based on the first illumination image information. When it is determined according to the preliminary defect detection result that the current collector plate has defects of undetermined category, the second illumination image information obtained by image acquisition of the current collector plate in the second illumination environment is acquired through the image acquisition component.

[0140] S506. Based on the first illumination image information and the second illumination image information, perform three-dimensional contamination defect detection on the defects of undetermined category to determine the defect category of the defects of undetermined category.

[0141] Among them, the three-dimensional contamination defect detection is a defect detection operation for determining whether the defects of undetermined category are three-dimensional contamination defects. By performing three-dimensional contamination defect detection on the defects of undetermined category, it can be accurately determined whether the defects of undetermined category are three-dimensional contamination defects, such as welding slag or three-dimensional dust, etc., or non-three-dimensional contamination defects, such as planar contamination defects. The imaging of three-dimensional contamination defects is different in the first illumination environment and the second illumination environment.

[0142] Among them, the defect category is a category parameter obtained by classifying the current collector plate defects according to the defect morphology. For example, the defect category may include three-dimensional contamination defects, planar contamination defects, pinhole explosion point defects, etc.

[0143] In some embodiments, the visual defect detection component may perform three-dimensional dirt defect detection on the defect of undetermined category according to the first illumination image information and the second illumination image information, that is, perform three-dimensional dirt defect detection on the defect of undetermined category according to the feature difference between the imaging features of the defect of undetermined category in the first illumination environment and the imaging features in the second illumination environment, and determine the defect category of the defect of undetermined category.

[0144] In some of these embodiments, the visual defect detection component may extract the first defect feature of the defect of undetermined category from the first illumination image information, extract the second defect feature of the defect of undetermined category from the second illumination image information, call the pre-trained three-dimensional dirt defect detection model, input the first defect feature and the second defect feature into the three-dimensional dirt defect detection model, perform three-dimensional dirt defect detection on the defect of undetermined category, and output the defect category of the defect of undetermined category.

[0145] In some of these embodiments, when the first illumination environment includes bright-field illumination and the second illumination environment includes a 2.5D imaging illumination environment, the first illumination image information may include bright-field image information, and the second illumination image information may include 2.5D image information. The visual defect detection component may perform three-dimensional feature extraction on the defect of undetermined category based on the bright-field image information and the 2.5D image information to obtain the three-dimensional features of the defect of undetermined category, perform three-dimensional topography fitting on the defect of undetermined category according to the three-dimensional features to obtain the three-dimensional topography of the defect of undetermined category, and when the three-dimensional topography of the defect of undetermined category meets the topography requirements of the three-dimensional dirt defect, the defect category of the defect of undetermined category may be determined to be the three-dimensional dirt defect.

[0146] In some of these embodiments, the visual defect detection component may determine the height information of the defect of undetermined category according to the three-dimensional topography, and when the height information indicates that the defect height of the defect of undetermined category is higher than the preset height threshold, it is determined that the three-dimensional topography of the defect of undetermined category meets the topography requirements of the three-dimensional dirt defect. It can be understood that the preset height threshold is a threshold parameter set in advance for determining whether a defect is a three-dimensional dirt defect.

[0147] S508. Determine the defect detection result of the current collector tray based on the defect category.

[0148] Wherein, the defect detection result is a detection result used to characterize whether the defect is a qualified defect or a non-qualified defect. By determining the defect detection result of the current collector tray, a data basis can be provided for subsequent determination of the overall qualification of the current collector tray. The qualification detection result may include that the defect detection is qualified or the defect detection is unqualified.

[0149] In some of these embodiments, when there is a non - conforming defect on the surface of the current collector plate, the qualification test result of the current collector plate can be determined as non - conforming, and the battery cell product to which the current collector plate belongs is transported to the defective product area for waiting processing.

[0150] In some embodiments, after obtaining the defect category of the defect with undetermined category, the visual defect detection component can determine the detection result of the defect with undetermined category of the current collector plate based on the defect category.

[0151] In the above - mentioned current collector plate defect detection method, the first illumination image information collected by the current collector plate under the first illumination environment at the first illumination angle is used to conduct a preliminary defect detection on the current collector plate. When it is determined that there is a defect with undetermined category in the current collector plate, it indicates that there are defects in the current collector plate that cannot be distinguished using only the first illumination image at this time. It is necessary to use the second illumination image information of the current collector plate for auxiliary identification to determine the defect category of the defect with undetermined category. Continue to provide the current collector plate with a second illumination environment at the second illumination angle, and obtain the second illumination image information obtained by image - collecting the current collector plate under the second illumination environment. Since the first illumination angle is higher than the second illumination angle of the second illumination environment, the imaging of the three - dimensional dirt defect in the first illumination environment and the second illumination environment will be different. The three - dimensional dirt defect detection is carried out on the defect with undetermined category according to the first illumination image information and the second illumination image information to determine the defect category of the defect with undetermined category, and the defect detection result of the current collector plate is determined based on the defect category. The above - mentioned method only needs to provide the current collector plate with the first illumination environment and the second illumination environment with different illumination angles, and add one image - collecting. It can utilize the imaging difference of the current collector plate in the first illumination environment and the second illumination environment to highlight the morphological characteristics of the defect, achieving the effect of accurately identifying three - dimensional dirt defects and non - three - dimensional dirt defects. While effectively improving the defect detection accuracy of the current collector plate and thus improving the battery production efficiency, it can also effectively reduce the detection cost of the accurate detection of the current collector plate defects.

[0152] The morphology of welding slag is similar to that of dirt, and when the size is small, it is more difficult to distinguish between the two. By conducting three - dimensional dirt defect detection on the defect, the three - dimensional dirt defects and planar dirt defects in the current collector plate defects can be accurately identified. The following will illustrate how to determine the defect category of the defect with undetermined category through several embodiments.

[0153] In some embodiments, the defect category includes three - dimensional dirt defects and planar dirt defects, the first illumination image information includes bright - field image information, and the second illumination image information includes dark - field image information. As Figure 6 shown, S506, according to the first illumination image information and the second illumination image information, conduct three - dimensional dirt defect detection on the defect with undetermined category to determine the defect category of the defect with undetermined category, including:

[0154] S602. Extract the gray - level features of the bright - field image information and the dark - field image information respectively to obtain the bright - field gray - level features and the dark - field gray - level features of the defect with undetermined category.

[0155] Among them, gray - level feature extraction refers to the operation of extracting the gray - level features corresponding to the defect with undetermined category from the image information. The bright - field gray - level features are the feature information used to characterize the imaging situation of the defect with undetermined category under the bright - field illumination environment, which can reflect the reflection situation of the defect with undetermined category to the bright - field illumination light under the bright - field illumination environment, and further reflect the planar shape of the defect with undetermined category.

[0156] The dark - field gray - level features are the feature information used to characterize the imaging situation of the defect with undetermined category under the dark - field illumination environment, which can reflect the scattering situation of the defect with undetermined category to the dark - field illumination light under the dark - field illumination environment, and further reflect the three - dimensional shape of the defect with undetermined category.

[0157] In some embodiments, the visual defect detection component can extract the gray - level features of the bright - field image information and the dark - field image information respectively to obtain the bright - field gray - level features and the dark - field gray - level features of the defect with undetermined category.

[0158] In some of these embodiments, a gray - level extraction model is set in the visual defect detection component. The visual defect detection component first extracts the bright - field defect information and the dark - field defect information of the defect with undetermined category from the bright - field image information and the dark - field image information respectively, and then calls the gray - level extraction model, and inputs the bright - field defect information and the dark - field defect information into the gray - level extraction model respectively, so as to obtain the bright - field gray - level features and the dark - field gray - level features of the defect with undetermined category output by the gray - level extraction model.

[0159] In some of these embodiments, the visual defect detection component can extract the bright - field gray - level values of each pixel point corresponding to the defect with undetermined category from the bright - field image information, and then take the average value of each bright - field gray - level value to obtain the bright - field gray - level features of the defect with undetermined category. Extract the dark - field gray - level values of each pixel point corresponding to the defect with undetermined category from the dark - field image information, and then take the average value of each dark - field gray - level value to obtain the dark - field gray - level features of the defect with undetermined category.

[0160] In some of these embodiments, before performing gray - level feature extraction, the visual defect detection component can pre - process the bright - field image information and the dark - field image information, such as performing noise reduction processing and image size adjustment processing, so as to improve the accuracy of gray - level feature extraction.

[0161] S604. When the feature difference degree between the bright - field gray - level features and the dark - field gray - level features is greater than the three - dimensional dirt difference degree threshold, determine that the defect category of the defect with undetermined category is a three - dimensional dirt defect.

[0162] Among them, the feature difference degree can reflect the imaging difference of the defect to be determined in two lighting environments. The three-dimensional dirt difference degree threshold is a preset judgment threshold for determining whether the defect to be determined is a three-dimensional dirt defect. The three-dimensional dirt difference degree threshold can be determined by designers according to experimental data or empirical data.

[0163] Among them, the three-dimensional dirt defect refers to a defect of the current collector plate with a three-dimensional shape, such as welding slag or dust.

[0164] It can be understood that in the bright-field illumination environment, both the three-dimensional dirt defect and the planar dirt defect will reflect the bright-field light. Therefore, both the three-dimensional dirt defect and the planar dirt defect appear black in the bright-field illumination environment. Due to its three-dimensionality, the three-dimensional dirt defect will scatter low-angle light. Therefore, in the dark-field illumination environment, the three-dimensional dirt defect will appear white, while the planar dirt defect will still appear black. Therefore, the defect category of the defect to be determined can be determined by the imaging difference of the defect to be determined in two lighting environments.

[0165] In some embodiments, the vision defect detection component can determine the feature difference degree between the bright-field gray feature and the dark-field gray feature, and compare the feature difference degree with the preset three-dimensional dirt difference degree threshold. When the feature difference degree is greater than the three-dimensional dirt difference degree threshold, it indicates that the imaging difference of the defect to be determined in two lighting environments is large, which conforms to the imaging habit of the three-dimensional dirt defect, and the defect category of the defect to be determined can be determined as the three-dimensional dirt defect.

[0166] In some of these embodiments, the bright-field gray feature and the dark-field gray feature can be the bright-field gray value and the dark-field gray value, and the feature difference value between the two is the absolute value of the difference between the bright-field gray value and the dark-field gray value.

[0167] In some of these embodiments, the bright-field gray feature and the dark-field gray feature can be the bright-field gray feature vector and the dark-field gray feature vector, and the feature difference value between the two can be determined by the vector distance of the feature vectors.

[0168] S606. When the feature difference degree is less than or equal to the three-dimensional dirt difference degree threshold, determine that the defect category of the defect to be determined is a planar dirt defect.

[0169] Among them, the planar dirt defect refers to a defect of the current collector plate that does not have a three-dimensional shape but only has a planar two-dimensional shape, such as oil stains on the surface of the current collector plate.

[0170] In some embodiments, when the visual defect detection component determines that the feature difference degree between the bright-field gray-scale feature and the dark-field gray-scale feature is less than or equal to the three-dimensional dirt difference degree threshold, it indicates that the imaging difference of the defect of undetermined category in the two lighting environments is small, which conforms to the imaging habit of the planar dirt defect, and the defect category of the defect of undetermined category can be determined as the planar dirt defect.

[0171] In the above embodiments, by extracting the bright-field gray-scale feature and the dark-field gray-scale feature of the defect of undetermined category, the imaging difference of the defect of undetermined category in the two illumination modes can be accurately and intuitively reflected, and then the defect type of the defect of undetermined category can be quickly judged according to the imaging difference, effectively improving the defect category determination efficiency and recognition accuracy of the defect of undetermined category.

[0172] In some embodiments, as Figure 7 shown in S602, gray-scale feature extraction is respectively performed on the bright-field image information and the dark-field image information to obtain the bright-field gray-scale feature and the dark-field gray-scale feature of the defect of undetermined category, including:

[0173] S702, according to the first defect contour of the defect of undetermined category, gray-scale feature extraction is performed on the bright-field image information to obtain the bright-field gray-scale feature of the defect of undetermined category.

[0174] Among them, the first defect contour of the defect of undetermined category refers to the defect area boundary of the defect of undetermined category in the bright-field image, which is a polygon or a closed curve. It can be understood that the first defect contour of the defect of undetermined category can be identified and determined during the preliminary defect detection of the current collector plate. That is, the visual defect detection component can obtain the first defect contour of the defect of undetermined category from the preliminary defect detection result. For example, the coordinates of each boundary point of the defect of undetermined category are obtained from the preliminary defect detection result, and the first defect contour of the defect of undetermined category is determined.

[0175] In some embodiments, the visual defect detection component can divide the bright-field defect image information of the defect of undetermined category from the bright-field image information according to the first defect contour of the defect of undetermined category, and then perform gray-scale feature extraction on the bright-field defect image information to obtain the bright-field gray-scale feature of the defect of undetermined category.

[0176] S704, using the first defect contour as the detection region of interest, perform region mapping on the dark-field image information to obtain the second defect contour of the defect of undetermined category.

[0177] Among them, the detection region of interest refers to the local region in the image that needs to be detected. Region mapping refers to the process of determining the corresponding contour position of the first defect contour in the dark-field image according to the first defect contour in the bright-field image. It can be understood that region mapping can be implemented by means of coordinate projection.

[0178] Among them, the second defect contour refers to the boundary of the defect area of the defect to be determined in the dark-field image. Similarly, the second defect contour is also a polygon or a closed curve.

[0179] In some embodiments, the visual defect detection component can define a region of interest (ROI) for detection according to the first defect contour, and map the boundary coordinates of the detection region of interest to the dark-field image coordinate system through a preset bright-dark image transformation matrix to obtain the second defect contour of the defect to be determined.

[0180] S706. Extract the gray-scale features of the dark-field image information based on the second defect contour to obtain the dark-field gray-scale features of the defect to be determined.

[0181] In some embodiments, the visual defect detection component can divide the dark-field defect image information of the defect to be determined from the dark-field image information based on the second defect contour, and then extract the gray-scale features of the dark-field defect image information to obtain the dark-field gray-scale features of the defect to be determined.

[0182] In the above embodiments, by using the first defect contour as the detection region of interest, performing region mapping on the dark-field image information to obtain the second defect contour, and then extracting the gray-scale features of the image information according to the first defect contour and the second defect contour respectively, the data processing amount during gray-scale feature extraction can be effectively reduced, and the gray-scale feature extraction efficiency can be improved. At the same time, through the way of region mapping, the feature matching degree between the bright-field gray-scale features and the dark-field gray-scale features can also be improved, thereby improving the accuracy of defect category determination.

[0183] When determining the qualification of the three-dimensional dirt defect, in order to reduce the risk of over-detection, it is necessary to consider the size compliance of the three-dimensional dirt defect. Therefore, in some embodiments, S508. Determine the defect detection result of the current collector tray based on the defect category, including: in the case where the defect category is a three-dimensional dirt defect, determine the second defect size of the three-dimensional dirt defect according to the second defect contour. When the second defect size is less than the first qualified size threshold set for the three-dimensional dirt defect, it is determined that the three-dimensional dirt defect detection of the current collector tray is qualified.

[0184] Among them, the defect size is an index parameter used to quantify the geometric features of the defect, which can reflect the projected area of the defect in the two-dimensional plane. The second defect size is the defect size determined according to the second defect contour. It can be understood that the second illumination image, such as the dark-field image, has three-dimensional morphological sensitivity. Therefore, the contrast of the three-dimensional dirt defect in the second illumination image will be higher than that of the three-dimensional dirt defect in the first illumination image, and the defect size in the second illumination image is also closer to the actual size of the defect under the detection of the metallographic microscope.

[0185] Among them, the first qualified size threshold set for three-dimensional dirt defects is a preset threshold parameter used to determine whether a three-dimensional dirt defect is a qualified defect. When the defect size of the three-dimensional dirt defect is smaller than the first qualified size threshold, it indicates that although there is a three-dimensional dirt defect on the surface of the current current collector plate, this three-dimensional dirt defect is an inevitable production defect during the production process and will not affect the operation reliability of the battery. This three-dimensional dirt defect can be determined as a qualified defect. On the contrary, when the defect size of the three-dimensional dirt defect is greater than or equal to the first qualified size threshold, it indicates that the three-dimensional dirt defect existing on the surface of the current collector plate at this time will affect the operation reliability of the battery, and this three-dimensional dirt defect can be determined as an unqualified defect. It can be understood that the first qualified size threshold can be determined by the designer according to actual production requirements. For example, if the designer determines that a three-dimensional dirt defect with a defect size less than 0.1 mm is a qualified defect according to production documents such as production manuals, then 0.1 mm can be determined as the first qualified size threshold set for three-dimensional dirt defects.

[0186] In some embodiments, when the visual defect detection component determines that the defect of undetermined category is a three-dimensional dirt defect, it can determine the second defect size of the three-dimensional dirt defect according to the second defect contour, and compare the second defect size with the first qualified size threshold set in advance for the three-dimensional dirt defect. When the second defect size is smaller than the first qualified size threshold, it is determined that this three-dimensional dirt defect is a qualified defect, and the detection of the three-dimensional dirt defect of the current collector plate is qualified.

[0187] In the above embodiments, by determining the defect size of the three-dimensional dirt defect through the second defect contour, the determined defect size can be closer to the true size of the three-dimensional dirt defect, effectively improving the detection accuracy of the qualification detection of the three-dimensional dirt defect. At the same time, performing size compliance rejudgment on the three-dimensional dirt defect can also effectively reduce the risk of over-detection of defects, improve the production efficiency of the battery, and reduce the production cost of the battery.

[0188] During the process of defect detection of the current collector plate, preliminary defect detection is an effective means for quickly locating defects and detecting obviously unqualified defects. The following will illustrate how to perform preliminary defect detection of the current collector plate through several embodiments.

[0189] In some embodiments, as Figure 8 shown, the method for detecting defects of the current collector plate further includes the following steps:

[0190] S802, when it is determined based on the first illumination image information that there are defects to be detected on the current collector plate, extract the first defect contour of the defects to be detected.

[0191] In some embodiments, the visual defect detection component invokes a pre-trained first defect recognition model, inputs the first illumination image information into the first defect recognition model, performs defect recognition on the first illumination image, and obtains an initial defect detection result of the current collector tray. When the initial defect detection result indicates that there is a defect to be detected in the current collector tray, the first defect contour of the defect to be detected is extracted from the first illumination image information.

[0192] In some of these embodiments, the visual defect detection component can enhance the defect boundary contrast of the defect to be detected based on the first illumination image information, and extract the first defect contour of the defect to be detected from the first illumination image through a segmentation algorithm.

[0193] S804. Determine the first defect size of the defect to be detected according to the first defect contour.

[0194] Wherein, the first defect size is the defect size determined according to the first defect contour.

[0195] In some embodiments, the visual defect detection component can determine the first defect size of the defect to be detected according to the first defect contour.

[0196] In some of these embodiments, the visual defect detection component can determine the minimum bounding rectangle of the contour according to the defect contour, and determine the rectangular area of the minimum bounding rectangle as the defect size.

[0197] In some of these embodiments, the visual defect detection component can, through the pixel counting method, count the total number of pixels in the defect contour, and determine the product of the total number of pixels and the actual pixel size as the defect size.

[0198] In some of these embodiments, the visual defect detection component can, through Green's formula, calculate the defect contour area based on the vertex coordinates of the defect contour to obtain the defect size.

[0199] S806. When the first defect size is less than the second qualified size threshold set for planar dirt defects and greater than or equal to the first qualified size threshold, determine the contour position of the first defect contour.

[0200] Among them, the second qualified size threshold set for planar dirt defects is a preset threshold parameter used to determine whether a defect to be detected is an obviously unqualified defect. It can be understood that the second qualified size threshold can be determined by designers according to actual production requirements. For example, if designers determine that planar dirt defects with a defect size less than 0.5 mm are qualified defects according to production documents such as production manuals, then 0.5 mm can be determined as the second qualified size threshold set for planar dirt defects. Since the defect size of planar dirt defects is generally large, the second qualified size threshold set for planar dirt defects will be greater than the first qualified size threshold set for three-dimensional dirt defects.

[0201] When the first defect size of the defect to be detected is greater than or equal to the second qualified size threshold, it indicates that regardless of whether the defect to be detected is a planar detection defect, or rather, regardless of what kind of defect the defect to be detected is, its size is too large and will affect the stable operation of the battery. Therefore, the defect to be detected can be directly determined as an unqualified defect.

[0202] When the first defect size of the defect to be detected is less than the first qualified size threshold. It indicates that regardless of whether the defect to be detected is a three-dimensional detection defect, or rather, regardless of what kind of defect the defect to be detected is, since its size is small, it will not affect the stable operation of the battery, and the defect to be detected can be directly determined as a qualified defect.

[0203] If neither of the above two situations is satisfied, that is, the first defect size of the defect to be detected is less than the second qualified size threshold and greater than or equal to the first qualified size threshold, it indicates that the defect to be detected is not an obviously unqualified defect nor an obviously qualified defect, and it is necessary to continue to perform defect detection on the defect to be detected to determine its qualification detection result.

[0204] Therefore, in some embodiments, the visual defect detection component compares the first defect size of the defect to be detected with the first qualified size threshold and the second qualified size threshold respectively. When the first defect size is less than the second qualified size threshold set for planar dirt defects and greater than or equal to the first qualified size threshold, the contour position of the first defect contour is determined.

[0205] S808, when it is determined that the defect to be detected needs to be detected for three-dimensional dirt defects based on the contour position, the defect to be detected is determined as a defect of undetermined category.

[0206] In some embodiments, the visual defect detection component can determine whether the defect to be detected needs to be detected for three-dimensional dirt defects based on the contour position. Only when the defect to be detected needs to be detected for three-dimensional dirt defects, the defect to be detected is determined as a defect of undetermined category.

[0207] In the above embodiments, by comparing the first defect size of the defect to be detected with the first qualified size threshold and the second qualified size threshold respectively, it is possible to quickly determine whether the defect to be detected is an obviously unqualified defect or an obviously qualified defect. Only when it is determined that the defect to be detected is not an obviously unqualified defect or an obviously qualified defect, will the contour position of the defect to be detected be further followed up to determine whether the defect to be detected needs to be detected for three-dimensional dirt defects, effectively improving the detection efficiency of the current collector plate defect detection.

[0208] In some embodiments, as Figure 9 shown, the current collector plate defect detection method further includes the following steps:

[0209] S902, for the weld bead area of the current collector plate, perform region recognition on the first illumination image information to obtain the region contour position of the weld bead area.

[0210] Among them, the weld bead area of the current collector plate is the continuous molten pool track formed on the surface of the current collector plate by laser welding. The region contour position of the weld bead area is the information data used to characterize the region position of the weld bead area in the first illumination image. For example, the region contour position may include the position coordinates of each region contour boundary point that makes up the weld bead area.

[0211] In some embodiments, the vision defect detection component can perform region recognition on the first illumination image information for the weld bead area of the current collector plate to obtain the region contour position of the weld bead area.

[0212] In some of these embodiments, a weld bead area recognition model is pre-configured in the vision defect detection component. By inputting the first illumination image information into the weld bead area recognition model, the region contour position of the weld bead area output by the weld bead area recognition model can be obtained.

[0213] S904, perform position matching between the contour position of the defect to be detected and the region contour position to obtain a defect position matching result.

[0214] In some embodiments, the vision defect detection component can perform position matching between the contour position of the defect to be detected and the region contour position to obtain a defect position matching result.

[0215] In some of these embodiments, the defect position matching result may include matching or not matching. Among them, matching means that the defect to be detected is located within the weld bead area, and not matching means that the defect to be detected is not located within the weld bead area.

[0216] In some of these embodiments, a pre-trained position matching model is set in the vision defect detection component. By inputting the contour position of the defect to be detected and the region contour position into the position matching model, the defect position matching result can be obtained.

[0217] S906: When the defect position matching result indicates that the defect to be detected is not located in the weld area, determine that the defect to be detected requires three-dimensional dirt defect detection.

[0218] In some embodiments, when the defect position matching result indicates that the defect to be detected is not located in the weld area, it means that the defect to be detected is located in the plane area of the collecting plate. At this time, it cannot be detected according to the defect detection rules in the weld area, but a three-dimensional dirt defect detection is required. Therefore, the visual defect detection component determines that the defect to be detected requires a three-dimensional dirt defect detection.

[0219] In the above embodiment, by matching the contour position of the defect to be detected with the regional contour position of the weld area, it can be quickly determined whether the defect to be detected is a weld defect. If it is determined that it is not a weld defect, subsequent three-dimensional contamination defect detection can be performed on it, which effectively improves the detection efficiency and detection accuracy of the collecting plate defect detection.

[0220] In some other embodiments, the current collecting plate defect detection method further includes: when the defect position matching result indicates that the defect to be detected is located in the weld area, determining that the defect to be detected is a pinhole burst defect. When the first defect size is less than a third qualified size threshold set for the pinhole burst defect, determining that the pinhole burst defect detection of the current collecting plate is qualified; the third qualified size threshold is greater than the first qualified size threshold and less than the second qualified size threshold.

[0221] Among them, the pinhole burst defect is a collector plate defect caused by tiny voids or local bulges and ruptures in the collector plate weld area. Due to the complex welding conditions in the weld area, for example, the weld surface may be wavy due to excessive molten pool or solder accumulation. Therefore, when performing defect detection on the weld area, there is no need to subdivide the defect categories. All defects in the weld area are directly identified as pinhole burst defects, and the third qualified size threshold set for pinhole burst defects is used for those qualification tests.

[0222] Among them, the third qualified size threshold set for the pinhole burst defect is a preset threshold parameter for judging whether the pinhole burst defect is an unqualified defect. It can be understood that the third qualified size threshold can be determined by the designer according to the actual survival needs. For example, the designer determines that the pinhole burst defect with a defect size less than 0.2mm is a qualified defect according to the production manual and other production documents, and then 0.2mm can be determined as the third qualified size threshold set for the pinhole burst defect. Since the pinhole burst defect is generally smaller than the large-sized planar dirt defect and larger than the small-sized three-dimensional dirt defect, the third qualified size threshold set for the pinhole burst defect will be greater than the first qualified size threshold set for the three-dimensional dirt defect, and less than the second qualified size threshold set for the planar dirt defect.

[0223] When the first defect size of the pinhole explosion defect is greater than or equal to the third qualified size threshold, it indicates that the size of the pinhole explosion defect is too large, which will affect the stable operation of the battery, and the pinhole explosion defect can be determined as a non-conforming defect. On the contrary, when the first defect size of the pinhole explosion defect is less than the third qualified size threshold, it indicates that the size of the pinhole explosion defect will not affect the stable operation of the battery, and the pinhole explosion defect can be determined as a non-conforming defect.

[0224] In some embodiments, when the visual defect detection component determines that the defect position matching result indicates that the defect to be detected is located in the weld area, it can determine that the defect to be detected is a pinhole explosion defect. Compare the first defect size of the pinhole explosion defect with the third qualified size threshold set for the pinhole explosion defect. When the first defect size of the pinhole explosion defect is less than the third qualified size threshold, determine that the pinhole explosion defect is a qualified defect, and the pinhole explosion defect detection of the current collector plate is qualified.

[0225] In the above embodiments, for the pinhole explosion defect located in the weld area, using the corresponding third qualified size threshold to perform the qualification detection on it can make the defect qualification detection process have a higher matching degree with the actual defect category, and effectively improve the detection accuracy of the current collector plate defect detection.

[0226] In order to further improve the detection accuracy of the current collector plate defect detection, in some embodiments, S902, for the weld area of the current collector plate, perform region recognition on the first illumination image information to obtain the region contour position of the weld area, including: using a preset region of interest to frame the initial region information including the weld area from the first illumination image information. Input the initial region information into a preset weld width detection model, and intercept and correct the initial region information based on the weld width of the weld area to obtain the region contour position of the weld area.

[0227] Among them, the preset region of interest is a region extraction frame set in advance. The size of the preset region of interest can be set by the designer in advance according to the actual situation of the weld area. It can be understood that the size of the preset region of interest should be larger than the region size of the weld area. Through the preset region of interest, the initial region information including the weld area can be quickly framed from the first illumination image information. The initial region information is the image sub-region information framed by the preset ROI, including the region information of the weld area and part of the current collector plate plane area.

[0228] Among them, the weld width detection model is a model tool for quantitatively positioning the weld width of the current collector plate, which can be trained by the designer in advance using historical image information. The weld width is the vertical distance between the edges on both sides of the weld center line.

[0229] In some embodiments, the visual defect detection component may use a preset region of interest to extract initial region information including the weld bead region from the total frame of the first illumination image represented by the first illumination image information. Subsequently, a pre-trained weld bead width detection model is called, and the initial region information is input into the weld bead width detection model. The weld bead width detection model will identify the weld bead width of the weld bead region and intercept and correct the initial region information based on the weld bead width of the weld bead region to obtain the region contour position of the weld bead region.

[0230] In some of these embodiments, the visual defect detection component may shrink the boundary of the preset region of interest based on the weld bead width of the weld bead region, intercept and correct the weld bead region image information that matches the actual weld bead region from the initial region information, and then obtain the region contour position of the weld bead region according to the weld bead region image information.

[0231] In the above embodiments, a relatively large range of the weld bead region is framed from the first illumination image through the preset region of interest, and then the relatively large range of the weld bead region is intercepted and corrected by the identified weld bead width to obtain the region contour position of the weld bead region, which can effectively improve the recognition accuracy of the region contour position of the weld bead region and provide an accurate data basis for the subsequent judgment of whether the defect to be detected is within the weld bead region.

[0232] In some embodiments, the contour position of the defect to be detected includes the defect contour position coordinates of the defect to be detected, and the region contour position includes the region contour position coordinates of the weld bead region. As Figure 10 shown, S904, perform position matching between the contour position of the defect to be detected and the region contour position to obtain a defect position matching result, including:

[0233] S1002, perform region mapping on the defect contour position coordinates of the defect to be detected and the region contour position coordinates of the weld bead region to determine the overlapping region area between the defect contour of the defect to be detected and the region contour of the weld bead region.

[0234] Among them, the defect contour position coordinates are a set of defect boundary point coordinates extracted by an image processing algorithm, which can characterize the shape, area, and position of the defect contour of the defect to be detected. The region contour position coordinates are a set of weld bead region boundary coordinates extracted by an image processing algorithm, which can characterize the shape, area, and position of the actual weld bead contour.

[0235] Region mapping refers to the mapping operation of converting the position coordinates of the defect contour of the defect to be detected and the region contour of the weld bead region to the same coordinate system to establish a spatial position correspondence relationship. By performing region mapping on the defect contour position coordinates of the defect to be detected and the region contour position coordinates of the weld bead region, the overlapping region between the defect contour of the defect to be detected and the region contour of the weld bead region can be intuitively and accurately determined, and then the overlapping region area between the two can be calculated.

[0236] Among them, the overlapping area is the geometric area of the overlapping part in space between the defect contour and the bead area contour.

[0237] In some embodiments, the vision detection component can perform area mapping on the defect contour position coordinates of the defect to be detected and the area contour position coordinates of the bead area, so as to determine the overlapping area between the defect contour of the defect to be detected and the area contour of the bead area, and then determine the overlapping area through an area calculation function or model.

[0238] S1004, determine the area ratio between the overlapping area and the contour area of the defect contour.

[0239] Among them, the contour area of the defect contour is the complete geometric area representing the defect coverage range of the defect to be detected. The area ratio between the overlapping area and the contour area refers to the percentage of the overlapping area between the defect contour and the bead area in the total defect area, and can represent the spatial intersection state of the defect to be detected in the bead area, such as inclusion, intersection or contact state.

[0240] In some embodiments, the vision detection component can calculate the contour area of the defect contour to be detected according to the defect contour position coordinates of the defect to be detected, and then calculate the area ratio between the overlapping area and the contour area of the defect contour.

[0241] S1006, when the area ratio is greater than the preset area ratio threshold, determine that the defect position matching result indicates that the defect to be detected is located in the bead area.

[0242] Among them, the preset area ratio threshold is a preset judgment threshold parameter for judging whether the defect to be detected is located in the bead area, and can be determined by the designer according to the actual detection accuracy. For example, in the case of high detection accuracy, 95% can be set as the preset area ratio threshold, that is, only when 95% of the defect to be detected is in the bead area, it is determined that the defect to be detected is located in the bead area. Another example is that in the case of low detection accuracy, 70% can be set as the preset area ratio threshold, that is, only when 70% of the defect to be detected is in the bead area, it is determined that the defect to be detected is located in the bead area.

[0243] In some embodiments, the vision detection component can compare the area ratio between the overlapping area and the contour area of the defect contour with the preset area ratio threshold. When the area ratio is greater than the preset area ratio threshold, it is determined that the defect position matching result indicates that the defect to be detected is located in the bead area. When the area ratio is less than or equal to the preset area ratio threshold, it is determined that the defect position matching result indicates that the defect to be detected is not located in the bead area.

[0244] In the above embodiments, by using a preset area ratio threshold, the area ratio of the overlapping area obtained by region mapping the defect contour position coordinates and the region contour position coordinates to the contour area is compared with the preset area ratio threshold, so as to quickly and accurately determine whether the defect to be detected is located in the weld area, improving the accuracy and detection efficiency of the current collector plate defect detection. The above embodiments have described in detail how to perform the preliminary defect detection of the current collector plate. Since during the preliminary defect detection process, a threshold judgment has been made on whether the defect size of the defect to be detected is greater than the second qualified size threshold set for planar contamination defects, in some embodiments, S508, determining the qualification detection result of the defect to be determined based on the defect category, includes: when the defect category is a planar contamination defect, determining the planar contamination defect as a qualified defect.

[0245] In some embodiments, if the defect to be detected is a defect to be determined, it can be explained that the defect size of the defect to be detected is smaller than the second qualified size threshold. On this basis, if the defect category of the defect to be determined is a planar contamination defect, it can be directly determined that the defect size of the planar contamination defect is smaller than the second qualified size threshold, and the visual defect detection component can directly determine the planar contamination defect as a qualified defect.

[0246] In the above embodiments, when the defect to be determined is a planar contamination defect, directly determining the planar contamination defect as a qualified defect can reduce the possibility that qualified defects are over-detected, resulting in an increase in defective products of the battery product, thereby improving the production efficiency of the battery product and reducing the production cost of the battery product.

[0247] In some embodiments, a method for detecting current collector plate defects is provided. Taking the case where this method is applied to the current collector plate defect detection system as shown in Figure 2 as an example for illustration, it can be understood that the current collector plate defect detection system can detect multiple cell current collector plates simultaneously. For example, it can detect 4 current collector plates simultaneously, and the technical solution of this application describes the defect detection process for any one of the current collector plates, and the steps of the defect detection process for each current collector plate are the same. The method for detecting current collector plate defects specifically includes two parts, one is the preliminary defect detection part, and the other is the defect category re-inspection part.

[0248] As Figure 11 shown, the preliminary defect detection part includes the following steps:

[0249] S1101, obtaining the bright-field image information obtained by image acquisition of the current collector plate under bright-field illumination.

[0250] Among them, when the battery cell reaches the current collector plate defect detection station, the vision defect detection component sends a bright-field light source turn-on command to the acquisition controller. In response to the bright-field light source turn-on command, the acquisition controller sends a in-place signal and the battery cell code to the coaxial light source and the bowl-shaped light source, and hard triggers to light up the light sources to construct a bright-field illumination environment for the current collector plate. Subsequently, the vision defect detection component controls the camera to take a first photo of the surface of the current collector plate to obtain the bright-field image information of the current collector plate.

[0251] S1102. Based on the bright-field image information, determine whether there are defects to be detected on the current collector plate. If not, execute S1103; if so, execute S1104.

[0252] S1103. Determine that the current collector plate is qualified for detection, and transport the battery cell to the next production station.

[0253] S1104. Extract the first defect contour of the defect to be detected, and determine the first defect size according to the first defect contour.

[0254] S1105. Determine whether the first defect size > the second qualified size threshold. If so, execute S1106; if not, execute S1107.

[0255] In some embodiments, the second qualified size threshold set for planar dirt defects may be 0.5 mm. Even if the defect to be detected is a planar dirt defect, when its defect size > 0.5 mm, it can be directly determined that the defect to be detected is a non-conforming defect.

[0256] S1106. Determine that the defect to be detected is a non-conforming defect, the current collector plate is unqualified for detection, and discharge the battery cell from the defective product transport trough.

[0257] Among them, the defective product transport trough is the NG trough in the production line. When there is one non-conforming defect in the current collector plate, it can be determined as a defective product (NG).

[0258] S1107. Determine whether the first defect size < the first qualified size threshold. If so, execute S1108; if not, execute S1109.

[0259] In some embodiments, the first qualified size threshold set for three-dimensional dirt defects, such as welding slag, may be 0.1 mm. Even if the defect to be detected is a three-dimensional dirt defect, when its defect size < 0.1 mm, it can be directly determined that the defect to be detected is a qualified defect.

[0260] S1108. Determine that the defect to be detected is a qualified defect.

[0261] It should be noted that only when all the defects in the current collector plate are qualified defects can it be determined that the current collector plate is qualified for detection (OK).

[0262] S1109, determine the contour position of the first defect contour.

[0263] S1110, for the weld bead area of the current collector plate, perform area recognition on the bright-field image information to obtain the area contour position of the weld bead area.

[0264] Among them, the visual defect detection component can first use a preset ROI to frame the initial area information including the weld bead area from the bright-field image information, and then input the initial area information into a pre-set weld bead width detection model, and intercept and correct the initial area information based on the weld bead width of the weld bead area to obtain the area contour position of the weld bead area.

[0265] S1111, perform position matching between the contour position and the area contour position to obtain a defect position matching result.

[0266] S1112, determine whether the defect position matching result indicates that the defect to be detected is located in the weld bead area. If not, execute S1113; if so, execute S1114.

[0267] S1113, determine that the defect to be detected is a defect with undetermined category.

[0268] Among them, in the case where the defect position matching result indicates that the defect to be detected is not located in the weld bead area, it is determined that the defect to be detected needs to be detected for three-dimensional dirt defects.

[0269] S1114, determine whether the first defect size < the third qualified size threshold. If so, execute S1108; if not, return to execute S1106.

[0270] Among them, in the case where the defect position matching result indicates that the defect to be detected is located in the weld bead area, it is determined that the defect to be detected is a pinhole explosion defect.

[0271] In some embodiments, the third qualified size threshold set for the pinhole explosion defect may be 0.2 mm.

[0272] In the case where it is determined through preliminary defect detection that there are defects with undetermined categories in the current collector plate, defect category re-inspection can be performed on the defects with undetermined categories. The method steps of the defect category re-inspection part are as Figure 12 shown, specifically including the following steps:

[0273] S1201, obtain the dark-field image information obtained by image acquisition of the current collector plate under dark-field illumination.

[0274] Among them, when it is determined that there are defects of undetermined categories in the current collector plate, it indicates that there are defects in the current collector plate that cannot be classified using only bright-field images at this time. It is necessary to assist in identification through the dark-field image information of the current collector plate to determine the defect category of the defects of undetermined categories. The visual defect detection component sends a dark-field light source turn-on instruction to the acquisition controller. In response to the dark-field light source turn-on instruction, the acquisition controller sends the cell code to the 0° ring light and hard triggers to light up the light source to construct a dark-field illumination environment for the current collector plate. The visual defect detection component controls the camera to take a second photo of the surface of the current collector plate to obtain the dark-field image information of the current collector plate.

[0275] S1202. Extract the gray-scale features from the bright-field image information according to the first defect contour of the defect of undetermined category to obtain the bright-field gray-scale features of the defect of undetermined category.

[0276] S1203. Use the first defect contour as the detection region of interest, perform region mapping on the dark-field image information, and obtain the second defect contour of the defect of undetermined category.

[0277] S1204. Extract the gray-scale features from the dark-field image information based on the second defect contour to obtain the dark-field gray-scale features of the defect of undetermined category.

[0278] S1205. Calculate the feature difference degree between the bright-field gray-scale features and the dark-field gray-scale features.

[0279] S1206. Determine whether the feature difference degree is greater than the three-dimensional dirt difference degree threshold. If not, execute S1207; if so, execute S1208 - S1210.

[0280] S1207. Determine that the defect category of the defect of undetermined category is a planar dirt defect and it is a qualified defect.

[0281] S1208. Determine that the defect category of the defect of undetermined category is a three-dimensional dirt defect, and determine the second defect size of the three-dimensional dirt defect according to the second defect contour.

[0282] S1209. Determine whether the second defect size < the first qualified size threshold. If so, execute S1210; if not, execute S1211.

[0283] S1210. Determine that the three-dimensional dirt defect is a qualified defect.

[0284] S1211. Determine that the three-dimensional dirt defect is an unqualified defect, the current collector plate inspection is unqualified, and the cell is discharged from the defective product transport trough.

[0285] The above-mentioned current collector plate defect detection method, on the one hand, uses a dual optical field composite detection method to achieve the effect of accurately identifying three-dimensional dirt and planar dirt that are difficult to identify and locate in a single optical field, which can effectively reduce the risk of misjudgment. Compared with the traditional technical solution, only a low-angle annular light is introduced, and the number of photo shootings is increased to 2 times, achieving low cost, simplicity, and high efficiency. And in addition to detecting three-dimensional dirt such as welding slag, this vision solution also needs to detect items such as weld beads. The combination of bright and dark field solutions can provide better imaging effects for each detection item. On the other hand, different-sized particles in the plane of the current collector plate and in the weld beads are classified, the detection order is optimized, and the amount of information processing is reduced. The position of the welding slag is identified using the bright field, and the size of the welding slag is calculated using the dark field, making the detection more accurate and rapid.

[0286] It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are sequentially shown according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0287] Based on the same inventive concept, the embodiments of the present application also provide a current collector plate defect detection device for implementing the above-mentioned current collector plate defect detection method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the current collector plate defect detection device provided below can refer to the limitations on the current collector plate defect detection method in the above text, and will not be repeated here.

[0288] In some embodiments, as Figure 13 shown, a current collector plate defect detection device 1300 is provided, including: a first illumination information acquisition module 1301, a second illumination information acquisition module 1302, a defect category determination module 1303, and a defect detection module 1304, where:

[0289] The first illumination information acquisition module 1301 is used to acquire first illumination image information obtained by image acquisition of the current collector plate in a first illumination environment.

[0290] The second illumination information acquisition module 1302 is configured to acquire second illumination image information obtained by image acquisition of the current collector tray in a second illumination environment when initially detecting defects of the current collector tray based on the first illumination image information and determining that there are defects of undetermined categories in the current collector tray; the first illumination angle of the first illumination environment is higher than the second illumination angle of the second illumination environment. The defect category determination module 1303 is configured to perform three-dimensional dirt defect detection on the defects of undetermined categories based on the first illumination image information and the second illumination image information to determine the defect categories of the defects of undetermined categories.

[0291] The defect detection module 1304 is configured to determine the qualification detection result of the defects of undetermined categories based on the defect categories.

[0292] In some embodiments, the defect categories include three-dimensional dirt defects and planar dirt defects, the first illumination image information includes bright-field image information, and the second illumination image information includes dark-field image information; the defect category determination module 1303 is configured to: respectively extract gray-scale features from the bright-field image information and the dark-field image information to obtain the bright-field gray-scale features and the dark-field gray-scale features of the defects of undetermined categories; when the feature difference degree between the bright-field gray-scale features and the dark-field gray-scale features is greater than the three-dimensional dirt difference degree threshold, determine that the defect category of the defects of undetermined categories is three-dimensional dirt defects; when the feature difference degree is less than or equal to the three-dimensional dirt difference degree threshold, determine that the defect category of the defects of undetermined categories is planar dirt defects.

[0293] In some embodiments, the defect category determination module 1303 is configured to: extract gray-scale features from the bright-field image information according to the first defect contour of the defects of undetermined categories to obtain the bright-field gray-scale features of the defects of undetermined categories; use the first defect contour as the detection region of interest to perform region mapping on the dark-field image information to obtain the second defect contour of the defects of undetermined categories; extract gray-scale features from the dark-field image information based on the second defect contour to obtain the dark-field gray-scale features of the defects of undetermined categories.

[0294] In some embodiments, the defect detection module 1304 is configured to: when the defect category is three-dimensional dirt defects, determine the second defect size of the three-dimensional dirt defects according to the second defect contour of the defects of undetermined categories in the second illumination image information; when the second defect size is less than the first qualified size threshold set for the three-dimensional dirt defects, determine that the three-dimensional dirt defects are qualified defects.

[0295] In some embodiments, the current collector tray defect detection device 1300 further includes:

[0296] The defect contour extraction module is configured to extract the first defect contour of the to-be-detected defects when determining that there are to-be-detected defects in the current collector tray based on the first illumination image information.

[0297] The first defect size determination module is configured to determine the first defect size of the defect to be detected according to the first defect contour.

[0298] The contour position determination module is configured to determine the contour position of the first defect contour when the first defect size is less than the second qualified size threshold set for planar dirt defects and greater than or equal to the first qualified size threshold; the second qualified size threshold is greater than the first qualified size threshold.

[0299] The defect of undetermined category determination module is configured to determine the defect to be detected as a defect of undetermined category when it is determined based on the contour position that the defect to be detected needs to be detected for three-dimensional dirt defects.

[0300] In some embodiments, the current collector plate defect detection device 1300 further includes:

[0301] The area contour position recognition module is configured to perform area recognition on the first illumination image information for the weld bead area of the current collector plate to obtain the area contour position of the weld bead area.

[0302] The position matching module is configured to perform position matching between the contour position of the defect to be detected and the area contour position to obtain a defect position matching result.

[0303] The result analysis module is configured to determine that the defect to be detected needs to be detected for three-dimensional dirt defects when the defect position matching result indicates that the defect to be detected is not located in the weld bead area.

[0304] In some embodiments, the current collector plate defect detection device 1300 further includes:

[0305] The pinhole explosion defect determination module is configured to determine the defect to be detected as a pinhole explosion defect when the defect position matching result indicates that the defect to be detected is located in the weld bead area.

[0306] The size comparison module is configured to determine that the pinhole explosion defect is a qualified defect when the first defect size is less than the third qualified size threshold set for the pinhole explosion defect; the third qualified size threshold is greater than the first qualified size threshold and less than the second qualified size threshold.

[0307] In some embodiments, the area contour position recognition module is configured to: use a preset region of interest to frame the initial region information including the weld bead area from the first illumination image information. Input the initial region information into a pre-set weld bead width detection model, and intercept and correct the initial region information based on the weld bead width of the weld bead area to obtain the area contour position of the weld bead area.

[0308] In some embodiments, the defect detection module 1304 is configured to: determine that the planar dirt defect is a qualified defect when the defect category is a planar dirt defect.

[0309] Each module in the above current collector tray defect detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0310] In some embodiments, a computer device is provided. The computer device can be a vision defect detection component, and its internal structure diagram can be as Figure 14 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for detecting defects in a current collector tray. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0311] Those skilled in the art can understand that Figure 14 the structure shown in

[0312] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0313] In some embodiments, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the specific steps of the above-described embodiment of the method for detecting defects in a current collector tray.

[0314] In some embodiments, a computer program product is provided, including a computer program which, when executed by a processor, implements the specific steps of the above-described embodiments of the method for detecting defects in the current collecting plate.

[0315] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties. Moreover, the acquisition, storage, processing, transmission, etc. of the data all comply with the relevant provisions of laws and regulations.

[0316] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0317] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0318] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for detecting defects of a current collecting plate, characterized in that The method includes: Obtaining first illumination image information obtained by collecting an image of the current collector tray under a first illumination environment; When initially detecting defects of the current collector tray based on the first illumination image information and determining that there are defects of undetermined category in the current collector tray, obtaining second illumination image information obtained by collecting an image of the current collector tray under a second illumination environment; the first illumination angle of the first illumination environment is higher than the second illumination angle of the second illumination environment; the defects of undetermined category refer to defects whose categories cannot be distinguished by using only the first illumination image information; Performing three-dimensional dirt defect detection on the defects of undetermined category according to the first illumination image information and the second illumination image information to determine the defect category of the defects of undetermined category; the imaging of three-dimensional dirt defects is different in the first illumination environment and the second illumination environment; Determining the defect detection result of the current collector tray based on the defect category.

2. The method according to claim 1, wherein The determining the defect detection result of the current collector tray based on the defect category includes: When the defect category is a three-dimensional dirt defect, determining the second defect size of the three-dimensional dirt defect according to the second defect contour of the defect of undetermined category in the second illumination image information; When the second defect size is less than the first qualified size threshold set for three-dimensional dirt defects, determining that the detection of three-dimensional dirt defects of the current collector tray is qualified.

3. The method according to claim 1 or 2, characterized in that, The method further includes: When it is determined based on the first illumination image information that there are defects to be detected in the current collector tray, extracting the first defect contour of the defects to be detected; Determining the first defect size of the defects to be detected according to the first defect contour; When the first defect size is less than the second qualified size threshold set for planar dirt defects and greater than or equal to the first qualified size threshold, determining the contour position of the first defect contour; the second qualified size threshold is greater than the first qualified size threshold; When it is determined based on the contour position that the defects to be detected need to be subjected to three-dimensional dirt defect detection, determining the defects to be detected as defects of undetermined category.

4. The method according to claim 3, wherein The method further includes: Performing region recognition on the first illumination image information for the weld bead region of the current collector tray to obtain the region contour position of the weld bead region; Performing position matching between the contour position of the defects to be detected and the region contour position to obtain a defect position matching result; When the defect position matching result indicates that the defects to be detected are not located in the weld bead region, determining that the defects to be detected need to be subjected to three-dimensional dirt defect detection.

5. The method according to claim 4, characterized in that The method further includes: When the defect position matching result indicates that the defects to be detected are located in the weld bead region, determining that the defects to be detected are pinhole explosion point defects; When the first defect size is less than the third qualified size threshold set for the pinhole explosion point defects, determining that the detection of pinhole explosion point defects of the current collector tray is qualified; the third qualified size threshold is greater than the first qualified size threshold and less than the second qualified size threshold.

6. The method according to claim 4, wherein Performing region recognition on the weld bead region of the current collector plate for the first illumination image information to obtain the region contour position of the weld bead region, including: Using a preset region of interest to frame the initial region information containing the weld bead region from the first illumination image information; Inputting the initial region information into a preset weld bead width detection model, and intercepting and correcting the initial region information based on the weld bead width of the weld bead region to obtain the region contour position of the weld bead region.

7. The method according to claim 4, wherein The contour position of the defect to be detected includes the defect contour position coordinates of the defect to be detected, and the region contour position includes the region contour position coordinates of the weld bead region; Performing position matching between the contour position of the defect to be detected and the region contour position to obtain a defect position matching result, including: Performing region mapping on the defect contour position coordinates of the defect to be detected and the region contour position coordinates of the weld bead region to determine the overlapping region area between the defect contour of the defect to be detected and the region contour of the weld bead region; Determining the area ratio between the overlapping region area and the contour area of the defect contour; When the area ratio is greater than a preset area ratio threshold, determining that the defect position matching result indicates that the defect to be detected is located in the weld bead region.

8. The method according to claim 3, characterized in that, Determining the defect detection result of the current collector plate based on the defect category, including: When the defect category is the planar dirt defect, determining that the planar dirt defect detection of the current collector plate is qualified.

9. The method according to claim 1 or 2, characterized in that, The defect category includes a three-dimensional dirt defect and a planar dirt defect; the first illumination image information includes bright field image information, and the second illumination image information includes dark field image information; Performing three-dimensional dirt defect detection on the defect of undetermined category according to the first illumination image information and the second illumination image information to determine the defect category of the defect of undetermined category, including: Respectively performing gray feature extraction on the bright field image information and the dark field image information to obtain the bright field gray feature and the dark field gray feature of the defect of undetermined category; When the feature difference degree between the bright field gray feature and the dark field gray feature is greater than the three-dimensional dirt difference degree threshold, determining that the defect category of the defect of undetermined category is a three-dimensional dirt defect; When the feature difference degree is less than or equal to the three-dimensional dirt difference degree threshold, determining that the defect category of the defect of undetermined category is a planar dirt defect.

10. The method according to claim 9, characterized in that, Respectively performing gray feature extraction on the bright field image information and the dark field image information to obtain the bright field gray feature and the dark field gray feature of the defect of undetermined category, including: Performing gray feature extraction on the bright field image information according to the first defect contour of the defect of undetermined category to obtain the bright field gray feature of the defect of undetermined category; Using the first defect contour as the detection region of interest to perform region mapping on the dark field image information to obtain the second defect contour of the defect of undetermined category; Performing gray feature extraction on the dark field image information based on the second defect contour to obtain the dark field gray feature of the defect of undetermined category.

11. A manifold defect detection device, characterized in that, The device includes: A first lighting information acquisition module, configured to acquire first lighting image information obtained by performing image acquisition on a current collector tray in a first lighting environment; A second lighting information acquisition module, configured to acquire second lighting image information obtained by performing image acquisition on the current collector tray in a second lighting environment when it is determined, based on the first lighting image information, that there are defects of undetermined categories on the current collector tray; the defects of undetermined categories refer to defects whose categories cannot be distinguished by using only the first lighting image information; A defect category determination module, configured to perform three-dimensional dirt defect detection on the defects of undetermined categories according to the first lighting image information and the second lighting image information, and determine the defect categories of the defects of undetermined categories; the first lighting angle of the first lighting environment is higher than the second lighting angle of the second lighting environment; there are differences in the imaging of three-dimensional dirt defects in the first lighting environment and the second lighting environment; A defect detection module, configured to determine the defect detection result of the current collector tray based on the defect categories.

12. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

15. A manifold defect detection system, characterized in that, The system includes a first lighting environment component, a second lighting environment component, an image acquisition component, and a visual defect detection component communicatively connected to the image acquisition component; The first lighting environment component is configured to provide a first lighting environment for the current collector tray; The second lighting environment component is configured to provide a second lighting environment for the current collector tray; the first lighting angle of the first lighting environment is higher than the second lighting angle of the second lighting environment; the image acquisition component is configured to acquire first lighting image information of the current collector tray in the first lighting environment and second lighting image information of the current collector tray in the second lighting environment; The visual defect detection component is configured to implement the current collector tray defect detection method according to any one of claims 1 to 10.

16. The system according to claim 15, characterized in that, The system further includes an acquisition control component communicatively connected to the visual defect detection component; The acquisition control component is electrically connected to the first lighting environment component, the second lighting environment component, and the image acquisition component respectively, and controls the opening and closing of the first lighting environment component or the second lighting environment component by sending an electrical signal to the first lighting environment component or the second lighting environment component, and controls the image acquisition component to perform image acquisition on the current collector tray by sending an electrical signal to the image acquisition component.

17. The system according to claim 15 or 16, characterized in that, The first lighting environment component includes a bowl-shaped light source and a coaxial light source with a first irradiation angle; The second lighting environment component includes an annular light source with a second irradiation angle.

Images