Lithium ion battery fire prediction and control method, equipment and medium

By extracting and analyzing the operation and environmental data of lithium-ion batteries, using machine learning algorithms to identify fire risks and control the power outage of solenoid valves, the limitations of fire prediction and suppression of lithium-ion batteries in the prior art are solved, and the further development of the new technology is achieved. Accurate fire warning and quick response.

CN119087227APending Publication Date: 2024-12-06PEOPLES POLICE UNIV OF CHINA (INT LAW ENFORCEMENT COOP INST OF THE MINISTRY OF PUBLIC SECURITY CHINA PEACEKEEPING POLICE TRAINING CENT)
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411238775.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing fire prevention measures for lithium-ion batteries are mainly passive protection. They fail to provide effective early warning and active suppression before the fire occurs, which has great limitations. How to effectively predict and suppress lithium-ion battery fires has become the focus and difficulty of research.

Method used

By obtaining the operating data and environmental data of lithium-ion batteries, feature extraction and merging are carried out, the operation feature database is constructed, the battery evaluation model is determined using machine learning algorithms, and the abnormality detection algorithm is used to identify batteries that deviate from the normal range, and the solenoid valve is opened and disconnected. Electricity is used to suppress fires.

Benefits of technology

It realizes early prediction and early warning of the fire risk of lithium-ion batteries, improves battery usage safety, significantly improves response speed and timeliness, and can prevent fires from occurring at the source.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119087227A_ABST
    Figure CN119087227A_ABST
Patent Text Reader

Abstract

The invention discloses a lithium ion battery fire prediction and control method and device and a medium, and relates to the field of battery monitoring, the method comprises the following steps: carrying out feature extraction on operation data and environmental data in a battery module, and merging the extracted features in time and space sequences; determining a battery evaluation model by adopting a machine learning algorithm according to the constructed lithium ion battery operation characteristic database; performing evaluation by using the battery evaluation model; according to an evaluation result, identifying the lithium ion battery deviating from a normal range by adopting an anomaly detection algorithm; and continuously monitoring the to-be-monitored object, when an evaluation result deviates from a normal range and exceeds a set threshold value, giving an alarm, controlling an electromagnetic valve in the lithium battery fire suppression device to be opened, and powering off the lithium ion battery. The thermal runaway fire risk of the battery can be predicted in real time, intervention measures are taken in advance, and the use safety of the lithium ion battery is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of battery monitoring, and in particular to a lithium-ion battery fire prediction and control method, device and medium. Background Art

[0002] The safety of lithium-ion batteries is mainly manifested in the problem of thermal runaway. During the operation of the battery, if it is affected by factors such as overcharging, over-discharging, short circuit, external impact, etc., it may cause a sharp rise in temperature, which in turn causes electrolyte decomposition and increased internal pressure, and may eventually cause the battery to burn or even explode. Especially in electric vehicles and large-scale energy storage systems, the number of batteries is huge. Once a fire occurs, it may cause huge property losses and casualties. Therefore, how to effectively predict and suppress lithium-ion battery fires has become the focus and difficulty of current research.

[0003] Existing lithium-ion battery fire prevention measures mainly include physical protection (such as thermal insulation materials), chemical protection (such as fire-retardant additives) and electrical protection (such as power-off measures). However, these methods are usually passive protection measures. Although they can reduce the probability of fire to a certain extent, they fail to provide effective warning and active suppression before the fire occurs, and have great limitations.

[0004] Therefore, based on the above problems, there is an urgent need to provide a lithium-ion battery fire prediction and control method, aiming to achieve early prediction and warning of battery fire risks. Summary of the invention

[0005] The purpose of this application is to provide a lithium-ion battery fire prediction and control method, device and medium, which can predict the thermal runaway fire risk of the battery in real time and take intervention measures in advance to improve the safety of lithium-ion battery use.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a lithium-ion battery fire prediction and control method, the lithium-ion battery fire prediction and control method comprising:

[0008] Obtaining operating data and environmental data in the battery module during a lithium-ion battery fire event; the operating data includes: temperature, voltage, current, humidity, pressure, charge, internal resistance, number of cycles, and thermal runaway characteristic gases in the battery module; the environmental data includes: ambient temperature, ambient humidity, ambient pressure, wind speed, and air pressure;

[0009] Extract features from the operating data and environmental data in the battery module, and merge the extracted features in time and space sequences;

[0010] constructing a lithium-ion battery operation characteristic database based on the combined characteristics;

[0011] Based on the lithium-ion battery operation characteristic database, a battery evaluation model is determined using a machine learning algorithm;

[0012] Use the battery evaluation model to evaluate the operating data and environmental data in the battery module;

[0013] According to the evaluation results, an abnormal detection algorithm is used to identify lithium-ion batteries that deviate from the normal range; and the identified lithium-ion batteries are used as objects to be monitored;

[0014] The monitored object continues to be monitored. When the evaluation result determined based on the operating data in the battery module of the monitored object and the environmental data deviates from the normal range and exceeds the set threshold, an alarm is issued, the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve.

[0015] Optionally, the obtaining of operating data and environmental data in the battery module in the lithium-ion battery fire event specifically includes:

[0016] Use the battery management system to obtain the operating data in the battery module;

[0017] Use the meteorological platform to obtain environmental data.

[0018] Optionally, the step of obtaining the operating data and environmental data in the battery module in the lithium-ion battery fire event further includes:

[0019] The operating data and environmental data in the battery module are preprocessed; the preprocessing includes: data filtering, data cleaning, missing value processing, outlier processing and standardization processing.

[0020] Optionally, the machine learning algorithms include: random forest algorithm, support vector machine, back propagation neural network, gradient boosting tree, dynamic deep learning and K-nearest neighbor algorithm.

[0021] Optionally, the anomaly detection algorithm is an isolation forest algorithm.

[0022] In a second aspect, the present application provides a lithium-ion battery fire prediction and control device, the lithium-ion battery fire prediction and control device comprising:

[0023] A data acquisition module is used to acquire operating data and environmental data in the battery module in the event of a lithium-ion battery fire; the operating data includes: temperature, voltage, current, humidity, pressure, charge, internal resistance, number of cycles and thermal runaway characteristic gases in the battery module; the environmental data includes: ambient temperature, ambient humidity, ambient pressure, wind speed and air pressure;

[0024] A feature processing module is used to extract features from the operating data and environmental data in the battery module and merge the extracted features in time and space sequences;

[0025] A lithium-ion battery operation characteristic database establishment module is used to construct a lithium-ion battery operation characteristic database according to the combined characteristics;

[0026] A battery evaluation model determination algorithm, which is used to determine a battery evaluation model using a machine learning algorithm based on a lithium-ion battery operation characteristic database;

[0027] An evaluation model, used to evaluate operating data and environmental data in a battery module using a battery evaluation model;

[0028] The module for determining the pair to be monitored is used to identify the lithium-ion batteries that deviate from the normal range by using an abnormality detection algorithm according to the evaluation results; and the identified lithium-ion batteries are used as the objects to be monitored;

[0029] The fire risk prediction and control module is used to continue monitoring the monitored object. When the evaluation result determined based on the operating data in the battery module of the monitored object and the environmental data deviates from the normal range and exceeds the set threshold, an alarm is issued, and the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve.

[0030] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the lithium-ion battery fire prediction and control method.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the lithium-ion battery fire prediction and control method when executed by a processor.

[0032] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0033] The present application provides a lithium-ion battery fire prediction and control method, device and medium, which extracts features from the operating data and environmental data in the battery module, merges the extracted features in time and space sequences, and extracts features by combining multi-source data and multi-dimensional data; and uses the merged features to build a lithium-ion battery operating feature database, and then uses a machine learning algorithm to determine the battery evaluation model to improve the accuracy and real-time performance of fire prediction. When an alarm is triggered, the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off. On the basis of predicting the fire risk, the preset emergency response mechanism is started in combination with intelligent control technology to prevent the occurrence of fire from the source. The present application can provide a more comprehensive and accurate battery status assessment, predict the thermal runaway fire risk of the battery in real time, issue early warnings in a timely manner, take intervention measures in advance, and significantly improve the response speed and timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 This is an application environment diagram of a lithium-ion battery fire prediction and control method in one embodiment of the present application;

[0036] Figure 2 A schematic diagram of a flow chart of a lithium-ion battery fire prediction and control method provided in one embodiment of the present application;

[0037] Figure 3 A schematic diagram of an environment corresponding to a lithium-ion battery fire prediction and control method provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0040] The lithium-ion battery fire prediction and control method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the operating data and environmental data in the battery module to be processed to the server 104. After the server 104 receives the operating data and environmental data in the battery module to be processed, the server 104 evaluates the operating data and environmental data in the battery module to be processed based on the battery evaluation model; according to the evaluation results, the abnormal detection algorithm is used to identify the lithium-ion battery that deviates from the normal range; and the identified lithium-ion battery is used as the object to be monitored; the object to be monitored continues to be monitored, and when the evaluation result determined according to the operating data and environmental data in the battery module of the object to be monitored deviates from the normal range and exceeds the set threshold, an alarm is issued, and the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve. The server 104 can feed back the obtained evaluation results to the terminal 102. In addition, in some embodiments, the lithium-ion battery fire prediction and control method can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly process the operating data and environmental data in the battery module to be processed, or the server 104 can obtain the operating data and environmental data in the battery module to be processed from the data storage system, and process the operating data and environmental data in the battery module to be processed.

[0041] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0042] In an exemplary embodiment, Figure 2 and Figure 3 As shown, a lithium-ion battery fire prediction and control method is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following S201 to S207. Among them:

[0043] S201, obtaining operating data and environmental data in the battery module in the lithium-ion battery fire event; the operating data includes: temperature, voltage, current, humidity, pressure, charge, internal resistance, number of cycles and thermal runaway characteristic gas in the battery module; the environmental data includes: ambient temperature, ambient humidity, ambient pressure, wind speed and air pressure;

[0044] S201 specifically includes:

[0045] Use the Battery Management System (BMS) to obtain the operating data in the battery module;

[0046] Use the meteorological platform to obtain environmental data. The meteorological platform is connected to the battery evaluation model through an API;

[0047] The data collection time interval is 100ms, and the data collection sensors are set on the battery cells and modules, and all levels monitor the regular operation data in an all-round way. The sensors used in this application include temperature sensors, voltage sensors, current sensors, smoke sensors, etc.

[0048] S201 and later also include:

[0049] The operating data and environmental data in the battery module are preprocessed; the preprocessing includes: data filtering, data cleaning, missing value processing, outlier processing and standardization processing.

[0050] Among them, using the formula The collected running data is Z-score standardized; where x is the original data point, μ and σ are the mean and standard deviation respectively. After the data is preprocessed, the sliding window technique is used to calculate the moving average or exponential smoothing value of the time series data:

[0051] The extracted features are stored in a database to form a lithium-ion battery operation feature database, which effectively extracts useful information from a large amount of operation data. The lithium-ion battery operation feature database is a comprehensive database that can reflect the health status of the battery and predict its future performance.

[0052] S202, extracting features from the operating data and environmental data in the battery module, and merging the extracted features in a temporal and spatial sequence;

[0053] S203, constructing a lithium-ion battery operation feature database based on the combined features;

[0054] S204, according to the lithium-ion battery operation characteristic database, a battery evaluation model is determined by using a machine learning algorithm; the machine learning algorithm includes but is not limited to: random forest algorithm (RandomFores), support vector machine (SupportVectorMachine), back propagation neural network, gradient boosting tree (GradientBoostingMachines), dynamic deep learning and K-nearestneighbors algorithm (K-NearestNeighbors).

[0055] The lithium-ion battery operation feature database is divided into a training set and a test set according to the time dimension. The six prediction models are trained using the training data set, and the model parameters are adjusted to obtain the best performance. The K-fold cross-validation method is then used to evaluate the performance of the model, and the best prediction model is selected to finally obtain the battery evaluation model.

[0056] The specific training process is:

[0057] Suppose the data set is D, containing N samples, and the number of cross-validation folds is k;

[0058] Divide the dataset D into k subsets D1, D2, ..., D k The size of each subset is approximately

[0059] For each fold i (i=1, 2, ..., k), perform the following operations:

[0060] Training set: D train =D\D i ; Test set: D val =D i ; Train the model and evaluate it on the test set to get the evaluation result e i .

[0061] Calculate the average of k evaluation results as the final evaluation result of the model:

[0062]

[0063] Calculate the average of k evaluation results as the final evaluation result of the model:

[0064]

[0065] S205, evaluating the operating data and environmental data in the battery module using the battery evaluation model;

[0066] Before evaluation, the operating data and environmental data in the battery module are processed by feature engineering, such as normalization: Among them, x is the original data, x is the normalized data, min(x) and max(x) are the minimum and maximum values ​​of feature x. After feature engineering, the above data are processed to avoid deviations in the model training process within a similar scale range.

[0067] S206, based on the evaluation result, an anomaly detection algorithm is used to identify lithium-ion batteries that deviate from a normal range; and the identified lithium-ion batteries are used as objects to be monitored; the anomaly detection algorithm is an isolation forest algorithm (IsolationForest).

[0068] The anomaly score of each battery is calculated based on the evaluation results, and samples below the threshold are marked as anomalies based on the anomaly score. Anomaly scoring formula: Among them, s(x, n) is the anomaly score of data point x, E(h(x)) is the average path length of data point x in the tree, and c(n) is the normalized path length of the tree. The detection results are visualized, such as scatter plots, line graphs, or heat maps, etc., to display lithium-ion batteries that deviate from the normal range and determine them as objects to be monitored.

[0069] By performing data filtering, feature extraction, threshold alarm, and data compression on the operating data and environmental data in the battery module, the threshold of each parameter is determined; under the threshold of each parameter, the battery can work normally but obviously deviates from the normal working range, and then the lithium-ion battery that deviates from the normal range is identified;

[0070] In an exemplary embodiment, the temperature threshold is set to 65°C. The temperature threshold is combined with the ambient temperature to take into account the situation where the battery is exposed to external fire, so as to provide timely warning of fire. The pressure threshold is set to 0.01 based on the data standard deviation of the sliding window. When it exceeds 0.01, it is inferred that the battery is swollen; the voltage threshold is set according to the specific parameters of the battery. The standard charging maximum voltage is +0.1V, and the specific embodiment is set to 3.8V. When it exceeds, it indicates that overcharging may occur, resulting in an internal short circuit. Data compression saves storage space by reducing the amount of data, thereby improving the efficiency of data transmission, storage and processing.

[0071] S207, continue to monitor the monitored object, when the evaluation result determined based on the operating data in the battery module of the monitored object and the environmental data deviates from the normal range and exceeds the set threshold, an alarm is issued, and the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve.

[0072] In a specific embodiment, the threshold is set to -0.5. When the anomaly score of a data point is lower than the set threshold, it is marked as a significant anomaly and relevant personnel are notified by sound alarm, text message or email.

[0073] After the early warning, the preset emergency response mechanism is immediately activated, and the suppression strategy is dynamically adjusted and optimized. The lithium battery fire suppression device is automatically activated.

[0074] The lithium battery fire suppression device is used to extinguish fire by controlling the opening of the solenoid valve; that is, by opening the solenoid valve, the fire extinguishing material (water) extinguishes the fire of the monitored object;

[0075] In another specific embodiment, according to the severity of the warning signal and the real-time change of the battery status, the emergency response strategy is dynamically adjusted to optimize the fire suppression effect, such as the fire extinguishing agent spraying system, the isolation switch power-off device, etc. S207 and subsequent steps also include:

[0076] Continuously monitor battery status to ensure suppression measures are effective, and provide real-time feedback and improvement recommendations to minimize fire risk.

[0077] Based on the same inventive concept, the embodiment of the present application also provides a lithium-ion battery fire prediction and control device for implementing the above-mentioned lithium-ion battery fire prediction and control device method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more lithium-ion battery fire prediction and control device embodiments provided below can refer to the limitations of the lithium-ion battery fire prediction and control method above, and will not be repeated here.

[0078] In an exemplary embodiment, a lithium-ion battery fire prediction and control device is provided, comprising:

[0079] A data acquisition module is used to acquire operating data and environmental data in the battery module in the event of a lithium-ion battery fire; the operating data includes: temperature, voltage, current, humidity, pressure, charge, internal resistance, number of cycles and thermal runaway characteristic gases in the battery module; the environmental data includes: ambient temperature, ambient humidity, ambient pressure, wind speed and air pressure;

[0080] A feature processing module is used to extract features from the operating data and environmental data in the battery module and merge the extracted features in time and space sequences;

[0081] A lithium-ion battery operation characteristic database establishment module is used to construct a lithium-ion battery operation characteristic database according to the combined characteristics;

[0082] A battery evaluation model determination algorithm, which is used to determine a battery evaluation model using a machine learning algorithm based on a lithium-ion battery operation characteristic database;

[0083] An evaluation model, used to evaluate operating data and environmental data in a battery module using a battery evaluation model;

[0084] The module for determining the pair to be monitored is used to identify the lithium-ion batteries that deviate from the normal range by using an abnormality detection algorithm according to the evaluation results; and the identified lithium-ion batteries are used as the objects to be monitored;

[0085] The fire risk prediction and control module is used to continue monitoring the monitored object. When the evaluation result determined based on the operating data in the battery module of the monitored object and the environmental data deviates from the normal range and exceeds the set threshold, an alarm is issued, and the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve.

[0086] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a lithium-ion battery fire prediction and control method is implemented.

[0087] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0088] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0090] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0091] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0092] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A lithium-ion battery fire prediction and control method, characterized in that: The lithium-ion battery fire prediction and control method comprises: Obtaining operating data and environmental data in the battery module during a lithium-ion battery fire event; the operating data includes: temperature, voltage, current, humidity, pressure, charge, internal resistance, number of cycles, and thermal runaway characteristic gases in the battery module; the environmental data includes: ambient temperature, ambient humidity, ambient pressure, wind speed, and air pressure; Extract features from the operating data and environmental data in the battery module, and merge the extracted features in time and space sequences; constructing a lithium-ion battery operation characteristic database based on the combined characteristics; Based on the lithium-ion battery operation characteristic database, a battery evaluation model is determined using a machine learning algorithm; Use the battery evaluation model to evaluate the operating data and environmental data in the battery module; According to the evaluation results, an abnormal detection algorithm is used to identify lithium-ion batteries that deviate from the normal range; and the identified lithium-ion batteries are used as objects to be monitored; The monitored object continues to be monitored. When the evaluation result determined based on the operating data in the battery module of the monitored object and the environmental data deviates from the normal range and exceeds the set threshold, an alarm is issued, the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve.

2. The lithium-ion battery fire prediction and control method according to claim 1, characterized in that: The obtaining of operating data and environmental data in the battery module in the lithium-ion battery fire event specifically includes: Use the battery management system to obtain the operating data in the battery module; Use the meteorological platform to obtain environmental data.

3. The lithium-ion battery fire prediction and control method according to claim 1, characterized in that: The method of obtaining the operating data and environmental data in the battery module in the lithium-ion battery fire event further includes: The operating data and environmental data in the battery module are preprocessed; the preprocessing includes: data filtering, data cleaning, missing value processing, outlier processing and standardization processing.

4. The lithium-ion battery fire prediction and control method according to claim 1, characterized in that: The machine learning algorithms include: random forest algorithm, support vector machine, back propagation neural network, gradient boosting tree, dynamic deep learning and K-nearest neighbor algorithm.

5. The lithium-ion battery fire prediction and control method according to claim 1, characterized in that: The anomaly detection algorithm is the isolation forest algorithm.

6. A lithium-ion battery fire prediction and control device, characterized in that: The lithium-ion battery fire prediction and control device comprises: A data acquisition module is used to acquire operating data and environmental data in the battery module in the event of a lithium-ion battery fire; the operating data includes: temperature, voltage, current, humidity, pressure, charge, internal resistance, number of cycles and thermal runaway characteristic gases in the battery module; the environmental data includes: ambient temperature, ambient humidity, ambient pressure, wind speed and air pressure; A feature processing module is used to extract features from the operating data and environmental data in the battery module and merge the extracted features in time and space sequences; A lithium-ion battery operation characteristic database establishment module is used to construct a lithium-ion battery operation characteristic database according to the combined characteristics; A battery evaluation model determination algorithm, which is used to determine a battery evaluation model using a machine learning algorithm based on a lithium-ion battery operation characteristic database; An evaluation model, used to evaluate operating data and environmental data in a battery module using a battery evaluation model; The module for determining the pair to be monitored is used to identify the lithium-ion batteries that deviate from the normal range by using an abnormality detection algorithm according to the evaluation results; and the identified lithium-ion batteries are used as the objects to be monitored; The fire risk prediction and control module is used to continue monitoring the monitored object. When the evaluation result determined based on the operating data in the battery module of the monitored object and the environmental data deviates from the normal range and exceeds the set threshold, an alarm is issued, and the solenoid valve in the lithium battery fire suppression device is controlled to open, and the lithium-ion battery is powered off; the lithium battery fire suppression device is used to extinguish the fire by controlling the opening of the solenoid valve.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the lithium-ion battery fire prediction and control method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the lithium-ion battery fire prediction and control method described in any one of claims 1 to 5 is implemented.

Citation Information

Cited By

  • Battery over-discharge monitoring and early warning method based on ultrasonic bottom wave feature recognition

    CN119758150A

  • Electrochemical energy storage facility fire supervision system and method based on big data

    CN120748166A

  • Lithium ion battery fire prediction and control method and system

    CN122525382A