Battery cell explosion-proof valve defect detection method, device and system and electronic equipment

Abstract

The invention discloses a cell explosion-proof valve defect detection method, device and system and electronic equipment. The method comprises the following steps: determining at least five target images of a target cell explosion-proof valve; and determining luminosity characteristics according to the at least five target images, reconstructing the target cell explosion-proof valve according to the luminosity characteristics to obtain a fusion image, and determining the defect condition of the target cell explosion-proof valve according to the fusion image. According to the method, information of tiny defects and deep pit defects on the explosion-proof valve of the target battery cell can be represented, so that the accuracy of defect detection is improved.

Description

Technical Field

[0001] The present invention relates to the field of defect detection technology, and in particular to a method, device, system and electronic equipment for detecting defects in a battery cell explosion-proof valve. Background Art

[0002] With the rapid development of the new energy industry, especially the increasing demand for new energy electric vehicles, the demand for batteries is also increasing. In recent years, spontaneous combustion of electric vehicle batteries has occurred from time to time, and major manufacturers have become more and more stringent in their requirements for battery quality. During the preparation process of the battery, some surface defects may occur, such as surface scratches, pits, electrolyte contamination, etc. The explosion-proof valve is an especially important part of the battery, and its surface defects may cause safety hazards. Common types of surface defects of explosion-proof valves include: scratches, damage, and missing of PP film, depressions and convex spots of aluminum foil, electrolyte contamination, foreign matter, etc.

[0003] Most of the existing explosion-proof valve defect detection methods use manual visual inspection, where quality inspectors observe various positions of the explosion-proof valve from different lighting directions to subjectively distinguish the degree of defects. Long-term visual inspection will cause eye fatigue, resulting in missed inspections and wrong inspections. Summary of the invention

[0004] The present invention provides a method, device, system and electronic equipment for detecting defects of a battery core explosion-proof valve, so as to solve the problem of inaccurate detection of defects of a battery core explosion-proof valve.

[0005] According to one aspect of the present invention, a method for detecting defects in a battery cell explosion-proof valve is provided, comprising:

[0006] Determine at least five target images of the target battery cell explosion-proof valve; the target images are images of the target battery cell explosion-proof valve taken at different angles and under different lighting conditions;

[0007] Determine photometric features according to at least five target images, and reconstruct the target battery cell explosion-proof valve according to the photometric features to obtain a fusion image; the photometric features are used to characterize the texture, structure and light and dark features of the surface of the target battery cell explosion-proof valve under different illumination; the fusion image is an image of the light and dark changes on the surface of the target battery cell explosion-proof valve;

[0008] The defect condition of the target battery cell explosion-proof valve is determined according to the fusion diagram.

[0009] According to another aspect of the present invention, there is provided a battery cell explosion-proof valve defect detection device, comprising:

[0010] A target image determination module, used to determine at least five target images of the target battery cell explosion-proof valve; the target images are images of the target battery cell explosion-proof valve taken at different angles and under different lighting conditions;

[0011] A fusion image determination module is used to determine photometric features based on at least five target images, and reconstruct the target battery cell explosion-proof valve based on the photometric features to obtain a fusion image; the photometric features are used to characterize the texture, structure and light and dark features of the surface of the target battery cell explosion-proof valve under different lighting conditions; the fusion image is an image of light and dark changes on the surface of the target battery cell explosion-proof valve;

[0012] The defect determination module is used to determine the defect status of the target battery cell explosion-proof valve according to the fusion graph.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for detecting defects in an explosion-proof valve of a battery cell according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for detecting defects in a battery cell explosion-proof valve according to any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention determines at least five target images of the target battery cell explosion-proof valve, and can provide images at different angles and different light intensities, providing a basis for detecting the defect conditions of the target battery cell explosion-proof valve; determines the photometric features according to the target images, and reconstructs the target battery cell explosion-proof valve according to the photometric features to obtain a fusion map, which can obtain feature information corresponding to small changes on the target battery cell explosion-proof valve; determines the defect conditions of the target battery cell explosion-proof valve according to the fusion map. This method can characterize the small defects and deep pit defect information existing on the target battery cell explosion-proof valve, thereby improving the accuracy of defect detection.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of a method for detecting defects in a battery explosion-proof valve provided by an embodiment of the present invention;

[0022] Figure 2 A plan view of a defect detection device for an explosion-proof valve of a battery cell provided by an embodiment of the present invention;

[0023] Figure 3 A front view of a battery core explosion-proof valve defect detection device provided by an embodiment of the present invention;

[0024] Figure 4 A side view of a battery core explosion-proof valve defect detection device provided by an embodiment of the present invention;

[0025] Figure 5 A top view of a battery core explosion-proof valve defect detection device provided by an embodiment of the present invention;

[0026] Figure 6 A target image of a No. 4 target battery explosion-proof valve under a planar coaxial light source provided by an embodiment of the present invention;

[0027] Figure 7 An image of a No. 4 target battery explosion-proof valve under a common annular light source provided by an embodiment of the present invention;

[0028] Figure 8 An image of the explosion-proof valve of target cell No. 3 under a common annular light source and a planar coaxial light source provided by an embodiment of the present invention;

[0029] Fig. 9 A target image of a No. 4 target battery cell explosion-proof valve under a partitioned annular light source provided by an embodiment of the present invention;

[0030] Fig.10 A target image of a No. 3 target battery cell explosion-proof valve under a partitioned annular light source provided by an embodiment of the present invention;

[0031] Fig.11 A fusion diagram of a No. 4 target battery cell explosion-proof valve provided in an embodiment of the present invention;

[0032] Fig.12 A fusion diagram of a No. 3 target battery cell explosion-proof valve provided in an embodiment of the present invention;

[0033] Fig.13A schematic diagram of a defect situation of a target battery cell explosion-proof valve provided in an embodiment of the present invention;

[0034] Fig.14 A circuit connection diagram of a battery core explosion-proof valve defect detection device provided by an embodiment of the present invention;

[0035] Fig.15 A schematic diagram of the structure of a battery core explosion-proof valve defect detection device provided by an embodiment of the present invention;

[0036] Fig.16 A schematic diagram of the structure of a battery core explosion-proof valve defect detection system provided by an embodiment of the present invention;

[0037] Fig.17 A schematic diagram of the structure of an electronic device for implementing the method for detecting defects of a battery cell explosion-proof valve according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0039] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0040] Figure 1 This is a flow chart of a method for detecting a defect in a battery explosion-proof valve provided by an embodiment of the present invention. This embodiment is applicable to the case of detecting defects in a battery explosion-proof valve. The method can be performed by a battery explosion-proof valve defect detection device. The battery explosion-proof valve defect detection device can be implemented in the form of hardware and / or software. The battery explosion-proof valve defect detection device can be configured in any electronic device with network communication function. Figure 1 As shown, the method includes:

[0041] S110, determining at least five target images of the target battery cell explosion-proof valve.

[0042] The target images are images of the target battery cell explosion-proof valve taken at different angles and under different lighting conditions.

[0043] Among them, different angles are achieved through partitioned ring light sources; different lighting is achieved by converting plane coaxial light sources and partitioned ring light sources.

[0044] The partitioned annular light source is composed of four arc-shaped light sources with an angle of 90°. The partitioned annular light source includes: a first arc-shaped light source, a second arc-shaped light source, a third arc-shaped light source and a fourth arc-shaped light source.

[0045] The arc-shaped light source is composed of multiple LED lamp beads arranged in a ring, and the light is irradiated from the side of the target battery explosion-proof valve at a certain angle to the surface of the target battery explosion-proof valve. The lighting method adopted is multi-angle oblique lighting. Since the light comes from different positions of the ring, reflected light in different directions will be generated on the surface of the target battery explosion-proof valve, which helps to observe the three-dimensional sense and layering of the surface of the target battery explosion-proof valve, and can effectively obtain the three-dimensional structure information or surface roughness of the target battery explosion-proof valve.

[0046] Among them, the plane coaxial light source is mainly composed of a light-emitting component, a semi-transparent and semi-reflective mirror, and a diffuser. The light emitted by the light-emitting component is reflected and transmitted by the semi-transparent and semi-reflective mirror, and then passes through the diffuser, so that the light is vertically and evenly irradiated on the surface of the target battery explosion-proof valve. Moreover, the reflected light can return along the original path and enter the lens of the shooting device. The lighting method adopts vertical coaxial lighting. This lighting method makes the surface of the target battery explosion-proof valve obtain uniform light intensity, can eliminate the interference of shadows and reflections, and realize clear imaging of two-dimensional defects on the surface of the target battery explosion-proof valve.

[0047] Among them, the two-dimensional defects can be color difference defects such as dirt and corrosion, and damage defects such as scratches.

[0048] Furthermore, the planar coaxial light source has a semi-transparent and semi-reflective luminous surface. In terms of light source size selection, a planar coaxial light source with a luminous surface size slightly larger than the partitioned ring light source is selected to ensure that the light from the partitioned ring light source is not blocked.

[0049] Furthermore, if Figure 2 The figure shows a plan view of a battery cell explosion-proof valve detection device. The partitioned annular light source 2 is used to provide lateral uneven illumination for the target battery cell explosion-proof valve 4. The partitioned annular light source 2 includes: a first arc-shaped light source 21 and a fourth arc-shaped light source 24 provide left-side uneven illumination for the target battery cell explosion-proof valve 4; a second arc-shaped light source 22 and a third arc-shaped light source 23 provide right-side uneven illumination for the target battery cell explosion-proof valve 4.

[0050] Furthermore, if Figure 2 As shown, the battery cell explosion-proof valve detection device also includes: a shooting device 1 for acquiring images of the target battery cell explosion-proof valve under different lighting conditions; and a planar coaxial light source 3 for providing uniform lighting for the target battery cell explosion-proof valve.

[0051] Furthermore, if Figure 3 , Figure 4 and Figure 5 As shown, it is a front view, a side view and a top view of the battery cell explosion-proof valve detection device. From the front view, it can be seen that the shooting device 1 is fixed by an I-shaped pad, and can be adjusted in the height direction along the slot, and the partitioned ring light source 2 is on the plane coaxial light source 3, and each is equipped with a fixing component for fixing, and can also be adjusted in the height direction along the slot. From the side view, it can be seen that in order to improve the imaging effect of the target battery cell explosion-proof valve 4, the partitioned ring light source 2 and the plane coaxial light source 3 are stacked and adjusted to the required height. From the top view, it can be seen that the shooting device 1, the partitioned ring light source 2 and the plane coaxial light source 3 are located on the same reference line, that is, on the optical axis of the shooting device 1.

[0052] Specifically, images of the target battery cell explosion-proof valve at different angles and under different lighting conditions are captured by a shooting device to obtain at least five target images.

[0053] The shooting device may be an area array camera, which is an imaging device that can obtain the entire two-dimensional plane image information of the target battery core explosion-proof valve at one time.

[0054] For example, Figure 6 As shown, the target image of the No. 4 target explosion-proof valve is taken under a planar coaxial light source. The pit of the No. 4 target explosion-proof valve is completely invisible in the figure.

[0055] For example, Figure 7 As shown, the image of the No. 4 target explosion-proof valve is taken under a common annular light source. It can be seen from the figure that the pit of the No. 4 target explosion-proof valve is not obvious.

[0056] For example, Figure 8 As shown, the image of the No. 3 target explosion-proof valve is taken under the ordinary ring light + plane coaxial light source. It can be seen from the figure that the pit of the No. 3 target explosion-proof valve is not obvious.

[0057] For example, Fig. 9 As shown, it is the target image of the explosion-proof valve of target battery cell No. 4 under the partitioned ring light source. The figure clearly shows the pit existing in the explosion-proof valve of target battery cell No. 4.

[0058] For example, Fig.10As shown, it is the target image of the explosion-proof valve of target battery cell No. 3 under the partitioned ring light source. The figure clearly shows the pits and protrusions existing in the explosion-proof valve of target battery cell No. 3.

[0059] Furthermore, from the above images, it can be seen that the partitioned ring light source overcomes the problem of unclear display of pits and protrusions existing in ordinary ring light sources and planar coaxial light sources, thereby improving the imaging effect of the target image.

[0060] S120, determining photometric features according to at least five target images, and reconstructing the target battery cell explosion-proof valve according to the photometric features to obtain a fusion image.

[0061] Among them, the photometric features are used to characterize the texture, structure and light and dark characteristics of the target battery cell explosion-proof valve surface under different lighting conditions.

[0062] Among them, the fusion image is an image of the light and dark changes on the surface of the target battery cell explosion-proof valve.

[0063] Specifically, a target image corresponding to a partitioned ring light source is obtained from at least five target images, and a photometric feature is determined according to the target image under the partitioned ring light source. A normal vector of the target explosion-proof valve surface is determined according to the light and dark features contained in the photometric feature and the light angle of the light source, and the normal vector and the photometric feature are fused to obtain a fusion image.

[0064] Furthermore, the fusion map can be determined by photometric stereo fusion method. Photometric stereo fusion method is a method that combines photometric stereo vision technology with other related technologies to restore the surface shape, reflection characteristics and other related information of the target battery cell explosion-proof valve. Photometric stereo vision mainly infers the normal direction of the target battery cell explosion-proof valve surface based on the change in the intensity of reflected light on the surface of the target battery cell explosion-proof valve under different lighting conditions, and then restores the three-dimensional shape of the target battery cell explosion-proof valve. Fusion is to comprehensively utilize data obtained by multiple photometric stereo vision or combine other data to improve the accuracy and reliability of shape recovery and feature extraction.

[0065] For example, Fig.11 As shown, this is the fusion map of the explosion-proof valve of target battery cell No. 4. It can be seen from the figure that the shape of the pit and the slight change information around the pit can be clearly characterized.

[0066] For example, Fig.12 As shown in FIG. 3 , it is a fusion diagram of the explosion-proof valve of target battery cell No. 3. As can be seen from the figure, the shapes of the pits and protrusions, as well as the slight changes in the surrounding areas of the pits and protrusions can be clearly characterized.

[0067] In the above steps, the generation of the fusion image can accurately display the tiny dents, protrusions and scratches in the target battery cell explosion-proof valve, thereby improving the accuracy of defect detection.

[0068] S130. Determine the defect status of the target battery cell explosion-proof valve according to the fusion graph.

[0069] Among them, the defect conditions include: the existence of defects and the non-existence of defects.

[0070] Specifically, feature information is extracted from the target image and the fusion image, the obtained feature information is fused and marked on the fusion image, and the marked image is input into the detection model to determine the defect status of the target battery cell explosion-proof valve.

[0071] Among them, the detection model can adopt convolutional neural network, YOLO algorithm, etc.

[0072] For example, Fig.13 The following are the defects of the explosion-proof valve of the target battery cell. From left to right, they are aluminum foil pits, PP film damage, PP film scratches and electrolyte contamination.

[0073] The above steps fuse the features of at least five target images and the fusion image, which can make the features of surface defects more comprehensive, that is, the color difference defects such as dirt and corrosion and the defect features such as pits and protrusions existing in the target battery cell explosion-proof valve are integrated, thereby improving the accuracy of defect detection.

[0074] Optionally, determining at least five target images of the target battery cell explosion-proof valve includes steps A1-A2:

[0075] Step A1: When the target battery cell explosion-proof valve is transmitted to the detection area, a trigger instruction is generated.

[0076] Among them, the trigger instruction is used to trigger the planar coaxial light source and the partitioned annular light source.

[0077] The partitioned annular light source is composed of four arc-shaped light sources, and the angle corresponding to each arc-shaped light source is 90°.

[0078] The detection area is below the optical axis of the camera, for example, Figure 2 The position corresponding to the dotted line.

[0079] Specifically, the target battery cell explosion-proof valve is transmitted through the transmission device, and when the target battery cell explosion-proof valve is transmitted to the optical axis of the shooting device, a trigger instruction of the light source and the shooting device is generated.

[0080] Step A2: triggering the planar coaxial light source and the partitioned annular light source in a preset order according to the trigger instruction, and photographing the target battery cell explosion-proof valve while triggering the planar coaxial light source or the partitioned annular light source to obtain at least five target images.

[0081] Specifically, according to the trigger instruction, the plane coaxial light source and the partitioned annular light source are sequentially lit in the order of plane coaxial light source → first arc-shaped light source → second arc-shaped light source → third arc-shaped light source → fourth arc-shaped light source. While lighting each light source, the target battery cell explosion-proof valve is photographed by a photographing device to obtain at least five target images.

[0082] For example, when the explosion-proof valve of the target battery moves to the detection position, the PLC controls the relay to close, thereby giving a trigger signal to the multi-channel timing controller. After receiving the trigger, the controller controls the light source output port to output, and the output order is plane coaxial light source → first arc light source → second arc light source → third arc light source → fourth arc light source. Each time the light source output is given, a trigger signal is also given to the shooting device, so the shooting device collects a total of 5 images.

[0083] For example, Fig.14 As shown, the multi-channel timing circuit is used to realize the control of the shooting device and the light source, and the multi-channel timing circuit includes three interfaces: the OUT interface is used to connect the shooting device, that is, the explosion-proof valve camera C1 in the figure; the IN interface is connected to the P line and the N line respectively and relays are configured on the connecting lines, wherein the P line is a protection line and the N line is a neutral line; the CH interface is used to connect the planar coaxial light source and the partitioned ring light source, that is, the planar coaxial light L2 and the partitioned ring light L1 in the figure.

[0084] Furthermore, the planar coaxial light source and the partitioned annular light source are connected via a 1-to-2 adapter cable, such as Fig.14 As shown in the red area, the control of the two light sources is merged. The small adapter on the right side of the 1-to-2 adapter cable is connected to the planar coaxial light source, and the large adapter is connected to the partitioned ring light source; the adapter on the left side is connected to the CH interface.

[0085] Optionally, according to the trigger instruction, the planar coaxial light source and the partitioned annular light source are triggered in a preset order, and the target battery cell explosion-proof valve is photographed while the planar coaxial light source or the partitioned annular light source is triggered to obtain at least five target images, including steps B1-B3:

[0086] Step B1, triggering the planar coaxial light source according to a trigger instruction, and capturing at least one first image while triggering the planar coaxial light source.

[0087] Specifically, the planar coaxial light source is triggered according to the trigger instruction. When the planar coaxial light source emits light, the target battery core explosion-proof valve is photographed by a photographing device to obtain at least one first image.

[0088] Step B2: After obtaining the first image, trigger each arc-shaped light source in the partitioned ring light source in sequence according to a preset order, and take at least four second images.

[0089] Specifically, after obtaining the first image, the first arc-shaped light source → the second arc-shaped light source → the third arc-shaped light source → the fourth arc-shaped light source are lit respectively in the order, and while lighting each arc-shaped light source, the target battery cell explosion-proof valve is photographed by a photographing device to obtain at least four second images.

[0090] Step B3: using at least one first image and at least four second images obtained by shooting as target images of the target battery cell explosion-proof valve.

[0091] Specifically, at least one first image and at least four second images are integrated to obtain at least five target images of the target battery cell explosion-proof valve.

[0092] Optionally, determining photometric features according to at least five target images, and reconstructing the target battery cell explosion-proof valve according to the photometric features to obtain a fusion image includes steps C1-C3:

[0093] Step C1, determining a first feature according to a first image.

[0094] Among them, the first feature can characterize the texture information of the surface of the target battery cell explosion-proof valve under uniform light.

[0095] Exemplarily, the first feature may include a texture feature of the surface of the target battery cell explosion-proof valve when it is not damaged or a texture feature after being contaminated by corrosion, dirt, etc.

[0096] Specifically, the first feature is determined according to a change in the surface of the target battery core explosion-proof valve in the first image.

[0097] Step C2: determining a second feature according to the second image.

[0098] Among them, the second feature can characterize the structural information of the surface of the target battery cell explosion-proof valve under uneven light.

[0099] Furthermore, the structural information may be light and dark changes in the structure of the target battery cell explosion-proof valve itself and / or light and dark changes in damage such as pits or protrusions on the target battery cell explosion-proof valve.

[0100] For example, Fig. 9 , 10 As shown, according to the change of light and dark, it can be seen that there are pits and protrusions on the target battery cell explosion-proof valve. When there are no pits and protrusions, only the place where the target battery cell explosion-proof valve itself is connected has light and dark changes in the first image.

[0101] Specifically, the second feature is determined according to the light and dark changes on the surface of the target battery core explosion-proof valve presented in the second image.

[0102] Step C3: reconstruct the surface of the target battery cell explosion-proof valve using the first feature and the second feature to obtain a fusion image.

[0103] Specifically, the normal vector of the target explosion-proof valve surface is determined according to the second feature and the light angle of the light source, and the normal vector, the first feature and the second feature are fused and reconstructed to obtain a fusion graph.

[0104] Optionally, the first feature and the second feature are used to reconstruct the surface of the target battery cell explosion-proof valve to obtain a fusion map, including steps D1-D2:

[0105] Step D1, matching the first feature and the second feature to obtain a reference feature.

[0106] Specifically, according to the position information in the target image, the first feature and the second feature are matched to obtain a reference feature.

[0107] Step D2: Perform three-dimensional reconstruction based on the reference features to obtain a fusion image.

[0108] Specifically, the normal vector of the target explosion-proof valve surface is determined according to the second feature, and the reference feature and the normal vector of the target explosion-proof valve surface are three-dimensionally reconstructed to obtain a fusion image.

[0109] Optionally, determining the defect of the target battery cell explosion-proof valve according to the fusion graph includes steps E1-E3:

[0110] Step E1: Determine structural features according to the fusion graph.

[0111] Among them, the structural features are used to characterize the structural information of the surface of the target battery cell explosion-proof valve.

[0112] Furthermore, the structural information may be structural information of the target battery cell explosion-proof valve itself and / or the outline and depth of damage such as pits or protrusions on the target battery cell explosion-proof valve.

[0113] Specifically, the structural features are determined according to the texture information on the surface of the target battery cell explosion-proof valve in the fusion image.

[0114] For example, Fig. 9 As shown, the structural features may be information such as the size and depth of the pits.

[0115] Step E2: determining texture features based on at least five target images.

[0116] Among them, texture features are used to characterize the length and shape of various boundaries on the surface of the target battery cell explosion-proof valve.

[0117] Specifically, texture features are obtained from at least five target images according to an edge extraction method.

[0118] For example, Fig.13As shown, the texture features may include length information of existing scratches, size and edge information of chipped corners, and the like.

[0119] Step E3: Determine the defect of the target battery cell explosion-proof valve according to the structural features and texture features.

[0120] Specifically, the structural features and texture features are annotated on the fusion image, and the annotated image is input into the detection model to determine whether the target battery cell explosion-proof valve has defects.

[0121] Furthermore, if a defect exists, the type of the defect is also determined.

[0122] Furthermore, the structural features and texture features can be compared with preset defect features to determine whether the target battery cell explosion-proof valve has defects.

[0123] Optionally, determining the defect of the target battery cell explosion-proof valve according to the structural features and the texture features includes steps F1-F2:

[0124] Step F1: Mark the structural features and texture features on the fusion image according to the position information to obtain a reference feature image.

[0125] Specifically, the structural features and the texture features are annotated on the fusion image according to the position information, that is, the structural features and the texture features are overlapped with the fusion image according to the corresponding positions to obtain a reference feature image.

[0126] Step F2: determining the defect condition of the target battery cell explosion-proof valve according to the reference feature image.

[0127] Specifically, the reference feature image is input into the detection model for detection, so as to determine whether the target explosion-proof valve has defects and, if defects exist, the type of defects.

[0128] The technical solution of this embodiment determines at least five target images of the target battery cell explosion-proof valve, which can provide images at different angles and different light intensities, and provide a basis for the detection of defects in the target battery cell explosion-proof valve; determines the photometric features based on at least five target images, and reconstructs the target battery cell explosion-proof valve based on the photometric features to obtain a fusion map, which can obtain feature information corresponding to small changes on the target battery cell explosion-proof valve; determines the defect of the target battery cell explosion-proof valve based on the fusion map. This method can characterize the small defects and deep pit defect information existing on the target battery cell explosion-proof valve, thereby improving the accuracy of defect detection.

[0129] Fig.15The present invention provides a schematic diagram of a structure of a battery explosion-proof valve defect detection device. This embodiment is applicable to the case of detecting defects in battery explosion-proof valves. The battery explosion-proof valve defect detection device can be implemented in the form of hardware and / or software. The battery explosion-proof valve defect detection device can be configured in any electronic device with network communication function. Fig.15 As shown, the device includes: a target image determination module 210, a fusion image determination module 220 and a defect determination module 230, wherein:

[0130] The target image determination module 210 is used to determine at least five target images of the target battery cell explosion-proof valve; the target images are images of the target battery cell explosion-proof valve taken at different angles and under different lighting conditions;

[0131] Fusion image determination module 220: used to determine photometric features based on at least five target images, and reconstruct the target battery cell explosion-proof valve based on the photometric features to obtain a fusion image; the photometric features are used to characterize the texture, structure and light and dark features of the target battery cell explosion-proof valve surface under different lighting conditions; the fusion image is an image of light and dark changes on the target battery cell explosion-proof valve surface;

[0132] The defect determination module 230 is used to determine the defect condition of the target battery cell explosion-proof valve according to the fusion graph.

[0133] Optionally, the target image determination module 210 includes:

[0134] Trigger instruction generation unit: used to generate a trigger instruction when the target battery explosion-proof valve is transmitted to the detection area; the trigger instruction is used to trigger the planar coaxial light source and the partitioned ring light source; the partitioned ring light source is composed of four arc-shaped light sources, and the angle corresponding to each arc-shaped light source is 90°;

[0135] Target image determination unit: used to trigger the planar coaxial light source and the partitioned annular light source in a preset order according to the trigger instruction, and shoot the target battery cell explosion-proof valve while triggering the planar coaxial light source or the partitioned annular light source to obtain at least five target images.

[0136] Optionally, the target image determination unit comprises:

[0137] A first image determination subunit: configured to trigger the planar coaxial light source according to a trigger instruction, and to capture at least one first image while triggering the planar coaxial light source;

[0138] The second image determination subunit is used to trigger the arc-shaped light sources in the partitioned ring light source in sequence according to a preset order after obtaining the first image, and to take at least four second images;

[0139] The target image determination subunit is used to use at least one first image and at least four second images obtained by shooting as target images of the target battery cell explosion-proof valve.

[0140] Optionally, the fusion graph determination module 220 includes:

[0141] A first feature determination unit: used to determine a first feature according to the first image; the first feature can characterize texture information of the surface of the target battery cell explosion-proof valve under uniform light;

[0142] A second feature determination unit: used to determine a second feature according to the second image; the second feature can characterize the structural information of the surface of the target battery cell explosion-proof valve under uneven light;

[0143] A fusion graph determination unit is used to reconstruct the surface of the target battery cell explosion-proof valve using the first feature and the second feature to obtain a fusion graph.

[0144] Optionally, the fusion graph determination unit includes:

[0145] A reference feature determination subunit is used to match the first feature with the second feature to obtain a reference feature;

[0146] Fusion image determination subunit: used to perform three-dimensional reconstruction according to reference features to obtain a fusion image.

[0147] Optionally, the defect determination module 230 includes:

[0148] Structural feature determination unit: used to determine structural features according to the fusion graph; the structural features are used to characterize the structural information of the surface of the target battery cell explosion-proof valve;

[0149] Texture feature determination unit: used to determine texture features based on at least five target images; the texture features are used to characterize the length and shape of various boundaries existing on the surface of the target battery cell explosion-proof valve;

[0150] Defect determination unit: used to determine the defect situation of the target battery cell explosion-proof valve according to the structural characteristics and texture characteristics.

[0151] Optionally, a defect determination unit, comprising:

[0152] Reference feature image determination subunit: used to mark the structural features and texture features on the fusion image according to the position information to obtain the reference feature image;

[0153] Defect determination subunit: used to determine the defect condition of the target battery cell explosion-proof valve according to the reference feature image.

[0154] The battery cell explosion-proof valve defect detection device provided in the embodiment of the present invention can execute the battery cell explosion-proof valve defect detection method provided in any embodiment of the present invention mentioned above, and has the corresponding functions and beneficial effects of executing the battery cell explosion-proof valve defect detection method. For detailed process, please refer to the relevant operations of the battery cell explosion-proof valve defect detection method in the aforementioned embodiment.

[0155] Fig.16 The structure diagram of a battery explosion-proof valve defect detection system provided by an embodiment of the present invention is a schematic diagram of a battery explosion-proof valve defect detection system provided by an embodiment of the present invention. The system can execute the battery explosion-proof valve defect detection method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Fig.16 As shown, the system comprises:

[0156] A shooting unit 1 is used to collect image data of a target battery cell explosion-proof valve 4;

[0157] The partitioned annular light source 2 is used to provide annular light at different angles for the target battery core explosion-proof valve 4;

[0158] The planar coaxial light source 3 is used to provide a planar light source for the target battery core explosion-proof valve 4; wherein:

[0159] The shooting unit 1, the partitioned ring light source 2 and the planar coaxial light source 3 are all arranged on the bracket;

[0160] The partitioned ring light source 2 and the planar coaxial light source 3 are arranged on the optical axis of the shooting unit 1 according to a preset distance;

[0161] The planar coaxial light source 3 is arranged under the partitioned annular light source 2;

[0162] The partitioned annular light source 2 is divided into a plurality of arc-shaped light sources according to preset angles.

[0163] Furthermore, the preset angle may be 90 degrees, and the partitioned ring light source 2 is then divided into four arc-shaped light sources.

[0164] Fig.17 A schematic diagram of the structure of an electronic device for implementing a method for detecting defects in a battery explosion-proof valve according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0165] like Fig.17As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0166] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0167] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for detecting defects in a battery cell explosion-proof valve.

[0168] In some embodiments, the battery cell explosion-proof valve defect detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the battery cell explosion-proof valve defect detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the battery cell explosion-proof valve defect detection method in any other appropriate manner (e.g., by means of firmware).

[0169] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0171] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0173] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0174] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0175] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0176] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting defects in a battery cell explosion-proof valve, characterized in that: include: Determine at least five target images of the target battery cell explosion-proof valve; The target image is an image of the target battery cell explosion-proof valve taken at different angles and under different lighting conditions; Determine photometric features according to at least five target images, and reconstruct the target battery cell explosion-proof valve according to the photometric features to obtain a fusion image; the photometric features are used to characterize the texture, structure and light and dark features of the surface of the target battery cell explosion-proof valve under different illuminations; The fusion image is an image of light and dark changes on the surface of the target battery core explosion-proof valve; The defect condition of the target battery cell explosion-proof valve is determined according to the fusion diagram.

2. The method according to claim 1, characterized in that The step of determining at least five target images of the target battery cell explosion-proof valve comprises: When the target battery explosion-proof valve is transmitted to the detection area, a trigger instruction is generated; the trigger instruction is used to trigger the planar coaxial light source and the partitioned annular light source; the partitioned annular light source is composed of four arc-shaped light sources, and the angle corresponding to each arc-shaped light source is 90°; The planar coaxial light source and the partitioned annular light source are triggered in a preset order according to the trigger instruction, and the target battery cell explosion-proof valve is photographed while the planar coaxial light source or the partitioned annular light source is triggered to obtain at least five target images.

3. The method according to claim 2, characterized in that The planar coaxial light source and the partitioned annular light source are triggered in a preset order according to the trigger instruction, and the target battery core explosion-proof valve is photographed while the planar coaxial light source or the partitioned annular light source is triggered to obtain at least five target images, including: triggering the planar coaxial light source according to a trigger instruction, and capturing at least one first image while triggering the planar coaxial light source; After obtaining the first image, triggering each arc-shaped light source in the partitioned ring light source in sequence according to a preset order, and taking at least four second images; The first image and the at least four second images are used as target images of the target battery cell explosion-proof valve.

4. The method according to claim 1, characterized in that: The determining of photometric features according to at least five target images, and reconstructing the target battery cell explosion-proof valve according to the photometric features to obtain a fusion image, includes: Determine a first feature according to the first image; the first feature can characterize texture information of the surface of the target battery cell explosion-proof valve under uniform light; Determine a second feature according to the second image; the second feature can characterize the structural information of the surface of the target battery cell explosion-proof valve under uneven light; The first feature and the second feature are used to reconstruct the surface of the target battery cell explosion-proof valve to obtain a fusion image.

5. The method according to claim 4, characterized in that The reconstructing the surface of the target battery core explosion-proof valve by using the first feature and the second feature to obtain a fusion graph includes: Matching the first feature with the second feature to obtain a reference feature; Three-dimensional reconstruction is performed according to the reference features to obtain a fusion image.

6. The method according to claim 1, characterized in that The step of determining the defect of the target battery cell explosion-proof valve according to the fusion graph includes: Determine a structural feature according to the fusion graph; the structural feature is used to characterize the structural information of the surface of the target battery cell explosion-proof valve; Determine texture features based on at least five target images; the texture features are used to characterize the lengths and shapes of various boundaries existing on the surface of the target battery cell explosion-proof valve; The defect condition of the target battery cell explosion-proof valve is determined according to the structural feature and the texture feature.

7. The method according to claim 6, characterized in that The determining the defect of the target battery cell explosion-proof valve according to the structural feature and the texture feature includes: Marking structural features and texture features on the target image and fusion image according to position information to obtain a reference feature image; The defect condition of the target battery cell explosion-proof valve is determined according to the reference feature image.

8. A battery core explosion-proof valve defect detection device, characterized in that: include: A target image determination module, used to determine at least five target images of target battery cell explosion-proof valves; The target image is an image of the target battery cell explosion-proof valve taken at different angles and under different lighting conditions; A fusion image determination module is used to determine photometric features based on at least five target images, and reconstruct the target battery cell explosion-proof valve based on the photometric features to obtain a fusion image; the photometric features are used to characterize the texture, structure and light and dark features of the target battery cell explosion-proof valve surface under different lighting conditions; The fusion image is an image of light and dark changes on the surface of the target battery core explosion-proof valve; The defect determination module is used to determine the defect status of the target battery cell explosion-proof valve according to the fusion graph.

9. A battery core explosion-proof valve defect detection system, characterized in that: The system comprises: A shooting unit, used for collecting image data of the target battery cell explosion-proof valve; A partitioned annular light source is used to provide annular light at different angles for the target battery cell explosion-proof valve; A planar coaxial light source is used to provide a planar light source for the target battery core explosion-proof valve; wherein: The shooting unit, the partitioned ring light source and the planar coaxial light source are all arranged on the bracket; The partitioned ring light source and the planar coaxial light source are arranged on the optical axis of the shooting unit at a preset distance; The planar coaxial light source is arranged under the partitioned annular light source; The partitioned annular light source is divided into a plurality of arc-shaped light sources according to preset angles.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for detecting defects of an explosion-proof valve of a battery cell according to any one of claims 1 to 7.

Images