Picture definition determination method and device, electronic equipment and storage medium

Abstract

The application provides a picture definition determination method and device, electronic equipment and storage medium. The method comprises collecting image data of different angles of an electric core, and performing instance segmentation on the image data to generate a segmentation mask of each instance region; determining an OH negative electrode region as a subgraph according to the segmentation mask, and taking a subgraph meeting a gray value calculation requirement as a target subgraph; performing gray value calculation on the target subgraph to generate a gray distribution graph, and a wave trough gray value of the gray distribution graph represents the number of layers of the electric core; calculating the number of layers of the electric core according to the gray distribution graph, and determining the picture definition according to the calculated number of layers of the electric core. The application helps to improve the accuracy and efficiency of electric core detection.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, electronic device, and storage medium for determining image clarity. Background Art

[0002] The use of X-ray imaging technology for nondestructive testing of wound lithium-ion cells is a critical step in battery production, helping to control battery quality. This method utilizes an X-ray transmitter to emit X-rays that penetrate the cell, which are then received and imaged by a flat panel. Software algorithms process the X-ray images to obtain relevant data and determine good and bad parts based on process requirements. During the inspection process, automated machinery primarily handles tasks such as cell or battery logistics, photo location, and unloading of failed (NG) parts. Software algorithms analyze the X-ray images of the cells to determine their condition, ensuring a smooth inspection.

[0003] Currently, X-ray imaging and inspection equipment uses the human eye to observe the OH (OverHang) region of the negative electrode, where the negative electrode extends beyond the positive electrode, and determines the image clarity based on whether the human eye can clearly see the number of layers in the battery cell. Therefore, it is necessary to provide a method for determining image clarity. Summary of the Invention

[0004] The present application provides a method, device, electronic device and storage medium for determining image clarity, so as to solve the problem of how to determine image clarity.

[0005] In a first aspect, the present application provides a method for determining image clarity, the method comprising:

[0006] Collect image data of the battery cell at different angles, and perform instance segmentation on the image data to generate a segmentation mask for each instance area;

[0007] Determine the OH negative electrode region as a sub-image according to the segmentation mask, and use the sub-image that meets the grayscale value calculation requirements as the target sub-image;

[0008] Performing grayscale calculation on the target sub-image to generate a grayscale distribution graph, wherein the grayscale value of a trough of the grayscale distribution graph represents the number of layers of the battery cell;

[0009] The number of layers of the battery cell is calculated according to the grayscale distribution diagram, and the image clarity is determined according to the calculated number of layers of the battery cell.

[0010] In some embodiments of the present application, the step of collecting image data of the battery cell at different angles and performing instance segmentation on the image data to generate a segmentation mask for each instance region includes:

[0011] Collect image data of at least one angle of the battery cell, the at least one angle includes a first angle, and the image data set A corresponding to the first angle is A={a1, a2, ..., a nb}, a i (1≤i≤n b ) is the i-th original image of the image dataset A corresponding to the first angle;

[0012] Use the preset segmentation algorithm to segment the original image a i Perform instance segmentation to generate segmentation masks for each instance region, where masks = {m1, m2, ..., m nb}, m i (1≤i≤n b ) is the i-th mask in the segmentation mask masks list.

[0013] In some embodiments of the present application, the step of determining the OH negative electrode region as a sub-image according to the segmentation mask and using the sub-image that meets the grayscale value calculation requirements as the target sub-image includes:

[0014] According to the segmentation mask and the characteristics of the target area, the OH negative electrode area is screened out from the original image and used as the initial sub-image;

[0015] Determine whether the sub-image has an area that affects grayscale value calculation;

[0016] If the sub-image has an area that affects the grayscale value calculation, the sub-image is optimized to obtain the target sub-image that meets the grayscale value calculation requirements.

[0017] In some embodiments of the present application, before performing the step of screening out the OH negative electrode region from the original image based on the segmentation mask and the features of the target region and using it as the initial sub-image, the method further includes:

[0018] If the target area is not found in the original image, optimizing the original image;

[0019] Re-segment the optimized image data to find the target area and obtain the corresponding segmentation mask.

[0020] In some embodiments of the present application, the step of performing grayscale calculation on the target sub-image to generate a grayscale distribution graph, wherein the grayscale value of the trough of the grayscale distribution graph represents the number of layers of the battery cell, includes:

[0021] Calculate the grayscale value of each column of pixels in the target sub-image using the following formula:

[0022]

[0023] Among them, sum(sub_img1_gray, 0) means calculating the grayscale value of each column of pixels in the target sub-image from left to right, and count(sub_img1_nonzero) means calculating the number of non-zero pixels in each column of the target sub-image from left to right;

[0024] The grayscale average value is calculated according to the grayscale values ​​of the pixels in each column to obtain a grayscale distribution diagram representing the grayscale average value.

[0025] In some embodiments of the present application, the step of calculating the number of layers of the battery cell according to the grayscale distribution map and determining the image clarity according to the calculated number of layers of the battery cell includes:

[0026] configuring a local minimum function, and finding a trough position according to the local minimum function, wherein the trough position represents an area with the lowest grayscale value in the image;

[0027] According to the distance between each layer and the valley position in the OH negative electrode region, the valley grayscale value is set to meet the first condition:

[0028] std(mingray_val-7:mingray_index+7)<δ;

[0029] Wherein, mingray_val≤min(mingray_index±0.8L), mingray_val represents the grayscale value of the trough, mingray_index represents the position of the trough, std() represents the standard deviation, min() represents the local minimum function, δ represents the preset threshold, L represents the distance between each layer in the OH negative electrode region, and min(mingray_index±0.8L) represents the minimum grayscale value within the length range of 0.8L before and after the trough;

[0030] According to the distance between each layer in the OH negative electrode region and the preset standard number of layers, the maximum length of the calculated cell layers is set to meet the second condition:

[0031] L max =L*N+bias;

[0032] Among them, L max Indicates the maximum length of the calculated battery cell layers, bias indicates the preset compensation value, and N indicates the preset standard number of layers;

[0033] When either the first condition or the second condition is not met, stopping counting the number of layers of the battery cell;

[0034] When both the first condition and the second condition are satisfied, the number of layers of the battery cell is continued to be calculated.

[0035] In some embodiments of the present application, the step of calculating the number of layers of the battery cell according to the grayscale distribution map and determining the image clarity according to the calculated number of layers of the battery cell further includes:

[0036] Determining whether the calculated number of battery cell layers is equal to the preset standard number of layers;

[0037] If they are equal, the image clarity is determined to be normal and it is determined that there is no need to adjust the device parameters;

[0038] If they are not equal, it is determined that the picture clarity is abnormal, and the device parameters are adjusted according to the difference between the preset standard number of layers and the calculated number of battery core layers, where the device parameters include current parameters and current parameters.

[0039] In a second aspect, the present application further provides a device for determining image clarity, the device comprising:

[0040] An instance segmentation module is used to collect image data of the battery cell at different angles and perform instance segmentation on the image data to generate a segmentation mask for each instance area;

[0041] a target sub-image generation module, configured to determine the OH negative electrode region as a sub-image according to the segmentation mask, and to use the sub-image that meets the grayscale value calculation requirements as the target sub-image;

[0042] a grayscale calculation module, configured to perform grayscale calculation on the target sub-image to generate a grayscale distribution graph, wherein the grayscale value of a trough of the grayscale distribution graph represents the number of layers of the battery cell;

[0043] The image clarity determination module is configured to calculate the number of layers of the battery cell according to the grayscale distribution diagram, and determine the image clarity according to the calculated number of layers of the battery cell.

[0044] In a third aspect, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for determining image clarity as described in any one of the first aspects are implemented.

[0045] In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for determining image clarity as described in any one of the first aspects.

[0046] The present application provides a method, device, electronic device and storage medium for determining image clarity. First, image data of battery cells at different angles are collected, and the image data is segmented by instances to generate a segmentation mask for each battery cell instance area. The OH negative electrode area is determined as a sub-image based on the segmentation mask, and the sub-image that meets the grayscale value calculation requirements is used as the target sub-image. Then, the grayscale calculation is performed on the target sub-image to generate a grayscale distribution map, and the number of layers of the battery cell is calculated based on the grayscale distribution map. Finally, the image clarity is determined based on the calculated number of battery cell layers. The present application calculates the number of battery cell layers through steps such as instance segmentation and grayscale calculation, thereby realizing the determination of image clarity, and then determines the image clarity based on the calculated number of battery cell layers, which helps to improve the accuracy and efficiency of battery cell detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 This is a flowchart of the method for determining image clarity provided by this application;

[0049] Figure 2 It is a schematic diagram of the original image provided in the embodiment of this application;

[0050] Figure 3 is a schematic diagram of a subgraph provided in an embodiment of the present application;

[0051] Figure 4 is a schematic diagram of a target subgraph provided in an embodiment of the present application;

[0052] Figure 5 is a grayscale distribution diagram of the target sub-image provided in an embodiment of the present application;

[0053] Figure 6 1 is a flow chart of a method for determining image clarity provided in an embodiment of the present application;

[0054] Figure 7 It is a structural diagram of the image clarity determination device provided in this application. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0056] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments described herein can be practiced in an order other than that shown or described herein.

[0057] In order to solve the problem of how to determine the clarity of an image, the present application provides a method, device, electronic device and storage medium for determining the clarity of an image. First, image data of a battery cell at different angles is collected, and the image data is segmented by instances to generate a segmentation mask for each battery cell instance area. According to the segmentation mask, the OH negative electrode area is determined as a sub-image, and the sub-image that meets the grayscale value calculation requirements is used as the target sub-image. The grayscale calculation is then performed on the target sub-image to generate a grayscale distribution map, and the number of layers of the battery cell is calculated based on the grayscale distribution map. Finally, the image clarity is determined based on the calculated number of battery cell layers. The present application calculates the number of battery cell layers through steps such as instance segmentation and grayscale calculation, thereby achieving the determination of image clarity, and then determines the image clarity based on the calculated number of battery cell layers, which helps to improve the accuracy and efficiency of battery cell detection.

[0058] The following combination Figure 1-Figure 7 The present invention describes a method, device, electronic device, and storage medium for determining image clarity.

[0059] Please refer to Figure 1 , Figure 1 The figure is a flow chart of a method for determining image clarity provided by the present application. A method for determining image clarity, the method comprising:

[0060] Step 110 : collecting image data of the battery cell at different angles, and performing instance segmentation on the image data to generate a segmentation mask for each instance region.

[0061] Step 120 : determining the OH negative electrode region as a sub-image according to the segmentation mask, and taking the sub-image that meets the grayscale value calculation requirement as the target sub-image.

[0062] Step 130 : performing grayscale calculation on the target sub-graph to generate a grayscale distribution graph, wherein the grayscale value at the trough of the grayscale distribution graph represents the number of layers of the battery cell.

[0063] Step 140 , calculating the number of layers of the battery cell according to the grayscale distribution diagram, and determining the image clarity according to the calculated number of layers of the battery cell.

[0064] Through instance segmentation and optimization, this application can accurately determine the target sub-image in the battery cell image, thereby improving the analysis accuracy of the battery cell. In addition, by using grayscale calculation and grayscale distribution map, the number of battery cell layers can be effectively determined, and the image clarity can be determined based on the calculated number of battery cell layers, thereby improving production efficiency and product quality. Therefore, this application uses image processing and data analysis technology to calculate the number of battery cell layers, and can determine the clarity of the battery cell image based on the calculated number of battery cell layers, providing a basis for adjusting equipment parameters in the production process, thereby improving the efficiency and quality of battery cell manufacturing.

[0065] The above steps 110 to 140 are described in detail below.

[0066] In some embodiments of the present application, in step 110, the steps of collecting image data of the battery cell at different angles and performing instance segmentation on the image data to generate a segmentation mask for each instance region include:

[0067] Step 1101: collect image data of at least one angle of the battery cell, wherein the at least one angle includes a first angle, and the image data corresponding to the first angle is A={a1, a2, ..., a nb}, a i (1≤i≤n b ) is the i-th original image of image data A corresponding to the first angle.

[0068] For example, the image data of the four corners of the battery cell are collected, and the four corners correspond to four angles. The first angle is angle A, and the original image of angle A is as follows: Figure 2 As shown, the image dataset A of angle A={a1,a2,...,a nb}.

[0069] Among them, the four corners are the original images taken of the battery cell from four different perspectives or directions of the battery cell. That is to say, the battery cell is photographed from different angles or directions to obtain more comprehensive battery cell information and improve the accuracy of the analysis. Among them, the original image usually refers to the original image directly obtained from the acquisition device (such as a camera, scanner, etc.). The original image is a form of image data, which can be the unprocessed source data originally obtained from the acquisition device. The image data can include the original image and the results obtained by various processing of the original image.

[0070] Step 1102: Use the preset segmentation algorithm to segment the original image a iPerform instance segmentation to generate segmentation masks for each instance region, where masks = {m1, m2, ..., m nb}, m i (1≤i≤n b ) is the i-th mask in the segmentation mask masks list.

[0071] For example, the Mask R-CNN (a deep learning model for object detection and instance segmentation) segmentation algorithm can automatically perform instance segmentation on the original image to generate a segmentation mask for each instance region (i.e., a mask in the masks list) without manual intervention, reducing labor costs. The generated segmentation mask can also provide boundary information for each instance region, facilitating subsequent processing and analysis of the number of battery cell layers, thereby improving the efficiency and accuracy of the battery cell manufacturing process.

[0072] It should be noted that the segmentation mask is generated by extracting the position and shape information of the target from the image, thereby providing accurate area information for subsequent image processing and analysis.

[0073] In some embodiments of the present application, in step 120, the step of determining the OH cathode region as a sub-image according to the segmentation mask and using the sub-image that meets the grayscale value calculation requirements as the target sub-image includes:

[0074] Step 1201 : Filter out the OH negative electrode region from the original image based on the segmentation mask and the characteristics of the target region, and use it as the initial sub-image.

[0075] Step 1202: Determine whether the sub-image has an area that affects the grayscale value calculation.

[0076] For example, Figure 3 The sub-image shown here has a white edge at the bottom, which affects the calculation result of the grayscale value. Therefore, the sub-image needs to be further optimized.

[0077] Step 1203: If the sub-image has an area that affects the grayscale value calculation, the sub-image is optimized to obtain the target sub-image that meets the grayscale value calculation requirements, such as Figure 4 shown.

[0078] The above steps 1201 to 1203 are used to select the OH negative electrode area as a sub-image from the original image based on the segmentation mask and the characteristics of the target area, and to accurately locate and extract the target sub-image by further detecting and processing the areas in the sub-image that may interfere with the grayscale value calculation, thereby providing reliable data for subsequent grayscale value calculations to improve the accuracy and reliability of the calculation results.

[0079] In some embodiments of the present application, before executing step 1201, the method further includes:

[0080] Step 1200: If the target region is not found in the original image, the original image is optimized and instance segmentation is performed again on the optimized image data to find the target region and obtain a corresponding segmentation mask.

[0081] Step 1200 optimizes the original image and re-segmentes the instance, thereby increasing the accuracy of the target region and the success rate of finding the target region. This allows for a better segmentation mask of the target region, providing a reliable data foundation for subsequent processing and analysis, thereby improving the effectiveness of target detection and segmentation.

[0082] In some embodiments of the present application, in step 130, performing grayscale calculation on the target sub-image to generate a grayscale distribution graph, wherein the grayscale value of the trough of the grayscale distribution graph represents the number of layers of the battery cell, includes:

[0083] Step 1301: Calculate the grayscale value of each column of pixels in the target sub-image. The calculation formula is:

[0084]

[0085] Among them, sum(sub_img1_gray,0) means calculating the grayscale value of each column of pixels in the target sub-image from left to right, and count(sub_img1_nonzero) means calculating the number of non-zero pixels in each column of the target sub-image from left to right;

[0086] Step 1302 : Calculate the grayscale average value according to the grayscale value of each column of pixels to obtain a grayscale distribution diagram representing the grayscale average value.

[0087] For example, please refer to Figure 5 , Figure 5 is the grayscale distribution diagram of the target sub-image provided by the embodiment of the present application. Figure 2 The darker lines in the third picture are the layers of the battery cell.

[0088] The above steps 1301 to 1302 avoid the influence of zero pixels on the results by calculating and counting the grayscale values ​​of each column of pixels in the target sub-image, and generating the average grayscale value. The grayscale distribution map of the target sub-image can be obtained, which can intuitively display the grayscale characteristics of the target sub-image and facilitate further analysis and comparison.

[0089] In some embodiments of the present application, in step 140, the step of calculating the number of layers of the battery cell according to the grayscale distribution map, and determining the image clarity according to the calculated number of layers of the battery cell includes:

[0090] Step 1401: configure a local minimum function, and search for a trough position according to the local minimum function, where the trough position represents an area with the lowest grayscale value in the image.

[0091] Step 1402: According to the distance between each layer and the valley position in the OH negative electrode region, the valley grayscale value is set to meet the first condition:

[0092] std(mingray_val-7:mingray_index+7)<δ;

[0093] Among them, mingray_val≤min(mingray_index±0.8L), mingray_val represents the grayscale value of the trough, mingray_index represents the trough position, std() represents the standard deviation, min() represents the local minimum function, δ represents the preset threshold, L represents the distance between each layer in the OH negative electrode region, and min(mingray_index±0.8L) represents the minimum grayscale value within the length range of 0.8L before and after the trough.

[0094] Step 1403: According to the distance between each layer in the OH negative electrode region and the preset standard number of layers, the maximum length of the calculated cell layers is set to meet the second condition:

[0095] L max =L*N+bias;

[0096] Among them, L max Indicates the maximum length of the calculated battery cell layers, bias indicates the preset compensation value, and N indicates the preset standard number of layers.

[0097] Step 1404: When either the first condition or the second condition is not satisfied, stop calculating the number of layers of the battery cell.

[0098] Step 1405: When both the first condition and the second condition are satisfied, continue to calculate the number of layers of the battery cell.

[0099] In the above steps 1401 to 1405, by configuring the local minimum function, the area with the lowest grayscale value in the image, that is, the position of the battery cell, can be accurately located. By setting the trough grayscale value and standard deviation (i.e., the first condition), the battery cell area that meets the requirements can be screened out, thereby improving the accuracy of the calculation results. And according to the preset standard number of layers and distance parameters, a maximum length is set to control the calculation range (i.e., the second condition), and the number of battery cell layers can be adaptively calculated. The setting of the stop calculation condition in step 1404 can prevent battery cells that do not meet the calculation requirements from being mistakenly identified, saving calculation time and resources.

[0100] In some embodiments of the present application, in step 140, the step of calculating the number of layers of the battery cell according to the grayscale distribution map and determining the image clarity according to the calculated number of layers of the battery cell further includes:

[0101] Step 1406: Determine whether the calculated number of battery cell layers is equal to the preset standard number of layers.

[0102] Step 1407: If they are equal, it is determined that the image clarity is normal and it is determined that there is no need to adjust the device parameters.

[0103] Step 1408: If they are not equal, it is determined that the image clarity is abnormal, and the device parameters are adjusted according to the difference between the preset standard number of layers and the calculated number of battery cell layers, the device parameters including current parameters and current parameters.

[0104] In steps 1406-1408, after calculating the number of cell layers, it is necessary to determine whether the calculated result is equal to the preset standard number of layers. If so, the image clarity is considered normal and no device parameter adjustment is required. If not, the image clarity is considered abnormal, and device parameters, including current and voltage parameters, are adjusted based on the difference between the preset standard number of layers and the calculated number of cell layers. This improves the efficiency and accuracy of image processing, avoids manual trial and error, and increases the degree of automation in the workflow.

[0105] For example, the device parameters can be adjusted according to the following formula:

[0106] Voltage parameter adjustment amount = preset voltage value * number of missing cell layers, where the number of missing cell layers = preset standard number of layers - calculated number of cell layers;

[0107] Current parameter adjustment amount = preset current value * number of missing battery cell layers, where the number of missing battery cell layers = preset standard number of layers - calculated number of battery cell layers.

[0108] Missing layers are called missing layers, meaning some layers in the cell are not fully formed. During image recognition, if the calculated number of cell layers is less than the preset standard number, it can be determined that there are missing layers.

[0109] For example, if the number of cell layers calculated in step 1405 is N-1, and the preset standard number of layers is N, and the image shows that the missing layer is the first layer, indicating that the voltage and current are too high, causing the first layer to break down, then the device's parameter control module will issue a parameter adjustment instruction to the PLC (Programmable Logic Controller), namely reducing the voltage by 1KV (1KV=1KV*1) and the current by 10μA (10μA=10μA*1). This adjustment is intended to solve the problem of the missing first layer.

[0110] For example, if the calculated number of cell layers is N-1, and the preset standard number of layers is N, and the image shows a missing layer, which is the last layer, this indicates that the voltage and current are too low to penetrate the battery, resulting in the missing last layer. The device's parameter control module will then send a parameter adjustment command to the PLC, increasing the voltage by 1 kV and the current by 10 μA. This adjustment attempts to resolve the problem of the missing last layer.

[0111] For example, if the calculated number of battery cell layers is N and the preset standard number of layers is N, it means that the image clarity is normal and there is no need to adjust the device parameters.

[0112] It should be noted that the grayscale value of the first layer can be used to identify whether it is the first or last layer. For example, if the grayscale value of the first layer is greater than T, where T represents the grayscale value threshold, it means that the first layer is missing. This is because when the first layer is broken down, the grayscale value of the first layer is often very high. If the last layer is missing, the grayscale value of the first layer will be very low.

[0113] Therefore, identifying the missing cell layers based on the calculation results of the cell layer number to adjust the voltage parameters and current parameters can solve the problem of missing cell layers, improve the accuracy and reliability of cell layer identification, and ensure that the equipment works in the best condition.

[0114] The following describes the method for determining image clarity described in this application through an embodiment.

[0115] Please refer to Figure 6 , Figure 6 1 is a flow chart of a method for determining image clarity provided in an embodiment of the present application. A method for determining image clarity, the method comprising:

[0116] Step 601 : Obtain original images of the battery cell at different angles, and perform instance segmentation based on the original images to generate segmentation masks.

[0117] Step 602: Determine whether the target area is found in the original image.

[0118] If not found, execute step 603; otherwise, execute step 604.

[0119] Step 603: Optimize the original image and return to step 601 to re-segment the optimized image data.

[0120] Step 604 : Acquire the OH negative electrode region as a sub-image according to the segmentation mask.

[0121] Step 605: Determine whether the sub-image has an area that affects the grayscale value calculation.

[0122] If so, execute step 606; otherwise, execute step 607.

[0123] In step 606, the sub-image is optimized to obtain the target sub-image that meets the grayscale value calculation requirements.

[0124] Step 607: Use the subgraph as the target subgraph.

[0125] Step 608 : Calculate the grayscale value of each column of pixels in the target sub-image, and calculate the grayscale average value based on the grayscale value of each column of pixels to obtain a grayscale distribution map.

[0126] Step 609: Calculate the number of battery cell layers and configure the conditions for stopping the calculation of the number of battery cell layers.

[0127] Exemplarily, the valley grayscale value is set to satisfy the first condition:

[0128] std(mingray_val-7:mingray_index+7)<δ;

[0129] Among them, mingray_val≤min(mingray_index±0.8L), mingray_val represents the grayscale value of the trough, mingray_index represents the trough position, std() represents the standard deviation, min() represents the local minimum function, δ represents the preset threshold, L represents the distance between each layer in the OH negative electrode region, and min(mingray_index±0.8L) represents the minimum grayscale value within the length range of 0.8L before and after the trough.

[0130] Set the maximum length of the calculated cell layers to meet the second condition:

[0131] L max =L*N+bias;

[0132] Among them, L maxIndicates the maximum length of the calculated battery cell layers, bias indicates the preset compensation value, and N indicates the preset standard number of layers.

[0133] When either the first condition or the second condition is not satisfied, the counting of the number of layers of the battery cell is stopped; when both the first condition and the second condition are satisfied, the counting of the number of layers of the battery cell is continued.

[0134] Step 610: Determine whether the calculated number of battery cell layers is equal to a preset standard number of layers.

[0135] If they are equal, execute step 611; if they are not equal, execute step 612.

[0136] Step 611: Determine that the image clarity is normal and that there is no need to adjust device parameters.

[0137] Step 612 , determining that the image clarity is abnormal, and adjusting the device parameters according to the difference between the preset standard number of layers and the calculated number of battery cell layers.

[0138] In some examples of the present application, when analyzing the actual measurement results of the battery cell, it is possible to further determine whether the battery cell has undergone a breakdown by detecting whether there is a missing layer. If a missing layer is found and a breakdown phenomenon occurs, the voltage and current values ​​will be reduced to avoid further damage to the battery cell. If no breakdown phenomenon occurs in the case of a missing layer, the voltage and current values ​​will be increased. The principle is that the missing layer usually causes the insulation performance inside the battery cell to decrease and the voltage and current to increase. When the battery cell suffers a breakdown, due to insulation failure, further increasing the voltage and current may cause more serious damage. Therefore, judging the breakdown situation based on the missing layer condition and adjusting the voltage and current accordingly can protect the battery cell from the influence of excessive voltage and current.

[0139] Specifically, a PLC can monitor the cell for missing layers and automatically adjust the voltage and current in conjunction with a parameter adjustment module. When a missing layer is detected, the system determines whether a breakdown condition exists. If so, the voltage and current are reduced to prevent further damage; otherwise, the voltage and current are increased to optimize the cell's performance.

[0140] This application accurately identifies whether a battery cell has broken down by analyzing the missing layer and intelligently adjusts parameters based on different situations. This improves the safety and reliability of the battery cell, reduces potential damage and failures, and optimizes the cell's operating state, improving its quality and performance.

[0141] The image clarity determination device provided in the present application is described below. The image clarity determination device described below and the image clarity determination method described above can be referenced to each other.

[0142] Please refer to Figure 7 , Figure 7 This is a structural diagram of the image clarity determination device provided in this application. An image clarity determination device 700 includes an instance segmentation module 710, a target sub-image generation module 720, a grayscale calculation module 730 and an image clarity determination module 740.

[0143] Exemplarily, the instance segmentation module 710 is used to:

[0144] Image data of the battery cell at different angles is collected, and instance segmentation is performed on the image data to generate a segmentation mask for each instance area.

[0145] Exemplarily, the target subgraph generation module 720 is used to:

[0146] The OH negative electrode region is determined as a sub-image according to the segmentation mask, and the sub-image that meets the grayscale value calculation requirement is used as the target sub-image.

[0147] Exemplarily, the grayscale calculation module 730 is used to:

[0148] Grayscale calculation is performed on the target sub-image to generate a grayscale distribution graph, where the valley grayscale value of the grayscale distribution graph represents the number of layers of the battery cell.

[0149] Exemplarily, the picture clarity determination module 740 is configured to:

[0150] The number of layers of the battery cell is calculated according to the grayscale distribution diagram, and the image clarity is determined according to the calculated number of layers of the battery cell.

[0151] Exemplarily, the instance segmentation module 710 is further configured to:

[0152] Collect image data of at least one angle of the battery cell, the at least one angle includes a first angle, and the image data set A corresponding to the first angle is A={a1, a2, ..., a nb}, a i (1≤i≤n b ) is the i-th original image of the image dataset A corresponding to the first angle;

[0153] Use the preset segmentation algorithm to segment the original image a i Perform instance segmentation to generate segmentation masks for each instance region, where masks = {m i , m2, ..., m nb}, m i (1≤i≤n b ) is the i-th mask in the segmentation mask masks list.

[0154] Exemplarily, the target subgraph generation module 720 is further configured to:

[0155] According to the segmentation mask and the characteristics of the target area, the OH negative electrode area is screened out from the original image and used as the initial sub-image;

[0156] Determine whether the sub-image has an area that affects grayscale value calculation;

[0157] If the sub-image has an area that affects the grayscale value calculation, the sub-image is optimized to obtain the target sub-image that meets the grayscale value calculation requirements.

[0158] Exemplarily, the target subgraph generation module 720 is further configured to:

[0159] If the target area is not found in the original image, optimizing the original image;

[0160] Re-segment the optimized image data to find the target area and obtain the corresponding segmentation mask.

[0161] Exemplarily, the grayscale calculation module 730 is further configured to:

[0162] Calculate the grayscale value of each column of pixels in the target sub-image using the following formula:

[0163]

[0164] Among them, sum(sub_img1_gray, 0) means calculating the grayscale value of each column of pixels in the target sub-image from left to right, and count(sub_img1_nonzero) means calculating the number of non-zero pixels in each column of the target sub-image from left to right;

[0165] The grayscale average value is calculated according to the grayscale values ​​of the pixels in each column to obtain a grayscale distribution diagram representing the grayscale average value.

[0166] Exemplarily, the picture clarity determination module 740 is further configured to:

[0167] configuring a local minimum function, and finding a trough position according to the local minimum function, wherein the trough position represents an area with the lowest grayscale value in the image;

[0168] According to the distance between each layer and the valley position in the OH negative electrode region, the valley grayscale value is set to meet the first condition:

[0169] std(mingray_val-7:mingray_index+7)<δ;

[0170] Wherein, mingray_val≤min(mingray_index±0.8L), mingray_val represents the grayscale value of the trough, mingray_index represents the position of the trough, std() represents the standard deviation, min() represents the local minimum function, δ represents the preset threshold, L represents the distance between each layer in the OH negative electrode region, and min(mingray_index±0.8L) represents the minimum grayscale value within the length range of 0.8L before and after the trough;

[0171] According to the distance between each layer in the OH negative electrode region and the preset standard number of layers, the maximum length of the calculated cell layers is set to meet the second condition:

[0172] L max =L*N+bias;

[0173] Among them, L max Indicates the maximum length of the calculated battery cell layers, bias indicates the preset compensation value, and N indicates the preset standard number of layers;

[0174] When either the first condition or the second condition is not met, stopping counting the number of layers of the battery cell;

[0175] When both the first condition and the second condition are satisfied, the number of layers of the battery cell is continued to be calculated.

[0176] Exemplarily, the picture clarity determination module 740 is further configured to:

[0177] Determining whether the calculated number of battery cell layers is equal to the preset standard number of layers;

[0178] If they are equal, the image clarity is determined to be normal and it is determined that there is no need to adjust the device parameters;

[0179] If they are not equal, it is determined that the picture clarity is abnormal, and the device parameters are adjusted according to the difference between the preset standard number of layers and the calculated number of battery core layers, where the device parameters include current parameters and current parameters.

[0180] It should be noted here that the above-mentioned image clarity determination device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0181] In some embodiments of the present application, the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of power battery pack temperature prediction as described above when executing the program.

[0182] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0183] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the image clarity determination method provided by the above methods.

[0184] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented to perform the above-mentioned image clarity determination methods when executed by a processor.

[0185] The embodiments of the present application provide an electronic device, a computer program product, and a processor-readable storage medium, on which the computer program stored enables the processor to implement all the method steps implemented in the above-mentioned method embodiment and to achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0186] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0187] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0188] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining image clarity, characterized in that: The method comprises: Collect image data of the battery cell at different angles, and perform instance segmentation on the image data to generate a segmentation mask for each instance area; Determine the OH negative electrode region as a sub-image according to the segmentation mask, and use the sub-image that meets the grayscale value calculation requirements as the target sub-image; Performing grayscale calculation on the target sub-image to generate a grayscale distribution map; The number of layers of the battery cell is calculated according to the grayscale distribution diagram, including: calculating the number of layers of the battery cell based on a trough grayscale value condition set based on a trough position of the grayscale distribution diagram, and a length condition set based on a preset standard number of layers; and determining the image clarity according to the calculated number of battery cell layers.

2. The method for determining image clarity according to claim 1, wherein: The step of collecting image data of the battery cell at different angles and performing instance segmentation on the image data to generate a segmentation mask for each instance area includes: Collect image data of at least one angle of the battery cell, the at least one angle including a first angle, and the image data set corresponding to the first angle , is the first image data set A corresponding to the first angle Original image; Use the preset segmentation algorithm to Perform instance segmentation to generate segmentation masks for each instance region, where , For the segmentation mask masks list A mask.

3. The method for determining image clarity according to claim 1, wherein: The step of determining the OH negative electrode region as a sub-image according to the segmentation mask and using the sub-image that meets the grayscale value calculation requirements as the target sub-image includes: According to the segmentation mask and the characteristics of the target area, the OH negative electrode area is screened out from the original image and used as the sub-image; Determine whether the sub-image has an area that affects grayscale value calculation; If the sub-image has an area that affects the grayscale value calculation, the sub-image is optimized to obtain the target sub-image that meets the grayscale value calculation requirements.

4. The method for determining image clarity according to claim 3, wherein: Before performing the step of screening out the OH negative electrode region from the original image based on the segmentation mask and the features of the target region and using it as the initial sub-image, the method further includes: If the target area is not found in the original image, optimizing the original image; Re-segment the optimized image data to find the target area and obtain the corresponding segmentation mask.

5. The method for determining image clarity according to claim 1, wherein: The step of performing grayscale calculation on the target sub-image to generate a grayscale distribution map comprises: Calculate the grayscale value of each column of pixels in the target sub-image using the following formula: in, Indicates that the grayscale value of each column of pixels in the target sub-image is calculated from left to right. It means counting the number of non-zero pixels in each column of the target sub-image from left to right; The grayscale average value is calculated according to the grayscale values ​​of the pixels in each column to obtain a grayscale distribution diagram representing the grayscale average value.

6. The method for determining image clarity according to claim 1, wherein: The step of calculating the number of layers of the battery cell according to the grayscale distribution map and determining the image clarity according to the calculated number of layers of the battery cell includes: configuring a local minimum function, and finding a trough position according to the local minimum function, wherein the trough position represents an area with the lowest grayscale value in the image; According to the distance between each layer and the valley position in the OH negative electrode region, the valley grayscale value is set to meet the first condition: ; in, , represents the trough gray value, Indicates the trough position, std() indicates the standard deviation, min() indicates the local minimum function, represents the preset threshold, L represents the distance between each layer in the OH negative electrode region, Indicates the minimum grayscale value within the 0.8L length range before and after the trough; According to the distance between each layer in the OH negative electrode region and the preset standard number of layers, the maximum length of the calculated cell layers is set to meet the second condition: ； in, Indicates the maximum length of the calculated battery layer number, Indicates the preset compensation value, Indicates the preset standard number of layers; When either the first condition or the second condition is not met, stopping counting the number of layers of the battery cell; When both the first condition and the second condition are satisfied, the number of layers of the battery cell is continued to be calculated.

7. The method for determining image clarity according to claim 6, wherein: The step of calculating the number of layers of the battery cell according to the grayscale distribution map and determining the image clarity according to the calculated number of layers of the battery cell further includes: Determining whether the calculated number of battery cell layers is equal to the preset standard number of layers; If they are equal, the image clarity is determined to be normal and it is determined that there is no need to adjust the device parameters; If they are not equal, it is determined that the picture clarity is abnormal, and the device parameters are adjusted according to the difference between the preset standard number of layers and the calculated number of battery core layers, where the device parameters include current parameters and current parameters.

8. A device for determining image clarity, characterized in that: The device comprises: An instance segmentation module is used to collect image data of the battery cell at different angles and perform instance segmentation on the image data to generate a segmentation mask for each instance area; a target sub-image generation module, configured to determine the OH negative electrode region as a sub-image according to the segmentation mask, and to use the sub-image that meets the grayscale value calculation requirements as the target sub-image; A grayscale calculation module, configured to perform grayscale calculation on the target sub-image to generate a grayscale distribution map; The image clarity determination module is used to calculate the number of layers of the battery cell based on the grayscale distribution map, including: calculating the number of layers of the battery cell based on the trough grayscale value condition set based on the trough position of the grayscale distribution map, and the length condition set based on the preset standard number of layers; and determining the image clarity based on the calculated number of battery cell layers.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for determining picture clarity according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for determining image clarity according to any one of claims 1 to 7 are implemented.

Images