Battery cell remaining life prediction method and apparatus, electronic device, medium, and product

Abstract

The application provides a method and device for predicting the remaining life of an electric core, electronic equipment, a medium and a product. It relates to the field of energy storage. The method comprises: collecting multi-dimensional operation data of each electric core in the energy storage system within a preset time period, wherein the multi-dimensional operation data comprises: the number of charge and discharge cycles, the electric quantity, the operating temperature, the charge and discharge rate and the discharge depth; determining the target cumulative damage value of each electric core within the preset time period according to the number of charge and discharge cycles, the electric quantity, the operating temperature, the charge and discharge rate and the discharge depth of each electric core within the preset time period; and determining the remaining life of each electric core based on the target cumulative damage value of each electric core within the preset time period. The method for predicting the remaining life of the electric core provided by the application can improve the accuracy of the prediction of the remaining life of the electric core.

Description

Technical Field

[0001] This application relates to the field of energy storage, and in particular to a method, apparatus, electronic device, medium, and product for predicting the remaining life of a battery cell. Background Technology

[0002] With the rapid development of the new energy industry, energy storage systems play a crucial role in scenarios such as grid-connected peak shaving of energy storage power stations, energy storage supporting photovoltaic / wind power systems, and maintenance of electric vehicle battery packs. Energy storage systems typically consist of battery clusters composed of hundreds to thousands of cells connected in series and parallel, requiring stable power output and cycle life during operation. However, during long-term charge-discharge cycles, cells exhibit significant differences in performance degradation rates due to manufacturing variations, environmental fluctuations (such as temperature changes and uneven discharge rates), and accumulated mechanical stress. This difference can cause some cells to fail first, triggering a chain reaction that reduces the performance of the entire battery cluster and may even lead to thermal runaway. Especially in scenarios where energy storage power stations require continuous and stable power output, cell failure not only causes a sharp drop in system efficiency but may also affect grid security. Therefore, predicting the remaining lifespan of cells and proactively locating and replacing pre-failure cells has become a core requirement for improving the safety and economy of energy storage systems.

[0003] Currently, related technologies construct single-factor lifetime prediction models by collecting parameters such as the number of charge-discharge cycles, temperature, or capacity of the battery cell. However, these models only focus on the impact of a single parameter on lifetime and cannot quantify the aging rate under the coupled effects of multiple parameters, leading to inaccurate predictions of the remaining battery cell lifetime. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, medium, and product for predicting the remaining life of a battery cell, which can improve the accuracy of predicting the remaining life of a battery cell.

[0005] In a first aspect, this application provides a method for predicting the remaining lifespan of a battery cell, comprising:

[0006] Collect multi-dimensional operating data of each cell in the energy storage system within a preset time period. The multi-dimensional operating data includes: number of charge-discharge cycles, energy capacity, operating temperature, charge-discharge rate, and depth of discharge.

[0007] Based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of each cell within a preset time period, determine the target cumulative damage value of each cell within a preset time period.

[0008] The remaining lifespan of each cell is determined based on the target cumulative damage value of each cell within a preset time period.

[0009] In one possible implementation, the target cumulative damage value of each battery cell within a preset time period is determined based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of each cell within a preset time period, including:

[0010] For each battery cell, the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate and discharge depth at each time point within a preset time period will be input into the trained aging model to obtain the aging rate of the battery cell at each time point.

[0011] Within a preset time period, the aging rate of each cell at each time point is integrated to obtain the target cumulative damage value of each cell within the preset time period.

[0012] In one possible implementation, the remaining lifespan of each cell is determined based on the target cumulative damage value of each cell within a preset time period, including:

[0013] For each cell, the target cumulative damage value of the cell is mapped based on the first mapping relationship between the cumulative damage value and the remaining life to obtain the remaining life of the cell.

[0014] In one possible implementation, determining the remaining lifespan of each cell includes:

[0015] Collect the expansion force and internal resistance of the battery cell;

[0016] Based on the second mapping relationship between expansion force and remaining life, the expansion force of the battery cell is mapped to obtain the first remaining life of the battery cell.

[0017] Based on the third mapping relationship between internal resistance and remaining lifetime, the internal resistance of the battery cell is mapped to obtain the second remaining lifetime of the battery cell.

[0018] The smaller value between the first remaining lifetime and the second remaining lifetime is determined as the remaining lifetime of the battery cell.

[0019] In one possible implementation, it also includes:

[0020] The weakest cells are identified based on the target cumulative damage value of each cell within a preset time period.

[0021] Collect real-time charge / discharge cycle count, real-time power, real-time operating temperature, real-time charge / discharge rate, and real-time depth of discharge for the short-circuit battery cells;

[0022] Based on the real-time charge-discharge cycle count, real-time power, real-time operating temperature, real-time charge-discharge rate and real-time discharge depth of the short-board cell, the real-time aging rate of the short-board cell is determined.

[0023] Integrate the real-time aging rate corresponding to the short-board cell to obtain the real-time cumulative damage value corresponding to the short-board cell;

[0024] When the real-time cumulative damage value of the short-circuit battery cell exceeds the first preset threshold, a preset early warning mechanism is triggered.

[0025] In one possible implementation, it also includes:

[0026] Acquire experimental data, including historical multidimensional operating data and historical aging rate of the battery cells;

[0027] Construct an initial aging model;

[0028] Historical multidimensional operating data is input into the initial aging model to obtain the corresponding predicted aging rate;

[0029] The loss value between the historical aging rate and the predicted aging rate is determined based on a preset loss function.

[0030] When the loss value is higher than the second preset threshold, the initial aging model is iteratively trained based on the loss function until the loss value is lower than the second preset threshold, and then the trained aging model is obtained.

[0031] Secondly, this application provides a device for predicting the remaining life of a battery cell, comprising:

[0032] The data acquisition module is used to collect multi-dimensional operating data of each cell in the energy storage system within a preset time period. The multi-dimensional operating data includes: number of charge-discharge cycles, energy capacity, operating temperature, charge-discharge rate, and depth of discharge.

[0033] The processing module is used to determine the target cumulative damage value of each cell within a preset time period based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of each cell within a preset time period.

[0034] The processing module is also used to determine the remaining lifespan of each cell based on the target cumulative damage value of each cell within a preset time period.

[0035] In one possible implementation, the processing module is specifically used to input the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate and discharge depth at each moment within a preset time period into the trained aging model for each battery cell, so as to obtain the aging rate of the battery cell at each moment.

[0036] The processing module is also used to integrate the aging rate of each cell at each time point within a preset time period to obtain the target cumulative damage value of each cell within the preset time period.

[0037] In one possible implementation, the processing module is further configured to, for each cell, map the target cumulative damage value of the cell based on a first mapping relationship between the cumulative damage value and the remaining lifespan, so as to obtain the remaining lifespan of the cell.

[0038] In one possible implementation, the processing module is further configured to collect the expansion force and internal resistance of the battery cell.

[0039] The processing module is further used to map the expansion force of the battery cell based on the second mapping relationship between expansion force and remaining life, so as to obtain the first remaining life of the battery cell.

[0040] The processing module is also specifically used to map the internal resistance of the battery cell based on the third mapping relationship between internal resistance and remaining lifetime, so as to obtain the second remaining lifetime of the battery cell.

[0041] The processing module is further configured to determine the smaller value between the first remaining lifespan and the second remaining lifespan as the remaining lifespan of the battery cell.

[0042] In one possible implementation, the processing module is further configured to determine the weakest battery cell based on the target cumulative damage value of each battery cell within a preset time period.

[0043] The processing module is also used to collect real-time charge and discharge cycle count, real-time power, real-time operating temperature, real-time charge and discharge rate, and real-time discharge depth of the short-board battery cell.

[0044] The processing module is also used to determine the real-time aging rate of the short-board cell based on the real-time charge-discharge cycle count, real-time power, real-time operating temperature, real-time charge-discharge rate and real-time discharge depth of the short-board cell.

[0045] The processing module is also used to integrate the real-time aging rate corresponding to the short-board cell to obtain the real-time cumulative damage value corresponding to the short-board cell.

[0046] The processing module is also used to trigger a preset early warning mechanism when the real-time cumulative damage value of the short-board cell exceeds a first preset threshold.

[0047] In one possible implementation, the processing module is further configured to acquire experimental data, wherein the experimental data includes historical multidimensional operating data and historical aging rate of the battery cell.

[0048] The processing module is also used to build the initial aging model;

[0049] The processing module is also used to input historical multidimensional operating data into the initial aging model to obtain the corresponding predicted aging rate;

[0050] The processing module is also used to determine the loss value between the historical aging rate and the predicted aging rate based on a preset loss function;

[0051] The processing module is also used to iteratively train the initial aging model based on the loss function when the loss value is higher than the second preset threshold, until the loss value is lower than the second preset threshold, and then the trained aging model is obtained.

[0052] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0053] The memory stores the instructions that the computer executes;

[0054] The processor executes computer execution instructions stored in memory to implement the cell remaining life prediction method as described in the first aspect and / or any possible implementation of the first aspect.

[0055] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement a method for predicting the remaining life of a battery cell as described in the first aspect and / or any possible implementation of the first aspect.

[0056] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements a method for predicting the remaining life of a battery cell as described in the first aspect and / or any possible implementation of the first aspect.

[0057] The method, apparatus, electronic device, medium, and product for predicting the remaining life of battery cells provided in this application first determine the target cumulative damage value of the battery cell through multi-dimensional operational data, and then determine the remaining life of the battery cell based on the target cumulative damage value. Multi-dimensional operational data can comprehensively reflect the operating performance of the battery cell, thus accurately reflecting the aging status of the battery cell, and ultimately improving the accuracy of predicting the remaining life of the battery cell. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0059] Figure 1 This is a schematic diagram of a scenario provided for an embodiment of this application;

[0060] Figure 2 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 1 ;

[0061] Figure 3A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 2 ;

[0062] Figure 4 This is a schematic diagram illustrating the first mapping relationship between cumulative damage value and remaining lifespan as an example.

[0063] Figure 5 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 3 ;

[0064] Figure 6 This is a schematic diagram illustrating the second mapping relationship between expansion force and remaining life, as an example.

[0065] Figure 7 This is a schematic diagram illustrating the third mapping relationship between internal resistance and remaining lifetime;

[0066] Figure 8 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 4 ;

[0067] Figure 9 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 5 ;

[0068] Figure 10 A schematic diagram of the structure of the battery cell remaining life prediction device provided in the embodiments of this application;

[0069] Figure 11 A schematic diagram of the structure of the electronic device provided in this application.

[0070] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0071] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0072] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0073] Figure 1 This is a schematic diagram of a scenario provided for an embodiment of this application, such as... Figure 1 As shown, an energy storage system comprises multiple parallel battery clusters, each connected to a DC bus and system ground. A battery cluster typically consists of hundreds to thousands of cells connected in series and parallel. During long-term charge-discharge cycles, cells exhibit significant differences in performance degradation rates due to manufacturing variations, environmental fluctuations (such as temperature changes and uneven discharge rates), and accumulated mechanical stress. These differences can cause some cells to fail first, triggering a chain reaction that reduces the performance of the entire battery cluster and may even lead to thermal runaway. Especially in scenarios where energy storage power stations need to provide continuous and stable power output, cell failure not only causes a sharp drop in system efficiency but may also affect grid security. Consider an energy storage system consisting of 50 battery clusters, each containing 200 cells. During operation, some cells experience accelerated aging due to high-temperature environments (such as sustained high temperatures in summer) and high-frequency charging and discharging (such as grid peak-shaving demands). If not identified and intervened in time, these cells may fail first, affecting the performance of the entire battery cluster and even triggering thermal runaway. Therefore, predicting the remaining lifespan of battery cells and locating and replacing pre-failure cells in advance has become a core requirement for improving the safety and economy of energy storage systems.

[0074] Currently, related technologies construct single-factor lifetime prediction models by collecting parameters such as the number of charge-discharge cycles, temperature, or capacity of the battery cell. These models only focus on the impact of a single parameter on lifetime and cannot quantify the aging rate under the coupled effects of multiple parameters, leading to inaccurate predictions of the battery cell's remaining lifetime. The battery cell remaining lifetime prediction method, apparatus, electronic equipment, medium, and product provided in this application first determine the target cumulative damage value of the battery cell using multi-dimensional operational data, and then determine the remaining lifetime of the battery cell based on the target cumulative damage value. Multi-dimensional operational data can comprehensively reflect the operating performance of the battery cell, thus accurately reflecting its aging status and ultimately improving the accuracy of predicting the battery cell's remaining lifetime.

[0075] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0076] Figure 2A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 1 ,like Figure 2 As shown, it includes:

[0077] S201. Collect multi-dimensional operating data of each cell in the energy storage system within a preset time period. The multi-dimensional operating data includes: number of charge and discharge cycles, power, operating temperature, charge and discharge rate, and depth of discharge.

[0078] In the context of specific scenarios, charge / discharge cycle count refers to the number of complete charge / discharge cycles. A complete charge / discharge cycle refers to the process of a battery cell going from fully charged to completely discharged and then back to fully charged. Each complete charge / discharge cycle counts as one cycle. Battery capacity refers to the battery cell's State of Charge (SoC). Operating temperature can be obtained by attaching a temperature sensor to the surface of the battery cell. The charge / discharge ratio is the ratio of the charge / discharge current to the rated capacity. This can be obtained by collecting the actual charge / discharge current and the rated capacity of the battery cell. Depth of Discharge (DoD) is complementary to battery capacity; that is, SoC + DoD = 100%.

[0079] S202. Based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of each cell within a preset time period, determine the target cumulative damage value of each cell within a preset time period.

[0080] Based on the scenario example, the preset duration can be determined according to the actual situation, such as 5 minutes. By measuring the number of charge-discharge cycles, charge level, operating temperature, charge-discharge rate, and depth of discharge of the battery cell within 5 minutes, the target cumulative damage value of the battery cell within these 5 minutes is determined.

[0081] Optional, Figure 3 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 2 ,like Figure 3 As shown, S202 includes:

[0082] S301. For each battery cell, the number of charge / discharge cycles, capacity, operating temperature, charge / discharge rate, and discharge depth at each time point within a preset time period will be input into the trained aging model to obtain the aging rate of the battery cell at each time point.

[0083] Based on the scenario example and the preceding content, we know that the preset duration can be 5 minutes. The number of charge / discharge cycles, battery capacity, operating temperature, charge / discharge rate, and depth of discharge for the battery cell within this preset duration include the number of charge / discharge cycles, battery capacity, operating temperature, charge / discharge rate, and depth of discharge at any given moment within those 5 minutes. Any given moment can be measured in seconds, determined according to a preset step size. The preset step size can be determined based on actual conditions. For example, the preset step size can be 1 second, meaning 300 moments are included within the 5 minutes. The number of charge / discharge cycles, battery capacity, operating temperature, charge / discharge rate, and depth of discharge for each moment are sequentially input into the aging model. The aging model can calculate the instantaneous aging rate based on these parameters at that moment to obtain the corresponding aging rate.

[0084] Optionally, the preset step size can also be 5 seconds, that is, a time point is determined every 5 seconds, which includes 60 time points within 5 minutes. Similarly, the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of the battery cell at each of these 60 time points are sequentially input into the aging model. The aging model can calculate the instantaneous aging rate based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge at that time point, and use the corresponding aging rate at that time point.

[0085] S302. Within a preset time period, integrate the aging rate of each cell at each time point to obtain the target cumulative damage value of each cell within the preset time period.

[0086] Using a scenario example, the aging rate is the performance degradation coefficient per unit time. Integrating the aging rate over time yields the total performance degradation, i.e., the cumulative damage value. Based on the aforementioned preset step size, the aging rate at each time point is integrated over time. For example, with a preset step size of 1 second, the aging rate of each cell is integrated over time at 300 time points to obtain the target cumulative damage value for each cell.

[0087] Based on the method provided in this example, the aging rate of the battery cell at each time point can be determined directly through the aging model. By integrating the aging rate at each time point, the target cumulative damage value of each battery cell can be accurately obtained, which can improve the accuracy of determining the remaining life of the battery cell.

[0088] S203. Determine the remaining lifespan of each cell based on the target cumulative damage value of each cell within a preset time period.

[0089] Based on scenario examples, the cumulative damage value of a battery cell is a quantitative indicator of the degree of performance degradation of the battery cell. The higher the cumulative damage value, the closer the battery cell is to failure.

[0090] Optionally, S203 includes:

[0091] For each cell, the target cumulative damage value of the cell is mapped based on the first mapping relationship between the cumulative damage value and the remaining life to obtain the remaining life of the cell.

[0092] Combined with scenario examples, Figure 4 This is a schematic diagram illustrating the first mapping relationship between cumulative damage value and remaining lifetime, as shown in the example. Figure 4 As shown, there is a negative correlation between the cumulative damage value and the remaining life of the battery cell; that is, the higher the cumulative damage value, the lower the remaining life of the cell. Experimental data of the battery cell can be obtained, and the cumulative damage value and the remaining life can be fitted within this data to obtain a first mapping relationship. Therefore, based on this first mapping relationship, a target cumulative damage value can be mapped to obtain a target remaining life that has a mapping relationship with the target cumulative damage value. This target remaining life is then determined as the remaining life of the battery cell. Based on the method provided in this example, the target cumulative damage value can be directly mapped based on the first mapping relationship obtained from fitting experimental data, which can improve the efficiency and accuracy of obtaining the remaining life of the battery cell.

[0093] Optional, Figure 5 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 3 ,like Figure 5 As shown in S203, determining the remaining lifespan of each cell includes:

[0094] S501, collect the expansion force and internal resistance of the battery cell.

[0095] In practical examples, the internal resistance of a battery cell is typically measured using AC impedance spectroscopy or pulse charge-discharge methods. For instance, a short-duration pulse current is applied to the cell, and the voltage response is collected; the internal resistance is then calculated using the ratio of the voltage step to the current pulse. The expansion force of a battery cell refers to the internal pressure generated during charging and discharging due to internal chemical reactions, which can be directly collected using a pressure sensor.

[0096] S502. Based on the second mapping relationship between expansion force and remaining life, the expansion force of the battery cell is mapped to obtain the first remaining life corresponding to the battery cell.

[0097] Combined with scenario examples, Figure 6 A schematic diagram illustrating the second mapping relationship between expansion force and remaining life, as shown below. Figure 6As shown, there is a negative correlation between the cell's expansion force and remaining lifespan; that is, the higher the cell's expansion force, the lower its remaining lifespan. By acquiring experimental data of the cells, the expansion force and remaining lifespan can be fitted together to obtain a second mapping relationship. Therefore, based on this second mapping relationship, the cell's expansion force can be mapped to obtain a first remaining lifespan that has a mapping relationship with the cell's expansion force.

[0098] S503. Based on the third mapping relationship between internal resistance and remaining lifetime, the internal resistance of the cell is mapped to obtain the second remaining lifetime of the cell.

[0099] Combined with scenario examples, Figure 7 This is a schematic diagram illustrating the third mapping relationship between internal resistance and remaining lifetime, as shown in the example. Figure 7 As shown, there is a negative correlation between the internal resistance of the battery cell and its remaining lifespan; that is, the higher the internal resistance of the battery cell, the lower its remaining lifespan. By obtaining experimental data of the battery cell, the internal resistance and remaining lifespan can be fitted together to obtain a third mapping relationship. Therefore, based on this third mapping relationship, the internal resistance of the battery cell can be mapped to obtain a second remaining lifespan that has a mapping relationship with the internal resistance of the battery cell.

[0100] S504. The smaller value between the first remaining life and the second remaining life is determined as the remaining life of the cell.

[0101] Based on scenario examples, the remaining lifespan obtained through different parameters may differ, that is, there may be a difference between the first remaining lifespan and the second remaining lifespan. The smaller value between the two can be determined as the remaining lifespan of the battery cell.

[0102] Based on the method provided in this example, the remaining lifespan of a battery cell can be obtained through cell expansion force or internal resistance.

[0103] Optional, Figure 8 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 4 ,like Figure 8 As shown, it also includes:

[0104] S801. Determine the weakest battery cell based on the target cumulative damage value of each battery cell within a preset time period.

[0105] Based on the scenario example, the higher the cumulative damage value of the battery cell, the more likely the battery cell is to fail. Therefore, the battery cell with the highest cumulative damage value can be identified as the weakest link battery cell.

[0106] S802: Collect the real-time charge / discharge cycle count, real-time power, real-time operating temperature, real-time charge / discharge rate, and real-time depth of discharge for the short-board battery cell.

[0107] Based on scenario examples, continuous monitoring is carried out on the short-board battery cells. Specifically, the real-time charge and discharge cycle count, real-time power, real-time operating temperature, real-time charge and discharge rate, and real-time discharge depth of the short-board battery cells are continuously collected.

[0108] S803. Based on the real-time charge-discharge cycle count, real-time power, real-time operating temperature, real-time charge-discharge rate, and real-time discharge depth of the short-board cell, determine the real-time aging rate of the short-board cell.

[0109] Based on scenario examples, the real-time charge-discharge cycle count, real-time power, real-time operating temperature, real-time charge-discharge rate, and real-time discharge depth of the short-board battery cell are input into the trained aging model to obtain the real-time aging rate corresponding to the short-board battery cell.

[0110] S804. Integrate the real-time aging rate corresponding to the short-board cell to obtain the real-time cumulative damage value corresponding to the short-board cell.

[0111] By combining scenario examples, the real-time aging rate corresponding to the short-board cell is continuously integrated to monitor the real-time cumulative damage value of the short-board cell.

[0112] S805. When the real-time cumulative damage value of the short-board cell exceeds the first preset threshold, a preset early warning mechanism is triggered.

[0113] Based on the scenario example, the first preset threshold can be determined according to the actual situation, such as 80%. When the real-time cumulative damage value of the short-pole cell exceeds 80%, it can be determined that the short-pole cell is about to fail, which can trigger an early warning mechanism. Specifically, the information of the battery cluster where the short-pole cell is located can be sent to the client of the maintenance personnel, so that the maintenance personnel can replace the battery cluster where the short-pole cell is located in a timely manner, which can ensure the continuous normal operation of the energy storage system.

[0114] Optional, Figure 9 A flowchart illustrating the method for predicting the remaining life of battery cells provided in this application. Figure 5 ,like Figure 9 As shown, it also includes:

[0115] S901. Obtain experimental data, including historical multi-dimensional operating data and historical aging rate of the battery cell.

[0116] Combined with scenario examples, the experimental data includes historical multi-dimensional operating data and historical aging rate of multiple battery cells in actual operation. The historical multi-dimensional operating data includes historical charge and discharge cycle count, historical power, historical operating temperature, historical charge and discharge rate, and historical discharge depth.

[0117] S902. Construct the initial aging model.

[0118] Based on scenario examples, the initial aging model is a mathematical model used to quantify the relationship between cell aging rate and multidimensional operating data.

[0119] S903. Input historical multidimensional operating data into the initial aging model to obtain the corresponding predicted aging rate.

[0120] Based on scenario examples, historical multidimensional operating data is input into the initial aging model. The initial aging model uses machine learning algorithms to extract and process features from the historical multidimensional operating data to obtain the corresponding predicted aging rate.

[0121] S904. Determine the loss value between the historical aging rate and the predicted aging rate based on the preset loss function.

[0122] Using scenario examples, and based on a preset loss function, the historical aging rate is compared with the predicted aging rate to obtain the difference between the two, i.e., the loss value.

[0123] S905. When the loss value is higher than the second preset threshold, the initial aging model is iteratively trained based on the loss function until the loss value is lower than the second preset threshold, and then the trained aging model is obtained.

[0124] Based on the scenario example, the second preset threshold can be determined according to the actual situation. When the loss value is higher than the second preset threshold, the parameters in the initial aging model are updated, and the initial aging model is iteratively trained based on historical multidimensional running data until the difference between the predicted aging rate output by the aging model and the historical aging rate is less than the second preset threshold. Then, a well-trained aging model is obtained. Alternatively, if the number of iterations reaches a third preset threshold, such as 200 iterations, the training of the aging model ends, and the aging model obtained by this training is determined as the well-trained aging model.

[0125] Based on the method provided in this example, a trained aging model can be obtained. The aging rate can then be quantified using multi-dimensional operating data based on the trained aging model, thereby improving the accuracy of cell life prediction.

[0126] Based on the cell remaining life prediction method provided in this embodiment, the target cumulative damage value of the cell can be determined first through multi-dimensional operational data of the cell, and then the remaining life of the cell can be determined based on the target cumulative damage value. Multi-dimensional operational data can comprehensively reflect the operating performance of the cell, thus accurately reflecting the aging status of the cell and ultimately improving the accuracy of predicting the remaining life of the cell.

[0127] Figure 10 This is a schematic diagram of the structure of the cell remaining life prediction device provided in the embodiments of this application, as shown below. Figure 10 As shown, it includes:

[0128] The data acquisition module 101 is used to acquire multi-dimensional operating data of each cell in the energy storage system within a preset time period. The multi-dimensional operating data includes: number of charge and discharge cycles, energy capacity, operating temperature, charge and discharge rate, and depth of discharge.

[0129] Processing module 102 is used to determine the target cumulative damage value of each battery cell within a preset time period based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate and discharge depth of each battery cell within a preset time period.

[0130] The processing module 102 is also used to determine the remaining lifespan of each battery cell based on the target cumulative damage value of each battery cell within a preset time period.

[0131] Optionally, the processing module 102 is specifically used to input the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate and discharge depth at each moment within a preset time period into the trained aging model for each battery cell, so as to obtain the aging rate of the battery cell at each moment.

[0132] The processing module 102 is further used to integrate the aging rate of each cell at each time point within a preset time period to obtain the target cumulative damage value of each cell within the preset time period.

[0133] Optionally, the processing module 102 is further configured to, for each cell, map the target cumulative damage value of the cell based on the first mapping relationship between the cumulative damage value and the remaining lifespan, so as to obtain the remaining lifespan of the cell.

[0134] Optionally, the processing module 102 is also used to collect the expansion force and internal resistance of the battery cell;

[0135] The processing module 102 is further configured to map the expansion force of the battery cell based on the second mapping relationship between the expansion force and the remaining life, so as to obtain the first remaining life of the battery cell.

[0136] The processing module 102 is further used to map the internal resistance of the battery cell based on the third mapping relationship between internal resistance and remaining life, so as to obtain the second remaining life of the battery cell.

[0137] The processing module 102 is further configured to determine the smaller value between the first remaining life and the second remaining life as the remaining life of the battery cell.

[0138] Optionally, the processing module 102 is also used to determine the weakest battery cell based on the target cumulative damage value of each battery cell within a preset time period;

[0139] The processing module 102 is also used to collect the real-time charge and discharge cycle count, real-time power, real-time operating temperature, real-time charge and discharge rate and real-time discharge depth of the short-board battery cell;

[0140] The processing module 102 is also used to determine the real-time aging rate of the short-board cell based on the real-time charge and discharge cycle count, real-time power, real-time operating temperature, real-time charge and discharge rate and real-time discharge depth of the short-board cell.

[0141] The processing module 102 is also used to integrate the real-time aging rate corresponding to the short-board cell to obtain the real-time cumulative damage value corresponding to the short-board cell.

[0142] The processing module 102 is also used to trigger a preset early warning mechanism when the real-time cumulative damage value of the short-board cell exceeds a first preset threshold.

[0143] Optionally, the processing module 102 is also used to acquire experimental data, including historical multidimensional operating data and historical aging rate of the battery cell.

[0144] Processing module 102 is also used to build an initial aging model;

[0145] The processing module 102 is also used to input historical multidimensional operating data into the initial aging model to obtain the corresponding predicted aging rate;

[0146] The processing module 102 is also used to determine the loss value between the historical aging rate and the predicted aging rate based on a preset loss function;

[0147] The processing module 102 is also used to iteratively train the initial aging model based on the loss function when the loss value is higher than the second preset threshold, until the loss value is lower than the second preset threshold, and then obtain the trained aging model.

[0148] The cell remaining life prediction device provided in this embodiment can execute the cell remaining life prediction method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0149] Figure 11 A schematic diagram of the structure of the electronic device provided in this application. Figure 11 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus.

[0150] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0151] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0152] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0153] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0154] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0155] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0156] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0157] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0158] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0159] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0160] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0161] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0162] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to related technologies, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0163] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0164] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for predicting the remaining lifespan of a battery cell, characterized in that, include: Collect multi-dimensional operating data of each cell in the energy storage system within a preset time period. The multi-dimensional operating data includes: number of charge-discharge cycles, energy level, operating temperature, charge-discharge rate, and depth of discharge. Based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of each cell within a preset time period, the target cumulative damage value of each cell within the preset time period is determined. The remaining lifespan of each battery cell is determined based on the target cumulative damage value of each battery cell within a preset time period.

2. The method according to claim 1, characterized in that, The determination of the target cumulative damage value of each battery cell within a preset time period based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate, and depth of discharge of each cell within a preset time period includes: For each battery cell, the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate and discharge depth at each time point within the preset time period are input into the trained aging model to obtain the aging rate of the battery cell at each time point. Within the preset time period, the aging rate of each cell at each time point is integrated to obtain the target cumulative damage value of each cell within the preset time period.

3. The method according to claim 2, characterized in that, The determination of the remaining lifespan of each battery cell based on the target cumulative damage value of each cell within a preset time period includes: For each cell, based on the first mapping relationship between the cumulative damage value and the remaining life, the target cumulative damage value of the cell is mapped to obtain the remaining life of the cell.

4. The method according to claim 1, characterized in that, Determining the remaining lifespan of each of the battery cells includes: The expansion force and internal resistance of the battery cell are collected; Based on the second mapping relationship between expansion force and remaining life, the expansion force of the battery cell is mapped to obtain the first remaining life corresponding to the battery cell; Based on the third mapping relationship between internal resistance and remaining lifetime, the internal resistance of the battery cell is mapped to obtain the second remaining lifetime corresponding to the battery cell. The smaller value between the first remaining lifetime and the second remaining lifetime is determined as the remaining lifetime of the battery cell.

5. The method according to claim 1, characterized in that, Also includes: The weakest battery cell is determined based on the target cumulative damage value of each battery cell within a preset time period; Collect the real-time charge / discharge cycle count, real-time power, real-time operating temperature, real-time charge / discharge rate, and real-time depth of discharge for the short-board battery cell; Based on the real-time charge-discharge cycle count, real-time power, real-time operating temperature, real-time charge-discharge rate and real-time discharge depth of the short-board cell, the real-time aging rate of the short-board cell is determined. Integrate the real-time aging rate corresponding to the short-board cell to obtain the real-time cumulative damage value corresponding to the short-board cell; When the real-time cumulative damage value of the short-circuit battery cell exceeds a first preset threshold, a preset early warning mechanism is triggered.

6. The method according to claim 2, characterized in that, Also includes: Acquire experimental data, including historical multidimensional operating data and historical aging rate of the battery cell; Construct an initial aging model; The historical multidimensional operating data is input into the initial aging model to obtain the corresponding predicted aging rate; The loss value between the historical aging rate and the predicted aging rate is determined based on a preset loss function. When the loss value is higher than the second preset threshold, the initial aging model is iteratively trained based on the loss function until the loss value is less than the second preset threshold, and then the trained aging model is obtained.

7. A device for predicting the remaining life of a battery cell, characterized in that, include: The data acquisition module is used to collect multi-dimensional operating data of each cell in the energy storage system within a preset time period. The multi-dimensional operating data includes: number of charge-discharge cycles, energy level, operating temperature, charge-discharge rate, and depth of discharge. The processing module is used to determine the target cumulative damage value of each battery cell within a preset time period based on the number of charge-discharge cycles, capacity, operating temperature, charge-discharge rate and discharge depth of each battery cell within a preset time period. The processing module is also used to determine the remaining lifespan of each of the battery cells based on the target cumulative damage value of each battery cell within a preset time period.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the cell remaining life prediction method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the cell remaining life prediction method as described in any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method for predicting the remaining life of a battery cell as described in any one of claims 1-6.

Images