Battery health state assessment method and system based on large model and sequence matching

Abstract

The invention discloses a large model and sequence matching-based battery health state evaluation method and system. The method comprises the following steps of: classifying battery health states according to a numerical range; extracting a charging sequence in a general form from the test battery monomers, and defining the charging sequence as a current sequence; the method comprises the following steps: extracting charging sequences with different median thresholds in a general form from known single batteries, and defining the charging sequences as candidate sequences; performing sequence matching on the current sequence and each candidate sequence; performing fine tuning on the large language model by adopting a matching sequence with a tag; and acquiring actual charging data of the to-be-tested single battery, extracting a charging sequence in a general form as a current sequence, performing sequence matching on the current sequence and each candidate sequence, and obtaining an evaluation category of the health state of the battery by using a fine-tuned large language model. According to the method, the numerical range of the health state of the battery is used as a state evaluation result, and the problem that the confidence coefficient of the method is reduced due to outlier estimation values in a traditional estimation method is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery health status assessment, and in particular to a battery health status assessment method and system based on large model and sequence matching. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As the most widely used secondary battery, lithium-ion batteries play a role in electric vehicles, energy storage systems, consumer electronics, and smart devices. However, in actual applications, the combined effects of complex working conditions, ambient temperature, material inconsistency, and other factors may cause nonlinear attenuation of the available capacity of lithium-ion batteries, leading to a decline in the overall performance of the battery.

[0004] Battery state of health (SOH) is used to assess the aging level of the battery to avoid potential failures and threats. In the prior art, most battery health status assessments use model-based estimation methods or data-driven estimation methods; model-based estimation methods mainly establish mathematical models that can accurately simulate the complex internal mechanisms of the battery to infer the battery health status. The drawback of this method is that the state value estimated based on the model is completely dependent on the completeness of the model, real-time data and parameter identification, making it poor in applicability, flexibility, portability and estimation accuracy. The data-driven estimation method is based on data processing, feature engineering and deep learning / machine learning algorithms to establish a mapping relationship between aging features and battery health status to achieve state estimation. Although this method does not require the establishment of a complex mathematical model, it is limited by the number of labels of lithium-ion batteries. Data-driven models are often small in scale and have poor model generalization capabilities.

[0005] The prior art discloses a battery state estimation method based on a pre-trained large language model. The pre-trained large language model provides multi-domain prior knowledge, which can improve the model training / fine-tuning efficiency and estimation accuracy. However, these methods all require manual extraction of aging features (such as IC curve peak, relaxation voltage, etc.) to establish a mapping relationship with the health state, and the prerequisites for feature extraction are harsh, which leads to the wide applicability of the model and high estimation complexity. At the same time, these methods all use health state floating point numbers as state estimation results. However, when the overall estimation performance of the model is good, individual outlier estimates will appear to reduce the confidence of the method. For ordinary users, in most cases, they only need to understand the range of health states, and do not need to know the explicit floating point number of the battery health state. In addition, in the prior art, one feature corresponds to one health state floating point data, and the acquisition of one feature requires one charge and discharge cycle; due to the limited battery charge and discharge cycles, the number of samples obtained will also be limited. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a battery health status assessment method and system based on a large model and sequence matching, which breaks the mindset of using health status floating-point numbers as state estimation results, and uses classification theory to match the charging sequence of the single cell to be tested with different candidate charging sequences. With the help of a fine-tuned large model, accurate, convenient and reliable battery health status assessment is achieved.

[0007] In some embodiments, the following technical solutions are adopted: A battery health status assessment method based on large model and sequence matching, comprising: The battery health status is classified according to the numerical range, and the median threshold of the battery health status of different categories is determined; Based on the historical charging data of the fragments, the voltage and charging amount are integrated to construct a general form of charging sequence; The battery cells of the historical charging data are divided into test battery cells and known battery cells; a general charging sequence is extracted from the test battery cells and defined as a current sequence; a general charging sequence with different median thresholds is extracted from the known battery cells and defined as a candidate sequence; The current sequence is concatenated with each candidate sequence to achieve sequence matching; a label is assigned to the matching sequence according to whether the current sequence and the concatenated candidate sequence belong to the same health status category; Fine-tune the large language model using labeled matching sequences; The actual charging data of the battery cell to be tested is obtained, and a general charging sequence is extracted as the current sequence. The current sequence is matched with each candidate sequence respectively, and based on the matching sequence, a fine-tuned large language model is used to obtain an evaluation category of the battery health status.

[0008] As a further solution, the battery health status is classified according to the numerical range, specifically: The battery health status is divided into 5 categories from good to bad, including: 95%< SOH ≤100%, 90%< SOH ≤95%, 85%< SOH ≤90%, 80%< SOH ≤85% and SOH <80%; Determine the median battery health threshold for each category.

[0009] As a further approach, a general form of charging sequence is constructed, specifically: Extract the original voltage sequence based on fragmented historical charging data V and charge sequence Q : ; Couple the voltage sequence described in the time dimension V and charge sequence Q , to construct a two-dimensional array E 0: ; Based on the two-dimensional array E 0, by point-by-point differentiation to reduce the array dimension, and then construct a general form of charging sequence E 1: ; in, n is the total number of charging data points, d Q / d V Represents point-by-point differentiation, i=1,2,…,n-1.

[0010] As a further solution, the current sequence is concatenated with each candidate sequence to achieve sequence matching, specifically: A voltage range of the current sequence is determined, and a complete candidate sequence is truncated based on the voltage range, and candidate sequence data within the voltage range is retained.

[0011] As a further solution, we use labeled matching sequences to fine-tune the large language model, specifically: Select BERT-large as the large language model, apply low-rank adaptation technology to the attention head and output module in the model, and use matching sequences to fine-tune the large language model multiple times; The input of the large language model is multiple matching sequences, and the output is a label for each matching sequence. If the label of the matching sequence is 1, the current sequence and the candidate sequence in the matching sequence belong to the same health status category; finally, the battery health status assessment category of the current sequence is obtained.

[0012] As a further solution, the large language model is fine-tuned multiple times using labeled matching sequences, and the large language model obtained after each fine-tuning is evaluated using evaluation indicators to screen out the best large language model.

[0013] As a further solution, the actual charging data of the battery cell to be tested is obtained, and the evaluation results of the battery health status are obtained by using the fine-tuned large language model, specifically: Based on the actual charging data, a general form of charging sequence is constructed as the current sequence; The candidate sequences are truncated and the current sequence is concatenated with each candidate sequence to achieve sequence matching; The matched sequence is input into the fine-tuned large language model, and the predicted label is output. The battery health status category corresponding to the candidate sequence in the matching sequence with label 1 is used as the battery health status assessment result of the battery cell to be tested.

[0014] In other embodiments, the following technical solutions are adopted: A battery health status assessment system based on large model and sequence matching, comprising: A classification module is used to classify the battery health status into categories according to the numerical range and determine the median threshold of the battery health status of different categories; A charging sequence building module is used to build a general form of charging sequence based on fragmented historical charging data, integrating voltage and charging amount; The sequence matching module is used to divide the battery cells of the historical charging data into test battery cells and known battery cells; extract the general form of charging sequence from the test battery cells, which is defined as the current sequence; extract the general form of charging sequences with different median thresholds from the known battery cells, which are defined as candidate sequences; splice the current sequence with each candidate sequence to achieve sequence matching; assign a label to the matching sequence according to whether the current sequence and the spliced ​​candidate sequence belong to the same health status category; A model fine-tuning module, which is used to fine-tune the large language model using labeled matching sequences; The status assessment module is used to obtain the actual charging data of the battery cell to be tested, extract the general form of the charging sequence as the current sequence, perform sequence matching on the current sequence and each candidate sequence respectively, and obtain the evaluation category of the battery health status based on the matching sequence using a fine-tuned large language model.

[0015] In other embodiments, the following technical solutions are adopted: A terminal device includes a processor and a memory, wherein the processor is used to implement instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the above-mentioned battery health status assessment method based on large model and sequence matching.

[0016] In other embodiments, the following technical solutions are adopted: A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned battery health status assessment method based on large model and sequence matching.

[0017] Compared with the prior art, the present invention has the following beneficial effects: (1) Compared with the feature engineering used for aging feature extraction in the prior art, the present invention does not require manual feature extraction, but adopts charging sequence matching to replace traditional feature engineering. The large model input is a one-dimensional array that integrates voltage and charge amount, which alleviates the problem of poor applicability of state assessment methods caused by complex feature engineering and harsh preconditions, and does not require additional data processing and complicated calculation processes.

[0018] (2) The present invention neither relies on complete charge / discharge data nor requires the establishment of complex mathematical models and mechanism models. The mapping relationship between model input and output is established through data-driven and large model fine-tuning, thereby realizing health status assessment.

[0019] The present invention adopts a large model to replace the small deep learning / machine learning model. The large model can provide rich prior knowledge, wide applicability and excellent parallel processing efficiency, which solves the problems of low accuracy, poor generalization ability and overfitting caused by the small parameter scale of the small model.

[0020] (3) Compared with the existing state estimation method that uses health status floating-point numbers as state estimation results, the present invention uses the numerical range of battery health status instead of floating-point numbers as the state estimation result, avoiding the problem of reduced method confidence caused by outlier estimation values ​​in traditional estimation methods; it meets the actual engineering needs, and ordinary users do not need precise floating-point values ​​to judge battery performance; and five categories of numerical ranges are used to replace a large number of discrete floating-point values, which can provide users with more intuitive state evaluation results.

[0021] The present invention realizes charging sequence matching with the help of classification theory, abandons feature engineering, and obtains battery health status assessment results by matching sequences. There is no need to calculate feature quantities, which reduces the complexity of model processing. In addition, a current sequence can match multiple different candidate sequences to obtain multiple sample data, thereby expanding the number of samples and greatly improving the assessment performance while maintaining similar status assessment functions.

[0022] Other features and additional advantages of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a battery health status assessment method based on large model and sequence matching in an embodiment of the present invention; Figure 2 The health state decay curve of each battery cell in the public data set in the embodiment of the present invention; Figure 3 is a candidate sequence curve when the voltage range is [3.7V, 4V] in an embodiment of the present invention; Figure 4 The battery health status assessment result based on sequence matching and large model in an embodiment of the present invention; Figure 5 Schematic diagram of a battery health status assessment system based on large model and sequence matching in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0026] Embodiment 1 In one or more embodiments, a battery health status assessment method based on large model and sequence matching is disclosed, combined with Figure 1 , specifically including the following process: S101: Classify the battery health status according to the value range.

[0027] In this embodiment, the battery health status is divided into 5 categories from good to bad, including: 95%< SOH ≤100%, 90%< SOH ≤95%, 85%< SOH ≤90%, 80%< SOH ≤85% and SOH <80%.

[0028] The median thresholds for each battery health status category are then determined, which are: 97.5%, 92.5%, 87.5%, 82.5%, and 77.5%.

[0029] S102: Based on the historical charging data of the fragments, the voltage and the charging amount are integrated to construct a charging sequence in a general form.

[0030] In this embodiment, the charging data of the fragments comes from a public data set, which contains 181 cyclic charge and discharge test data of nickel-cobalt-manganese ternary lithium-ion battery cells, with a rated capacity of 2.5Ah, a charging current rate of 3C (7.5A), a test temperature of 25°C, and a number of cycle samples of 21720. Figure 2 The health status decay curve of each monomer in the public dataset is shown.

[0031] The complete charging data of each monomer in any cycle in the public dataset is randomly truncated to generate fragmented charging data. The first 91 monomers form the training set, and the remaining 90 form the test set.

[0032] The specific process of constructing a general form of charging sequence is as follows: Extract the original voltage sequence based on fragmented charging data V and charge sequence Q : ; in, n is the total number of charging data points, which is related to the sampling frequency; and Represent the voltage and charge amount of the nth charging data point respectively.

[0033] Coupling voltage sequences in the time dimension V and charge sequence Q , to construct a two-dimensional array E 0: ; Based on two-dimensional array E 0, by point-by-point differentiation to reduce the array dimension, and then construct a general form of charging sequence E 1: ; Among them, d Q / d V For point-by-point differentiation, i=1,2,…,n-1.

[0034] Both voltage and charge capacity are closely related to the electrochemistry, thermodynamics, and aging mechanisms of lithium-ion batteries, and are also parameters that can be recorded in ordinary battery management systems. The charging sequence obtained by coupling the two can reflect the battery characteristics to the greatest extent.

[0035] S103: Divide the battery cells of the historical charging data into test battery cells and known battery cells; extract a general charging sequence from the test battery cells and define it as a current sequence; extract multiple general charging sequences with a health state of a median threshold from the known battery cells and define them as candidate sequences.

[0036] In this embodiment, the first cell in the public data set in S102 is used as a known cell, and the remaining cells are used as test battery cells.

[0037] The charging sequence extracted from the charging data of the test battery cell is defined as the current sequence; the charging sequences when the health status of the known cells is the median threshold (97.5%, 92.5%, 87.5%, 82.5% and 77.5%) are extracted and defined as candidate sequences respectively. Figure 3 The candidate sequence curves for the voltage range [3.7V, 4V] are shown.

[0038] The candidate sequence is further truncated to make it consistent with the current sequence in voltage range. For example, the voltage range covered by the current sequence is [3.7V, 4.0V]. First, extract the complete candidate sequence, whose voltage range is approximately [2.8V, 4.2V]; second, extract the corresponding candidate sequence according to the voltage range of the current sequence, that is, truncate the candidate sequence; finally, obtain the candidate sequence with a voltage range of [3.7V, 4.0V].

[0039] This embodiment does not need to obtain the battery feature vector, but instead obtains a general form of charging sequence by constructing a one-dimensional array that integrates the voltage and the charge amount. The data acquisition is simple and convenient with high reliability. This alleviates the problem of poor applicability of the state assessment method due to complex feature engineering and harsh preconditions.

[0040] S104: Concatenate the current sequence with each candidate sequence to achieve sequence matching; assign a label to the matching sequence according to whether the current sequence and the concatenated candidate sequence belong to the same health status category.

[0041] In this embodiment, a label is assigned to the sequence matching. When the current sequence and the candidate sequence belong to the same health status category, the label is 1, otherwise it is 0.

[0042] This embodiment matches the current sequence with the candidate sequences, and matches one current sequence with five candidate sequences respectively, so as to obtain five sample data, expand the number of samples, improve the accuracy and reliability of model evaluation, and solve the problem of limited number of labeled data sets in traditional models.

[0043] S105: Fine-tune the large language model using the labeled matching sequence.

[0044] In this embodiment, based on the nonlinear characteristics of lithium-ion batteries, BERT-large is selected as the large model. The input of the large language model is multiple matching sequences, and the output is a label for each matching sequence. If the label of the matching sequence is 1, the current sequence and the candidate sequence in the matching sequence belong to the same health status category; finally, the battery health status assessment category of the current sequence is obtained.

[0045] For the BERT-large model, set the linear layer with an output dimension of 1 as the output module, set the cross entropy as the loss function, initialize the model parameters, and implement model loading.

[0046] Using the matching sequence in S104, the low-rank adaptation (LoRA) technology is applied to the attention head and output module in the model to perform multiple fine-tuning on the large language model. The low-rank matrix is ​​introduced to reduce the amount of parameter updates, thereby reducing the computing and storage costs. Multiple fine-tuning of the large language model can avoid the problem of inaccurate evaluation results caused by fluctuations in model performance.

[0047] This embodiment selects accuracy, recall, precision and F1 score as evaluation indicators, and calculates the evaluation indicators for the large language model obtained by each fine-tuning. Finally, the best large language model can be screened out according to the calculation results of the evaluation indicators. As a specific example, the model corresponding to the maximum F1 score can be selected as the best large language model.

[0048] In this embodiment, the original data set is labeled through sequence matching, and a total of 20,460 positive samples (labeled 1) and 82,710 negative samples (labeled 0) are generated, which significantly expands the number of samples compared to the original cycle samples of 21,720; BERT-large contains 24 Transformer encoder layers, the hidden state size is 1024, and the total number of parameters is 340 million; during the model fine-tuning process, the learning rate is 2e-5, the batch size is 64, the number of fine-tuning rounds is 5, the Dropout is 0.3, the gradient decay is 0.01, the learning rate strategy is linear decay, and the optimizer is AdamW.

[0049] S106: Acquire actual charging data of the battery cell to be tested, extract a general form of charging sequence as the current sequence, perform sequence matching on the current sequence and each candidate sequence respectively, and obtain the evaluation result of the battery health status based on the matching sequence using a fine-tuned large language model.

[0050] The specific implementation process is as follows: S1061: constructing a general charging sequence based on actual charging data as a current sequence; S1062: truncating the candidate sequence and concatenating the current sequence with each candidate sequence to achieve sequence matching; S1063: Input the matched sequence into the fine-tuned large language model, output the predicted label, and use the battery health status category corresponding to the candidate sequence in the matching sequence with label 1 as the battery health status assessment result of the battery cell to be tested.

[0051] The method of this embodiment uses the numerical range of the battery health status instead of the floating-point number as the status evaluation result, which can meet the requirements of most ordinary users for the battery health status evaluation results. At the same time, there is no need to calculate the battery characteristic quantity, which saves additional data processing and complicated calculation processes, and improves the evaluation efficiency.

[0052] As a specific verification example, actual charging data is selected from the test set. Figure 4 The battery health status assessment results based on sequence matching and large models are shown. It can be seen that 9937 out of 10068 positive samples were correctly identified, and 41158 out of 41232 negative samples were correctly identified. The overall accuracy rate reached 99.6%, the recall rate reached 98.7%, the precision rate reached 99.3%, and the F1 score reached 99.0%, which fully demonstrated the accuracy and reliability of the battery health status assessment results of the method in this embodiment.

[0053] Embodiment 2 In one or more embodiments, a battery health status assessment system based on large model and sequence matching is disclosed, combined with Figure 5, specifically including: A classification module is used to classify the battery health status into categories according to the numerical range and determine the median threshold of the battery health status of different categories; A charging sequence building module is used to build a general form of charging sequence based on fragmented historical charging data, integrating voltage and charging amount; The sequence matching module is used to divide the battery cells of the historical charging data into test battery cells and known battery cells; extract the general form of charging sequence from the test battery cells, which is defined as the current sequence; extract the general form of charging sequences with different median thresholds from the known battery cells, which are defined as candidate sequences; splice the current sequence with each candidate sequence to achieve sequence matching; assign a label to the matching sequence according to whether the current sequence and the spliced ​​candidate sequence belong to the same health status category; A model fine-tuning module, which is used to fine-tune the large language model using labeled matching sequences; The status assessment module is used to obtain the actual charging data of the battery cell to be tested, extract the general form of the charging sequence as the current sequence, perform sequence matching on the current sequence and each candidate sequence respectively, and obtain the evaluation category of the battery health status based on the matching sequence using a fine-tuned large language model.

[0054] It should be noted that the specific implementation methods of the above modules have been described in detail in Example 1 and will not be described in detail here.

[0055] Embodiment 3 In one or more embodiments, a terminal device is disclosed, which includes a processor and a memory, the processor is used to implement instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the battery health status assessment method based on large model and sequence matching described in Example 1.

[0056] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0057] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0058] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.

[0059] Embodiment 4 In one or more embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the battery health status assessment method based on large model and sequence matching described in Example 1.

[0060] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A battery health status assessment method based on large model and sequence matching, characterized in that: include: The battery health status is classified according to the numerical range, and the median threshold of the battery health status of different categories is determined; Based on the fragmented historical charging data, the voltage and charging amount are integrated to construct a general form of charging sequence; The battery cells of the historical charging data are divided into test battery cells and known battery cells; Extracting a general form of charging sequence from the test battery cell, which is defined as the current sequence; extracting a general form of charging sequence with different median thresholds from the known battery cells, which is defined as the candidate sequence; The current sequence is concatenated with each candidate sequence to achieve sequence matching; a label is assigned to the matching sequence according to whether the current sequence and the concatenated candidate sequence belong to the same health status category; Fine-tune the large language model using labeled matching sequences; The actual charging data of the battery cell to be tested is obtained, and a general charging sequence is extracted as the current sequence. The current sequence is matched with each candidate sequence respectively, and based on the matching sequence, a fine-tuned large language model is used to obtain an evaluation category of the battery health status.

2. A battery health status assessment method based on large model and sequence matching as claimed in claim 1, characterized in that: The battery health status is classified according to the numerical range, specifically: The battery health status is divided into 5 categories from good to bad, including: 95%< SOH ≤100%, 90%< SOH ≤95%, 85%< SOH ≤90%, 80%< SOH ≤85% and SOH <80%; Determine the median battery health threshold for each category.

3. A battery health status assessment method based on large model and sequence matching as claimed in claim 1, characterized in that: Construct a charging sequence of general form, specifically: Extract the original voltage sequence based on fragmented historical charging data V and charge sequence Q : ； Couple the voltage sequence described in the time dimension V and charging sequence Q , to construct a two-dimensional array E 0: ； Based on the two-dimensional array E 0, by point-by-point differentiation to reduce the array dimension, and then construct a general form of charging sequence E 1: ； in, n is the total number of charging data points, d Q / d V Represents point-by-point differentiation, i=1,2,…,n-1.

4. A battery health status assessment method based on large model and sequence matching as claimed in claim 1, characterized in that: The current sequence is concatenated with each candidate sequence to achieve sequence matching, specifically: A voltage range of the current sequence is determined, and a complete candidate sequence is truncated based on the voltage range, and candidate sequence data within the voltage range is retained.

5. The battery health status assessment method based on large model and sequence matching according to claim 1, characterized in that: Fine-tune the large language model using labeled matching sequences, specifically: Select BERT-large as the large language model, apply low-rank adaptation technology to the attention head and output module in the model, and use matching sequences to fine-tune the large language model multiple times; The input of the large language model is multiple matching sequences, and the output is a label for each matching sequence. If the label of the matching sequence is 1, the current sequence and the candidate sequence in the matching sequence belong to the same health status category; finally, the battery health status assessment category of the current sequence is obtained.

6. A battery health status assessment method based on large model and sequence matching as claimed in claim 1, characterized in that: The large language model is fine-tuned multiple times using labeled matching sequences, and the large language model obtained through each fine-tuning is evaluated using evaluation indicators to select the best large language model.

7. A battery health status assessment method based on large model and sequence matching as claimed in claim 1, characterized in that: The actual charging data of the battery cell to be tested is obtained, and the evaluation results of the battery health status are obtained by using the fine-tuned large language model, which are as follows: Based on the actual charging data, a general form of charging sequence is constructed as the current sequence; The candidate sequences are truncated and the current sequence is concatenated with each candidate sequence to achieve sequence matching; The matched sequence is input into the fine-tuned large language model, and the predicted label is output. The battery health status category corresponding to the candidate sequence in the matching sequence with label 1 is used as the battery health status assessment result of the battery cell to be tested.

8. A battery health status assessment system based on large model and sequence matching, characterized in that: include: A classification module is used to classify the battery health status into categories according to the numerical range and determine the median threshold of the battery health status of different categories; A charging sequence building module is used to build a general form of charging sequence based on fragmented historical charging data, integrating voltage and charging amount; The sequence matching module is used to divide the battery cells of the historical charging data into test battery cells and known battery cells; extract the general form of charging sequence from the test battery cells, which is defined as the current sequence; extract the general form of charging sequences with different median thresholds from the known battery cells, which are defined as candidate sequences; splice the current sequence with each candidate sequence to achieve sequence matching; assign a label to the matching sequence according to whether the current sequence and the spliced ​​candidate sequence belong to the same health status category; A model fine-tuning module, which is used to fine-tune the large language model using labeled matching sequences; The status assessment module is used to obtain the actual charging data of the battery cell to be tested, extract the general form of the charging sequence as the current sequence, perform sequence matching on the current sequence and each candidate sequence respectively, and obtain the evaluation category of the battery health status based on the matching sequence using a fine-tuned large language model.

9. A terminal device, comprising a processor and a memory, wherein the processor is used to implement instructions; and the memory is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the battery health status assessment method based on large model and sequence matching as described in any one of claims 1-7.

10. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the battery health status assessment method based on large model and sequence matching as described in any one of claims 1-7.

Images