Test method, device, equipment, storage medium and product of battery cell capacity

Abstract

The application relates to the technical field of batteries, in particular to a battery capacity testing method and device, equipment, a storage medium and a product. The method comprises the following steps: obtaining a current batch of battery cells to be tested; classifying the battery cells to be tested to obtain first to third types of battery cells to be tested; performing capacity testing on the first and second types of battery cells to be tested based on a capacity testing model, performing capacity adjustment testing on the three types of battery cells to be tested, and generating a test result corresponding to the current batch of battery cells to be tested, wherein the capacity testing model is obtained based on the test result of the previous batch and a test data set. Therefore, the problem of high cost and low testing accuracy of the capacity testing in the related art is solved.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a method, apparatus, equipment, storage medium, and product for testing the capacity of a battery cell. Background Technology

[0002] Capacity testing is a crucial step in lithium-ion cell manufacturing. It not only calibrates the cell's capacity but also serves as a vital basis for rejecting defective products and ensuring cell consistency. However, the currently widely adopted production model, which combines actual measurement with temperature fitting, has several significant problems: 1) High testing costs: Current full-cell capacity testing requires at least two complete discharge-charge cycles, leading to significant power consumption and increased overall testing time and labor costs. 2) Poor data robustness: The one-time calibration process lacks the ability to cope with subsequent manufacturing system disturbances. This means that if production conditions change, the calibrated data may no longer be accurate, potentially leading to the omission of false defects or genuinely defective products in batches. Summary of the Invention

[0003] This application provides a method, apparatus, equipment, storage medium, and product for testing the capacity of battery cells, in order to solve the problems of high cost and low accuracy in capacity testing in related technologies.

[0004] The first aspect of this application provides a method for testing the capacity of battery cells, comprising the following steps: obtaining the battery cells to be tested in the current batch; classifying the battery cells to be tested into first to third categories of battery cells to be tested; performing capacity testing on the first category of battery cells to be tested and the second category of battery cells to be tested based on a capacity testing model, performing capacity adjustment testing on the three categories of battery cells to be tested, and generating test results corresponding to the battery cells to be tested in the current batch, wherein the capacity testing model is optimized based on the test results and test dataset of the previous batch.

[0005] Optionally, after generating the test results for the current batch of cells to be tested, the method further includes: merging the test results of the previous batch into the test dataset; and optimizing the capacity test model based on the merged test dataset and the test results for the current batch of cells to be tested.

[0006] Optionally, before acquiring the current batch of cells to be tested, the method further includes: acquiring an initial test dataset; establishing an initial test model based on the initial test dataset, acquiring cells from any batch, testing cells from any batch based on the initial test model to obtain test errors; and updating the initial test model based on the test errors to obtain a capacity test model.

[0007] Optionally, an initial test model is established based on the initial capacity test dataset, including: calculating the covariance of each test data and capacity in the test dataset, determining the target test data based on the covariance; constructing multiple exponential regression equations for each target test data and capacity, and generating the initial test model based on the multiple exponential regression equations.

[0008] Optionally, the test error is obtained by testing any batch of cells based on the initial test model, including: testing all cells in any batch to obtain the predicted capacity of each cell; selecting outlier cells and some cells other than outlier cells from all cells to obtain the predicted capacity; and calculating the prediction error of the initial test model based on the predicted capacity.

[0009] Optionally, the test dataset includes at least one of the following: capacity dataset, injection dataset, assembly dataset, formation dataset, dual injection dataset, and DC internal resistance measurement dataset.

[0010] A second aspect of this application provides a battery cell capacity testing device, comprising: a first acquisition module for acquiring a batch of battery cells to be tested; a classification module for classifying the battery cells to be tested into first to third categories of battery cells to be tested; and a testing module for performing capacity tests on the first and second categories of battery cells to be tested based on a capacity testing model, performing capacity adjustment tests on the three categories of battery cells to be tested, and generating test results corresponding to the current batch of battery cells to be tested, wherein the capacity testing model is optimized based on the test results and test dataset of the previous batch.

[0011] Optionally, the cell capacity testing device further includes: an optimization module, used to merge the test results of the previous batch into the test dataset after generating the test results corresponding to the current batch of cells to be tested; and to optimize the capacity test model based on the merged test dataset and the test results corresponding to the current batch of cells to be tested.

[0012] Optionally, the cell capacity testing device further includes: a second acquisition module, used to acquire an initial test dataset before acquiring the current batch of cells to be tested; an establishment module, used to establish an initial test model based on the initial test dataset, acquire cells from any batch, and test cells from any batch based on the initial test model to obtain test errors; and an update module, used to update the initial test model based on the test errors to obtain the capacity test model for the next batch.

[0013] Optionally, the module is further used to calculate the covariance of each test data point and capacity in the test dataset, determine the target test data based on the covariance, construct multiple exponential regression equations for each target test data point and capacity, and generate an initial test model based on the multiple exponential regression equations.

[0014] Optionally, the module is further used to test all cells in any batch to obtain the predicted capacity of each cell; select outlier cells from all cells and some cells other than outlier cells to test to obtain the predicted capacity; and calculate the prediction error of the initial test model based on the predicted capacity.

[0015] Optionally, the test dataset includes at least one of the following: capacity dataset, injection dataset, assembly dataset, formation dataset, dual injection dataset, and DC internal resistance measurement dataset.

[0016] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the electronic device as described above.

[0017] A fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed, are used to implement the cell capacity testing method as described in the above embodiments.

[0018] A fifth aspect of this application provides a computer program product, including: a computer program or instructions, which, when executed, implement the cell capacity testing method as described in the above embodiments.

[0019] Therefore, this application has at least the following beneficial effects:

[0020] This application's embodiments reduce overall testing costs by classifying the cells to be tested, performing actual capacity testing on a subset of cells, and using a purely fitted capacity method for the others. Furthermore, by continuously optimizing and updating the capacity testing model, it maintains high reliability and robustness while preserving high prediction accuracy. This solves the problems of high cost and low accuracy in capacity testing in related technologies.

[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0023] Figure 1 This is a flowchart of a cell capacity testing method provided according to an embodiment of this application;

[0024] Figure 2 This is an example diagram illustrating a test of cell capacity according to an embodiment of this application;

[0025] Figure 3 This is an example diagram of a battery cell capacity testing apparatus provided according to an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0027] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0028] The following description, with reference to the accompanying drawings, outlines a method, apparatus, device, storage medium, and product for testing battery cell capacity according to embodiments of this application. Addressing the problems mentioned in the background section, this application provides a method for testing battery cell capacity. In this method, by classifying the battery cells to be tested and performing actual capacity testing on a subset of cells while using a pure fitting capacity method for the remaining cells, the number of full discharge-charge cycles is significantly reduced, lowering the overall testing cost. Furthermore, by continuously optimizing and updating the capacity testing model, high reliability and robustness can be maintained while preserving high prediction accuracy. Thus, the problems of high cost and low accuracy in capacity testing in related technologies are solved.

[0029] Specifically, Figure 1 This is a schematic flowchart of a cell capacity testing method provided in an embodiment of this application.

[0030] like Figure 1 As shown, the method for testing the cell capacity includes the following steps:

[0031] In step S101, the cells to be tested in the current batch are obtained.

[0032] In this application embodiment, a certain number of cells (e.g., 1,000 to 50,000) can be selected as the current batch, and these cells will serve as the basis for subsequent classification and testing.

[0033] In step S102, the cells to be tested are classified to obtain the first to third categories of cells to be tested.

[0034] Specifically, in this application embodiment, a portion of the battery cells (e.g., 5% to 30%) can be randomly selected as the first type of battery cells, and the battery cells that are expected to be at the edge of performance or may deviate from the normal range can be selected as the second type of battery cells. This portion of battery cells usually accounts for 5% to 10% of the total number of battery cells, and the remaining battery cells are selected as the third type of battery cells.

[0035] In step S103, capacity tests are performed on the first type of test cells and the second type of test cells based on the capacity test model, and capacity adjustment tests are performed on the three types of test cells to generate test results for the current batch of test cells. The capacity test model is optimized based on the test results and test dataset of the previous batch.

[0036] This application embodiment can employ conventional capacity testing methods to conduct comprehensive charge-discharge cycle tests on the first type of battery cells to obtain their actual capacity data. The second type of battery cells also undergoes capacity testing to detect those predicted as edge cases or potential outliers, thereby identifying potential anomalies. For the remaining third type of battery cells, this application embodiment does not perform a complete capacity test, but instead performs capacity prediction based on a previously established and continuously updated capacity testing model. This approach can significantly reduce the time and resource consumption required for actual testing while maintaining sufficient accuracy. Therefore, by implementing different testing strategies for the three types of battery cells, this application embodiment can efficiently generate test results for all battery cells in the current batch, helping to reduce overall testing costs.

[0037] In practice, the capacity testing model is continuously optimized based on the results of the previous batch of tests and the accumulated dataset. This means that after each batch of tests is completed, the system collects newly generated data and integrates it into the existing dataset. Through a feedback mechanism, it adjusts model parameters, such as weights, to generate a more accurate new version of the model (e.g., updating from α0 to α1). This process ensures that the model can adapt to changes in the production environment and maintain high prediction accuracy and robustness.

[0038] In one embodiment of this application, after generating the test results corresponding to the current batch of cells to be tested, the method further includes: merging the test results of the previous batch into the test dataset; and optimizing the capacity test model based on the merged test dataset and the test results corresponding to the current batch of cells to be tested.

[0039] It is understood that, in this embodiment of the application, the actual test results and related feature data of all cells from the previous batch (including the first, second, and third types) can be added to the existing test dataset. This step helps to increase the diversity and richness of the dataset, thereby improving the quality of model training. A new capacity testing model is then regenerated based on the merged dataset, which will be used in the next batch. Through such an iterative process, the system can continuously learn from each test and self-correct, not only improving prediction accuracy but also enhancing the adaptability of the entire testing system to external changes. This adaptability is an advantage that traditional static models do not possess, enabling the new prediction system to maintain high reliability and robustness while ensuring high efficiency.

[0040] In one embodiment of this application, before obtaining the current batch of cells to be tested, the method further includes: obtaining an initial test dataset; establishing an initial test model based on the initial test dataset, and obtaining cells from any batch; testing cells from any batch based on the initial test model to obtain test errors; and updating the initial test model based on the test errors to obtain a capacity test model.

[0041] The test dataset includes at least one of the following: capacity dataset, injection dataset, assembly dataset, formation dataset, two-injection dataset, and DC internal resistance measurement dataset.

[0042] This application embodiment can collect an initial test dataset: collecting data such as the full capacity test current I. 0～n ~Voltage V 0～n ~Time T O Data / Conversion Current I 1～n ~Voltage V 1～n Data such as time T1 and electrode surface density M1 are collected, and a model α0 corresponding to the initial data is established. By selecting a new batch of cells, the capacity of the cells in the batch is predicted using the established initial test model. The predicted results of the model are compared with the actual results after the actual capacity test of the cells in the batch. The prediction error is calculated. Based on the error feedback, the parameter settings of the model are adjusted or different algorithms are tried to improve the prediction effect, which helps to continuously improve the accuracy of the capacity test model.

[0043] Furthermore, an initial test model is established based on the initial capacity test dataset, including: calculating the covariance of each test data and capacity in the test dataset, determining the target test data based on the covariance; constructing multiple exponential regression equations for each target test data and capacity, and generating the initial test model based on the multiple exponential regression equations.

[0044] It is understood that the embodiments of this application can perform correlation analysis between all data corresponding to each cell and its capacity to calculate parameters such as the formation voltage V. 11 The covariance X1 between the data and the test capacity C is calculated, and so on, the covariances X2, X3, ..., Xn between each data point and the test capacity C are calculated.

[0045] Furthermore, in this embodiment, the covariance values ​​can be sorted from largest to smallest through data filtering. After sorting, the largest preset number of values ​​(e.g., 10-15) are selected, and the data tuples S corresponding to the selected values ​​are named S1, S2, S3...S10-15. An exponential regression (least squares as the loss function) between S1, S2, S3...S10-15 and C is calculated using methods such as R. The exponential regression equations fx are f1, f2, f3...f10-15, respectively. Assuming that the initial weights of each data point are the same, the weights are set to wx0. After normalization, the initial test model is obtained.

[0046]

[0047] Furthermore, the test error is obtained by testing any batch of cells based on the initial test model, including: testing all cells in any batch to obtain the predicted capacity of each cell; selecting outlier cells and some cells other than outlier cells from all cells to obtain the predicted capacity; and calculating the prediction error of the initial test model based on the predicted capacity.

[0048] Specifically, in this embodiment of the application, before importing a batch of battery cells (1000-50000ea) for prediction, a batch of battery cells R1 is randomly selected, and the remaining battery cells are divided into test cells A1 and outlier cells B1. Using α0 as the judgment criterion, the entire batch of battery cells is imported for prediction to obtain the predicted capacity value T. The outlier cell B and the first selected cell R are subjected to a complete capacity test Cr1. The data tuples corresponding to the selected values ​​are selected to calculate the test error ex of fx corresponding to each tuple:

[0049]

[0050] Further adjustments to the model's weight parameters based on the test error generate a new model α1. Through continuous data input and model iteration, the capacity prediction accuracy and robustness can be gradually improved. The specific formula is as follows:

[0051] fx = 1 / 2ln((1-ex) / ex)

[0052]

[0053] In summary, the embodiments of this application use fully automated self-convergence as a long-term prediction system strategy, takes the real-time fluctuations of the actual state as the focus, and also takes historical data into account as a stage strategy. This can effectively distinguish between fluctuations in individual data and changes in the overall system, greatly reducing the maintenance cost of the system and improving the stability of the data.

[0054] The following is combined Figure 2 The method for testing the cell capacity according to embodiments of this application is described in detail, including the following steps:

[0055] 1) Conduct capacity testing and collect initial data according to the standard procedure;

[0056] 2) Establish the model α0 corresponding to the initial data;

[0057] 3) Classify the subsequent cells of a certain order of magnitude (1000-50000ea) as a single batch;

[0058] A. Randomly select battery cells (accounting for 5% to 30% of the total).

[0059] B. Modeling and predicting overall marginal outlier data (representing 5%–10% of the total).

[0060] C. Remaining battery cells

[0061] 4) Test the three types of cells: A / B type cells undergo conventional capacity testing, and C type cells undergo capacity adjustment testing;

[0062] 5) Collect all process data (A0) for Category A;

[0063] 6) Add A0 data as new data to the starting data as feedforward validation of the starting dataset;

[0064] 7) After the feedforward validation is completed, the weights are adjusted and a new model α1 is generated.

[0065] 8) Repeat steps 3 to 7, using positive feedback and other cyclical data patterns to make real-time changes to the data and adjust historical weights to ensure the robustness of the data system.

[0066] The cell capacity testing method proposed in this application classifies the cells to be tested, performs actual capacity testing on a subset of cells, and uses a pure fitting capacity method for the others. This significantly reduces the number of full discharge-charge cycles, lowers the overall testing cost, and, through continuous optimization and updating of the capacity testing model, maintains high reliability and robustness while preserving high prediction accuracy. Therefore, it solves the problems of high cost and low accuracy in capacity testing in related technologies.

[0067] Next, the battery cell capacity testing apparatus according to an embodiment of this application is described with reference to the accompanying drawings.

[0068] Figure 3 This is a block diagram of a battery cell capacity testing device according to an embodiment of this application.

[0069] like Figure 3As shown, the battery cell capacity testing device 10 includes: a first acquisition module 100, a classification module 200, and a testing module 300.

[0070] The first acquisition module 100 is used to acquire the battery cells to be tested in the current batch; the classification module 200 is used to classify the battery cells to be tested into first to third categories of battery cells to be tested; the testing module 300 is used to perform capacity testing on the first and second categories of battery cells to be tested based on the capacity testing model, perform capacity adjustment testing on the three categories of battery cells to be tested, and generate the test results corresponding to the battery cells to be tested in the current batch. The capacity testing model is optimized based on the test results and test dataset of the previous batch.

[0071] In one embodiment of this application, the cell capacity testing device 10 further includes: an optimization module, used to merge the test results of the previous batch into the test dataset after generating the test results corresponding to the current batch of cells to be tested; and to optimize the capacity test model based on the merged test dataset and the test results corresponding to the current batch of cells to be tested.

[0072] In one embodiment of this application, the cell capacity testing device 10 further includes: a second acquisition module, used to acquire an initial test dataset before acquiring the current batch of cells to be tested; an establishment module, used to establish an initial test model based on the initial test dataset, acquire any batch of cells, and test any batch of cells based on the initial test model to obtain test errors; and an update module, used to update the initial test model based on the test errors to obtain the capacity test model for the next batch.

[0073] In one embodiment of this application, the establishment module is further used to calculate the covariance of each test data and capacity in the test dataset, determine the target test data based on the covariance, construct multiple exponential regression equations for each target test data and capacity, and generate an initial test model based on the multiple exponential regression equations.

[0074] In one embodiment of this application, the establishment module is further configured to test all cells in any batch to obtain the predicted capacity of each cell; select outlier cells and some cells other than outlier cells from all cells to test to obtain the predicted capacity; and calculate the prediction error of the initial test model based on the predicted capacity.

[0075] In one embodiment of this application, the test dataset includes at least one of the following: a capacity dataset, a liquid injection dataset, an assembly dataset, a formation dataset, a dual-injection dataset, and a DC internal resistance measurement dataset.

[0076] It should be noted that the explanation of the aforementioned method embodiment for testing cell capacity also applies to the cell capacity testing device of this embodiment, and will not be repeated here.

[0077] The cell capacity testing apparatus proposed in this application classifies the cells to be tested, performs actual capacity testing on a subset of cells, and uses a pure fitting capacity method for the others. This significantly reduces the number of full discharge-charge cycles, lowers the overall testing cost, and, through continuous optimization and updating of the capacity testing model, maintains high reliability and robustness while preserving high prediction accuracy. Therefore, it solves the problems of high cost and low accuracy in capacity testing in related technologies.

[0078] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0079] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0080] When the processor 402 executes the program, it implements the cell capacity testing method provided in the above embodiments.

[0081] Furthermore, electronic devices also include:

[0082] Communication interface 403 is used for communication between memory 401 and processor 402.

[0083] The memory 401 is used to store computer programs that can run on the processor 402.

[0084] The memory 401 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0085] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0086] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0087] Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0088] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for testing the cell capacity.

[0089] This application also provides a computer program product, including: a computer program or instructions, which, when executed, implement the above-described method for testing the cell capacity.

[0090] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0091] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0092] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0093] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0094] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0095] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method of testing the capacity of an electric cell, characterized in that, The method comprises the following steps: obtaining a current batch of battery cells to be tested; classifying the battery cells to be tested to obtain first to third types of battery cells to be tested; performing capacity testing on the first and second types of battery cells to be tested based on a capacity testing model, performing capacity adjustment testing on the three types of battery cells to be tested, and generating test results corresponding to the current batch of battery cells to be tested, wherein the capacity testing model is obtained based on test results of a previous batch and a test data set; Before obtaining the current batch of battery cells to be tested, the method further comprises: obtaining an initial test data set; establishing an initial test model based on the initial test data set, and obtaining battery cells of any batch, testing the battery cells of any batch based on the initial test model to obtain a test error; and updating the initial test model based on the test error to obtain the capacity testing model; establishing an initial test model based on the initial test data set comprises: calculating the covariance of each test data and the capacity of the battery cells in the initial test data set, and determining target test data based on the covariance; constructing a plurality of exponential regression equations of each target test data and the capacity of the battery cells, and generating the initial test model based on the plurality of exponential regression equations; testing battery cells of any batch based on the initial test model to obtain a test error comprises: testing all battery cells in the battery cells of any batch to obtain a predicted capacity of each battery cell; selecting an outlying battery cell in the all battery cells and a part of battery cells other than the outlying battery cell to obtain a predicted capacity of the part of battery cells; and calculating a prediction error of the initial test model based on the predicted capacity of each battery cell and the predicted capacity of the part of battery cells other than the outlying battery cell.

2. The method of claim 1, wherein, After the test results corresponding to the current batch of battery cells to be tested are generated, the method further comprises: merging the test results of the previous batch into the test data set; and optimizing the capacity testing model based on the merged test data set and the test results corresponding to the current batch of battery cells to be tested.

3. The method of claim 1 or 2, wherein, The initial test data set comprises at least one of a capacity data set, a liquid injection data set, an assembly data set, a formation data set, a second liquid injection data set, and a direct current internal resistance measurement data set.

4. An apparatus for testing the capacity of an electric cell, characterized by The method comprises: a first obtaining module configured to obtain a current batch of battery cells to be tested; a classification module configured to classify the battery cells to be tested to obtain first to third types of battery cells to be tested; a testing module configured to perform capacity testing on the first and second types of battery cells to be tested based on a capacity testing model, perform capacity adjustment testing on the three types of battery cells to be tested, and generate test results corresponding to the current batch of battery cells to be tested, wherein the capacity testing model is obtained based on test results of a previous batch and a test data set; a second obtaining module configured to obtain an initial test data set before obtaining the current batch of battery cells to be tested; an establishing module configured to establish an initial test model based on the initial test data set, and obtain battery cells of any batch, test the battery cells of any batch based on the initial test model to obtain a test error, and update the initial test model based on the test error to obtain the capacity testing model; an establishing module configured to establish an initial test model based on the initial test data set, and obtain battery cells of any batch, test the battery cells of any batch based on the initial test model to obtain a test error, and update the initial test model based on the test error to obtain the capacity testing model; An updating module is configured to update the initial test model according to a test error to obtain a capacity test model; The establishing module is further configured to: calculate a covariance between each test data in the initial test data set and the battery capacity, determine target test data according to the covariance, and construct a plurality of exponential regression equations of each target test data and the battery capacity, and generate the initial test model according to the plurality of exponential regression equations. The establishing module is further configured to: test all the battery cells in the arbitrary batch to obtain a predicted capacity of each battery cell, select an outlier battery cell in the all battery cells and a part of battery cells other than the outlier battery cell, test the outlier battery cell and the part of battery cells to obtain a predicted capacity, and calculate a prediction error of the initial test model according to the predicted capacity of each battery cell and the predicted capacity of the outlier battery cell and the part of battery cells.

5. An electronic device, comprising: Comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the battery capacity test method according to any one of claims 1-3.

6. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, The computer program or instructions are executed to implement the battery capacity test method according to any one of claims 1-3.

7. A computer program product, comprising: The computer program or instructions are executed to implement the battery capacity test method according to any one of claims 1-3.

Images