Lithium ion battery electrical performance acquisition method and system, product and storage medium

Abstract

The invention provides a lithium ion battery electrical performance acquisition method and system, a product and a storage medium, and relates to the technical field of battery data processing. Marking the microscopic data according to the conventional data at the same time to generate marked data, the marked data comprising the microscopic data and a corresponding marked file, the marked file comprising a target category and bounding box coordinates, the target category being determined when a certain kind of data in the conventional data falls into a corresponding sub-range, and the bounding box coordinates being determined when the certain kind of data falls into the corresponding sub-range; continuous conventional data is discretized, so that the change of the microstructure can be associated with a specific performance index range, the change of a specific region in the battery can be directly associated with an external performance index, and the model can learn the relationship between the performance index and the microstructure; internal changes of a single battery sample can be continuously monitored throughout the aging period without interrupting the test process or using multiple samples. Not only is the demand for a plurality of battery samples reduced, but also time and resource consumption is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of battery data processing, and in particular to a method, system, product and storage medium for obtaining electrical properties of a lithium-ion battery. Background Art

[0002] In the battery industry, aging testing is a critical link. This process aims to monitor the performance degradation of batteries after long-term use. Minor changes on the surface of the battery, such as changes in color depth, slight expansion, or other subtle changes in shape, are important observation indicators. By using sophisticated imaging and analysis techniques, researchers can identify and record these small but critical changes. These data provide an important basis for optimizing and improving battery design. The battery design team can continuously adjust and optimize the chemical composition and structural design of the battery based on these observations to extend the battery's service life and improve its overall performance.

[0003] However, in related technologies, obtaining information about the internal structure of a battery usually requires disassembling the battery. But for the aging test team, once the battery is disassembled, the aging test cannot be continued, which means that every time the internal structure changes need to be understood, a new battery sample needs to be used, which not only increases the cost, but also significantly extends the entire test cycle. This situation leads to a dilemma: researchers need long-term aging data to evaluate battery performance, but also need to understand the changes in the internal structure at different stages. This requires testing on multiple identical battery samples at the same time, some of which are used for the complete aging cycle, and the other parts are disassembled and analyzed at different time points. Although this method is feasible, it greatly increases the consumption of time and resources. Summary of the invention

[0004] The present application provides a method, system, product and storage medium for obtaining electrical performance of a lithium-ion battery, which are used to reduce the demand for multiple battery samples and reduce time and resource consumption.

[0005] In a first aspect, a method for obtaining electrical properties of a lithium-ion battery comprises: Acquire conventional data of the target battery at different times, the conventional data including discharge cycle, charge and discharge rate, temperature change, voltage and current waveform; acquire microscopic data of the target battery at different times, the microscopic data including microstructure image and crystal structure data of the target battery; annotate the microscopic data according to the conventional data at the same time to generate annotated data; wherein the annotated data includes microscopic data and corresponding annotation files, the annotation files include target categories and bounding box coordinates corresponding to the target categories, the target category is a certain type of data in the conventional data that falls into the corresponding sub-range, and the bounding box coordinates are determined by the microscopic data; form a data set with annotated data at different times; input the data set into a preset battery performance prediction model for training; input the current conventional data into the battery performance prediction model to obtain the corresponding current microscopic data.

[0006] By adopting the above technical solution, by acquiring the conventional data and microscopic data of the target battery at different times, the time correlation between the external performance and internal structure of the battery is established, and the microscopic data is annotated according to the conventional data at the same time to generate annotated data. The annotated data includes microscopic data and corresponding annotation files, wherein the annotation file contains the target category and the bounding box coordinates, and the target category is determined by whether a certain type of data in the conventional data falls into the corresponding sub-range. The continuous conventional data is discretized so that the changes in the microstructure can be associated with a specific performance indicator range, so that the changes in a specific area inside the battery can be directly associated with the external performance indicators. The annotated data at different times are combined into a data set and used to train the battery performance prediction model, so that the model can learn the relationship between performance indicators and microstructures, so that researchers can continuously monitor the internal changes of a single battery sample throughout the aging cycle without interrupting the test process or using multiple samples. Not only does it reduce the need for multiple battery samples, it also reduces time and resource consumption.

[0007] In combination with some embodiments of the first aspect, in some embodiments, the step of determining the bounding box coordinates by micro data specifically includes: performing contour detection on the micro data to obtain a set of contours; screening the contours to retain contours that meet the conditions based on preset area thresholds and shape features; calculating the minimum enclosing rectangle of each retained contour, and using the coordinates of the minimum enclosing rectangle as the bounding box coordinates.

[0008] By adopting the above technical solution, contour detection is performed on micro data to obtain a set of contours, which can automatically identify prominent structures in micro data. The contours are screened by preset area thresholds and shape features, effectively eliminating noise and irrelevant structures, and calculating the minimum circumscribed rectangle as the bounding box coordinates to improve the accuracy of annotation. This automated bounding box determination method significantly reduces human intervention, improves the objectivity and consistency of annotation, and reduces the errors that may be caused by manual annotation.

[0009] In combination with some embodiments of the first aspect, in some embodiments, before the step of performing contour detection on micro data to obtain a set of contours, the method also includes: preprocessing the micro data to convert the micro data into a grayscale image; performing edge detection on the grayscale image to obtain an edge map; performing dilation and erosion operations on the edge map to obtain a processed map; binarizing the processed map; applying connected region analysis to the binarized processed map to remove areas smaller than a predetermined area threshold.

[0010] By adopting the above technical solutions, the microscopic data is converted into grayscale images to facilitate subsequent edge detection. Edge detection highlights the contours of the microstructure, while the expansion and erosion operations further enhance the clarity of these contours. Binarization converts the image into black and white, effectively separating the target structure from the background. Finally, connected region analysis removes areas smaller than a predetermined area threshold, effectively filtering out noise and small irrelevant structures.

[0011] In combination with some embodiments of the first aspect, in some embodiments, the step of obtaining the microscopic data of the target battery at different times specifically includes: obtaining the capacity decay curve of the same battery, wherein the same battery is the same type of battery as the target battery; obtaining characteristic points in the capacity decay curve; and obtaining the microscopic data of the target battery at the time corresponding to the characteristic points.

[0012] By adopting the above technical solution, the capacity decay curve of similar batteries is obtained, providing a reference benchmark for the performance changes of the target battery. By analyzing the characteristic points in the capacity decay curve, the key time nodes are determined, which usually represent the moments when the battery performance changes significantly. The microscopic data of the target battery is obtained at the time corresponding to these characteristic points, ensuring that the time points of the microscopic analysis are representative and important. Therefore, the number of times microscopic data is obtained is reduced, which not only saves usage time, but also reduces the workload of professional and technical personnel.

[0013] In combination with some embodiments of the first aspect, in some embodiments, the step of obtaining characteristic points in the capacity decay curve specifically includes: taking points on the capacity decay curve at preset intervals, and calculating the curvature of each taken point; selecting points whose curvature is greater than a preset high extreme value of the curvature, and points whose curvature is lower than a preset low extreme value of the curvature as characteristic points; calculating the curvature change rate of each taken point according to the curvature; selecting the taken points whose curvature change rate is higher than a preset curvature mutation threshold as characteristic points; dividing the capacity decay curve into multiple sections; determining the number of points to be taken in each section according to the length of the section; and randomly taking characteristic points in each section according to the number of points to be taken.

[0014] By adopting the above technical solution, by setting the high and low extreme values ​​of the curvature, the most significant points of the curve change are selected as feature points, ensuring that the key change points are captured. The curvature change rate is calculated and the mutation threshold is set to further identify the mutation points in the curve. These points often represent important turning points in battery performance. The curve is divided into segments and points are randomly selected in each segment to ensure that the feature points are evenly distributed on the entire curve. This multi-level and multi-angle feature point selection method not only captures the key changes of the curve, but also takes into account the overall trend, greatly improving the representativeness and comprehensiveness of the feature points.

[0015] In combination with some embodiments of the first aspect, in some embodiments, after the step of obtaining the capacity decay curve of the same battery, the method further includes: determining whether the capacity decay curve is continuous; if the capacity decay curve is discontinuous, using interpolation technology to supplement the data at the missing parts of the capacity decay curve; if the capacity decay curve is continuous, executing the step of obtaining characteristic points in the capacity decay curve.

[0016] By adopting the above technical solution, the continuity of the capacity decay curve can be judged, and possible missing or abnormal data can be identified. For discontinuous curves, interpolation technology is used to supplement the missing data to ensure the integrity and continuity of the curve.

[0017] In combination with some embodiments of the first aspect, in some embodiments, the micro data is labeled according to the conventional data of the same time, and the step of generating labeled data specifically includes: treating the time within the same range as the same time, and the same range is determined according to the degree of capacity attenuation.

[0018] By adopting the above technical solution, the time within the same period is regarded as the same time, which solves the problem that the conventional data and micro data are not strictly corresponding in time, and also solves the problem that the conventional data and micro data are not equal in quantity.

[0019] In a second aspect, the present application provides a lithium-ion battery electrical performance acquisition system, the lithium-ion battery electrical performance acquisition system comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the lithium-ion battery electrical performance acquisition system to perform the method described in the first aspect and any possible implementation method of the first aspect.

[0020] In a third aspect, the present application provides a computer program product comprising instructions, which, when executed on a lithium-ion battery electrical performance acquisition system, enables the lithium-ion battery electrical performance acquisition system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a lithium-ion battery electrical performance acquisition system, enables the lithium-ion battery electrical performance acquisition system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By acquiring the conventional data and microscopic data of the target battery at different times, the time correlation between the external performance and internal structure of the battery is established. The microscopic data is annotated according to the conventional data at the same time to generate annotated data. The annotated data includes microscopic data and corresponding annotation files, where the annotation files contain target categories and bounding box coordinates. The target category is determined by whether a certain type of data in the conventional data falls into the corresponding sub-range. The continuous conventional data is discretized so that the changes in the microstructure can be associated with a specific performance indicator range, so that the changes in specific areas inside the battery can be directly associated with external performance indicators. The annotated data at different times are combined into a data set and used to train a battery performance prediction model, so that the model can learn the relationship between performance indicators and microstructures, allowing researchers to continuously monitor the internal changes of a single battery sample throughout the aging cycle without interrupting the test process or using multiple samples. This not only reduces the need for multiple battery samples, but also reduces time and resource consumption.

[0023] 2. Perform contour detection on micro data to obtain a set of contours, which can automatically identify prominent structures in micro data. The contours are screened by preset area thresholds and shape features, effectively eliminating noise and irrelevant structures, and calculating the minimum circumscribed rectangle as the bounding box coordinates to improve the accuracy of annotation. This automated bounding box determination method significantly reduces human intervention, improves the objectivity and consistency of annotation, and reduces the errors that may be caused by manual annotation.

[0024] 3. Obtaining the capacity decay curve of similar batteries provides a reference benchmark for the performance changes of the target battery. By analyzing the characteristic points in the capacity decay curve, key time nodes are determined, which usually represent the moments when the battery performance changes significantly. The microscopic data of the target battery is obtained at the time corresponding to these characteristic points, ensuring that the time points of the microscopic analysis are representative and important. Therefore, the number of times microscopic data is obtained is reduced, which not only saves usage time, but also reduces the workload of professional technicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart of a method for obtaining electrical properties of a lithium-ion battery in an embodiment of the present application; Figure 2 yes Figure 1A flow chart of step S103; Figure 3 yes Figure 1 A flow chart of step S102 in FIG. Figure 4 yes Figure 3 A flow chart of step S302 in FIG. Figure 5 It is a schematic diagram of an exemplary hardware structure of a lithium-ion battery electrical performance acquisition system in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0027] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0028] See also Figure 1 , Figure 1 This is a flow chart of a method for obtaining electrical properties of a lithium-ion battery in an embodiment of the present application; In some embodiments, a method for obtaining electrical properties of a lithium-ion battery includes: S101, acquiring conventional data of a target battery at different times, the conventional data including discharge cycle, charge and discharge rate, temperature change, voltage and current waveforms; Among them, the target battery refers to the specific lithium-ion battery that needs to be analyzed and predicted for performance, the conventional data refers to the external performance indicators that can be directly measured or observed during the use of the battery, the discharge cycle refers to the time required for the battery to complete a complete discharge, and the charge and discharge rate is used to indicate the speed of charging and discharging of the battery. Temperature change refers to the temperature fluctuation of the battery during operation, and the voltage and current waveforms refer to the voltage and current value curves that change over time.

[0029] In some embodiments, one or more target batteries are selected and the performance data of these batteries are recorded at different time points (which may span days, weeks or months), including recording the duration of each charge and discharge cycle, the current during charge and discharge, the change in battery surface temperature, and the real-time change curves of voltage and current during the whole process, and sending these data to the terminal.

[0030] It should be noted that, in this embodiment, only the acquisition of conventional data is involved, and the specific collection method or source of conventional data is not involved.

[0031] S102, acquiring microscopic data of the target battery at different times, the microscopic data including a microscopic structure image and crystal structure data of the target battery; Among them, microscopic data refers to data that reflects the internal structure and material properties of the battery. The microscopic structure image represents visual information on the morphology, distribution and structural characteristics of the internal materials of the battery. The crystal structure data refers to data that describes the arrangement of atoms or molecules in the battery material, including lattice parameters, atomic positions and other information.

[0032] In some embodiments, a microscopic analysis of the target battery is performed at a predetermined time point. This may involve disassembling the battery or using non-invasive analysis techniques. Microstructure images are usually obtained through an electron microscope (such as a scanning electron microscope SEM or a transmission electron microscope TEM), which can show the morphology, particle size, pore distribution, etc. of the electrode material. Crystal structure data is usually obtained through techniques such as X-ray diffraction (XRD), which can reflect changes in the crystal structure of the material, such as phase change, lattice expansion or contraction, and send these data to the terminal.

[0033] It should be noted that, in this embodiment, only the acquisition of micro data is involved, and the specific collection method or source of micro data is not involved.

[0034] S103, annotating the micro data according to the conventional data of the same time to generate annotated data; wherein the annotated data includes the micro data and the corresponding annotation file, the annotation file includes the target category and the bounding box coordinates corresponding to the target category, the target category is a certain type of data in the conventional data that falls into the corresponding sub-range, and the bounding box coordinates are determined by the micro data; In some embodiments, the indicators in the conventional data (such as capacity attenuation rate) are divided into several sub-ranges, each sub-range corresponds to a target category, and for the micro data at each time point, the target category to which it belongs is determined based on the conventional data at the same time point, key areas are identified on the microstructure image, and the bounding box coordinates of these areas are recorded. Each micro data is assigned a target category label and corresponding bounding box information to form complete annotated data.

[0035] In some specific embodiments, the total range of the indicators in the statistical conventional data is taken, and then the total range is divided into a corresponding number of sub-ranges according to the number of categories to be divided, which is not limited here.

[0036] In some specific embodiments, all capacity decay rate data are sorted, and corresponding quantiles are calculated according to the required number of categories, and these quantiles are used as boundaries of sub-ranges, which are not limited here.

[0037] In some specific embodiments, researchers determine the sub-range themselves based on their own experience, which is not limited here.

[0038] In some specific embodiments, researchers observe the image, identify key areas that need to be annotated, such as specific crystal structures, defects, or microscopic features of interest, and use the drawing tools provided by the software (usually rectangle tools) to manually draw bounding boxes on the image to enclose the key areas. A label is assigned to each bounding box to describe the characteristics or type of the area, and the coordinate information of each bounding box is automatically recorded, usually including the x and y coordinates of the upper left corner and the lower right corner, which are not limited here.

[0039] S104, combining the labeled data at different times into a data set; S105, inputting the data set into a preset battery performance prediction model for training; In some embodiments, the data set generated in the previous step is used as input to a pre-designed battery performance prediction model. The model will use this data for learning and gradually adjust its internal parameters to minimize the error between the predicted results and the actual annotations. During the training process, the model will learn the complex relationship between the conventional data and the microscopic data of the battery, so that it can predict the corresponding microstructural changes given the conventional data.

[0040] S106 , input current conventional data into the battery performance prediction model to obtain corresponding current microscopic data.

[0041] It can be seen that by obtaining the conventional data and micro data of the target battery at different times, the time correlation between the external performance and internal structure of the battery is established. The micro data is annotated according to the conventional data at the same time to generate annotated data. The annotated data includes micro data and corresponding annotation files, where the annotation files contain target categories and bounding box coordinates. The target category is determined by whether a certain type of data in the conventional data falls into the corresponding sub-range. The continuous conventional data is discretized so that the changes in the microstructure can be associated with a specific performance indicator range, so that the changes in specific areas inside the battery can be directly associated with external performance indicators. The annotated data at different times are combined into a data set and used to train a battery performance prediction model, so that the model can learn the relationship between performance indicators and microstructures, allowing researchers to continuously monitor the internal changes of a single battery sample throughout the aging cycle without interrupting the test process or using multiple samples. Not only does it reduce the need for multiple battery samples, it also reduces time and resource consumption.

[0042] As mentioned in step S103 above, researchers manually draw bounding boxes on the image to enclose the key areas based on experience and tools. However, in actual use, manual annotation of micro data may be subjective, and different researchers may have different annotation results for the same image. The annotation process is time-consuming and prone to errors, especially when dealing with large amounts of data.

[0043] See also Figure 2 , Figure 2 yes Figure 1 A flowchart diagram of step S103 in FIG.

[0044] Therefore, in some embodiments, the determination of the bounding box coordinates from the microscopic data in step S103 specifically includes: S201, preprocessing the microscopic data to convert the microscopic data into a grayscale image; In some embodiments, the original microscopic image data is read, which is usually in color image format, and a specific algorithm is used to convert the color image into a grayscale image. The converted grayscale image retains the structural information of the original image, but the data volume is reduced, which is conducive to subsequent processing.

[0045] In some specific embodiments, a weighted average method is used to calculate the grayscale value by assigning different weights to the three colors red, green, and blue according to the different sensitivities of the human eye; optionally, the average value of the three RGB channels is directly taken as the grayscale value; optionally, only the value of a certain color channel is retained as the grayscale value. It is understandable that other color space conversion methods can also be used to achieve the generation of grayscale images, which are not limited here.

[0046] S202, performing edge detection on the grayscale image to obtain an edge map; In some embodiments, grayscale image data is read and then an edge detection algorithm is applied. The edge detection algorithm usually calculates the gradient of the image to identify areas where pixel values ​​change sharply, which are likely to correspond to the edges or contours of objects. The detection result is usually a binary image, in which edge pixels are marked as white (or high brightness value) and non-edge pixels are marked as black (or low brightness value).

[0047] S203, performing expansion and corrosion operations on the edge image to obtain a processed image; In some embodiments, the edge map is dilated, which makes the edges thicker and fills small gaps that may exist in the edges, and then the dilated image is eroded, which makes the edges thinner and removes some fine structures that may be caused by noise, smoothing the outline of objects, filling small holes, and eliminating narrow gaps.

[0048] S204, performing binarization processing on the processed image; In some embodiments, a threshold is set, and then each pixel in the processing image is traversed. For each pixel, if its grayscale value is greater than or equal to the threshold, it is set to white (255); if it is less than the threshold, it is set to black (0). This process simplifies the grayscale information in the image to only include foreground (white) and background (black) information, which helps subsequent contour detection and analysis.

[0049] S205 , applying connected region analysis to the processed image after the binarization process, and removing regions smaller than a predetermined area threshold.

[0050] In some embodiments, a connected region analysis is performed on a binary image to identify and mark all connected white (or black) pixel regions. Then, the area (number of pixels) of each connected region is calculated. The area of ​​each region is compared with a predetermined threshold, and if it is less than the threshold, all pixels in the region are set to the background color (usually black). This process can effectively remove interference caused by noise or unimportant small structures, so that only the main target structure is retained in the image.

[0051] It can be seen that converting microscopic data into grayscale images facilitates subsequent edge detection. Edge detection highlights the contours of microstructures, while dilation and erosion operations further enhance the clarity of these contours. Binarization converts the image into black and white, effectively separating the target structure from the background. Finally, connected region analysis removes areas smaller than a predetermined area threshold, effectively filtering out noise and small irrelevant structures.

[0052] S206, performing contour detection on the microscopic data to obtain a set of contours; The micro data refers to the micro data processed through the above-mentioned S201 to S205.

[0053] In some embodiments, the processed binary image is analyzed using a contour detection algorithm. The algorithm traverses the image and identifies the boundaries between the foreground (usually white) and the background (usually black). Each closed boundary is identified as a contour and represented by a series of point coordinates.

[0054] In some specific embodiments, an edge tracking algorithm is used to start from an edge point and gradually track along the edge until returning to the starting point to form a complete outline, which is not limited here.

[0055] S207, screening the contours, and retaining contours that meet the conditions according to the preset area threshold and shape characteristics; In some embodiments, the area of ​​each contour is calculated and compared with a preset area threshold to remove contours that are too small or too large. Then, shape features such as circularity, rectangularity, aspect ratio, etc. are calculated for the remaining contours, and further screening is performed according to preset shape feature standards. This process can effectively remove contours that do not meet expectations, such as noise, background structures, or incomplete targets, thereby retaining the contours that are most likely to represent the true target structure.

[0056] S208 , calculating the minimum bounding rectangle of each retained contour, and using the coordinates of the minimum bounding rectangle as the bounding box coordinates.

[0057] In some embodiments, the minimum bounding rectangle of each retained contour is calculated. The minimum bounding rectangle may be tilted, so further processing is required to obtain a rectangle parallel to the image coordinate axis. Then, the coordinates of the upper left corner and lower right corner of the rectangle parallel to the coordinate axis are extracted, and these two sets of coordinates constitute the bounding box coordinates. This process simplifies the irregular contour into a regular rectangular bounding box, which is convenient for subsequent analysis and processing.

[0058] It can be seen that contour detection is performed on micro data to obtain a set of contours, which can automatically identify prominent structures in micro data. The contours are screened by preset area thresholds and shape features, effectively eliminating noise and irrelevant structures, and calculating the minimum circumscribed rectangle as the bounding box coordinates to improve the accuracy of annotation. This automated bounding box determination method significantly reduces human intervention, improves the objectivity and consistency of annotation, and reduces the errors that may be caused by manual annotation.

[0059] In actual use, the method for determining the bounding box coordinates mentioned in step S103 and the method for determining the bounding box coordinates mentioned in steps S201 to S208 can be combined to obtain more accurate and reliable results. A simple method is to further determine the bounding box coordinates obtained in steps S201 to S208 using the method for determining the bounding box coordinates mentioned in step S103.

[0060] In actual use, obtaining microstructure images and crystal structure data usually requires expensive equipment and professional techniques, which may increase research costs. Frequent microscopic analysis may prolong the research cycle and affect experimental efficiency.

[0061] See also Figure 3 , Figure 3 yes Figure 1 A flow chart of step S102 in FIG. Therefore, step S102 specifically includes: S301, obtaining a capacity decay curve of a same battery, wherein the same battery is a battery of the same type as the target battery; The capacity decay curve is a graph showing the change of battery capacity over time or charge and discharge cycles. The same battery refers to a battery with the same model, specification and manufacturing process as the target battery.

[0062] In some embodiments, researchers will select a batch of batteries of the same model and specification as the target battery, conduct long-term charge and discharge cycle tests on them, and record the battery capacity after each cycle. With these data, a curve of battery capacity changing over time or number of cycles, i.e., capacity decay curve, is drawn. This curve can reflect the overall trend and characteristics of battery capacity change during use.

[0063] S302, obtaining characteristic points in the capacity decay curve; In some embodiments, researchers will carefully analyze the capacity decay curve obtained in S301 to find important nodes that can represent changes in battery performance. These feature points may be selected based on mathematical features (such as changes in the first-order derivative or second-order derivative of the curve) or based on important thresholds in practical applications (such as the capacity drops to 80% of the rated capacity).

[0064] S303 , obtaining microscopic data of the target battery at a time corresponding to the characteristic point.

[0065] It can be seen that obtaining the capacity decay curve of similar batteries provides a reference benchmark for the performance changes of the target battery. By analyzing the characteristic points in the capacity decay curve, key time nodes are determined, which usually represent the moments when the battery performance changes significantly. The microscopic data of the target battery is obtained at the time corresponding to these characteristic points, ensuring that the time points of the microscopic analysis are representative and important. Therefore, the number of times microscopic data is obtained is reduced, which not only saves usage time, but also reduces the workload of professional technicians.

[0066] In actual use, which characteristic points in the capacity decay curve best represent the important nodes that represent the changes in battery performance? See also Figure 4 , Figure 4 yes Figure 3 A flow chart of step S302 in FIG. Therefore, in some other embodiments, step S302 specifically includes: S401, taking points on the capacity decay curve at preset intervals, and calculating the curvature of each taken point; In some embodiments, a suitable point-taking interval is first determined, which should be small enough to capture the detailed changes of the curve but not to generate too many data points. Then, starting from the starting point of the curve, points are taken on the entire curve according to this fixed interval. For each point obtained, a mathematical method is used to calculate the curvature of the point. The calculation of curvature usually involves the first and second order derivatives of the curve at the point.

[0067] However, in actual use, the capacity decay curve is obtained by measuring a limited number of sampling points. Since it is impossible to measure the battery continuously and uninterruptedly, sampling can only be performed at specific time points. A continuous curve is drawn between these discrete sampling points through interpolation or fitting methods. Therefore, most of the points on the curve are actually calculated rather than directly measured. This may cause some points on the curve to not accurately reflect the actual capacity decay.

[0068] Therefore, in some embodiments, sampling points used to draw the capacity decay curve can be directly selected as data points for subsequent processing to complete the next operation. By using actual measured data rather than interpolation points on the curve, the actual situation of battery capacity decay can be more accurately reflected.

[0069] S402, selecting points whose curvature is greater than a preset high extreme value of curvature and points whose curvature is lower than a preset low extreme value of curvature as feature points; The preset high curvature extreme value refers to a preset larger curvature threshold value, which is used to identify points where the curve changes sharply. The preset low curvature extreme value refers to a preset smaller curvature threshold value, which is used to identify points where the curve changes slowly.

[0070] In some embodiments, the appropriate curvature upper and lower extreme values ​​are determined in advance. Then, the curvature values ​​of all points calculated in S401 are traversed, and those points whose curvature exceeds the upper extreme value or is lower than the lower extreme value are marked as feature points.

[0071] S403, calculating the curvature change rate of each taken point according to the curvature; In some embodiments, by calculating the curvature difference between adjacent points and dividing by the time or position interval between these points, the curvature change rate calculation can reveal the areas where the curve has undergone abrupt changes, and these changes may correspond to important turning points in battery performance.

[0072] S404, selecting the points whose curvature change rate is higher than a preset curvature mutation threshold as feature points; In some embodiments, according to the determined appropriate curvature mutation threshold, the curvature change rates of all points calculated in S403 are then traversed, and those points whose change rates exceed the preset threshold are marked as feature points. These feature points usually represent key turning points in the capacity decay process, and may correspond to major changes in the internal structure or performance of the battery.

[0073] S405, dividing the capacity decay curve into multiple sections; In some embodiments, the entire curve is divided into several sections according to previously identified feature points, or according to predefined time intervals or capacity change amplitudes. Each section may represent a specific stage in the battery decay process, such as an initial rapid decay period, a stable decay period, an accelerated decay period, etc.

[0074] S406, determining the number of points to be taken for each paragraph according to the length of the paragraph; In some embodiments, according to the length of each paragraph, a certain rule is used to determine how many feature points should be selected in the paragraph. This method can ensure that more points are selected in longer paragraphs and fewer points are selected in shorter paragraphs, thereby avoiding oversampling while maintaining data representativeness.

[0075] S407, randomly select feature points on each paragraph according to the number of points to be selected.

[0076] It can be seen that by setting the high and low extreme values ​​of the curvature and selecting the most significant points of the curve change as feature points, the key change points are ensured to be captured. The curvature change rate is calculated and the mutation threshold is set to further identify the mutation points in the curve. These points often represent important turning points in battery performance. The curve is divided into segments and points are randomly selected in each segment to ensure the uniform distribution of feature points on the entire curve. This multi-level and multi-angle feature point selection method not only captures the key changes of the curve, but also takes into account the overall trend, greatly improving the representativeness and comprehensiveness of the feature points.

[0077] In actual use, the capacity decay curve may be incomplete. Since subsequent data processing and analysis are mainly based on points selected from this curve, the incompleteness of the curve will have a significant impact on the entire analysis process.

[0078] In some embodiments, after step S301, the method further includes: S304, determining whether the capacity attenuation curve is continuous; In some embodiments, the time or charge and discharge intervals between all adjacent data points are calculated; then a threshold is set, such as twice the normal sampling interval; finally, it is checked whether there is an interval exceeding this threshold, and if so, it is determined to be discontinuous, which is not limited here.

[0079] In some embodiments, the capacity data is first subjected to a first-order difference to calculate the rate of change between adjacent points; a reasonable range of the rate of change is then set; and then a check is made to see if there are points whose rate of change exceeds this range. If there are points, this may indicate that the curve is discontinuous, which is not limited here.

[0080] S305. If the capacity decay curve is discontinuous, use interpolation technology to supplement the data at the missing part of the capacity decay curve; In some embodiments, the specific location and range of the missing data are first determined, and then an appropriate interpolation method is selected. Common interpolation methods include linear interpolation, polynomial interpolation, spline interpolation, etc. The interpolation process considers the known data points around the missing points, and calculates reasonable estimates based on the values ​​and distribution characteristics of these points. The interpolated data should be consistent with the original data and be able to reflect the overall trend of capacity attenuation.

[0081] In some specific embodiments, the starting and ending points of the missing data are determined; then a linear interpolation method is used, i.e., the missing portion is assumed to be a straight line; finally, the capacity value of each time point at the missing portion is calculated proportionally based on the values ​​of the starting and ending points, which is not limited here.

[0082] In some specific embodiments, several known points around the missing point are first selected; then a polynomial interpolation method, such as Lagrange interpolation or Newton interpolation, is used; and then the capacity value of the missing point is calculated based on the fitted polynomial function, which is not limited here.

[0083] If the capacity decay curve is continuous, step S302 is executed.

[0084] It can be seen that judging the continuity of the capacity decay curve can identify possible missing or abnormal data. For discontinuous curves, interpolation technology is used to supplement the missing data to ensure the integrity and continuity of the curve.

[0085] In actual use, the conventional data and micro data should ideally correspond one to one in terms of time and quantity. However, there may be situations where the time and quantity do not completely correspond. For example, in the above steps S301 to S303, the sampling frequency and sampling time of the micro data are changed. In theory, one solution is to adjust the conventional data accordingly. Another method is as follows: The time within the same range is regarded as the same time, and the same range is determined according to the degree of capacity attenuation.

[0086] In some embodiments, the capacity decay curve is first analyzed to identify time periods with similar capacity decay rates; then, all time points within these time periods are regarded as the same time to simplify the data processing process; this processing method is based on the assumption that within the time period with similar capacity decay rates, the performance and characteristics of the battery do not change much, so the data within this time period can be regarded as homogeneous.

[0087] In some specific embodiments, the slope of the capacity decay curve is first calculated to obtain the capacity decay rate; then a threshold range of the capacity decay rate is set; finally, the continuous time periods in which the capacity decay rate is within the threshold range are divided into the same range, which is not limited here.

[0088] In some specific embodiments, the capacity decay curve is first divided into several segments according to time; then the capacity decay percentage in each segment is calculated; and then, according to a preset capacity decay percentage interval, adjacent time periods falling into the same interval are merged into the same range, which is not limited here.

[0089] In some embodiments, in each time period, there may be multiple micro data corresponding to one regular data, or vice versa. This method effectively solves the problem of mismatched quantities by treating all data points in the same time period as data at the same moment. The specific processing can be as follows: If there are multiple micro data corresponding to one regular data in a time period, the average of these micro data or other statistical methods (such as median) can be used to represent the micro data of this time period. If there are multiple regular data corresponding to one micro data in a time period, the regular data can also be averaged or other statistical methods can be used.

[0090] The micro data and regular data in each time period can also be matched arbitrarily.

[0091] It can be seen that treating the time within the same period as the same time solves the problem of the non-strict temporal correspondence between conventional data and micro data, and also solves the problem of the inequality in quantity between conventional data and micro data.

[0092] The following introduces an exemplary lithium-ion battery electrical performance acquisition system 500 provided in an embodiment of the present application. Figure 5 Schematic diagram of an exemplary hardware structure of a lithium-ion battery electrical performance acquisition system 500 provided in an embodiment of the present application.

[0093] In some embodiments, the lithium-ion battery electrical performance acquisition system 500 is a computer device or the lithium-ion battery electrical performance acquisition system 500 includes a computer device. The computer device includes a processor, a memory and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with other external terminals or servers through a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, the method in the embodiment of the present application is implemented.

[0094] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0095] As described above, 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 cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0096] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0097] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0098] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for obtaining electrical properties of a lithium-ion battery, characterized in that: include: Acquire routine data of the target battery at different times, the routine data including discharge cycle, charge and discharge rate, temperature change, voltage and current waveforms; Acquiring microscopic data of the target battery at different times, wherein the microscopic data includes a microstructure image and crystal structure data of the target battery; The micro data is annotated according to the conventional data of the same time to generate annotated data; wherein the annotated data includes the micro data and a corresponding annotation file, the annotation file includes a target category and bounding box coordinates corresponding to the target category, the target category is data corresponding to a certain type of data in the conventional data falling into a corresponding sub-range, and the bounding box coordinates are determined by the micro data; Combining the labeled data at different times into a data set; Inputting the data set into a preset battery performance prediction model for training; Input current conventional data into the battery performance prediction model to obtain corresponding current microscopic data.

2. The method according to claim 1, characterized in that The step of determining the bounding box coordinates from the micro data specifically comprises: Performing contour detection on the microscopic data to obtain a set of contours; Screening the contours, and retaining the contours that meet the conditions according to preset area thresholds and shape features; The minimum bounding rectangle of each retained contour is calculated, and the coordinates of the minimum bounding rectangle are used as the bounding box coordinates.

3. The method according to claim 2, characterized in that Before the step of performing contour detection on the microscopic data to obtain a set of contours, the method further comprises: Preprocessing the microscopic data to convert the microscopic data into a grayscale image; Performing edge detection on the grayscale image to obtain an edge map; Performing dilation and erosion operations on the edge map to obtain a processed map; Performing binarization processing on the processed image; Connected region analysis is applied to the processed image after the binarization process to remove regions smaller than a predetermined area threshold.

4. The method according to claim 1, characterized in that The step of obtaining the microscopic data of the target battery at different times specifically includes: Obtaining a capacity decay curve of a same battery, wherein the same battery is a battery of the same type as the target battery; Obtaining characteristic points in the capacity decay curve; The microscopic data of the target battery is acquired at a time corresponding to the characteristic point.

5. The method according to claim 4, characterized in that The step of obtaining the characteristic points in the capacity decay curve specifically includes: Taking points on the capacity decay curve at preset intervals, and calculating the curvature of each taken point; Selecting points whose curvature is greater than a preset high curvature extreme value and points whose curvature is lower than a preset low curvature extreme value as the feature points; Calculating the curvature change rate of each point taken according to the curvature; Selecting the point whose curvature change rate is higher than a preset curvature mutation threshold as the feature point; dividing the capacity decay curve into a plurality of sections; Determine the number of points to be taken for each of the paragraphs according to the length of the paragraphs; The feature points are randomly selected on each of the paragraphs according to the number of selected points.

6. The method according to claim 4, characterized in that After the step of obtaining the capacity decay curve of the same battery, the method further includes: Determining whether the capacity decay curve is continuous; If the capacity decay curve is discontinuous, interpolation technology is used to supplement the data at the missing part of the capacity decay curve; If the capacity decay curve is continuous, the step of obtaining characteristic points in the capacity decay curve is performed.

7. The method according to claim 4, characterized in that The step of annotating the micro data according to the conventional data at the same time to generate annotated data specifically includes: The time within the same range is regarded as the same time, and the same range is determined according to the degree of capacity attenuation.

8. A lithium-ion battery electrical performance acquisition system, characterized in that: The lithium-ion battery electrical performance acquisition system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the lithium-ion battery electrical performance acquisition system to perform the method described in any one of claims 1-7.

9. A computer program product comprising instructions, characterized in that When the computer program product runs on a lithium-ion battery electrical performance acquisition system, the lithium-ion battery electrical performance acquisition system is enabled to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a lithium-ion battery electrical performance acquisition system, the lithium-ion battery electrical performance acquisition system is enabled to execute the method according to any one of claims 1 to 7.

Images