Failure prediction method and device for lithium iron phosphate battery, computer equipment and medium
By constructing a lithium iron phosphate battery failure prediction model based on graph convolutional neural networks and long-term neural networks, the problems of prediction time and low efficiency in the existing technology are solved, and efficient and accurate battery failure prediction in complex environments are achieved.
Patent Information
- Application Number
- CN202411276038.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2025-01-07
AI Technical Summary
In the prior art, lithium iron phosphate battery failure prediction takes a long time and is inefficient, and it has failed to effectively solve the problem of battery failure prediction in complex environments.
The failure prediction model is adopted based on graph convolutional neural networks and long-term neural networks. By obtaining cell structure change data and property change data, simulation and data augmentation processing are carried out, and the model is trained to predict the battery failure results.
It significantly reduces the prediction time, improves prediction efficiency and accuracy, and can accurately predict whether the battery fails in complex environments.
Smart Images
Figure CN119270078A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method, device, computer equipment and medium for predicting failure of a lithium iron phosphate battery. Background Art
[0002] Lithium iron phosphate battery is a lithium-ion battery with high theoretical specific capacity, stable operating voltage, excellent chemical stability and high safety. It is widely used in portable electronic devices, new energy vehicles and energy storage power stations. However, current research only focuses on improving the electrochemical performance of lithium iron phosphate, while ignoring the discussion of its failure after modification or in complex environments. Failure prediction can help researchers understand and optimize the working principle and performance of batteries, reduce test and experimental cycles, and save R&D costs and resource investment.
[0003] In the prior art, the failure prediction of lithium iron phosphate batteries usually involves analyzing the existing measured life data, determining the failure of the battery in multiple cycles by fitting a function model, and obtaining the battery failure result.
[0004] Although this method can predict battery failure, it is time-consuming and inefficient. Summary of the invention
[0005] Based on this, it is necessary to provide a lithium iron phosphate battery failure prediction method, device, computer equipment and medium that can reduce the prediction time and improve the prediction efficiency in response to the above technical problems.
[0006] In a first aspect, the present application provides a method for predicting failure of a lithium iron phosphate battery, comprising:
[0007] Obtaining the cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data;
[0008] The cell failure data is input into the failure prediction model to obtain the cell failure results of the battery to be tested; the failure prediction model is constructed based on graph convolutional neural network and long-short term neural network.
[0009] In one embodiment, a method for training a failure prediction model includes:
[0010] Simulate the changes in the cell structure of the sample battery under the failure environment to obtain the failure data of the sample cell;
[0011] Based on the sample battery cell failure data, the failure prediction model is trained;
[0012] The failure environment includes at least one of an element-doped environment, a carbon-coated environment, and a high-humidity environment.
[0013] In one embodiment, the change of the cell structure of the sample battery under the failure environment is simulated to obtain the failure data of the sample cell, including:
[0014] Simulate the change of the cell structure of the sample battery under the failure environment to obtain the original cell failure data; wherein the original cell failure data includes the original cell structure change data;
[0015] The original cell failure data is subjected to data enhancement processing to obtain sample cell failure data of the sample battery.
[0016] In one embodiment, the change of the cell structure of the sample battery under the failure environment is simulated to obtain the original cell structure change data, including:
[0017] Obtaining original cell structure data corresponding to the cell structure of the sample battery under normal conditions;
[0018] Simulate the changes in the cell structure of the sample battery under the failure environment to obtain the failed cell structure data;
[0019] According to the failed battery cell structure data and the original battery cell structure data, the original battery cell structure change data is determined.
[0020] In one embodiment, determining the original cell structure change data according to the failed cell structure data and the original cell structure data includes:
[0021] Determine the cell structure difference data according to the difference between the failed cell structure data and the original cell structure data;
[0022] The original cell structure change data is determined based on the ratio between the cell structure difference data and the failed cell structure data.
[0023] In one embodiment, the cell failure data is input into a failure prediction model to obtain a failure result of the battery to be tested, including:
[0024] The cell failure data is input into the graph convolutional neural network to obtain the cell failure characteristics of the battery to be tested;
[0025] The cell failure characteristics are input into the long-term and short-term neural network to obtain the cell failure results of the battery to be tested.
[0026] In a second aspect, the present application also provides a lithium iron phosphate battery failure prediction device, comprising:
[0027] A data acquisition module is used to acquire the cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data;
[0028] The failure prediction module is used to input the cell failure data into the failure prediction model to obtain the cell failure result of the battery to be tested; the failure prediction model is constructed based on the graph convolutional neural network and the long-short term neural network.
[0029] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0030] Obtaining the cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data;
[0031] The cell failure data is input into the failure prediction model to obtain the cell failure results of the battery to be tested; the failure prediction model is constructed based on graph convolutional neural network and long-short term neural network.
[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0033] Obtaining the cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data;
[0034] The cell failure data is input into the failure prediction model to obtain the cell failure results of the battery to be tested; the failure prediction model is constructed based on graph convolutional neural network and long-short term neural network.
[0035] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0036] Obtaining the cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data;
[0037] The cell failure data is input into the failure prediction model to obtain the cell failure results of the battery to be tested; the failure prediction model is constructed based on graph convolutional neural network and long-short term neural network.
[0038] The above-mentioned lithium iron phosphate battery failure prediction method, device, computer equipment and medium obtain the cell failure data of the battery to be tested; the cell failure data includes the cell structure change data and the cell property change data; the cell failure data is input into the failure prediction model to obtain the cell failure result of the battery to be tested; the failure prediction model is constructed based on the graph convolutional neural network and the long-term and short-term neural network. This application analyzes the cell failure data through the failure prediction model, which can directly determine whether the battery to be tested has failed, thereby improving the accuracy and prediction efficiency of the failure of the battery to be tested. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0040] FIG1 is an application environment diagram of a lithium iron phosphate battery failure prediction method provided by this embodiment;
[0041] FIG2 is a schematic diagram of a flow chart of a first lithium iron phosphate battery failure prediction method provided in this embodiment;
[0042] FIG3 is a schematic diagram of a battery cell structure provided in this embodiment;
[0043] FIG4 is a structural block diagram of a lithium iron phosphate battery failure prediction device provided in this embodiment;
[0044] FIG5 is an internal structure diagram of a first computer device provided in this embodiment;
[0045] FIG6 is a diagram showing the internal structure of a second type of computer device provided in this embodiment. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0047] The lithium iron phosphate battery failure prediction method provided in the embodiment of the present application can be applied in the application environment shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The computer device obtains the battery cell failure data of the battery to be tested; the battery cell failure data includes battery cell structure change data and battery cell property change data; the battery cell failure data is input into the failure prediction model to obtain the battery cell failure result of the battery to be tested; the failure prediction model is constructed based on the graph convolutional neural network and the long-term and short-term neural network. Among them, the computer device can be either a terminal or a server. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.
[0048] In an exemplary embodiment, as shown in FIG2 , a method for predicting failure of a lithium iron phosphate battery is provided, which is described by taking the method applied to the computer device in FIG1 as an example, and includes the following steps 201 to 202. Among them:
[0049] Step 201, obtaining cell failure data of a battery to be tested.
[0050] Among them, the battery to be tested may be a battery to be tested for failure, and the battery to be tested may be a lithium iron phosphate (LiFePO4) battery, which uses lithium iron phosphate as the positive electrode material and carbon-based or silicon-based as the negative electrode material. The cell structure may be the ground state structure of the battery cell, as shown in the schematic diagram of the cell structure in FIG3 , (a) in FIG3 is the cell structure of lithium iron phosphate under normal conditions, and (b) in FIG3 is the cell structure of lithium iron phosphate under failure conditions (high humidity environments). The cell failure data includes cell structure change data and cell property change data. The cell structure change data may be data on changes in the cell structure after external strain is applied to the cell cell. The cell property change data may include changes in electronic properties, magnetic properties, electrochemical properties, ion diffusion properties, etc. The cell failure data may be determined manually, or may be determined by simulating the battery condition of the battery to be tested in a failure environment using simulation software.
[0051] Step 202: input the cell failure data into a failure prediction model to obtain a cell failure result of the battery to be tested.
[0052] Among them, the failure prediction model is built based on Graph Convolutional Networks (GCN) and Long Short-Term Memory Networks (LSTM).
[0053] In one of the embodiments, the cell failure data is input into a failure prediction model, and the failure prediction model analyzes the local features and timing features in the cell failure data to determine the cell failure result of the battery to be tested.
[0054] In another embodiment, the cell failure data is input into a failure prediction model to obtain the failure result of the battery to be tested, including: inputting the cell failure data into a graph convolutional neural network to obtain the cell failure characteristics of the battery to be tested; inputting the cell failure characteristics into a long-term and short-term neural network to obtain the cell failure result of the battery to be tested.
[0055] The cell failure feature may be a feature related to battery failure extracted from the cell failure data.
[0056] Specifically, the cell failure data is input into a graph convolutional neural network to obtain the cell failure characteristics of the battery to be tested, and then the cell failure characteristics are input into a long-term and short-term neural network to obtain the cell failure results of the battery to be tested.
[0057] The above-mentioned lithium iron phosphate battery failure prediction method obtains the cell failure data of the battery to be tested; the cell failure data includes the cell structure change data and the cell property change data; the cell failure data is input into the failure prediction model to obtain the cell failure result of the battery to be tested; the failure prediction model is constructed based on the graph convolutional neural network and the long-term and short-term neural network. The present application analyzes the cell failure data through the failure prediction model, which can directly determine whether the battery to be tested has failed, thereby improving the accuracy and prediction efficiency of the failure of the battery to be tested.
[0058] In some embodiments, a method for training a failure prediction model includes: simulating changes in the cell structure of a sample battery under a failure environment to obtain sample cell failure data; and training a failure prediction model based on the sample cell failure data.
[0059] Among them, failure environments include element doping environment, nano-sizing environment, carbon coating environment, high humidity environment, high salt environment, adding external stress, etc.
[0060] Exemplarily, the method of simulating the change of the cell structure of the sample battery under the failure environment to obtain the failure data of the sample cell may be: simulating the change of the cell structure of the sample battery under the failure environment by simulation software, simulating the failure of the sample battery, and obtaining the failure data of the sample cell. Alternatively, the cell structure corresponding to the sample battery under each failure environment is obtained, the cell structure of the sample battery is compared with the cell structure of the failure environment, the change of the cell structure is determined, and the change of the cell structure is used as the failure data of the sample cell.
[0061] Exemplarily, training a failure prediction model based on sample battery cell failure data includes: inputting the sample battery cell failure data into the failure prediction model to obtain the sample battery cell failure result; determining an evaluation index of the failure prediction model based on the sample battery cell failure result and the actual battery cell failure result; when the evaluation index is less than a preset index threshold, determining a loss value of the failure prediction model based on the evaluation index, adjusting the failure prediction model according to the loss value until the evaluation index is greater than the preset index threshold, thereby completing the training of the failure prediction model.
[0062] It should be noted that the evaluation indicators can be expressed by the mean absolute error (MAE), mean square error (MSE) and coefficient of determination (R 2 ) and other methods.
[0063] This embodiment trains the failure prediction model based on the failure data of sample cells of sample batteries under failure environments to improve the accuracy and stability of failure prediction. At the same time, this embodiment fully considers various failure factors, and the acquired failure data of sample cells are accurately obtained, and the data acquisition is efficient. It has the advantages of easy operation and wide application range, and has great practical value and broad application prospects.
[0064] In some embodiments, the changes in the cell structure of the sample battery in a failure environment are simulated to obtain sample cell failure data, including: simulating the changes in the cell structure of the sample battery in a failure environment to obtain original cell failure data; performing data enhancement processing on the original cell failure data to obtain sample cell failure data of the sample battery.
[0065] Among them, the original battery cell failure data includes the original battery cell structure change data.
[0066] Specifically, the changes in the cell structure of the sample battery under the failure environment are simulated to obtain original cell failure data, the original cell failure data is enhanced, and the enhanced data is used as the sample cell failure data of the sample battery.
[0067] Exemplarily, data enhancement processing can be a process of adding Gaussian noise to the data to expand the original battery cell failure data. Gaussian noise is a random noise that follows a normal distribution. In machine learning, Gaussian noise is usually added to the input data during the training process to enhance the robustness and generalization ability of the model. By introducing noise into the input data, the machine learning model is forced to learn features with small changes in the data, which helps to obtain better prediction performance in unknown data.
[0068] This embodiment can increase the sample size of sample cell failure data.
[0069] In some embodiments, the changes in the cell structure of the sample battery in a failure environment are simulated to obtain original cell structure change data, including: obtaining original cell structure data corresponding to the cell structure of the sample battery in a normal environment; simulating the changes in the cell structure of the sample battery in a failure environment to obtain failed cell structure data; determining the original cell structure change data based on the failed cell structure data and the original cell structure data.
[0070] Specifically, the original cell structure data corresponding to the cell structure of the sample battery under normal conditions is obtained. At the same time, the change of the cell structure of the sample battery under a failure environment is simulated to obtain the failed cell structure data. According to the failed cell structure data and the original cell structure data, the original cell structure change data is determined.
[0071] In some embodiments, determining the original cell structure change data based on the failed cell structure data and the original cell structure data includes: determining the cell structure difference data based on the difference between the failed cell structure data and the original cell structure data; and determining the original cell structure change data based on the ratio between the cell structure difference data and the failed cell structure data. Specifically, as shown in the following formula (1-1).
[0072] (1-1)
[0073] Among them, ε represents the original battery cell structure change data, a represents the failed battery cell structure data, and a0 represents the original battery cell structure data. A positive value of the original battery cell structure change data indicates that the battery has been subjected to tensile strain, and a negative value of the original battery cell structure change data indicates compressive strain.
[0074] It should be noted that the present embodiment can also determine the sample cell failure data of the sample battery by density functional theory. Density functional theory includes adiabatic approximation (Born-Oppenheimer approximation), single particle approximation (Hartree-Fock) and single particle orbital equation (Kohn-Sham). Among them, under the adiabatic approximation, the system wave function can be written as the product of the electron wave function and the atomic nucleus wave function.
[0075] This embodiment can more accurately determine the failure data of the sample battery cells by simulating the battery cell structure of the sample battery.
[0076] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0077] Based on the same inventive concept, the embodiment of the present application also provides a lithium iron phosphate battery failure prediction device for implementing the above-mentioned lithium iron phosphate battery failure prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the lithium iron phosphate battery failure prediction device provided below can refer to the limitations of the lithium iron phosphate battery failure prediction method above, and will not be repeated here.
[0078] In an exemplary embodiment, as shown in FIG4 , a failure prediction device for a lithium iron phosphate battery is provided, comprising: a data acquisition module 10 and a failure prediction module 11, wherein:
[0079] The data acquisition module 10 is used to acquire the cell failure data of the battery to be tested; the cell failure data includes the cell structure change data and the cell property change data;
[0080] The failure prediction module 11 is used to input the cell failure data into the failure prediction model to obtain the cell failure result of the battery to be tested; the failure prediction model is constructed based on a graph convolutional neural network and a long-term and short-term neural network.
[0081] In one embodiment, the lithium iron phosphate battery failure prediction device in FIG4 further includes:
[0082] The model training module is used to simulate the changes in the cell structure of the sample battery under the failure environment to obtain the sample cell failure data; based on the sample cell failure data, the failure prediction model is trained; wherein the failure environment includes at least one of an element doping environment, a carbon coating environment and a high humidity environment.
[0083] In one embodiment, the model training module in Figure 4 is also used to simulate the changes in the cell structure of the sample battery under a failure environment to obtain original cell failure data; wherein the original cell failure data includes original cell structure change data; the original cell failure data is subjected to data enhancement processing to obtain sample cell failure data of the sample battery.
[0084] In one embodiment, the model training module in Figure 4 is also used to obtain original cell structure data corresponding to the cell structure of the sample battery under normal conditions; simulate the change of the cell structure of the sample battery under a failure environment to obtain the failed cell structure data; and determine the original cell structure change data based on the failed cell structure data and the original cell structure data.
[0085] In one embodiment, the model training module in FIG. 4 is also used to determine the cell structure difference data based on the difference between the failed cell structure data and the original cell structure data; and to determine the original cell structure change data based on the ratio between the cell structure difference data and the failed cell structure data.
[0086] In one embodiment, the failure prediction module 11 in Figure 4 is also used to input the battery cell failure data into the graph convolutional neural network to obtain the battery cell failure characteristics of the battery to be tested; and input the battery cell failure characteristics into the long-term and short-term neural network to obtain the battery cell failure results of the battery to be tested.
[0087] Each module in the above-mentioned lithium iron phosphate battery failure prediction device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0088] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to 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 data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a lithium iron phosphate battery failure prediction method is implemented.
[0089] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for predicting failure of a lithium iron phosphate battery is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0090] Those skilled in the art will understand that the structures shown in FIGS. 5 and 6 are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figures, or combine certain components, or have a different arrangement of components.
[0091] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
[0092] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0093] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0094] It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0096] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.
[0097] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for predicting failure of a lithium iron phosphate battery, characterized in that: The method comprises: Obtaining cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data; The cell failure data is input into a failure prediction model to obtain the cell failure result of the battery to be tested; the failure prediction model is constructed based on a graph convolutional neural network and a long-short term neural network.
2. The method according to claim 1, characterized in that The training method of the failure prediction model comprises: Simulate the changes in the cell structure of the sample battery under the failure environment to obtain the failure data of the sample cell; Performing model training on the failure prediction model according to the sample battery cell failure data; Wherein, the failure environment includes at least one of an element doping environment, a carbon coating environment and a high humidity environment.
3. The method according to claim 2, characterized in that The simulation of the change of the cell structure of the sample battery under the failure environment to obtain the failure data of the sample cell includes: Simulating the change of the cell structure of the sample battery under the failure environment to obtain original cell failure data; wherein the original cell failure data includes original cell structure change data; The original battery cell failure data is subjected to data enhancement processing to obtain sample battery cell failure data of the sample battery.
4. The method according to claim 3, characterized in that The simulation of the change of the cell structure of the sample battery under the failure environment to obtain the original cell structure change data includes: Obtaining original cell structure data corresponding to the cell structure of the sample battery under normal conditions; Simulate the changes in the cell structure of the sample battery under the failure environment to obtain the failed cell structure data; The original cell structure change data is determined according to the failed cell structure data and the original cell structure data.
5. The method according to claim 4, characterized in that The determining the original cell structure change data according to the failed cell structure data and the original cell structure data includes: Determining cell structure difference data according to the difference between the failed cell structure data and the original cell structure data; The original cell structure change data is determined according to a ratio between the cell structure difference data and the failed cell structure data.
6. The method according to claim 1, characterized in that The step of inputting the cell failure data into a failure prediction model to obtain a failure result of the battery to be tested includes: Inputting the cell failure data into a graph convolutional neural network to obtain cell failure characteristics of the battery to be tested; The cell failure characteristics are input into the long-term and short-term neural network to obtain the cell failure results of the battery to be tested.
7. A lithium iron phosphate battery failure prediction device, characterized in that: The device comprises: A data acquisition module, used to acquire the cell failure data of the battery to be tested; the cell failure data includes cell structure change data and cell property change data; A failure prediction module is used to input the cell failure data into a failure prediction model to obtain the cell failure result of the battery to be tested; the failure prediction model is constructed based on a graph convolutional neural network and a long-short term neural network.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
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 method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.