Detection method and device, program product and storage medium

Abstract

The invention discloses a detection method and device, a program product and a storage medium. The detection method is used for the lithium ion battery, the lithium ion battery comprises a pole piece, and the detection method comprises the steps of obtaining an initial reference image of the pole piece; preprocessing the initial reference image to obtain a processed image; and labeling the abnormal information of the processed image according to a preset feature gray gradient to obtain a detection result of the pole piece, the detection result of the pole piece comprising abnormal type information and abnormal area proportion information of the pole piece. The pole piece image of the lithium ion battery is detected through an image recognition technology, so that compared with the prior art that the pole piece is detected through naked eyes of an engineer and the abnormity of the pole piece is judged according to working experience, the accuracy of whether the pole piece is abnormal or not in a detection result can be improved; and the abnormal type and the abnormal area proportion of the pole piece can be accurately known.

Description

Technical Field

[0001] The present application belongs to the technical field of energy storage batteries, and in particular relates to a detection method, a first detection device, a second detection device, a computer program product, and a non-volatile computer-readable storage medium. Background Art

[0002] In related technologies, during the charge and discharge process of lithium-ion batteries, due to defects such as bubbles and diaphragm wrinkles between the electrodes, black spots, brown spots, yellow spots, and lithium deposition may appear on the electrodes, resulting in loss of battery capacity and affecting the normal use of the battery. In severe cases, lithium deposition may pierce the diaphragm, causing the lithium-ion battery to short-circuit, catch fire, explode, etc., posing a safety hazard.

[0003] Currently, the industry generally relies on naked-eye inspection by engineers to detect abnormalities in lithium-ion battery electrodes. However, this method is subject to strong subjectivity and lacks quantitative standards for determining the type of electrode anomaly and the proportion of the abnormal area. This relies entirely on the engineer's experience, and different engineers may have different naked-eye recognition methods, resulting in inaccurate test results. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a detection method, a first detection device, a second detection device, a computer program product, and a non-volatile computer-readable storage medium.

[0005] An embodiment of the present invention provides a detection method for a lithium-ion battery, wherein the lithium-ion battery includes a pole piece. The detection method includes obtaining an initial reference image of the pole piece; preprocessing the initial reference image to obtain a processed image; and marking abnormal information of the processed image according to a preset characteristic grayscale gradient to obtain a detection result of the pole piece, wherein the detection result of the pole piece includes abnormal type information and abnormal area ratio information of the pole piece.

[0006] In this way, by using image recognition technology to inspect images of lithium-ion battery electrode sheets, it is possible to detect the type of anomaly and the area occupied by the anomaly if an anomaly is present. Compared to the existing technology of inspecting electrode sheets with the naked eye and judging anomalies based on work experience, this method can improve the accuracy of the detection results of whether an anomaly is present in the electrode sheet, and can accurately determine the type of anomaly and the area occupied by the anomaly.

[0007] In some embodiments, acquiring the initial reference image of the pole piece includes adjusting a posture of a camera so that the camera can acquire the complete initial reference image of the pole piece.

[0008] In this way, by adjusting the position of the camera so that the camera can capture the complete electrode, it is possible to avoid anomalies on the electrode that are missed when the camera is shooting, which may lead to inaccurate detection results.

[0009] In some embodiments, the preprocessing of the initial reference image to obtain multiple processed images includes cutting the initial reference image according to a preset characteristic color value distribution to obtain a cut image; and graying the cut image to obtain the processed image.

[0010] In this way, by cutting the initial reference image through the characteristic color value distribution, a cutting image containing only the pole pieces can be obtained, avoiding the influence of the environment on the detection results; by graying the cutting image, the abnormality can be determined according to the grayscale value of the grayscale image.

[0011] In certain embodiments, the abnormal information of the processed image is marked according to a preset characteristic grayscale gradient to obtain the detection result of the pole piece, including establishing a rectangular coordinate system based on the processed image; calculating the first characteristic grayscale gradient in the first axis direction and the second characteristic grayscale gradient in the second axis direction of the rectangular coordinate system in the processed image; comparing the first characteristic grayscale gradient and the second characteristic grayscale gradient with the preset characteristic grayscale gradient to obtain the abnormal boundary of the pole piece; and highlighting the abnormal boundary to obtain the detection result of the pole piece.

[0012] In this way, by establishing a rectangular coordinate system and calculating the characteristic grayscale gradient of the processed image, the abnormal boundary of the pole piece can be obtained according to the preset characteristic grayscale gradient, and then the type and area ratio of the abnormality can be obtained.

[0013] In certain embodiments, the detection method includes detecting the processed image according to a preset edge detection algorithm or neural network model to obtain a detection result of the electrode.

[0014] In this way, the processed image can be detected according to the edge detection algorithm or the neural network model, so that the detection result of the electrode can be obtained. Compared with the existing technology of detecting the electrode with the naked eye of the engineer and judging the abnormality of the electrode based on work experience, the accuracy of whether the electrode has abnormalities in the detection results can be improved, and the type of abnormality of the electrode and the proportion of the abnormal area can be accurately known.

[0015] In some embodiments, the detection method includes storing the detection results of the pole piece.

[0016] In this way, by storing the test results, the loss of the test results can be prevented, thereby avoiding repeated testing and improving the detection efficiency.

[0017] In certain embodiments, the detection method is performed in a protective chamber filled with protective gas.

[0018] In this way, by setting the detection process in a protective chamber, the electrode can be prevented from being contaminated by external links, which may lead to inaccurate detection results.

[0019] In certain embodiments, the detection method includes controlling the type of protective gas introduced into the protective chamber according to the type of the lithium-ion battery.

[0020] In this way, by determining the type of protective gas in the protective chamber according to the type of lithium-ion battery, it is possible to avoid the protective gas from reacting with the electrode, thereby preventing the detection result from being inaccurate.

[0021] An embodiment of the present invention provides a first detection device for a lithium-ion battery, the lithium-ion battery including a pole piece. The first detection device includes a control module and an identification module. The control module is configured to obtain an initial reference image of the pole piece; the identification module is configured to preprocess the initial reference image to obtain a processed image, and to annotate abnormal information in the processed image according to a preset characteristic grayscale gradient to obtain a detection result for the pole piece.

[0022] In some embodiments, the first detection device includes an image acquisition module, which includes a camera, a bracket and a placement platform. The placement platform is used to place the pole piece of the lithium-ion battery. The camera is installed on the bracket. The image acquisition module is used to control the movement of the bracket to adjust the position of the camera so that the camera can obtain an initial reference image of the complete pole piece.

[0023] In this way, by controlling the bracket to adjust the position of the camera, the camera can capture the complete electrode, which can prevent abnormalities from being missed and improve the accuracy of the detection results.

[0024] In certain embodiments, the first detection device includes a storage module, and the storage module is configured to store the detection results of the electrode.

[0025] In this way, by storing the test results in the storage module, the loss of the test results can be prevented, thereby avoiding repeated testing and improving the detection efficiency.

[0026] In some embodiments, the first detection device includes a protection module, which includes a protection chamber, a protection gas, and a pressure reducing valve. The image acquisition module is arranged in the protection chamber. The protection gas is introduced into the protection chamber to isolate the image acquisition module from the outside air. The pressure reducing valve is used to control the protection gas from entering the protection chamber.

[0027] By performing the test in a protective chamber, the electrode can be protected from contamination by external factors, which could lead to inaccurate test results. By installing a pressure reducing valve, the protective gas can be continuously controlled to flow into the protective chamber, preventing the protective gas from being interrupted and affecting the test results.

[0028] The present invention provides a second detection device including a processor and a memory, wherein the memory stores a computer program. When the computer program is executed by the processor, the processor implements the above-mentioned detection method.

[0029] A computer program product provided by an embodiment of the present invention includes a computer program, and the computer program includes instructions for executing the detection method described in any one of the above embodiments.

[0030] An embodiment of the present invention provides a non-volatile computer-readable storage medium containing computer-executable instructions. When the computer program is executed by a processor, the processor executes the detection method described in any one of the above embodiments.

[0031] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0033] Figure 1 A schematic structural diagram of a first detection device and a lithium-ion battery in certain embodiments of the present invention;

[0034] Figure 2 is a schematic structural diagram of a second detection device in certain embodiments of the present invention;

[0035] Figure 3 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0036] Figure 4 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0037] Figure 5 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0038] Figure 6 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0039] Figure 7 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0040] Figure 8 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0041] Figure 9 Schematic diagram of the detection method flow of certain embodiments of the present invention;

[0042] Figure 10 is a schematic diagram of a module of a first detection device according to certain embodiments of the present invention;

[0043] Figure 11 The figure is a schematic diagram of the connection state between a non-volatile computer-readable storage medium and a processor according to certain embodiments of the present invention.

[0044] Description of Figure Numbers:

[0045] 100. Lithium-ion battery; 10. Electrode; 11. Positive electrode; 12. Negative electrode; 200. First detection device; 210. Control module; 220. Identification module; 230. Image acquisition module; 231. Camera; 232. Bracket; 233. Placement platform; 240. Storage module; 250. Protection module; 251. Protection compartment; 252. Pressure reducing valve; 260. Selection module; 300. Second detection device; 310. Processor; 320. Memory; 321. Computer program; 400. Storage medium. DETAILED DESCRIPTION

[0046] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and should not be understood as limiting the embodiments of the present application.

[0047] See also Figure 1 、 Figure 2 and Figure 3 The present invention provides a detection method for a lithium-ion battery 100, wherein the lithium-ion battery 100 includes a pole piece 10, and the detection method includes:

[0048] Step 011: Acquire an initial reference image of the pole piece 10;

[0049] Step 012: pre-processing the initial reference image to obtain a processed image;

[0050] Step 013: Annotate the abnormal information of the processed image according to the preset characteristic grayscale gradient to obtain the detection result of the pole piece 10. The detection result of the pole piece 10 includes the abnormal type information and abnormal area ratio information of the pole piece 10.

[0051] In this way, by using image recognition technology to inspect the image of the electrode 10 of the lithium-ion battery 100, if an abnormality exists on the electrode 10, the type of abnormality and the area occupied by the abnormality can be detected. Compared with the prior art of inspecting the electrode 10 with the naked eye and judging the abnormality of the electrode 10 based on work experience, the accuracy of the detection results of whether the electrode 10 has an abnormality is improved, and the type of abnormality and the area occupied by the abnormality in the electrode 10 can be accurately determined.

[0052] The lithium-ion battery 100 is a secondary battery system that uses two different intercalation compounds that can reversibly intercalate and deintercalate lithium ions as positive and negative electrodes. It operates by the movement of lithium ions between the positive and negative electrodes. During the charge and discharge process, Li+ intercalates and deintercalates back and forth between the two electrodes. During charging, Li+ deintercalates from the positive electrode and then intercalates into the negative electrode through the electrolyte, leaving the negative electrode in a lithium-rich state. During discharge, the opposite occurs, with Li+ deintercalating from the negative electrode and returning to the positive electrode material through the electrolyte. This process is accompanied by the flow of electrons in an external circuit, generating an electric current.

[0053] The lithium-ion battery 100 can be lithium iron phosphate, ternary lithium, or lithium-rich manganese-based, and includes pole pieces 10, which include a positive electrode 11 and a negative electrode 12. During the charge and discharge process, the lithium-ion battery 100 may develop black spots, brown spots, yellow spots, or lithium deposition due to defects such as bubbles between the pole pieces 10 and diaphragm wrinkles. This can lead to battery capacity loss and affect normal battery operation. In severe cases, the deposited lithium can pierce the diaphragm, causing the battery to short-circuit, catch fire, or explode, posing a safety hazard. Therefore, in the production of lithium-ion batteries 100, it is very important to detect abnormalities in the pole pieces 10.

[0054] The second detection device 300 can be used to detect whether the electrode 10 of the lithium-ion battery 100 has an abnormality. The second detection device 300 includes a processor 310, a memory 320, and a computer program 321. The computer program 321 is stored in the memory 320 and can be executed by the processor 310. The computer program 321 includes instructions for executing the detection method.

[0055] Specifically, when inspecting the electrode 10 of the lithium-ion battery 100, the processor 310 needs to obtain an initial reference image of the electrode 10. The initial reference image of the electrode 10 includes information indicating whether the electrode 10 has any abnormalities. After receiving the initial reference image, the processor 310 needs to preprocess the initial reference image to obtain a processed image. The processed image removes background noise present in the initial reference image and retains only the complete image of the electrode 10, thereby preventing interference with the inspection results caused by images other than the electrode 10.

[0056] Then, the processor 310 can mark the abnormalities in the processed image according to the preset characteristic grayscale gradient to obtain a detection result. In the case where the processed image contains the marked information, the processor 310 can identify the presence of the abnormality in the processed image, so that the obtained detection result can include the abnormality type information and abnormal area ratio information of the electrode 10. For example, in the case where the processed image contains the marked information, the processor 310 can identify whether the abnormality is one or more of a black spot, a yellow spot, or a lithium deposition abnormality, and how much area the abnormality occupies in the electrode 10.

[0057] In the case where no annotation information is detected in the processed image, it indicates that there is no abnormality in the electrode piece 10 and the lithium-ion battery 100 can operate normally.

[0058] In some embodiments, the abnormality type information included in the detection result of the electrode piece 10 is determined by the remaining power of the lithium-ion battery 100.

[0059] Specifically, when the electrode 10 is a lithium iron phosphate battery electrode 10 with 100% remaining power, the electrode 10 includes a positive electrode 11 and a negative electrode 12. The negative electrode 12 is made of graphite and appears golden yellow at 100% remaining power. Due to defects in battery manufacturing, some areas are blocked by gas and gaps, resulting in black spots and brown spots indicating incomplete charging, and abnormal lithium deposition areas where lithium ion intercalation and deintercalation are hindered.

[0060] When the electrode 10 is a lithium iron phosphate battery electrode 10 with a remaining charge of 25%, the electrode 10 includes a positive electrode 11 and a negative electrode 12. The negative electrode is made of graphite and appears black at a remaining charge of 25%. Due to defects in battery manufacturing, some areas are blocked by gas and gaps, resulting in yellow spots of incomplete discharge and lithium plating due to hindered lithium ion insertion and extraction.

[0061] When the electrode 10 is a ternary lithium battery electrode 10 with 100% remaining charge, the electrode 10 includes a positive electrode 11 and a negative electrode 12. The negative electrode 12 is made of graphite and appears golden yellow at 100% remaining charge. Due to defects in battery manufacturing, some areas are blocked by gas and gaps, resulting in black spots and brown spots indicating incomplete charging, as well as abnormal lithium deposition areas where lithium ion intercalation and deintercalation are hindered.

[0062] See also Figure 4 In some embodiments, step 011: obtaining an initial reference image of the pole piece 10 includes:

[0063] Step 0111 : Adjust the position of the camera 231 so that the camera 231 can obtain an initial reference image of the complete pole piece 10 .

[0064] Specifically, the first detection device 200 is provided with an image acquisition module 230. The image acquisition module 230 includes a camera 231. When the processor 310 needs to obtain an initial reference image of the electrode piece 10, the processor 310 sends an image acquisition instruction to the image acquisition module 230. Upon receiving the instruction, the image acquisition module 230 controls the camera 231 to take a picture of the electrode piece 10 to obtain the initial reference image of the electrode piece 10. Among them, the initial reference image of the pole piece 10 taken by the camera 231 may be missing. At this time, the processor 310 can determine the edge position of the pole piece 10 through the preset characteristic color value of the pole piece 10. If the preset characteristic color value of the pole piece 10 does not exist in the initial reference image, it indicates that the pole piece 10 is missing. The processor 310 can send an instruction to the image acquisition module 230 to re-capture the initial reference image of the pole piece 10. After receiving the re-capture instruction, the image acquisition module 230 can adjust the posture of the camera 231, such as controlling the camera 231 to move left, right, forward, and backward, and adjusting the distance of the camera 231 relative to the pole piece 10, so that the complete pole piece 10 is within the shooting range of the camera 231.

[0065] In this way, the processor 310 can obtain an initial reference image of the complete pole piece 10 .

[0066] See also Figure 5 In some embodiments, step 012: pre-processing the initial reference image to obtain a plurality of processed images includes:

[0067] Step 0121: performing a segmentation process on the initial reference image according to a preset characteristic color value distribution to obtain a segmented image;

[0068] Step 0122: Grayscale the cut image to obtain a processed image.

[0069] Specifically, after the processor 310 obtains the initial reference image, the initial reference image needs to be processed. Since the initial reference image at this time includes a background image outside the pole piece 10, the noise in the background image can affect the detection results and reduce the accuracy of the detection results, so it is necessary to remove the background image outside the pole piece 10.

[0070] The processor 310 can perform a cutting process on the initial reference image according to a preset characteristic color value distribution. The preset characteristic color value distribution can be a characteristic color value range or a color threshold preset in the first detection device 200 to match the electrode 10. Then, based on the characteristic color value distribution of the electrode 10, the pixels in the image that meet the characteristic color value range are separated from the pixels that do not meet the range. For example, the processor 310 can achieve this by comparing the color value of each pixel with a preset threshold. Then, based on the result of the threshold segmentation, the image area that needs to be cut in the initial reference image is determined. Finally, the processor 310 can use the image cutting function to cut the image according to the determined cutting area to obtain a cut image.

[0071] After obtaining the cut image, processor 310 grayscales the cut image to produce a grayscale processed image. The grayscale processed image contains only brightness information. Converting a color cut image to a grayscale image removes color information, retaining only brightness information. This simplifies the image content, reduces the amount of data required for processing, and helps lower the computational complexity of subsequent image processing, improving processing efficiency. Furthermore, pixel value changes in a grayscale image are simpler and more direct, enabling processor 310 to accurately extract image features when detecting abnormal characteristic grayscale gradients.

[0072] See also Figure 6 In some embodiments, step 013: marking abnormal information of the processed image according to a preset characteristic grayscale gradient to obtain a detection result of the electrode 10 includes:

[0073] Step 0131: Establish a rectangular coordinate system based on the processed image;

[0074] Step 0132: Calculate a first characteristic grayscale gradient along a first axis direction and a second characteristic grayscale gradient along a second axis direction in the processed image;

[0075] Step 0133: Compare the first characteristic grayscale gradient and the second characteristic grayscale gradient with a preset characteristic grayscale gradient to obtain an abnormal boundary of the pole piece 10;

[0076] Step 0134: Highlight the abnormal boundary to obtain the detection result of the pole piece 10.

[0077] Specifically, after the processor 310 acquires the processed image, a rectangular coordinate system is established on the pole piece 10 in the processed image, so that the processor 310 can calculate the first characteristic grayscale gradient along the first axis direction of the rectangular coordinate system and the second characteristic grayscale gradient along the second axis direction in the processed image. The first axis direction of the rectangular coordinate system can be one of the horizontal axis or the vertical axis of the rectangular coordinate system, and the second axis direction is the other of the horizontal axis or the vertical axis of the rectangular coordinate system.

[0078] Processor 310 then compares the first characteristic grayscale gradient with the second characteristic grayscale gradient based on a preset characteristic grayscale gradient. The preset characteristic grayscale gradient includes grayscale gradients specific for melasma, macula, and lithium deposition. Based on the comparison results, processor 310 can determine the boundaries of abnormalities in the processed image and highlight the abnormal boundaries.

[0079] Finally, the processor 310 can obtain the detection result of the pole piece 10 based on the highlighted abnormalities.

[0080] See also Figure 7 In some embodiments, step 013: obtaining the detection result of the electrode includes:

[0081] Step 0131: Detect the processed image according to a preset edge detection algorithm or neural network model to obtain a detection result of the electrode 10.

[0082] Specifically, after the processor 310 acquires the processed image, it detects the processed image using a preset edge detection algorithm or neural network model, thereby obtaining the detection results of the electrode 10. The edge detection algorithm can detect locations in the image where grayscale changes are discontinuous, and locations where discontinuities occur can indicate an abnormality on the electrode 10. For the grayscale processed image, the edge detection algorithm calculates the image gradient to identify locations where pixel values change rapidly, thereby determining the location and direction of the edge.

[0083] For example, edge detection algorithms calculate the gradient size and direction of each pixel in the image to determine the intensity and trend of grayscale changes. Among them, gradient calculations usually use various edge detection operators, such as the Sobel operator, Prewitt operator, Roberts operator, etc. Then, by comparing the gradient size, only the local maximum value in the gradient direction is retained, thereby removing non-edge points. Then, strong edges and weak edges are determined by setting two thresholds (high threshold and low threshold). Pixels above the high threshold are determined as strong edges, pixels below the low threshold are determined as non-edges, and pixels between the two thresholds are determined as weak edges or discarded based on the connectivity of the neighboring pixels. Finally, a connection algorithm (such as hysteresis threshold) is used to connect the weak edges into a complete edge contour, thereby improving the accuracy of edge detection.

[0084] The neural network model may be a convolutional neural network model. After the processor 310 inputs the processed image into the convolutional neural network model, the convolutional neural network model includes an input layer, a convolution layer, a pooling layer, a connection layer, and an output layer, and can detect the processed image, thereby outputting a detection result of the electrode 10.

[0085] Please refer again Figure 1 and Figure 8 In certain embodiments, the detection method comprises:

[0086] Step 014: Store the detection result of the electrode 10.

[0087] Specifically, after the processor 310 obtains the detection result of the electrode piece 10, it can transmit the detection result of the electrode piece 10 and the processed image of the electrode piece 10 to the storage module 240 of the first detection device 200 for storage. The storage module 240 can be not only a computer unit with a storage device, but also an independent storage medium 400 such as an SD card or a hard disk with read and write functions.

[0088] See also Figure 9 In certain embodiments, the detection method comprises:

[0089] Step 015: Control the type of protective gas introduced into the protective chamber 251 according to the type of the lithium-ion battery 100 .

[0090] Specifically, when the first detection device 200 detects the electrode 10, it is necessary to control the detection environment of the electrode 10 to prevent the environment from contaminating the electrode 10 and causing inaccurate detection results. For example, the electrode 10 can be detected in a protective chamber 251, and the protective chamber 251 is filled with a protective gas. The protective gas can prevent the active electrode 10 from contacting the external environment, causing anomalies and thus affecting the detection results.

[0091] The processor 310 can control the type of protective gas introduced into the protective chamber 251 based on the type of lithium-ion battery 100 being tested. For example, if the lithium-ion battery 100 is a lithium iron phosphate battery, the protective gas includes, but is not limited to, dry gas, a gas that is free of water and has an oxygen content no greater than that of air, or a gas with a lower oxidizing ability. If the lithium-ion battery 100 is a ternary lithium or lithium-manganese-rich lithium battery, the protective gas includes, but is not limited to, nitrogen or an inert gas. Since the electrode 10 is highly active, easily oxidized, and flammable and explosive, nitrogen or an inert gas should be selected as the protective gas to prevent oxidation and denaturation of the electrode 10 during the testing process, which could affect the accuracy of the test, and to prevent the electrode 10 from spontaneously combusting or exploding, which could pose a risk.

[0092] See also Figure 10To facilitate better implementation of the detection method of the embodiment of the present invention, the embodiment of the present invention further provides a first detection device 200. The first detection device 200 is used for a lithium-ion battery 100, which includes a pole piece 10. The first detection device 200 includes a control module 210 and an identification module 220. The control module 210 is used to obtain an initial reference image of the pole piece 10; the identification module 220 is used to preprocess the initial reference image to obtain a processed image, and to annotate abnormal information in the processed image according to a preset characteristic grayscale gradient to obtain a detection result of the pole piece 10.

[0093] The control module 210 is specifically configured to adjust the position of the camera 231 so that the camera 231 can obtain an initial reference image of the complete pole piece 10 .

[0094] The recognition module 220 is specifically configured to perform a segmentation process on the initial reference image according to a preset characteristic color value distribution to obtain a segmented image; and perform grayscale conversion on the segmented image to obtain a processed image.

[0095] The identification module 220 is specifically used to establish a rectangular coordinate system based on the processed image; calculate the first characteristic grayscale gradient along the first axis direction and the second characteristic grayscale gradient along the second axis direction of the rectangular coordinate system in the processed image; compare the first characteristic grayscale gradient and the second characteristic grayscale gradient with the preset characteristic grayscale gradient to obtain the abnormal boundary of the pole piece 10; highlight the abnormal boundary to obtain the detection result of the pole piece 10.

[0096] The recognition module 220 is specifically configured to detect the processed image according to a preset edge detection algorithm or neural network model to obtain a detection result of the pole piece 10 .

[0097] The first detection device 200 further includes a storage module 240 , which is specifically used to store the detection results of the electrode 10 .

[0098] The first detection device 200 further includes a selection module 260 , which is specifically configured to control the type of protective gas introduced into the protective chamber 251 according to the type of the lithium-ion battery 100 .

[0099] In some embodiments, the recognition module 220 may be not only a computer unit, but also a portable device or an embedded system or other device with image processing and recognition functions.

[0100] The first detection device 200 is described above from the perspective of a functional module in conjunction with the accompanying drawings. The functional module can be implemented in hardware form, can be implemented by instructions in software form, or can be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present invention can be completed by the hardware integrated logic circuit and / or software form instructions in the processor 310. The steps of the method disclosed in conjunction with the embodiment of the present invention can be directly embodied as being executed by the hardware encoding processor 310, or can be executed by a combination of hardware and software modules in the encoding processor 310. Optionally, the software module can be located in a mature storage medium 400 in the art, such as a random access memory 320, a flash memory, a read-only memory 320, a programmable read-only memory 320, an electrically erasable programmable memory 320, or a register. The storage medium 400 is located in the memory 320, and the processor 310 reads the information in the memory 320 and completes the steps in the above method embodiment in conjunction with its hardware.

[0101] Please refer again Figure 1 In some embodiments, the first detection device 200 includes an image acquisition module 230, which includes a camera 231, a bracket 232 and a placement platform 233. The placement platform 233 is used to place the pole piece 10 of the lithium-ion battery 100. The camera 231 is installed on the bracket 232. The image acquisition module 230 is used to control the movement of the bracket 232 to adjust the position of the camera 231 so that the camera 231 can obtain an initial reference image of the complete pole piece 10.

[0102] In this way, by controlling the bracket 232 to adjust the position of the camera 231, the camera 231 can capture the complete pole piece 10, thereby preventing abnormalities from being missed and improving the accuracy of the detection results.

[0103] Specifically, the first detection device 200 includes an image acquisition module 230, which can be used to acquire an initial reference image of the electrode piece 10. The image acquisition module 230 includes a camera 231, a bracket 232, and a placement platform 233. The placement platform 233 can be used to place the electrode piece 10 of the lithium-ion battery 100. The camera 231 is mounted on the bracket 232, and the bracket 232 can move forward, backward, left, right, upward, and downward. The position of the camera 231 can be adjusted by controlling the movement of the bracket 232, so that the camera 231 can acquire an initial reference image of the complete electrode piece 10.

[0104] See also Figure 1 In some embodiments, the first detection device 200 includes a storage module 240 , which is configured to store the detection results of the electrode 10 .

[0105] In this way, by storing the detection results in the storage module 240, it is possible to prevent the detection results from being lost, thereby avoiding repeated detection and improving detection efficiency.

[0106] Specifically, the first detection device 200 includes a storage module 240, which is configured to store the detection results of the electrode piece 10. For example, the storage module 240 can store the detection results of the electrode piece 10 and the processed image of the electrode piece 10. The storage module 240 can be not only a computer with a storage device, but also an independent storage medium 400 such as an SD card or a hard disk with read and write functions.

[0107] See also Figure 1 In some embodiments, the first detection device 200 includes a protection module 250, the protection module 250 includes a protection chamber 251, a protection gas and a pressure reducing valve 252, the image acquisition module 230 is arranged in the protection chamber 251, the protection gas is introduced into the protection chamber 251 to isolate the image acquisition module 230 from the outside air, and the pressure reducing valve 252 is used to control the protection gas to enter the protection chamber 251.

[0108] Thus, by setting the detection process in the protective chamber 251, the electrode 10 can be prevented from being contaminated by external links, which may lead to inaccurate detection results. By setting the pressure reducing valve 252, the air pressure in the protective chamber 251 can be controlled to avoid the protective gas from being interrupted and affecting the detection results.

[0109] Specifically, the first detection device 200 also includes a protection module 250, which can be used to protect the electrode 10 of the lithium-ion battery 100 from interference from the external environment. The protection module 250 includes a protection chamber 251, a protective gas, and a pressure reducing valve 252. The protection chamber 251 can be a glass protection chamber 251. The image acquisition module 230 can be disposed in the protection chamber 251. The protective gas is introduced into the protection chamber 251 through the pressure reducing valve 252. The protective gas enters from one end of the protection chamber 251 and exits from the other end, thereby isolating the image acquisition module 230 from the outside air.

[0110] See also Figure 11 The present invention provides a non-volatile computer-readable storage medium 400 containing a computer program 321, characterized in that when the computer program 321 is executed by the processor 310, the processor 310 implements the above-mentioned detection method.

[0111] In some embodiments, the computer-readable storage medium 400 may be a storage medium 400 built into the electronic device, such as the memory 320, or a storage medium 400 that can be plugged into the electronic device, such as an SD card.

[0112] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related software using a computer program 321. The program can be stored in a non-volatile computer-readable storage medium 400. When executed, the program can include the processes in the above-described method embodiments. The storage medium 400 can be a magnetic disk, an optical disk, a read-only memory (ROM), or the like.

[0113] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "example", "specific example" or "some examples" is intended to mean that the specific features, structures, materials or characteristics described in combination with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are mutually contradictory. At the same time, the description with reference to the terms "first", "second" and the like is intended to distinguish the same or similar operations. In some embodiments, there is a logical relationship between "first" and "second", but in some embodiments, there is not necessarily a logical or front-to-back relationship. It needs to be determined based on the actual embodiment and should not be determined only by the literal meaning.

[0114] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0115] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A detection method for lithium-ion batteries, characterized in that: The lithium-ion battery includes a pole piece, and the detection method includes: Acquiring an initial reference image of the pole piece; Preprocessing the initial reference image to obtain a processed image; The abnormal information of the processed image is marked according to a preset characteristic grayscale gradient to obtain a detection result of the pole piece, and the detection result of the pole piece includes abnormal type information and abnormal area ratio information of the pole piece.

2. The detection method according to claim 1, wherein The obtaining of the initial reference image of the pole piece includes: The position of the camera is adjusted so that the camera can obtain a complete initial reference image of the pole piece.

3. The detection method according to claim 1, wherein Preprocessing the initial reference image to obtain a plurality of processed images includes: Performing a segmentation process on the initial reference image according to a preset characteristic color value distribution to obtain a segmented image; Grayscale the cut image to obtain the processed image.

4. The detection method according to claim 1, wherein The abnormal information of the processed image is marked according to a preset characteristic grayscale gradient to obtain the detection result of the electrode, including: establishing a rectangular coordinate system according to the processed image; Calculate a first characteristic grayscale gradient along a first axis direction and a second characteristic grayscale gradient along a second axis direction of the rectangular coordinate system in the processed image; Comparing the first characteristic grayscale gradient and the second characteristic grayscale gradient with the preset characteristic grayscale gradient to obtain an abnormal boundary of the pole piece; The abnormal boundary is highlighted to obtain the detection result of the pole piece.

5. The detection method according to claim 1, wherein The detection method comprises: The processed image is detected according to a preset edge detection algorithm or neural network model to obtain a detection result of the electrode.

6. The detection method according to claim 1, characterized in that The detection method comprises: The detection result of the pole piece is stored.

7. The detection method according to claim 1, characterized in that The detection method is carried out in a protective chamber which is filled with protective gas.

8. The detection method according to claim 7, characterized in that The detection method comprises: The type of protective gas introduced into the protective chamber is controlled according to the type of the lithium-ion battery.

9. A first detection device for lithium-ion batteries, characterized in that: The lithium-ion battery includes a pole piece, and the first detection device includes: A control module, configured to obtain an initial reference image of the pole piece; The recognition module is used to pre-process the initial reference image to obtain a processed image, and to mark abnormal information of the processed image according to a preset characteristic grayscale gradient to obtain a detection result of the electrode.

10. The first detection device according to claim 9, characterized in that: The first detection device includes an image acquisition module, which includes a camera, a bracket and a placement platform. The placement platform is used to place the pole piece of the lithium-ion battery. The camera is installed on the bracket. The image acquisition module is used to control the movement of the bracket to adjust the position of the camera so that the camera can obtain an initial reference image of the complete pole piece.

11. The first detection device according to claim 9, characterized in that: The first detection device includes a storage module, and the storage module is configured to store the detection results of the pole piece.

12. The first detection device according to claim 9, characterized in that: The first detection device includes a protection module, which includes a protection chamber, a protection gas and a pressure reducing valve. The image acquisition module is arranged in the protection chamber. The protection gas is introduced into the protection chamber to isolate the image acquisition module from the outside air. The pressure reducing valve is used to control the protection gas from entering the protection chamber.

13. A second detection device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor implements the detection method according to any one of claims 1 to 8.

14. A computer program product, characterized in that The invention comprises a computer program comprising instructions for executing the detection method according to any one of claims 1 to 8.

15. A non-volatile computer-readable storage medium containing a computer program, characterized in that When the computer program is executed by a processor, the processor implements the detection method according to any one of claims 1 to 8.

Images