Power battery detection method and device, and nonvolatile storage medium

Abstract

The application discloses a power battery detection method and device and a nonvolatile storage medium. The method comprises the following steps: obtaining multiple operation data of a target power battery; determining multiple sets of text data for describing the multiple operation data, wherein the multiple operation data and the multiple sets of text data are in one-to-one correspondence; importing the multiple sets of text data into a target large language model, and outputting a detection result of the target power battery by the target large language model, wherein the target large language model is obtained by fine-tuning parameters of a large language model by a fine-tuning database, and the fine-tuning database comprises sample text data and a sample detection result. The application solves the technical problem of low efficiency of the fault detection method of the power battery.

Description

Technical Field

[0001] This invention relates to the field of health monitoring and management technology for new energy power batteries, and more specifically, to a power battery testing method, device, and non-volatile storage medium. Background Technology

[0002] In recent years, global attention to the environment and energy has been increasing, and electric vehicles have gained widespread recognition due to their clean energy advantages. In particular, ternary lithium batteries, with their high energy density, excellent cycle performance, and good low-temperature resistance, have become the preferred energy storage device for electric vehicles. Nevertheless, thermal runaway events caused by battery system failures are frequent in electric vehicles, making their safety a major concern. However, current battery maintenance mainly relies on reactive measures after a failure or regular inspections, which typically require significant expert experience and manpower. This results in the consultation, diagnosis, decision-making, and service processes in the maintenance workflow consuming substantial time and human resources.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a power battery testing method, apparatus, and non-volatile storage medium to at least solve the technical problem of low efficiency in power battery fault detection methods.

[0005] According to one aspect of the present invention, a method for detecting a power battery is provided, comprising: acquiring various operational data of a target power battery; determining multiple sets of text data to describe the various operational data, wherein the various operational data correspond one-to-one with the multiple sets of text data; importing the multiple sets of text data into a target large language model, and outputting the detection result of the target power battery by the target large language model, wherein the target large language model is obtained by fine-tuning the parameters of the large language model through a fine-tuning database, the fine-tuning database including sample text data and sample detection results. This embodiment utilizes a target large language model to detect power batteries, achieving the technical effect of improving detection efficiency.

[0006] Optionally, multiple sets of text data are determined to describe various operational data, including: converting the various operational data into time series data to obtain multiple time series data corresponding one-to-one with the various operational data; extracting features from the multiple time series data to obtain multiple feature data corresponding one-to-one with the multiple time series data; and converting the multiple feature data into text to obtain multiple sets of text data, wherein the multiple sets of text data are used to describe the characteristics of each of the multiple time series. This embodiment converts the operational data of the power battery into text data that can be recognized and analyzed by the target large language model, thereby improving the accuracy of the target large language model in fault detection.

[0007] Optionally, feature extraction is performed on multiple time series data separately to obtain multiple feature data corresponding one-to-one with the multiple time series data. This includes: extracting target feature data from multiple time series data using the following method: decomposing the target time series data to obtain trend factors and seasonality factors, where the trend factor represents the changing trend of the target time series data, and the seasonality factor represents the periodic change of the target time series data; extracting features from the trend factor to obtain the trend characteristics of the target time series data; extracting features from the seasonality factor to obtain the seasonal characteristics of the target time series data; and obtaining the target feature data based on the trend characteristics and seasonal characteristics of the target time series data. This embodiment illustrates how to extract feature data from time series data, providing more accurate data for subsequent analysis.

[0008] Optionally, the target large language model is obtained as follows: acquiring sample text data and sample detection results; generating a fine-tuning database based on the sample text data and sample detection results; and fine-tuning the parameters of the large language model based on the fine-tuning database to obtain the target large language model. This embodiment illustrates how to obtain the target large language model from the large language model, that is, to customize the large language model and better apply it to the battery detection scenario, thereby achieving the technical effect of improving detection accuracy.

[0009] Optionally, the parameters of the large language model are fine-tuned according to the fine-tuning database to obtain the target large language model. This includes: obtaining the first weight matrix corresponding to the parameters of the large language model; constructing a second weight matrix with the same dimensions as the first weight matrix; and adjusting the second weight matrix according to the fine-tuning database to determine the target large language model. This embodiment illustrates the process of fine-tuning the parameters of the large language model. While ensuring that the knowledge learned by the original large language model is not lost, it makes the large language model more suitable for power battery testing scenarios, achieving the technical effect of improving the detection accuracy of the target large language model.

[0010] Optionally, the second weight matrix is ​​adjusted according to the fine-tuning database to determine the target large language model. This includes: iteratively training the large language model with the first and second weight matrices set according to the fine-tuning database based on a preset number of iterations, and iteratively adjusting the second weight matrix to obtain a third weight matrix; and determining the target large language model based on the third weight matrix. This embodiment further adjusts the parameters of the large language model, and the resulting large language model is better suited for power battery testing scenarios, achieving the technical effect of improving the efficiency and accuracy of power battery testing results.

[0011] According to another aspect of the present invention, a power battery testing device is provided, comprising: a first acquisition module for acquiring various operating data of a target power battery; a first determination module for determining multiple sets of text data respectively used to describe the various operating data, wherein the various operating data correspond one-to-one with the multiple sets of text data; and a first import module for importing the multiple sets of text data into a target large language model, wherein the target large language model outputs the detection result of the target power battery, wherein the target large language model is obtained by fine-tuning the parameters of the large language model through a fine-tuning database, the fine-tuning database including sample text data and sample detection results.

[0012] According to another aspect of the present invention, a non-volatile storage medium is provided, which stores a plurality of instructions adapted for a power battery detection method to be loaded by a processor and executed at any one of them.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any one of the power battery detection methods.

[0014] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the power battery detection method described above.

[0015] In this embodiment of the invention, various operational data of the target power battery are acquired; multiple sets of text data are determined to describe these operational data, with a one-to-one correspondence between the various operational data and the multiple sets of text data; the multiple sets of text data are imported into a target large language model, which outputs the detection results of the target power battery. The target large language model is obtained by fine-tuning the parameters of the large language model using a fine-tuning database, which includes sample text data and sample detection results. This solves the technical problem of low efficiency in power battery fault detection methods, achieving the goal of rapidly detecting potential faults in power batteries, and thus improving the technical result of power battery fault detection efficiency. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a power battery testing method provided according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of a power battery testing device according to an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram of an electronic device provided according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0023] According to an embodiment of the present invention, a method for detecting a power battery is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] Figure 1 This is a flowchart of a power battery testing method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0025] Step S102: Obtain various operating data of the target power battery.

[0026] In this step, testing the power battery essentially involves analyzing various operational data. When these data deviate from normal values, an abnormality is identified. During operation, the power battery generates various operational data, including but not limited to current, voltage, charge / discharge status, and operating temperature. This data is collected for subsequent testing steps.

[0027] Step S104: Determine multiple sets of text data used to describe various types of operational data, wherein each type of operational data corresponds one-to-one with a set of text data.

[0028] In this step, the multiple operating data of the power battery contains various types of information. However, the large language model is mainly designed for modeling and processing text data and cannot directly process other types of information in the multiple operating data. Therefore, it is necessary to convert the multiple operating data of the power battery into multiple sets of text data that the large language model can directly process. Each type of operating data corresponds to a set of text data.

[0029] In one optional embodiment, determining multiple sets of text data to describe various types of operational data includes: converting the various types of operational data into time series data to obtain multiple time series data that correspond one-to-one with the various types of operational data; extracting features from the multiple time series data to obtain multiple feature data that correspond one-to-one with the multiple time series data; and converting the multiple feature data into text to obtain multiple sets of text data, wherein the multiple sets of text data are used to describe the features of each of the multiple time series.

[0030] Optionally, various operating data of the power battery include, but are not limited to, current, voltage, and temperature data. These data change over time and can therefore be regarded as time series data.

[0031] For example, representing current data as time series data:

[0032]

[0033] Where, x 1 Represents a current time series data vector. n represents any value in the current time series data vector, and n1 represents the length of the current time series data vector.

[0034] Representing voltage as time series data:

[0035] in x 2 Represents a voltage time series data vector. n represents any data in the voltage time series data vector, and n2 represents the length of the voltage time series data vector.

[0036] Represent temperature as time series data;

[0037]

[0038] Where, x 3 Represents a vector of temperature time series data. n represents any data in the temperature time series data vector, and n3 represents the length of the temperature time series data vector.

[0039] Following the method described above, all operational data of the power battery are converted into corresponding time series data, resulting in multiple time series data. However, these multiple time series data cannot be recognized and analyzed by the large language model for power battery detection. It is necessary to extract feature information from each time series data and convert the feature information into text to obtain text data that can be recognized and analyzed by the large language model for power battery detection.

[0040] In one optional embodiment, feature extraction is performed on multiple time series data to obtain multiple feature data corresponding one-to-one with the multiple time series data. This includes: extracting target feature data from multiple time series data using the following method: decomposing the target time series data to obtain trend factors and seasonality factors, where the trend factor characterizes the changing trend of the target time series data, and the seasonality factor characterizes the periodic changes of the target time series data; extracting features from the trend factor to obtain the trend characteristics of the target time series data; extracting features from the seasonality factor to obtain the seasonal characteristics of the target time series data; and obtaining the target feature data based on the trend characteristics and seasonal characteristics of the target time series data.

[0041] Optionally, data analysis for each time series can determine the overall trend of the data point distribution within that time series, i.e., the trend factor of the time series. Simultaneously, since time series may be influenced by temperature, humidity, or other factors, this overall trend may contain multiple regular periodic variations. Therefore, after analyzing the overall trend of the distribution, the trend of these periodic variations can also be analyzed, i.e., the seasonality factor of the time series can be determined. Furthermore, other situations may exist that cause a very small number of data points in the time series to deviate from the complete trend and periodic trend. In other words, the trend factor is used to characterize the overall trend of the time series, the seasonality factor is used to characterize the regular periodic trend, and the residual factor is used to characterize the very few data points that deviate from the complete trend and periodic trend.

[0042] By extracting features from the distribution of trend factors and seasonal factors, we can obtain trend features and seasonal features, which can then be combined to obtain the feature data of the corresponding time series data.

[0043] The calculation method for time series is as follows:

[0044] Specifically, for sequence x k For k = 1, 2, 3, the following formula can be used to decompose the equation.

[0045] x k =t k +s k +r k

[0046] Among them, t k For sequence x k Trend factor, s k For x k Seasonal factors, r k For xk The residual factor.

[0047] By extracting features from the trend and seasonality factors of time series, we can obtain the characteristic data of the time series.

[0048] Step S106: Import multiple sets of text data into the target large language model, and output the detection results of the target power battery from the target large language model. The target large language model is obtained by fine-tuning the parameters of the large language model through a fine-tuning database, which includes sample text data and sample detection results.

[0049] In this step, the sample detection results can correspond to the sample text data, or they can be determined based on actual needs, specifying the output of the large language model after it has detected the sample text data. The large language model can be a commonly available open-source large model. The sample text data is input into the open-source large language model, along with the corresponding detection results. This involves fine-tuning the parameters of the large language model using the sample text data and the sample detection results. The open-source large language model will learn based on the sample running data and the sample detection results to obtain the large language model for power battery fault detection required in this application. After obtaining the large language model for power battery fault detection, it can be used to detect power batteries. The detection process involves inputting the operating data of the power battery in the actual application scenario into the large language model for power battery fault detection, and the large language model will output the corresponding detection results.

[0050] In one optional embodiment, the target large language model is obtained by: acquiring sample text data and sample detection results; generating a fine-tuning database based on the sample text data and sample detection results; and fine-tuning the parameters of the large language model based on the fine-tuning database to obtain the target large language model.

[0051] Optionally, the sample text data can be text describing the changing trends of the sample battery's operating data, and the sample detection results can be the labeled results of this text data, i.e., the actual detection results of the sample battery, used to guide how the open-source large language model used in this application learns. The sample text data and sample detection results are stored in a fine-tuning database. The open-source large language model calls the sample text data and sample detection results from the fine-tuning database to train the open-source large language model, obtaining the battery detection large language model required in this application. In addition, the fine-tuning database can also include a large amount of text data, including but not limited to books, academic literature, technical reports, expert knowledge and experience related to power battery health monitoring, health status assessment, and health maintenance, for further training of the language model.

[0052] In one optional embodiment, the parameters of the large language model are fine-tuned according to the fine-tuning database to obtain the target large language model, including: obtaining a first weight matrix corresponding to the parameters of the large language model; constructing a second weight matrix with the same dimension as the first weight matrix; and adjusting the second weight matrix according to the fine-tuning database to determine the target large language model.

[0053] Optionally, the parameters of the large language model include, but are not limited to, the model structure, number of layers, number of hidden units, and learning rate. In this application, the parameters of the large language model used for power battery detection can be a first weight matrix W. If the parameters in the first weight matrix are directly adjusted according to the fine-tuning database, the already relatively perfected large language model may lose the content it has learned, thereby reducing the accuracy of the model output. Therefore, in order to make the large language model more adaptable to the power battery detection scenario, another weight matrix can be introduced into the large language model, that is, a second weight matrix A can be constructed using an adapter. The dimensions of the second weight matrix are the same as those of the first weight matrix W. When training with the fine-tuning database, only the second weight matrix can be adjusted to obtain a large language model that retains the knowledge in the original large language model and is also applicable to the power battery detection scenario.

[0054] In one optional embodiment, adjusting the second weight matrix according to the fine-tuning database to determine the target large language model includes: iteratively training the large language model with a first weight matrix and a second weight matrix based on a preset number of iterations and the fine-tuning database, and iteratively adjusting the second weight matrix to obtain a third weight matrix; and determining the target large language model based on the third weight matrix.

[0055] Optionally, when training a large language model including a second weight matrix based on a fine-tuning database, a loss function can be set, and the second weight matrix can be iteratively adjusted according to the value of the loss function. When a pre-set iteration termination condition is met, the trained target large language model can be obtained. The iteration termination condition can include an iteration count condition and a loss value condition. The iteration count condition means that iteration stops after a certain number of iterations, and the final weight matrix is ​​obtained. The loss value condition means that iteration stops after a certain number of iterations, and the final weight matrix is ​​obtained. This optional embodiment takes the iteration count condition as an example to apply the iteration condition to the second weight matrix. When determining the iteration count, the number of samples in the fine-tuning database can be determined, and the number of iterations can be determined based on the number of samples. It should be noted that the third weight matrix refers to the weight matrix obtained by combining the first and second weight matrices.

[0056] The formula for iterative updates is:

[0057] W FT =W+A

[0058] Among them, W FT This represents the third weight matrix obtained after fine-tuning. When updating W... FT At this point, W remains constant, while A is updated with each iteration until convergence. The update formula for A is as follows:

[0059] A = U T V

[0060] Where U is the left decomposition matrix with row and column dimensions m and d respectively, V is the right decomposition matrix with row and column dimensions d and l respectively, and d is the rank of the adapter.

[0061] You can start the fine-tuning training program, setting parameters such as the rank *d* of the training adapter, the number of fine-tuning iterations, and the learning rate; use a dedicated word segmenter imported from the model to vectorize the fine-tuning database; start fine-tuning training until the preset loss value or the number of fine-tuning iterations is reached. End the fine-tuning training and save the final third weight matrix W. FT , as parameters of the large language model for power battery testing.

[0062] The process involves acquiring various operational data of the target power battery, determining multiple sets of text data to describe these operational data (each set corresponding to a different operational data point), importing these text data into a target large language model, and then having the target large language model output the detection results for the target power battery. The target large language model is obtained by fine-tuning its parameters using a fine-tuning database, which includes sample text data and sample detection results. This approach solves the technical problem of low efficiency in power battery fault detection methods, achieving the goal of rapidly detecting potential faults in power batteries and thus improving the efficiency of power battery fault detection.

[0063] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method, which may include the following steps:

[0064] Step S1: Convert various types of operational data into time series data to obtain multiple time series data that correspond one-to-one with the various types of operational data; extract features from the multiple time series data to obtain multiple feature data that correspond one-to-one with the multiple time series data; convert the multiple feature data into text to obtain multiple sets of text data, wherein the multiple sets of text data are used to describe the features of each of the multiple time series.

[0065] Optionally, various operating data of the power battery, including but not limited to current, voltage, and temperature data, can be regarded as time series data.

[0066] For example, representing current data as time series data:

[0067]

[0068] Where, x 1 Represents a current time series data vector. n represents any value in the current time series data vector, and n1 represents the length of the current time series data vector.

[0069] Representing voltage as time series data:

[0070] in x 2 Represents a voltage time series data vector. n represents any data in the voltage time series data vector, and n2 represents the length of the voltage time series data vector.

[0071] Represent temperature as time series data;

[0072]

[0073] Where, x 3 Represents a vector of temperature time series data. n represents any data in the temperature time series data vector, and n3 represents the length of the temperature time series data vector.

[0074] Following the method described above, all operational data of the power battery are converted into corresponding time series data, resulting in multiple time series data. However, these multiple time series data cannot be recognized and analyzed by the large language model for power battery detection. It is necessary to extract feature information from each time series data to obtain text data that can be recognized and analyzed by the large language model for power battery detection.

[0075] Step S11 involves extracting features from multiple time series data to obtain multiple feature data corresponding to each time series data. This includes: extracting target feature data from multiple time series data using the following method: decomposing the target time series data to obtain trend factors and seasonal factors, where the trend factor represents the changing trend of the target time series data, and the seasonal factor represents the periodic change of the target time series data; extracting features from the trend factor to obtain the trend characteristics of the target time series data; extracting features from the seasonal factor to obtain the seasonal characteristics of the target time series data; and obtaining the target feature data based on the trend characteristics and seasonal characteristics of the target time series data.

[0076] Optional data analysis can be performed on each time series to determine the overall trend of the data point distribution within each time series, i.e., to identify the trend factor of the time series. Simultaneously, since time series may be affected by temperature, humidity, or other factors, this overall trend may contain multiple regular periodic variations. Therefore, after analyzing the overall distribution trend of the data in the time series, the trend of periodic variations can also be analyzed, i.e., to determine the seasonality factor of the time series. Furthermore, there may be other situations that cause a very small number of data points in the time series to deviate from the overall trend and periodic trend. In other words, the trend factor is used to characterize the overall trend of the time series, the seasonality factor is used to characterize the regular periodic trend, and the residual factor is used to characterize the very few data points that deviate from the overall trend and periodic trend. The calculation method for time series is as follows:

[0077] For sequence x k For k = 1, 2, 3, decompose using the following formula:

[0078] x k =t k +s k +r k

[0079] Among them, t k For sequence x k Trend factor, s k For x k Seasonal factors, r k For x k The residual factor.

[0080] By extracting features from the trend and seasonality factors of time series, we can obtain the characteristic data of the time series.

[0081] Step S2: Obtain sample text data and sample detection results; generate a fine-tuning database based on the sample text data and sample detection results; fine-tune the parameters of the large language model based on the fine-tuning database to obtain the target large language model.

[0082] Optionally, Query, Answer, and Instruction commands can be constructed. These three commands can be used to build templates, obtain a fine-tuned database, train a large language model, and obtain a large language model for power battery detection.

[0083] For example, {"Instruction": "You are an expert in the health monitoring and management of new energy power batteries. Please analyze the information provided."}

[0084] "Query": "Analysis of the collected data shows that the frequency domain mean of the sequence is..." <c>The peak value is <d>kurtosis value <d>"What is the battery status at this time?"

[0085] "Answer": "Battery status <Status analysis results> Please continue to monitor"}.

[0086] For example, {"Instruction":"You are an expert in the health monitoring and management of new energy power batteries. Please analyze the information given."}

[0087] "Query": "How should the battery <status> be maintained?"

[0088] "Answer":"<Maintenance Plan>"}.

[0089] The above template is not the complete template; it needs to be expanded and modified according to the actual situation to adapt to battery health management.

[0090] Step S22, fine-tuning the parameters of the large language model according to the fine-tuning database to obtain the target large language model, includes: obtaining the first weight matrix corresponding to the parameters of the large language model; constructing a second weight matrix with the same dimension as the first weight matrix; adjusting the second weight matrix according to the fine-tuning database to determine the target large language model.

[0091] Optionally, the parameters of the large language model include, but are not limited to, the model structure, number of layers, number of hidden units, learning rate, etc. In this application, the parameters of the large language model used for power battery detection can be the first weight matrix W. If the parameters in the first weight matrix are directly adjusted according to the fine-tuning database, the already relatively perfect large language model may lose the content that has been learned, which will lead to a decrease in the accuracy of the model output. Another standard weight matrix is ​​introduced, that is, a second weight matrix A is constructed. The dimension of the second weight matrix is ​​the same as that of the first weight matrix W. When training the second weight matrix using the fine-tuning database, only the second weight matrix can be adjusted, which can obtain a large language model that retains the knowledge in the original large language model and can also be used in the power battery detection scenario.

[0092] Step S23, adjusting the second weight matrix according to the fine-tuning database to determine the target large language model, includes: based on a preset number of iterations, iteratively training the large language model with the first and second weight matrices set according to the fine-tuning database, and iteratively adjusting the second weight matrix to obtain the third weight matrix; and determining the target large language model according to the third weight matrix.

[0093] Optionally, when training a large language model including a second weight matrix based on a fine-tuning database, a loss function can be set, and the second weight matrix can be iteratively adjusted according to the value of the loss function. When a pre-set iteration termination condition is met, the trained target large language model can be obtained. The iteration termination condition can include an iteration count condition and a loss value condition. The iteration count condition means that iteration stops after a certain number of iterations, and the final weight matrix is ​​obtained. The loss value condition means that iteration stops after a certain iteration and the loss value meets a certain condition, and the final weight matrix is ​​obtained. This optional embodiment takes the iteration count condition as an example to iterate the second weight matrix. When determining the iteration count, the number of samples in the fine-tuning database can be determined, and the number of iterations can be determined based on the number of samples. It should be noted that the third weight matrix refers to the weight matrix obtained by combining the first and second weight matrices.

[0094] The formula for iterative updates is:

[0095] W FT =W+A,

[0096] Among them, W FT This represents the fine-tuned third weight matrix. When updating W... FT At this point, W remains constant, while A is updated with each iteration until convergence. The update formula for A is as follows:

[0097] A = U T V,

[0098] Where U is the left decomposition matrix with row and column dimensions m and d respectively, V is the right decomposition matrix with row and column dimensions d and l respectively, and d is the rank of the adapter.

[0099] You can start the fine-tuning training program, setting parameters such as the rank *d* of the training adapter, the number of fine-tuning iterations, and the learning rate; use a dedicated word segmenter imported from the model to vectorize the fine-tuning database; start fine-tuning training until the preset loss value or the number of fine-tuning iterations is reached. End the fine-tuning training and save the final third weight matrix W. FT , as parameters of the large language model for power battery testing.

[0100] The above optional implementation methods achieve at least the following effects: The present invention provides a power battery health detection method based on a large language model, which can translate battery detection signals into text descriptions that the large language model can understand, and analyze them using a large language model fine-tuned with professional data related to the health detection and management of new energy power batteries, thereby achieving the technical effect of improving the efficiency of battery health detection.

[0101] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0102] This embodiment also provides a power battery testing device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0103] According to embodiments of the present invention, an embodiment of an apparatus for implementing a power battery testing method is also provided. Figure 2 This is a schematic diagram of a power battery testing device according to an embodiment of the present invention, as shown below. Figure 2 As shown, the above-mentioned power battery testing device includes a first acquisition module 21, a first determination module 22, and a first import module 23. The device will be described below.

[0104] The first acquisition module 21 is used to acquire various operating data of the target power battery;

[0105] The first determining module 22, connected to the first acquiring module, is used to determine multiple sets of text data that describe various types of operational data, wherein the various types of operational data correspond one-to-one with the multiple sets of text data;

[0106] The first import module 23, connected to the first determination module, is used to import multiple sets of text data into the target large language model, and the target large language model outputs the detection results of the target power battery. The target large language model is obtained by fine-tuning the parameters of the large language model through a fine-tuning database, which includes sample text data and sample detection results.

[0107] This invention provides a power battery testing device that includes a first acquisition module for acquiring various operational data of a target power battery; a first determination module for determining multiple sets of text data describing the various operational data, wherein each set of text data corresponds one-to-one with the various operational data; and a first import module for importing the multiple sets of text data into a target large language model, which then outputs the detection results of the target power battery. The target large language model is obtained by fine-tuning the parameters of the large language model using a fine-tuning database, which includes sample text data and sample detection results. This invention solves the technical problem of low efficiency in power battery fault detection methods, achieving the goal of rapidly detecting potential faults in power batteries, and thus improving the technical result of power battery fault detection efficiency.

[0108] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0109] It should be noted that the first acquisition module 21, the first determination module 22, and the first import module 23 mentioned above correspond to steps S102 to S106 in the embodiments. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but they are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run on a computer terminal.

[0110] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0111] The aforementioned power battery testing device may also include a processor and a memory. The first acquisition module 21, the first determination module 22, the first import module 23, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0112] The processor contains a core that retrieves the corresponding program unit from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0113] This invention provides a non-volatile storage medium storing a program that, when executed by a processor, implements a power battery detection method.

[0114] like Figure 3 As shown, this embodiment of the invention provides an electronic device. The electronic device 10 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: the memory is used to store a computer program, wherein when the computer program is executed by the processor, the processor implements the above-mentioned power battery detection method. The device in this article may be a server, PC, etc.

[0115] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: computer instructions are executed by a processor to perform the above-described power battery detection method.

[0116] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0118] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0121] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0122] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0124] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.< / d> < / d> < / c>

Claims

1. A method for detecting a power cell, characterized in that, The method comprises the following steps: acquiring a plurality of operating data of a target power battery; determining a plurality of sets of text data respectively used for describing the plurality of operating data, wherein the plurality of operating data and the plurality of sets of text data correspond one by one; inputting the plurality of sets of text data into a target large language model, and outputting a detection result of the target power battery by the target large language model, wherein the target large language model is obtained by fine-tuning parameters of a large language model by a fine-tuning database, and the fine-tuning database comprises sample text data and sample detection results; wherein the determining the plurality of sets of text data respectively used for describing the plurality of operating data comprises: converting the plurality of operating data into time series data respectively to obtain a plurality of time series data corresponding to the plurality of operating data; and performing feature extraction on the plurality of time series data respectively by a manner of extracting target feature data from a target time series data among the plurality of time series data to obtain a plurality of feature data corresponding to the plurality of time series data: decomposing the target time series data to obtain a trend factor and a seasonal factor of the target time series data, wherein the trend factor represents a change trend of the target time series data, and the seasonal factor represents a periodic change of the target time series data; performing feature extraction on the trend factor to obtain a trend feature of the target time series data; performing feature extraction on the seasonal factor to obtain a seasonal feature of the target time series data; and obtaining the target feature data according to the trend feature of the target time series data and the seasonal feature of the target time series data; and obtaining the plurality of sets of text data based on the plurality of feature data; wherein the target large language model is obtained by the following manner: acquiring a first weight matrix corresponding to parameters of the large language model; constructing a second weight matrix consistent in dimension with the first weight matrix; based on a preset number of iterations, performing iterative training on the large language model provided with the first weight matrix and the second weight matrix according to the fine-tuning database, and iteratively adjusting the second weight matrix to obtain a third weight matrix; and determining the target large language model according to the third weight matrix.

2. The method of claim 1, wherein, The determining the plurality of sets of text data respectively used for describing the plurality of operating data comprises: converting the plurality of feature data into texts respectively to obtain the plurality of sets of text data, wherein the plurality of sets of text data are used for describing respective features of the plurality of time series.

3. The method according to claim 1 or 2, characterized in that, The target large language model is obtained by the following manner: acquiring the sample text data and the sample detection results; generating the fine-tuning database according to the sample text data and the sample detection results; fine-tuning parameters of the large language model according to the fine-tuning database to obtain the target large language model.

4. A power cell detection device, characterized by The method comprises the following steps: a first acquiring module is configured to acquire a plurality of operating data of a target power battery; a first determining module is configured to determine a plurality of sets of text data respectively used for describing the plurality of operating data, wherein the plurality of operating data and the plurality of sets of text data correspond one by one; The first import module is configured to import the multiple sets of text data into a target large language model, and output a detection result of the target power battery by the target large language model, wherein the target large language model is obtained by fine-tuning parameters of a large language model by a fine-tuning database, and the fine-tuning database includes sample text data and sample detection results. The first determining module is further configured to convert the multiple types of operation data into time series data respectively to obtain multiple time series data corresponding to the multiple types of operation data respectively; and perform feature extraction on the multiple time series data respectively to obtain multiple feature data corresponding to the multiple time series data respectively by using a manner of extracting target feature data from target time series data from the multiple time series data as follows: decomposing the target time series data to obtain a trend factor and a seasonal factor of the target time series data, wherein the trend factor represents a change trend of the target time series data, and the seasonal factor represents a periodic change of the target time series data; performing feature extraction on the trend factor to obtain a trend feature of the target time series data; performing feature extraction on the seasonal factor to obtain a seasonal feature of the target time series data; and obtaining the target feature data according to the trend feature of the target time series data and the seasonal feature of the target time series data; and obtaining the multiple sets of text data based on the multiple feature data. The target large language model is obtained by the following manner: obtaining a first weight matrix corresponding to parameters of the large language model; constructing a second weight matrix with a same dimension as the first weight matrix; based on a preset number of iterations, performing iterative training on the large language model provided with the first weight matrix and the second weight matrix according to the fine-tuning database, and performing iterative adjustment on the second weight matrix to obtain a third weight matrix; and determining the target large language model according to the third weight matrix.

5. A non-volatile storage medium, characterized by, The non-volatile storage medium stores a plurality of instructions, which are suitable for being loaded and executed by the processor to implement the power battery detection method in any one of claims 1 to 3.

6. An electronic device, comprising: One or more processors and a memory, the memory being configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the power battery detection method in any one of claims 1 to 3. The computer instructions are executed by the processor to implement the power battery detection method in any one of claims 1 to 3.

7. A computer program product comprising computer instructions, characterized in that, ​

Images