Life prediction method, device and equipment of lithium ion battery, medium and product

Abstract

The invention discloses a lithium ion battery life prediction method and device, equipment, a medium and a product, and relates to the technical field of battery safety, and the method comprises the steps: obtaining historical charge-discharge cycle data of a lithium ion battery; extracting time sequence features from the historical charge-discharge cycle data; inputting the time sequence characteristics into an expansion force prediction model to obtain predicted expansion force of the lithium ion battery; and inputting the predicted expansive force into a battery life prediction model to obtain the predicted life of the lithium ion battery.

Description

Technical Field

[0001] The present application relates to the technical field of battery safety, and particularly to a method, device, equipment, medium and product for predicting the life of a lithium-ion battery. Background Art

[0002] As a battery system with high energy density and long cycle life, lithium-ion batteries have been widely used in fields such as electric vehicles and energy storage systems. However, the life of lithium-ion batteries is affected by various factors, including charge and discharge rate, ambient temperature, battery material properties, etc. Among them, the change in expansion force during the charge and discharge process of the battery is considered to be one of the important factors affecting the battery life. The expansion force not only reflects the changes in internal stress and volume of the battery, but also is closely related to the internal structure, material properties and electrolyte state of the battery.

[0003] Regarding the prediction of the life of lithium-ion batteries, various methods have been developed in the industry, including prediction methods based on physical models, data-driven prediction methods, and hybrid prediction methods that combine the two. The physical model method predicts the battery life by simulating the electrochemical reactions and physical processes inside the battery, but requires a large amount of prior knowledge and complex calculations. The data-driven method uses historical data to establish statistical models or machine learning models for prediction, with high flexibility and adaptability. However, most of these methods focus on the electrochemical performance and external working conditions of the battery, and do not pay attention to this key parameter of expansion force. Summary of the Invention

[0004] The purpose of the present application is to provide a method, device, equipment, medium and product for predicting the life of a lithium-ion battery.

[0005] To achieve the above purpose, the present application provides the following solutions: In a first aspect, the present application provides a method for predicting the life of a lithium-ion battery, including: Obtaining historical charge and discharge cycle data of the lithium-ion battery; Extracting time series features from the historical charge and discharge cycle data; Inputting the time series features into an expansion force prediction model to obtain the predicted expansion force of the lithium-ion battery; Inputting the predicted expansion force into a battery life prediction model to obtain the predicted life of the lithium-ion battery.

[0006] Optionally, the expansion force prediction model is trained through the following steps: Obtaining sample charge and discharge cycle data and standard expansion force; Labeling the corresponding standard expansion force for the sample charge and discharge cycle data to obtain an expansion force prediction training set; Train the initial swelling force prediction model using the swelling prediction training set.

[0007] Optionally, the step of obtaining the sample charge-discharge cycle data and the standard swelling force includes: Perform cyclic tests on the sample lithium-ion battery at different charge rates and discharge rates; Detect the swelling force of the sample ion battery during the cyclic test to obtain the standard swelling force.

[0008] Optionally, the battery life prediction model is trained through the following steps: Obtain sample swelling force data and the standard battery life; Label the corresponding standard battery life for the sample swelling force data to obtain a life prediction training set; Train the initial life prediction model using the life prediction training set.

[0009] Optionally, the step of obtaining the sample swelling force data and the standard battery life includes: Detect the sample lithium-ion battery during the cyclic test of the sample lithium-ion battery to obtain battery evaluation indicators under different swelling forces; Calculate the standard battery life under different swelling forces based on the battery evaluation indicators.

[0010] Optionally, the historical charge-discharge cycle data includes at least: the number of cycles of the lithium-ion battery, the charge rate, and the discharge rate.

[0011] In a second aspect, the present application provides a device for predicting the life of a lithium-ion battery, including: An acquisition module for acquiring historical charge-discharge cycle data of the lithium-ion battery; A prediction module for extracting time series features from the historical charge-discharge cycle data; Input the time series features into the swelling force prediction model to obtain the predicted swelling force of the lithium-ion battery; Input the predicted swelling force into the battery life prediction model to obtain the predicted life of the lithium-ion battery.

[0012] Optionally, the device further includes: a training module for: Obtain sample charge-discharge cycle data and the standard swelling force; Label the corresponding standard swelling force for the sample charge-discharge cycle data to obtain a swelling force prediction training set; Train the initial swelling force prediction model using the swelling prediction training set.

[0013] Optionally, the training module is further used for: The sample lithium-ion battery is cycled tested at different charging rates and discharging rates; During the cycling test, the swelling force of the sample ion battery is detected to obtain the standard swelling force.

[0014] Optionally, the device further includes: a training module, configured to: Obtain sample swelling force data and standard battery life; Label the corresponding standard battery life for the sample swelling force data to obtain a life prediction training set; Train an initial life prediction model using the life prediction training set.

[0015] Optionally, the training module is further configured to: During the cycling test of the sample lithium-ion battery, the sample lithium-ion battery is detected to obtain battery evaluation indicators under different swelling forces; Calculate the standard battery life under different swelling forces based on the battery evaluation indicators.

[0016] Optionally, the historical charge and discharge cycle data at least includes: the number of cycles of the lithium-ion battery, the charging rate, and the discharging rate.

[0017] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method for predicting the life of a lithium-ion battery according to any one of the above.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method for predicting the life of a lithium-ion battery according to any one of the above.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the method for predicting the life of a lithium-ion battery according to any one of the above.

[0020] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application: The present application provides a method, device, equipment, medium, and product for predicting the life of a lithium-ion battery. By combining the historical charge and discharge cycle data, the swelling force change law, and the influencing factors of the battery life of the lithium-ion battery, an effective prediction model can be established to achieve accurate early warning of the life of the lithium-ion battery, which not only helps to improve the use efficiency of the battery, but also provides a strong guarantee for the safe operation of new energy vehicles. Description of the Drawings

[0021] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0022] Figure 1 It is a schematic flowchart of a method for predicting the life of a lithium-ion battery provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the functional modules of a device for predicting the life of a lithium-ion battery provided by an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0024] As Figure 1 shown, some embodiments of the present application provide a method for predicting the life of a lithium-ion battery. In the embodiments of the present application, the following steps 101 to 104 are included. Among them: Step 101, obtain the historical charge and discharge cycle data of the lithium-ion battery.

[0025] In the embodiments of the present application, the lithium-ion battery will experience multiple charge and discharge cycles during use. The parameters such as voltage, current, capacity, and temperature will change in each cycle, and these changes are closely related to the life and health status of the battery. Therefore, it is first necessary to collect these historical data, including but not limited to the charge and discharge curves, charge and discharge times, charge and discharge currents, voltage changes, temperature data, etc. of the battery. These data are usually recorded by a battery management system (BMS) or a dedicated test device.

[0026] Step 102, extract time series features from the historical charge and discharge cycle data.

[0027] In the embodiments of the present application, after obtaining the original data, it is necessary to preprocess this data to extract time series features useful for prediction. Time series features refer to those data that can reflect the variation law of battery performance over time, such as the voltage change rate, current change rate, temperature change trend, etc. during the charge and discharge process. By extracting these features, the original data can be transformed into a more concise and representative form, facilitating subsequent model training and prediction.

[0028] Step 103: Input the time series features into the swelling force prediction model to obtain the predicted swelling force of the lithium-ion battery.

[0029] In the embodiments of the present application, the swelling force is the force generated by a lithium-ion battery due to internal chemical reactions and physical changes during the charge and discharge process, and its magnitude is closely related to the battery life and health status. It is mentioned in the document that through experimental observations, there is a strong correlation between the swelling force change of the battery during the charge and discharge process and the number of battery cycles and capacity attenuation. Therefore, a swelling force prediction model can be trained based on historical data and the extracted time series features. This model can predict the magnitude of the swelling force of the battery at a future moment according to the input time series features.

[0030] Step 104: Input the predicted swelling force into the battery life prediction model to obtain the predicted life of the lithium-ion battery.

[0031] In the embodiments of the present application, after obtaining the predicted swelling force of the battery, it is necessary to input it into the battery life prediction model to obtain the predicted life of the battery. Since there is a strong correlation between the swelling force and the battery life, this relationship can be used to establish a battery life prediction model. This model comprehensively evaluates the remaining life of the battery by analyzing the change trend of the swelling force and combining other performance indicators of the battery (such as capacity attenuation, internal resistance change, etc.). Finally, the model will output a predicted value indicating the time length that the battery is expected to be able to maintain normal operation in the future.

[0032] The embodiments of the present application can establish an effective prediction model by combining the historical charge and discharge cycle data of lithium-ion batteries, the swelling force change law, and the influencing factors of battery life, realizing accurate early warning of the life of lithium-ion batteries. This not only helps to improve the battery usage efficiency but also provides a strong guarantee for the safe operation of new energy vehicles.

[0033] Optionally, the swelling force prediction model is trained through the following steps: Step 201: Obtain sample charge and discharge cycle data and standard swelling force.

[0034] In the embodiments of the present application, a certain number of lithium-ion battery samples need to be collected and subjected to charge-discharge cycle tests. During the test process, not only basic parameters such as the voltage, current, and capacity of the battery need to be recorded, but special attention also needs to be paid to the expansion force generated by the battery during charge and discharge. In order to obtain accurate expansion force data, a special test device, such as the expansion force test device mentioned in the document, is usually used to measure the change in the expansion force of the battery at different charge-discharge stages. These charge-discharge cycle data and the corresponding expansion force data constitute the sample data required for training the model.

[0035] Step 202: Label the corresponding standard expansion force for the sample charge-discharge cycle data to obtain an expansion force prediction training set.

[0036] In the embodiments of the present application, after obtaining the sample charge-discharge cycle data and the corresponding expansion force data, these data need to be labeled, that is, each charge-discharge cycle data point is matched with its corresponding expansion force value. In this way, each set of charge-discharge cycle data corresponds to a standard expansion force value. Through this process, we obtain an expansion force prediction training set containing multiple samples. This training set will be used in the subsequent model training process to learn the complex relationship between the charge-discharge cycle data and the expansion force.

[0037] Step 203: Use the expansion prediction training set to train the initial expansion force prediction model.

[0038] In the embodiments of the present application, after obtaining the expansion force prediction training set, these data can be used to train the initial expansion force prediction model. The initial model can be a machine learning model, such as linear regression, neural network, etc., and its specific form depends on the complexity of the problem and the characteristics of the data. The training process includes inputting the data in the training set into the model and optimizing the prediction performance of the model by continuously adjusting the model parameters. Specifically, it is to enable the model to accurately predict the expansion force of the battery based on the charge-discharge cycle data. This process usually involves multiple iterations and parameter tuning until the prediction accuracy of the model reaches satisfaction. Finally, the trained expansion force prediction model will be able to be used in actual scenarios to accurately predict the expansion force of lithium-ion batteries.

[0039] In the embodiments of the present application, by constructing a training set containing charge-discharge cycle data and corresponding expansion force values and using this training set to train the initial model, a prediction model that can accurately predict the expansion force of lithium-ion batteries can be obtained.

[0040] Optionally, step 201 includes.

[0041] Step 2011: Perform cycle tests on the sample lithium-ion batteries according to different charge rates and discharge rates.

[0042] In the embodiments of the present application, in order to comprehensively evaluate the performance of lithium-ion batteries under different working conditions, especially the change in their swelling force, it is necessary to conduct cyclic tests on sample lithium-ion batteries under various combinations of charge and discharge rates. The charge rate refers to the ratio between the current and the battery capacity during the charging process of the battery, indicating the proportion of the electric charge that the battery can charge or discharge per unit time to the rated capacity of the battery. The discharge rate is the same. By setting different charge and discharge rates, various load conditions of the battery in actual applications can be simulated, thus more truly reflecting the performance of the battery.

[0043] Step 2012, during the cyclic test, detect the swelling force of the sample ion battery to obtain the standard swelling force.

[0044] In the embodiments of the present application, during the cyclic test, in addition to the detection of conventional parameters such as voltage, current, and capacity, special attention needs to be paid to the change in the swelling force of the battery. The swelling force refers to the force generated by the battery due to internal chemical reactions and physical changes during charge and discharge, which reflects the stability and health status of the internal structure of the battery. In order to obtain accurate standard swelling force data, a special test device (such as the swelling force test device mentioned in the document) needs to be used to monitor the change in the swelling force of the battery in real time during the cyclic test. These detection data are crucial for subsequent analysis of battery performance, establishment of a swelling force prediction model, and prediction of battery life.

[0045] Through the above cyclic test and swelling force detection process, a series of data on the change in the swelling force of the battery under different charge and discharge rates can be obtained. After these data are processed and analyzed, the standard swelling force values of the battery under different working conditions can be refined. The standard swelling force refers to the average or characteristic swelling force value shown by the battery during the cyclic test under specific working conditions (such as a specific combination of charge and discharge rates). These standard swelling force values will serve as an important basis for the training and verification of the subsequent swelling force prediction model, and contribute to the establishment of a more accurate and reliable battery life warning model.

[0046] Optionally, the battery life prediction model is trained through the following steps: Step 301, obtain sample swelling force data and the standard battery life.

[0047] In the embodiments of the present application, first, a series of expansion force data of lithium-ion batteries under actual operation or experimental conditions need to be collected. These data can be obtained in real-time during the charge and discharge cycles of the batteries through a dedicated testing device (such as the expansion force testing device mentioned in the document). At the same time, for each set of expansion force data, the standard life information of the corresponding battery needs to be known. The standard life of the battery can be obtained in various ways, such as through actual operation records, accelerated aging experiments, or theoretical calculations based on the chemical and physical properties of the battery. These expansion force data and the corresponding standard battery life constitute the sample data required for training the life prediction model.

[0048] Step 302: Label the corresponding standard battery life for the sample expansion force data to obtain a life prediction training set.

[0049] In the embodiments of the present application, after obtaining the sample expansion force data and the standard battery life, it is necessary to match and label each set of expansion force data with its corresponding standard battery life. This process is similar to the label annotation work in data preprocessing. Through annotation, each set of expansion force data has the corresponding life information, thus forming a life prediction training set. This training set contains rich sample information, including both the expansion force performance of the battery during operation and its corresponding life data, providing a solid foundation for subsequent model training.

[0050] Step 303: Use the life prediction training set to train an initial life prediction model.

[0051] In the embodiments of the present application, after obtaining the life prediction training set, these data can be used to train the initial life prediction model. The initial model can be a machine learning model (such as linear regression, decision tree, support vector machine, etc.), or it can be a more complex deep learning model (such as neural network, convolutional neural network, recurrent neural network, etc.). The training process includes inputting the data in the training set into the model and continuously adjusting the parameters of the model through iterative optimization algorithms, so that the model can accurately predict the life of the battery according to the input expansion force data. This process usually requires multiple iterations, and techniques such as cross-validation may be needed to evaluate the generalization ability of the model to ensure that the performance of the model on different data sets is robust.

[0052] Optionally, step 301 includes: Step 3011: Detect the sample lithium-ion battery during the cycle test of the sample lithium-ion battery to obtain battery evaluation indicators under different expansion forces.

[0053] In the embodiments of the present application, when conducting research on the life prediction model of lithium-ion batteries, it is first necessary to perform a cycling test on sample lithium-ion batteries. This test process simulates the charge and discharge cycles of the battery during actual use, aiming to observe the performance changes of the battery under different conditions. During the test process, special equipment and sensors are used to monitor the battery in real-time, including parameters such as the battery voltage, current, temperature, and swelling force. In particular, the swelling force is an important indicator reflecting the internal stress and volume changes of the battery, and is closely related to the life and health status of the battery.

[0054] By performing a cycling test on the sample lithium-ion battery, the swelling force data of the battery can be recorded at different charge and discharge stages. At the same time, other evaluation indicators related to the battery performance can also be obtained, such as the state of health (SOH), internal resistance change, charge and discharge efficiency, etc. These evaluation indicators jointly describe the comprehensive performance of the battery under different swelling forces. In particular, during the cycling test of lithium-ion batteries, as the battery ages and the swelling force changes, these evaluation indicators will also change accordingly.

[0055] Step 3012, calculate the standard battery life under different swelling forces based on the battery evaluation indicators.

[0056] In the embodiments of the present application, after obtaining the battery evaluation indicators under different swelling forces, it is necessary to use these data and the known battery aging mechanism to calculate the standard battery life. The standard battery life refers to the number of cycles or time that the battery can maintain its performance to a certain specific level (such as the state of health drops to 80%) under specific conditions (such as a specific charge and discharge regime, temperature, etc.). This calculation process may involve complex mathematical models and algorithms, such as estimation based on empirical formulas, machine learning models based on data-driven, etc. By analyzing and comparing the relationship between the battery evaluation indicators and the standard battery life under different swelling forces, a mapping relationship between the swelling force and the battery life can be established, thus providing a basis for subsequent life prediction.

[0057] Optionally, the historical charge and discharge cycle data at least includes: the number of cycles of the lithium-ion battery, charge rate, and discharge rate.

[0058] Based on the same inventive concept, the embodiments of the present application also provide a life prediction device for a lithium-ion battery for implementing the above-mentioned life prediction method of the lithium-ion battery. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the following life prediction devices for lithium-ion batteries can refer to the limitations on the life prediction method of the lithium-ion battery in the above text, and will not be repeated here.

[0059] In an exemplary embodiment, such asFigure 2 As shown in the figure, a device 40 for predicting the life of a lithium-ion battery is provided, including: An acquisition module 401, configured to acquire historical charge and discharge cycle data of the lithium-ion battery; A prediction module 402, configured to extract time series features from the historical charge and discharge cycle data; Input the time series features into an expansion force prediction model to obtain the predicted expansion force of the lithium-ion battery; Input the predicted expansion force into a battery life prediction model to obtain the predicted life of the lithium-ion battery.

[0060] Optionally, the device further includes: a training module, configured to: Acquire sample charge and discharge cycle data and standard expansion force; Label the corresponding standard expansion force for the sample charge and discharge cycle data to obtain an expansion force prediction training set; Train an initial expansion force prediction model using the expansion prediction training set.

[0061] Optionally, the training module is further configured to: Perform cyclic tests on sample lithium-ion batteries at different charge rates and discharge rates; Detect the expansion force of the sample ion battery during the cyclic test to obtain the standard expansion force.

[0062] Optionally, the device further includes: a training module, configured to: Acquire sample expansion force data and standard battery life; Label the corresponding standard battery life for the sample expansion force data to obtain a life prediction training set; Train an initial life prediction model using the life prediction training set.

[0063] Optionally, the training module is further configured to: Detect the sample lithium-ion battery during the cyclic test of the sample lithium-ion battery to obtain battery evaluation indicators under different expansion forces; Calculate the standard battery life under different expansion forces based on the battery evaluation indicators.

[0064] Optionally, the historical charge and discharge cycle data at least includes: the number of cycles of the lithium-ion battery, the charge rate, and the discharge rate.

[0065] By combining the historical charge-discharge cycle data of lithium-ion batteries, the variation law of expansion force, and the influencing factors of battery life, the embodiments of the present application can establish an effective prediction model to achieve accurate early warning of the life of lithium-ion batteries, which not only helps to improve the usage efficiency of the batteries, but also provides a strong guarantee for the safe operation of new energy vehicles.

[0066] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 3 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the life prediction data of lithium-ion batteries. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for predicting the life of lithium-ion batteries.

[0067] Those skilled in the art can understand that Figure 3 the structure shown in

[0068] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0069] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above method embodiments.

[0070] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0072] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0073] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0074] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0075] In this article, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for predicting the life of a lithium-ion battery, characterized in that: The life prediction model method of the lithium-ion battery includes: Obtain historical charge and discharge cycle data of lithium-ion batteries; Extracting time series features from the historical charge and discharge cycle data; Inputting the time series characteristics into an expansion force prediction model to obtain a predicted expansion force of the lithium-ion battery; The predicted expansion force is input into a battery life prediction model to obtain the predicted life of the lithium-ion battery.

2. The method for predicting the life of a lithium-ion battery according to claim 1, characterized in that: The expansion force prediction model is trained by the following steps: Obtain sample charge and discharge cycle data and standard expansion force; Annotating the sample charge-discharge cycle data with corresponding standard expansion forces to obtain an expansion force prediction training set; The expansion prediction training set is used to train the initial expansion force prediction model.

3. The method for predicting the life of a lithium-ion battery according to claim 2, characterized in that: The step of obtaining sample charge-discharge cycle data and standard expansion force includes: Perform cycle tests on sample lithium-ion batteries at different charge and discharge rates; During the cycle test, the expansion force of the sample ion battery is detected to obtain a standard expansion force.

4. The method for predicting the life of a lithium-ion battery according to claim 1, characterized in that: The battery life prediction model is trained by the following steps: Obtain sample expansion force data and typical battery life; Annotating the sample expansion force data with the corresponding standard battery life to obtain a life prediction training set; The life prediction training set is used to train the initial life prediction model.

5. The method for predicting the life of a lithium-ion battery according to claim 4, characterized in that: The step of obtaining sample expansion force data and standard battery life includes: During the cycle test of the sample lithium-ion battery, the sample lithium-ion battery is tested to obtain battery evaluation indicators under different expansion forces; The standard battery life under different expansion forces is calculated based on the battery evaluation index.

6. The method for predicting the life of a lithium-ion battery according to claim 1, characterized in that: The historical charge and discharge cycle data at least includes: the number of cycles, the charge rate and the discharge rate of the lithium-ion battery.

7. A life prediction device for a lithium-ion battery, characterized in that: The life prediction device of the lithium-ion battery comprises: An acquisition module is used to obtain historical charge and discharge cycle data of lithium-ion batteries; A prediction module, used to extract time series features from the historical charge and discharge cycle data; Inputting the time series characteristics into an expansion force prediction model to obtain a predicted expansion force of the lithium-ion battery; The predicted expansion force is input into a battery life prediction model to obtain the predicted life of the lithium-ion battery.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the life prediction method for a lithium-ion battery according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the life prediction method of a lithium-ion battery according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of the life prediction method of a lithium-ion battery according to any one of claims 1 to 6.

Images