Lithium ion battery thermal runaway early warning method for fast charging scene

Abstract

The invention discloses a lithium ion battery thermal runaway early warning method for a fast charging scene. The method comprises the following steps: constructing an electrochemical-thermal coupling model and a battery thermal runaway decomposition heating model, fusing to obtain a thermal runaway mechanism model, simulating thermal runaway data, and forming a deep learning training data set; a battery thermal runaway experiment is designed and developed based on a real battery fast charging scene, and a machine learning training data set composed of experiment data is obtained; constructing a thermal runaway early warning model which comprises a deep learning model and a machine learning model, training the deep learning model based on the deep learning training data set, and training the machine learning model based on the machine learning training data set; and multi-element features are obtained under the battery fast charging working condition, prediction results of the deep learning model and the machine learning model are fused, and a lithium ion battery thermal runaway early warning result is output. The method is applied to the field of energy storage management, and early warning of thermal runaway of the lithium ion battery is realized in combination with fusion of multi-dimensional parameters and multivariate characteristic signals.

Description

Technical Field

[0001] The present invention relates to the field of energy storage management technology, and in particular to a lithium-ion battery thermal runaway early warning method for fast charging scenarios. Background Art

[0002] Energy storage systems are divided into two types: fixed energy storage and mobile energy storage. Fixed energy storage is mainly used for energy storage power stations for life support and uninterruptible power supply for some key facilities. This type of energy storage system can be placed indoors to provide a certain degree of insulation. Mobile energy storage is mainly for outdoor application scenarios, mainly used for general starting power supply for low-temperature starting or low-power starting of vehicles, communication power supply for communication equipment, and portable power supply, etc.

[0003] Considering the diverse forms and wide distribution of energy storage systems, the safety of energy storage systems has become a major hidden danger. In this regard, through research on key technologies related to fault diagnosis and safety warning methods of lithium-ion batteries, the changing laws of early physical parameters of thermal runaway of energy storage lithium-ion batteries over the entire life cycle and wide temperature range, as well as the sporadic occurrence of special behaviors (such as gas discharge and pressure changes) are explored. Combined with multi-sensor analysis of characteristic signals before the triggering of battery thermal runaway, a lithium-ion battery thermal runaway occurrence model is constructed, and an accurate lithium-ion battery thermal runaway warning method is proposed to reduce the risk of lithium-ion battery explosion and extend the operating life of the energy storage system, which has extremely critical application value.

[0004] During long-term use, aging and consistency degradation of lithium-ion batteries are inevitable phenomena. These degradation problems may cause single-cell battery overheating, overcharging, and even thermal runaway events. Thermal runaway may not only occur within a single battery cell, but can also easily spread within the energy storage cabinet and between battery packs. Battery thermal runaway occurs very quickly and is often difficult to predict in advance, making it difficult for energy storage system managers to obtain reliable early warning signals before thermal runaway occurs, thus posing serious safety hazards.

[0005] The main causes of thermal runaway of lithium-ion batteries can be divided into: mechanical abuse, such as puncture or extrusion, which may cause short circuits and heat accumulation in the battery; thermal abuse, which may cause the internal diaphragm to melt; electrical abuse, such as fast charging, overcharging or over-discharging, which may form dendrites inside the battery and increase the risk of diaphragm penetration. All of these situations may cause internal short circuits in the battery, thereby inducing thermal runaway.

[0006] At present, researchers at home and abroad have explored various routes for battery thermal runaway warning strategies, taking the evolution of related signals such as temperature, gas, impedance, voltage, pressure, etc. as the research object, and combining advanced machine learning methods to provide early warning of thermal runaway. The mainstream research methods can be roughly divided into the following three categories: the first category is to monitor the changes in key physical parameters or characteristic information of the battery, and issue warnings after capturing the information of interest. It can be divided into multiple levels of warnings according to the complexity or confidence of the information; the second category is data-driven thermal runaway warning methods; the third category is model-based thermal runaway warning methods.

[0007] In current research, thermal runaway early warning methods mainly rely on the detection of a single signal, but this method is susceptible to noise interference, insufficient detection accuracy, and other faults. Therefore, in order to improve the reliability of thermal runaway early warning, it is necessary to develop an early warning strategy that comprehensively considers the synergy of multiple signals. Whether it is a model-based approach or a data-driven approach, the core of early thermal runaway warning is to monitor abnormal changes in characteristic parameters through data collected by the BMS, thereby providing more time to deal with thermal runaway problems. Summary of the invention

[0008] In view of the shortcomings of the lithium-ion battery thermal runaway warning strategy in the above-mentioned prior art, such as lack of mechanism model support, reliance on single or a small number of features, narrow applicability, and unclear warning targets, the present invention provides a lithium-ion battery thermal runaway warning method for fast charging scenarios. For fast charging scenarios, based on the fact that high-rate charging will cause accelerated decay of battery performance such as capacity and output power, and the large amount of heat generated during charging is difficult to dissipate evenly and effectively, which will also induce battery degradation and reduced safety, the early warning of lithium-ion battery thermal runaway is achieved by combining the fusion of multi-dimensional parameters and multi-dimensional feature signals.

[0009] To achieve the above object, the present invention provides a lithium-ion battery thermal runaway early warning method for fast charging scenarios, comprising the following steps: Step 1, constructing an electrochemical-thermal coupling model under normal operating conditions of the battery and a battery thermal runaway decomposition temperature rise model under thermal runaway conditions; Step 2, integrating the electrochemical-thermal coupling model with the battery thermal runaway decomposition and temperature rise model to obtain a thermal runaway mechanism model, and simulating thermal runaway data of batteries in different states based on the thermal runaway mechanism model to form a deep learning training data set; Step 3: Conduct a battery thermal runaway experiment based on a real battery fast charging scenario, and measure multi-dimensional features during the experiment to obtain a machine learning training data set composed of experimental data; Step 4, constructing a thermal runaway warning model, wherein the thermal runaway warning model includes multiple deep learning models and multiple machine learning models, and training the deep learning model based on the deep learning training data set, and training the machine learning model based on the machine learning training data set; Step 5, obtain its multivariate features under the battery fast charging condition, and input the trained thermal runaway warning model, and after fusing the prediction results of each of the deep learning models and each of the machine learning models, output the thermal runaway warning result of the lithium-ion battery.

[0010] In one embodiment, in step 1, the electrochemical-thermal coupling model adopts a combination of a Newman model or a pseudo-two-dimensional model and a solid heat transfer model, and a mixed power pulse characteristic condition is used for parameter identification; The battery thermal runaway decomposition and heating model adopts the Hatchard decomposition and heating model, and the parameters of the model are identified using the battery adiabatic thermal runaway data tested by an adiabatic calorimeter.

[0011] In one embodiment, in step 2, the electrochemical-thermal coupling model is integrated with the battery thermal runaway decomposition temperature rise model to obtain a thermal runaway mechanism model, specifically: The boundary of the electrochemical-thermal coupling model is expanded, and its applicable temperature boundary is expanded to the starting temperature point of the thermal runaway process of the Hatchard decomposition and heating model, that is, the internal physical parameters of the electrochemical-thermal coupling model are used as the initial state parameters of the Hatchard decomposition and heating model to simulate the thermal runaway process.

[0012] In one embodiment, the feature data in the deep learning training data set includes voltage, current, capacity, temperature and internal physical parameters of the battery; The characteristic data in the machine learning training data set include voltage, temperature, impedance, gas composition and expansion force change characteristic signals of the battery.

[0013] In one embodiment, the input data of the deep learning model includes the voltage, current, capacity, temperature and internal physical parameters of the battery, and the output is the result of whether the battery is in thermal runaway; The input data of the machine learning model includes the battery's voltage, temperature, impedance, gas composition, and expansion force change characteristic signals, and the output is the result of whether the battery is in thermal runaway.

[0014] In one of the embodiments, in both the deep learning model and the machine learning model, a temperature point at which the temperature rise rate is higher than 1°C / s and lasts for more than 3s is used as a battery thermal runaway label.

[0015] In one embodiment, step 5 is specifically: Acquire multivariate characteristics of the battery under fast charging conditions, wherein the multivariate characteristics include voltage, current, capacity, temperature, internal physical parameters, impedance, gas composition, and expansion force change characteristic signals of the battery; Inputting the voltage, current, capacity, temperature and internal physical parameters of the battery in the multivariate features into each trained deep learning model, and obtaining the prediction results of each deep learning model; Inputting the voltage, temperature, impedance, gas composition and expansion force change characteristic signals of the battery in the multivariate characteristics into each trained machine learning model, and obtaining the prediction results of each machine learning model; The prediction results of each of the deep learning models and each of the machine learning models on whether the battery is in thermal runaway are combined, and the larger item is output as the final lithium-ion battery thermal runaway warning result.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: 1. Compared with the previous methods that only rely on single-dimensional features or manually annotated warning signals, the present invention extracts and builds models through joint multi-features in the information-physical domain, and uses an integrated learning strategy to fuse the base models to build a thermal runaway warning model, which can achieve early and effective warning of thermal runaway of lithium-ion batteries; 2. The present invention combines the mechanism model of the whole process of battery thermal runaway evolution, triggers from the underlying principle of fast charging-induced thermal runaway, integrates multiple base models trained by the thermal runaway simulation label data set containing multi-features and the thermal runaway experimental data set to form an integrated learning framework, which greatly improves the robustness of early warning judgment of thermal runaway; 3. The present invention can make a current thermal runaway warning judgment on the battery based on the offline trained thermal runaway warning model and the current fast charging condition battery operation data containing multi-element characteristic signals, and has strong practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0018] Figure 1 This is a flow chart of a lithium-ion battery thermal runaway early warning method for fast charging scenarios in an embodiment of the present invention; Figure 2 is a flow chart for constructing a thermal runaway mechanism model in an embodiment of the present invention; Figure 3 This is a flowchart of early multivariate feature extraction of thermal runaway in the information-physical domain combination according to an embodiment of the present invention; Figure 4 This is a flow chart of building and training a thermal runaway warning model in an embodiment of the present invention; Figure 5 This is a flow chart of early warning of thermal runaway for fast charging in an embodiment of the present invention.

[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0022] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0023] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, a physical connection, or a wireless communication connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0025] In view of the problems that the existing thermal runaway warning strategy of lithium-ion batteries lacks the support of mechanism models, relies on single or a small number of features, has narrow applicability, and the warning target is not clear enough, this embodiment discloses a thermal runaway warning method for lithium-ion batteries in fast charging scenarios. By integrating conventional electrochemical models, classical thermal models, and the Hatchard electrochemical decomposition and heating model after reaching a certain temperature threshold, a thermal runaway mechanism model that can describe the whole process of thermal runaway caused by fast charging is constructed. At the same time, the fast charging-induced thermal runaway experiment in real scenarios is designed to parameterize and verify the constructed thermal runaway mechanism model, and in this process, a variety of characteristic signal measurements are performed to obtain a physical experimental data set with multivariate features. Subsequently, the simulation data set obtained from the thermal runaway mechanism model is used to train the deep learning model, and the machine learning model is trained by a small sample physical experimental data set, and these base models are combined to form an integrated learning framework to complete the construction of the thermal runaway warning model. By introducing the multivariate feature information of the early stage of thermal runaway, the integrated learning method composed of multiple warning models greatly improves the early warning time of thermal runaway of lithium-ion batteries in fast charging scenarios, and improves the accuracy of warning.

[0026] refer to Figure 1 In this embodiment, the lithium-ion battery thermal runaway warning method for fast charging scenarios specifically includes the following steps: Step 1, constructing an electrochemical-thermal coupling model under normal operating conditions of the battery and a battery thermal runaway decomposition temperature rise model under thermal runaway conditions; Step 2: The electrochemical-thermal coupling model is integrated with the battery thermal runaway decomposition and temperature rise model to obtain a thermal runaway mechanism model, and thermal runaway data of batteries in different states are simulated based on the thermal runaway mechanism model to form a deep learning training data set; Step 3: Conduct a battery thermal runaway experiment based on a real battery fast charging scenario, and measure multi-dimensional features during the experiment to obtain a machine learning training data set composed of experimental data; Step 4: construct a thermal runaway warning model, which includes multiple deep learning models and multiple machine learning models, and train the deep learning model offline based on the deep learning training data set, and train the machine learning model offline based on the machine learning training data set; Step 5: Obtain the multivariate features of the battery under fast charging conditions, input them into the trained thermal runaway warning model, integrate the prediction results of each deep learning model and each machine learning model, and output the thermal runaway warning result of the lithium-ion battery.

[0027] Current thermal runaway warning research and practical applications lack the construction of a battery model for the early stages of thermal runaway development. In addition, the fusion of the underlying electrochemical model during normal battery operation and the thermal runaway process model during thermal runaway has not yet been effectively studied. To this end, this embodiment describes the entire process of fast charging-induced thermal runaway by constructing a mechanism model for the battery to develop from a normal operating state in the early stages of thermal runaway to a thermal runaway state and effectively integrating multiple models.

[0028] In this embodiment, the electrochemical-thermal coupling model adopts the form of a combination of the Newman model or a pseudo-two-dimensional model and a solid heat transfer model, and uses a mixed power pulse characteristic working condition for parameter identification. The battery thermal runaway decomposition and heating model adopts the Hatchard decomposition and heating model, and the battery adiabatic thermal runaway data tested by an adiabatic calorimeter is used to identify the parameters of the model. Among them, the parameter identification method can adopt conventional particle swarm optimization, nonlinear least squares method or other intelligent optimization algorithms. Before performing parameter identification, sensitivity analysis can also be used to identify the parameters that have the greatest impact on the model output, so as to determine which parameters need to be identified and their identification order.

[0029] refer to Figure 2 The electrochemical-thermal coupling model is integrated with the battery thermal runaway decomposition and heating model to obtain the thermal runaway mechanism model. Specifically, the boundary of the electrochemical-thermal coupling model considering the internal physical parameters is expanded, and its applicable temperature boundary is expanded to the starting temperature point of the thermal runaway process of the Hatchard decomposition and heating model. That is, the internal physical parameters of the electrochemical-thermal coupling model (such as the concentration of each material component) are used as the initial state parameters of the Hatchard decomposition and heating model to simulate the thermal runaway process.

[0030] In this embodiment, the deep learning training data set obtained through simulation and the machine learning training data set obtained through actual experiments jointly complete the training of the thermal runaway warning model, realizing the information-physical domain combination, which can greatly improve the robustness of the warning judgment of thermal runaway.

[0031] refer to Figure 3, for the generation of thermal runaway simulation label data sets, this embodiment uses the Monte Carlo sampling method to generate a large number of thermal runaway simulation curves of batteries in various states within a given variable parameter range, and uses the temperature rise rate dT / dt ≥ 1℃ / s and the temperature point that lasts for more than 3s as the battery thermal runaway label, wherein the characteristic data in the thermal runaway simulation label data set include the battery's voltage, current, capacity, temperature and internal physical parameters. It is worth noting that the Monte Carlo method is used in this embodiment to ensure the uniformity of sample distribution when the number of samples is small, but in the specific application process, it is not limited to sampling using only the Monte Carlo method, and direct random sampling and other sampling methods can be applied. For the generation of thermal runaway experimental label data sets, it is mainly to collect multiple characteristic signals of the battery in the real scene thermal runaway experiment, wherein the characteristic data in the thermal runaway experiment label data set include the battery's voltage, temperature, impedance, gas composition and expansion force change characteristic signals.

[0032] After the thermal runaway simulation label data set and the thermal runaway experiment label data set are generated, the multi-dimensional features of the thermal runaway simulation label data set and the thermal runaway experiment label data set can be subjected to feature screening. This embodiment uses the Kullback-Leibler (KL) test method to perform normal distribution and difference tests on the extracted features to screen out features that can effectively associate with the thermal runaway state, thereby forming a deep learning training data set and a machine learning training data set that are ultimately used for early warning model training. Through this feature screening process, the effectiveness of the selected features in subsequent analysis is ensured, the algorithm efficiency is improved, and the accuracy and reliability of the model are improved. It is worth noting that in the specific application process, it is not limited to using only the Kullback-Leibler (KL) test method for feature screening, and Pearson and Spearman correlation coefficients and other feature screening methods can also be used.

[0033] The thermal runaway warning model in this embodiment is composed of multiple deep learning models and multiple machine learning models. Among them, for the construction and training of the deep learning model, the time series historical input data features in the deep learning training data set are extracted through a neural network and the nonlinearity and long-term dependencies of the data are processed. The corresponding loss function is used to calculate the loss between the network output and the true label, and the model parameters are adjusted through the back propagation algorithm to gradually reduce the loss. Since the feature dimension of the thermal runaway experimental label data in the machine learning training data set is higher and the samples are fewer, this embodiment adopts a binary classification machine learning model, and optimizes the model evaluation performance by selecting a suitable optimizer (such as SGD, Adam, etc.) and adjusting the model hyperparameters (such as learning rate, regularization parameter, tree depth, etc.).

[0034] After completing the training of all deep learning models and machine learning models, the prediction results of each base model can be combined to obtain the final lithium-ion battery thermal runaway warning result. Among them, the fusion method can be simple (such as averaging, weighted average, voting) or complex (such as learned combinations). Use the test set to evaluate the final integrated model and calculate indicators such as accuracy, precision, recall, and F1 score. According to the evaluation results, it may be necessary to return to the model training stage and further adjust the base model or integration strategy to obtain better performance. It should be noted that common integrated learning strategies, including but not limited to Bagging, Boosting, and Stacking, three major families of algorithms and their sub-algorithms, are applicable to the method of this embodiment.

[0035] refer to Figure 5 In this embodiment, the process of using the trained thermal runaway warning model to warn the lithium-ion battery about thermal runaway is specifically as follows: First, the multivariate characteristics of the battery are obtained under fast charging conditions. The multivariate characteristics include the battery's voltage, current, capacity, temperature, internal physical parameters, impedance, gas composition, and expansion force change characteristic signals. Then, the voltage, current, capacity, temperature and internal physical parameters of the battery in the multivariate features are respectively input into each trained deep learning model, and the prediction results of each deep learning model are obtained; At the same time, the voltage, temperature, impedance, gas composition and expansion force change characteristic signals of the battery in the multivariate features are respectively input into each trained machine learning model, and the prediction results of each machine learning model are obtained; Finally, the prediction results of each deep learning model and each machine learning model on whether the battery is in thermal runaway are combined, and the item with the larger number is output as the final lithium-ion battery thermal runaway warning result, that is, the prediction results of all models are integrated by the voting method.

[0036] It is worth noting that although this embodiment Figures 1 to 5 The steps in the process are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps can be executed in other orders. Figures 1 to 5 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0037] The above description is only a preferred embodiment of the present invention, and does not limit the protection scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the protection scope of the present invention.

Claims

1. A lithium-ion battery thermal runaway early warning method for fast charging scenarios, characterized in that: The steps include: Step 1, constructing an electrochemical-thermal coupling model under normal operating conditions of the battery and a battery thermal runaway decomposition temperature rise model under thermal runaway conditions; Step 2, integrating the electrochemical-thermal coupling model with the battery thermal runaway decomposition and temperature rise model to obtain a thermal runaway mechanism model, and simulating thermal runaway data of batteries in different states based on the thermal runaway mechanism model to form a deep learning training data set; Step 3: Conduct a battery thermal runaway experiment based on a real battery fast charging scenario, and measure multi-dimensional features during the experiment to obtain a machine learning training data set composed of experimental data; Step 4, constructing a thermal runaway warning model, wherein the thermal runaway warning model includes multiple deep learning models and multiple machine learning models, and training the deep learning model based on the deep learning training data set, and training the machine learning model based on the machine learning training data set; Step 5, obtain its multivariate features under the battery fast charging condition, and input the trained thermal runaway warning model, and after fusing the prediction results of each of the deep learning models and each of the machine learning models, output the thermal runaway warning result of the lithium-ion battery.

2. The lithium-ion battery thermal runaway early warning method for fast charging scenarios according to claim 1, characterized in that: In step 1, the electrochemical-thermal coupling model adopts a combination of a Newman model or a pseudo two-dimensional model and a solid heat transfer model, and uses a mixed power pulse characteristic working condition for parameter identification; The battery thermal runaway decomposition and heating model adopts the Hatchard decomposition and heating model, and the parameters of the model are identified using the battery adiabatic thermal runaway data tested by an adiabatic calorimeter.

3. The lithium-ion battery thermal runaway early warning method for fast charging scenarios according to claim 2, characterized in that: In step 2, the electrochemical-thermal coupling model is integrated with the battery thermal runaway decomposition temperature rise model to obtain a thermal runaway mechanism model, specifically: The boundary of the electrochemical-thermal coupling model is expanded, and its applicable temperature boundary is expanded to the starting temperature point of the thermal runaway process of the Hatchard decomposition and heating model, that is, the internal physical parameters of the electrochemical-thermal coupling model are used as the initial state parameters of the Hatchard decomposition and heating model to simulate the thermal runaway process.

4. The lithium-ion battery thermal runaway early warning method for fast charging scenarios according to claim 1, 2 or 3, characterized in that: The characteristic data in the deep learning training data set include the voltage, current, capacity, temperature and internal physical parameters of the battery; The characteristic data in the machine learning training data set include voltage, temperature, impedance, gas composition and expansion force change characteristic signals of the battery.

5. The lithium-ion battery thermal runaway early warning method for fast charging scenarios according to claim 4, characterized in that: The input data of the deep learning model includes the voltage, current, capacity, temperature and internal physical parameters of the battery, and the output is the result of whether the battery is in thermal runaway; The input data of the machine learning model includes the battery's voltage, temperature, impedance, gas composition, and expansion force change characteristic signals, and the output is the result of whether the battery is in thermal runaway.

6. The lithium-ion battery thermal runaway early warning method for fast charging scenarios according to claim 5, characterized in that: In both the deep learning model and the machine learning model, the temperature point at which the temperature rise rate is higher than 1°C / s and lasts for more than 3s is used as a battery thermal runaway label.

7. The lithium-ion battery thermal runaway early warning method for fast charging scenarios according to claim 5, characterized in that: Step 5 is as follows: Obtain the multi-dimensional characteristics of the battery under fast charging conditions. The multivariate characteristics include voltage, current, capacity, temperature, internal physical parameters, impedance, gas composition and expansion force change characteristic signals of the battery; Inputting the voltage, current, capacity, temperature and internal physical parameters of the battery in the multivariate features into each trained deep learning model, and obtaining the prediction results of each deep learning model; Inputting the voltage, temperature, impedance, gas composition and expansion force change characteristic signals of the battery in the multivariate characteristics into each trained machine learning model, and obtaining the prediction results of each machine learning model; The prediction results of each of the deep learning models and each of the machine learning models on whether the battery is in thermal runaway are combined, and the larger item is output as the final lithium-ion battery thermal runaway warning result.

Images