阅读说明：本技术 一种火灾预警方法、火灾预警系统和计算机设备 (Fire early warning method, fire early warning system and computer equipment ) 是由 李国庆 叶林 朱勇 刘明义 徐若晨 刘大为 曹曦 裴杰 曹传钊 汪琳 于 2021-07-31 设计创作，主要内容包括：本申请提出一种火灾预警方法、火灾预警系统和计算机设备,涉及电池储能安全分析技术领域,其中,该方法包括通过获取目标设备的一类预警参数,一类预警参数为可直接采集测量的参数；根据一类预警参数确定二类预警参数,二类预警参数为不可直接采集测量的参数；根据一类预警参数的带关联性系数评分和二类预警参数的带关联性系数评分,确定目标设备的着火概率。采用上述方案的本申请通过兼顾可直接采集测量参数和不能直接采集测量的参数的火灾预警因素来提高对目标设备进行预测的准确性,以实现降低火灾事故的发生概率。(The application provides a fire early warning method, a fire early warning system and computer equipment, and relates to the technical field of battery energy storage safety analysis, wherein the method comprises the steps of obtaining one type of early warning parameters of target equipment, wherein the one type of early warning parameters are parameters capable of being directly collected and measured; determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured; and determining the firing probability of the target equipment according to the relevance coefficient score of the first-class early warning parameters and the relevance coefficient score of the second-class early warning parameters. By adopting the scheme, the accuracy of predicting the target equipment is improved by considering the fire early warning factors of directly collecting and measuring parameters and parameters which cannot be directly collected and measured, so that the occurrence probability of fire accidents is reduced.)

1. A fire early warning method, comprising:

acquiring a class of early warning parameters of target equipment, wherein the class of early warning parameters are parameters capable of being directly acquired and measured;

determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured;

and determining the firing probability of the target equipment according to the relevance coefficient score of the first-class early warning parameter and the relevance coefficient score of the second-class early warning parameter.

2. The method of claim 1, wherein the one type of pre-warning parameters include, but are not limited to, one or more of voltage, current, temperature, and deformation, and wherein the two type of pre-warning parameters include, but are not limited to, one or more of increased internal resistance, capacity fade, health status, SEI film, and dendrite status.

3. The method of claim 1 or 2, wherein determining a second type of early warning parameter from the first type of early warning parameter comprises:

determining one or more first-class early warning parameters related to the second-class early warning parameters;

and determining the second-class early warning parameters according to one or more first-class early warning parameters related to the second-class early warning parameters.

4. The method of claim 1 or 2, further comprising, prior to determining the probability of fire for the target device based on the band relevance coefficient score for the one type of early warning parameter and the band relevance coefficient score for the second type of early warning parameter:

determining the relevance coefficient score of the early warning parameters according to the relevance coefficient and the system score;

and determining a second-class relevance coefficient and a second-class system score which are matched with the second-class early warning parameters, and determining the relevance coefficient score with the second-class early warning parameters according to the second-class relevance coefficient and the second-class system score.

5. The method of claim 4, wherein in determining the relevance coefficient score for the class of early warning parameters based on the class of relevance coefficients and the class of system scores, the relevance coefficient score for the class of early warning parameters is obtained by:

G_i＝a_i·X_i

wherein G is_iScoring the correlation coefficient matched with the ith class of early warning parameters, a_iIs a class of correlation coefficient, X, matched with the ith class of early warning parameters_iIs one matched with the ith class of early warning parametersGrading a class system;

in determining the relevance coefficient score of the second type of early warning parameters according to the second type of relevance coefficient and the second type of system score, obtaining the relevance coefficient score of the second type of early warning parameters through the following formula:

G_j＝b_j·Y_j

wherein G is_jScoring the relevance coefficient of the band matched with the jth class II early warning parameter, b_jIs a second-class relevance coefficient, Y, matched with the jth second-class early warning parameter_jAnd scoring the second-class system matched with the jth second-class early warning parameter.

6. The method of claim 5, wherein in determining the probability of fire of the target device based on the band relevance coefficient score for the one type of early warning parameter and the band relevance coefficient score for the two types of early warning parameters, the probability of fire of the target device is obtained by:

wherein eta is the firing probability of the target equipment, m is the total number of the first-class early warning parameters, n is the total number of the second-class early warning parameters, and Z is the total score of each early warning parameter scoring system.

7. A fire early warning system, the system comprising:

the acquisition module is used for acquiring one type of early warning parameters of the target equipment, wherein the one type of early warning parameters are parameters capable of being directly acquired and measured;

the first determining module is used for determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured;

and the second determination module is used for determining the firing probability of the target equipment according to the relevance coefficient score of the first class of early warning parameters and the relevance coefficient score of the second class of early warning parameters.

8. The system of claim 7, wherein the first determination module is further configured to:

determining one or more first-class early warning parameters related to the second-class early warning parameters;

and determining the second-class early warning parameters according to one or more first-class early warning parameters related to the second-class early warning parameters.

9. The system of claim 7, wherein the first determination module is further configured to:

determining the relevance coefficient score of the early warning parameters according to the relevance coefficient and the system score;

and determining a second-class relevance coefficient and a second-class system score which are matched with the second-class early warning parameters, and determining the relevance coefficient score with the second-class early warning parameters according to the second-class relevance coefficient and the second-class system score.

10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 6 when executing the computer program.

Technical Field

The application relates to the technical field of battery energy storage safety analysis, in particular to a fire early warning method, a fire early warning system and computer equipment.

Background

With the rapid development of new energy, the fluctuation and randomness of the power generation process of the new energy provide great challenges for the safe and stable operation of a power system. The stored energy is a technology capable of realizing peak regulation and frequency modulation and reducing the operation risk of a power system, and plays an important role in the context of a policy of '3060'. Among the energy storage technologies, the battery energy storage technology is an important branch of the energy storage field. At present, the battery energy storage technology is basically mature, but the ignition prediction of the battery in the prior art is inaccurate, and the ignition safety accident often happens.

Disclosure of Invention

The present application is directed to solving, at least to some extent, one of the technical problems in the related art.

Therefore, a first objective of the present application is to provide a fire early warning method, which improves the accuracy of predicting a target device by considering both the directly collected and measured parameters and the fire early warning factors that cannot directly collect and measure the parameters, so as to reduce the occurrence probability of a fire accident.

A second object of the present application is to provide a fire early warning system.

A third object of the present application is to propose a computer device.

In order to achieve the above object, a fire early warning method is provided in an embodiment of a first aspect of the present application, including:

acquiring a class of early warning parameters of target equipment, wherein the class of early warning parameters are parameters capable of being directly acquired and measured;

determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured;

and determining the firing probability of the target equipment according to the relevance coefficient score of the first-class early warning parameter and the relevance coefficient score of the second-class early warning parameter.

Optionally, in one embodiment of the present application, the one type of pre-warning parameter includes, but is not limited to, one or more of voltage, current, temperature, and deformation, and the two type of pre-warning parameter includes, but is not limited to, one or more of internal resistance increase, capacity fade, health state, SEI film, and dendrite state.

Optionally, in an embodiment of the present application, determining a second class of warning parameters according to the first class of warning parameters includes:

determining one or more first-class early warning parameters related to the second-class early warning parameters;

and determining the second-class early warning parameters according to one or more first-class early warning parameters related to the second-class early warning parameters.

Optionally, in an embodiment of the present application, before determining the probability of fire of the target device according to the band relevance coefficient score of the first class of warning parameters and the band relevance coefficient score of the second class of warning parameters, the method further includes:

determining the relevance coefficient score of the early warning parameters according to the relevance coefficient and the system score;

and determining a second-class relevance coefficient and a second-class system score which are matched with the second-class early warning parameters, and determining the relevance coefficient score with the second-class early warning parameters according to the second-class relevance coefficient and the second-class system score.

Optionally, in an embodiment of the present application, in determining the score with relevance coefficient of the first category of warning parameters according to the first category of relevance coefficient and the first category of system score, the score with relevance coefficient of the first category of warning parameters is obtained through the following formula:

G_i＝a_i·X_i

wherein G is_iScoring the correlation coefficient matched with the ith class of early warning parameters, a_iIs a class of correlation coefficient, X, matched with the ith class of early warning parameters_iScoring a class of system matched with the ith class of early warning parameter;

in determining the relevance coefficient score of the second type of early warning parameters according to the second type of relevance coefficient and the second type of system score, obtaining the relevance coefficient score of the second type of early warning parameters through the following formula:

G_j＝b_j·Y_j

wherein G is_jScoring the relevance coefficient of the band matched with the jth class II early warning parameter, b_jIs a second-class relevance coefficient, Y, matched with the jth second-class early warning parameter_jAnd scoring the second-class system matched with the jth second-class early warning parameter.

Optionally, in an embodiment of the present application, in determining the firing probability of the target device according to the band relevance coefficient score of the first class of warning parameters and the band relevance coefficient score of the second class of warning parameters, the firing probability of the target device is obtained by the following formula:

wherein eta is the firing probability of the target equipment, m is the total number of the first-class early warning parameters, n is the total number of the second-class early warning parameters, and Z is the total score of each early warning parameter scoring system.

According to the fire early warning method provided by the embodiment of the first aspect of the application, one type of early warning parameters of the target equipment are obtained, and the one type of early warning parameters are parameters which can be directly collected and measured; determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured; and determining the firing probability of the target equipment according to the relevance coefficient score of the first-class early warning parameters and the relevance coefficient score of the second-class early warning parameters. Therefore, the accuracy of prediction of the target equipment is improved by considering the fire early warning factors of directly collecting and measuring parameters and parameters which cannot be directly collected and measured, so that the occurrence probability of fire accidents is reduced.

In order to achieve the above object, a fire early warning system is provided in an embodiment of the second aspect of the present application, the system including:

the acquisition module is used for acquiring one type of early warning parameters of the target equipment, wherein the one type of early warning parameters are parameters capable of being directly acquired and measured;

the first determining module is used for determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured;

and the second determination module is used for determining the firing probability of the target equipment according to the relevance coefficient score of the first class of early warning parameters and the relevance coefficient score of the second class of early warning parameters.

Optionally, in an embodiment of the present application, the first determining module is further configured to:

determining one or more first-class early warning parameters related to the second-class early warning parameters;

and determining the second-class early warning parameters according to one or more first-class early warning parameters related to the second-class early warning parameters.

Optionally, in an embodiment of the present application, the first determining module is further configured to:

determining the relevance coefficient score of the early warning parameters according to the relevance coefficient and the system score;

and determining a second-class relevance coefficient and a second-class system score which are matched with the second-class early warning parameters, and determining the relevance coefficient score with the second-class early warning parameters according to the second-class relevance coefficient and the second-class system score.

In the fire early warning system provided by the embodiment of the second aspect of the application, one type of early warning parameters of the target device are obtained through the obtaining module, and the one type of early warning parameters are parameters which can be directly collected and measured; the first determining module determines a second type of early warning parameters according to the first type of early warning parameters, wherein the second type of early warning parameters are parameters which cannot be directly acquired and measured; and the second determining module determines the firing probability of the target equipment according to the relevance coefficient score of the first-class early warning parameters and the relevance coefficient score of the second-class early warning parameters. Therefore, the accuracy of prediction of the target equipment is improved by considering the fire early warning factors of directly collecting and measuring parameters and parameters which cannot be directly collected and measured, so that the occurrence probability of fire accidents is reduced.

In order to achieve the above object, a third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the fire early warning method according to the first aspect of the present application is implemented.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a flowchart of a fire warning method provided in embodiment 1 of the present application;

fig. 2 is a flowchart of a fire warning method according to embodiment 2 of the present application;

fig. 3 is a schematic diagram of a fire early warning scoring method in embodiment 2 of the present application; and

fig. 4 is a schematic structural diagram of a fire early warning system provided in embodiment 3 of the present application.

Detailed Description

Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application. On the contrary, the embodiments of the application include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

With the rapid development of new energy, the fluctuation and randomness of the power generation process of the new energy provide great challenges for the safe and stable operation of a power system, energy storage is a technology capable of realizing peak regulation and frequency modulation and reducing the operation risk of the power system, and must play a great role in the context of a policy of '3060', and among a plurality of energy storage technologies, a battery energy storage technology is an important branch in the field of energy storage. Although the battery energy storage technology is basically mature, the safety accident of fire often happens.

At present, in order to reduce the frequency of accidents caused by battery ignition, the ignition probability of the battery energy storage device is usually predicted by analyzing directly collected measurement parameters, and if the ignition probability is greater than a preset threshold, a fire early warning forecast is sent out. However, since the operation process of the battery energy storage system is a complex physical and chemical interweaving process, parameters such as voltage, current, temperature, deformation and the like can be detected by the sensors, but some intrinsic parameters (such as internal resistance increase, capacity attenuation, health state and the like) representing the inside of the battery cannot be obtained through direct measurement. These quantities, which cannot be measured directly, are related to a number of measurable parameters, and scientific analytical calculations have revealed that when all measurable parameters are within a threshold range, some of the unmeasurable parameters are already within an abnormal range, i.e., the operational data produces a correlation anomaly.

Based on the above analysis, embodiments of the present application provide a fire early warning method, a fire early warning system, and a computer device, which improve accuracy of predicting a target device by considering both fire early warning factors that can directly acquire measurement parameters and parameters that cannot directly acquire measurement parameters, so as to reduce occurrence probability of a fire accident. A fire early warning method and system according to an embodiment of the present application will be described with reference to the accompanying drawings.

Example 1

Fig. 1 is a flowchart of a fire early warning method according to an embodiment of the present disclosure.

As shown in fig. 1, a fire early warning method provided in an embodiment of the present application includes:

step S110, acquiring one type of early warning parameters of the target equipment, wherein the one type of early warning parameters are parameters capable of being directly acquired and measured.

In an embodiment of the application, parameters related to ignition of the battery cell, such as voltage, current, temperature, deformation and the like, can be acquired through a sensor, and the parameters are used as a type of early warning parameters.

And step S120, determining second-class early warning parameters according to the first-class early warning parameters, wherein the second-class early warning parameters are parameters which cannot be directly acquired and measured.

In an embodiment of the present application, two types of warning parameters related to the ignition of the target device (battery cell) may be determined according to one or more types of warning parameters, for example, one or more of internal resistance increase, capacity attenuation, health state, SEI film and dendrite state, and the parameters determined by the one or more types of warning parameters are taken as the two types of warning parameters.

And step S130, determining the firing probability of the target equipment according to the relevance coefficient scores of the first-class early warning parameters and the second-class early warning parameters.

In the embodiment of the application, the relevance coefficient score corresponding to the first-class early warning parameter and the second-class early warning parameter is determined according to the related information of the first-class early warning parameter and the second-class early warning parameter respectively, then the relevance coefficient score of the first-class early warning parameter and the relevance coefficient score of the second-class early warning parameter are determined, the firing probability of the target device is determined, and when the firing probability is larger than or equal to a preset value, fire early warning is carried out, namely, a warning is sent to a related responsible person to remind of taking a countermeasure, and a fire accident caused by firing of the battery energy storage device is avoided.

In addition, aiming at the problem that the battery cell is on fire due to the fact that all measurable parameters are within the threshold range and the fact that the non-measurable parameters are within the abnormal range, namely, correlation abnormality is generated in operation data, the embodiment of the application acquires relevant information of the measurable parameters, such as temperature, voltage and other early warning parameters, through the sensor, and calculates and acquires the non-directly measurable parameters related to the measurable parameters and the battery cell on fire, namely, the scheme of the two early warning parameters is used for solving the problem.

In summary, the fire early warning method according to the embodiment of the present application improves the accuracy of predicting the target device by considering the fire early warning factors that can directly acquire the measurement parameters and cannot directly acquire the measurement parameters, so as to reduce the occurrence probability of the fire accident.

Example 2

Fig. 2 is a flowchart of a fire warning method according to an embodiment of the present disclosure.

As shown in fig. 1, a fire early warning method provided in an embodiment of the present application includes:

step 210, acquiring a type of early warning parameters of the target device, where the type of early warning parameters is parameters that can be directly collected and measured, for example, the type of early warning parameters includes one or more of voltage, current, temperature, and deformation, and the directly measurable factors related to the ignition of the battery cell include, but are not limited to, the above-mentioned.

Step 220, determining one or more first-class early warning parameters related to the second-class early warning parameters.

In the embodiment of the application, a relevant algorithm may be used to calculate one or more first-class parameters to determine second-class early warning parameters related to the ignition of the battery core, and regarding the selection of the algorithm, a most suitable algorithm may be selected according to characteristics of the early warning parameters, data quality and the like, including but not limited to determining the second-class early warning parameters through an algorithm of an isolated forest and a support vector machine.

Step 230, determining the second-class early warning parameters according to one or more first-class early warning parameters related to the second-class early warning parameters; specifically, according to one or more first-class warning parameters, second-class warning parameters related to ignition of the target device (battery cell) may be determined, for example, one or more parameters of internal resistance increase, capacity attenuation, health state, SEI film and dendrite state, and the parameters determined by the one or more first-class warning parameters are used as the second-class warning parameters.

Further, step 230 in the above embodiment includes the following steps:

and determining the relevance coefficient score with the early warning parameters according to the relevance coefficient and the system score.

Specifically, in the embodiment of the present application, the score of the coefficient with relevance of one type of the early warning parameters may be calculated and obtained through the following formula:

G_i＝a_i·X_i

wherein G is_iScoring the correlation coefficient matched with the ith class of early warning parameters, a_iIs a class of correlation coefficient, X, matched with the ith class of early warning parameters_iAnd scoring the system of the type matched with the ith type of early warning parameter.

In the embodiment of the application, each directly measurable parameter can be scored according to the same scoring system and recorded as a system score, for example, a percentage system, and a corresponding relevance coefficient is determined according to the influence of each parameter on ignition.

In other words, since the first-class correlation coefficient is determined according to the magnitude of the fire influence of each class of parameters, in the embodiment of the present application, a multiplier of the first-class correlation coefficient and the first-class system score is used as the score with the correlation coefficient of the first-class early warning parameter.

Step S232, determining a second type correlation coefficient and a second type system score which are matched with the second type early warning parameters, and determining the relevance coefficient score of the second type early warning parameters according to the second type correlation coefficient and the second type system score.

Specifically, in the embodiment of the present application, the score of the coefficient with relevance of one type of the early warning parameters may be calculated and obtained through the following formula:

G_j＝b_j·Y_j

wherein G is_jScoring the relevance coefficient of the band matched with the jth class II early warning parameter, b_jIs a second-class relevance coefficient, Y, matched with the jth second-class early warning parameter_jAnd scoring the second-class system matched with the jth second-class early warning parameter.

In other words, the second type of correlation coefficient in the embodiment of the present application is determined according to the size of the influence of the above-mentioned non-directly measurable parameter on fire, and the second type of system score is determined according to the first type of correlation coefficient and the first type of system score, wherein a multiplier of the second type of correlation coefficient and the second type of zone correlation coefficient score is used as the zone correlation coefficient score of the second type of early warning parameter.

And step S240, determining the firing probability of the target equipment according to the relevance coefficient score of the first-class early warning parameters and the relevance coefficient score of the second-class early warning parameters.

In this embodiment, each of the two types of early warning parameters may be related to one or more of the one type of early warning parameters, where if the one type of early warning parameter is directly related to the ignition of the battery cell, the coefficient is greater than 0, and if the one type of early warning parameter is not directly related to the ignition of the battery cell, and is only used for calculating and obtaining the two types of early warning parameters, the first type of coefficient is 0.

Whether the correlation coefficient of one type is directly related to the ignition of the battery core or not, the accumulated value of the correlation coefficients of the first type and the second type is 100 percent, namely

And superposing the relevance coefficient scores of the first type of early warning parameters and the relevance coefficient scores of the second type of early warning parameters, wherein the superposition is a total fire early warning score of the target equipment, namely a total fire early warning score of the battery cell, the total fire early warning score of the battery cell is a safety index of the battery cell, and the larger the numerical value is, the higher the safety of the battery cell is.

Based on the total fire warning score of the battery cell and the total score of each parameter score system, the firing probability of the battery cell can be obtained, and the firing probability of the target device in step S240 in the embodiment of the present application can be obtained by the following calculation:

wherein η is the firing probability of the target device, m is the total number of the first-class early warning parameters, n is the total number of the second-class early warning parameters, and Z is the total score of the scoring system of each early warning parameter, and when the scoring system is adopted, Z is 100.

To facilitate a better understanding of the embodiments of the present application, reference is now made to fig. 3, which shows the following details:

as shown in fig. 3, the first-type warning parameter 1 and the second-type warning parameter 2 are both related to the ignition of the battery, and the number of the first-type warning parameter and the second-type warning parameter is determined according to the actual situation.

For a type of early warning parameters 1, the parameters mainly comprise voltage, current, temperature, deformation and the like, and each parameter is scored according to the same scoring system, namely X_iSuch as percent. Determining a correlation coefficient a according to the influence of each parameter on the ignition_iWherein the product of the first-class correlation coefficient and the second-class systematic score (a)_i·X_i) A score 3 with relevance coefficient for a class of early warning parameters.

For the second-class early warning parameters 2, mainly because the direct acquisition and measurement cannot be realized, the first-class early warning parameters 1 are required to be calculated and obtained, and the scores Y of the second-class early warning parameters are calculated through a certain intelligent algorithm_jAnd combining a second relevance coefficient b of the influence of the second-class early warning parameters 2 on the ignition of the battery cell_jThe product of (b) and_j·Y_j) And 4, scoring the relevance coefficient of the second type of early warning parameters. Each second-class early warning parameter 2 may be related to one or a plurality of first-class early warning parameters 1, and if the related first-class early warning parameters 1 are directly related to the ignition of the battery cellThe coefficient is greater than 0, and if the coefficient is not directly related to the ignition of the battery cell and is only used for calculating the second type parameter 2, the coefficient is 0.

The accumulated value of the relevance coefficients of the first-class early warning parameters 1 and the second-class early warning parameters 2 is 100%, the relevance system scores 3 of the first-class early warning parameters and the relevance coefficient scores 4 of the second-class early warning parameters are accumulated to obtain a cell fire early warning total score, the early warning total score is a safety index of a cell, and the higher the numerical value is, the higher the safety is.

Based on the total fire early warning score, the firing probability of the battery cell can be obtained by combining the total score of each parameter score system, namely:

in the above formula, Z is the total score of each parameter, and when a percentage is used, Z is 100.

In summary, the fire early warning method of the embodiment of the application can give consideration to both directly collecting and measuring parameters and parameters which cannot be directly collected and measured due to the adoption of the grading scoring method, and the fire early warning factor is more comprehensive; due to the adoption of the comprehensive scoring method with the relevance coefficient, different weights can be given to different fire influence factors, and the scoring rule is more scientific; due to the adoption of the concept of the ignition probability of the battery cell, the fire early warning of the battery cell is more intuitive.

Example 3

Fig. 4 is a schematic structural diagram of a fire warning system according to an embodiment of the present disclosure.

As shown in fig. 4, the present application provides a fire early warning system, including:

the acquisition module 10 is used for acquiring one type of early warning parameters of the target equipment, wherein the one type of early warning parameters are parameters which can be directly acquired and measured;

the first determining module 20 is configured to determine a second type of early warning parameters according to the first type of early warning parameters, where the second type of early warning parameters are parameters that cannot be directly acquired and measured;

and the second determining module 30 is configured to determine the firing probability of the target device according to the relevance coefficient score of the first-class early warning parameter and the relevance coefficient score of the second-class early warning parameter.

Further, in an embodiment of the present application, the first determining module 20 is further configured to:

determining a first-class correlation coefficient and a first-class system score which are matched with a first-class early warning parameter;

and determining second-class early warning parameters according to the first-class correlation coefficient and the first-class system score.

Further, in an embodiment of the present application, the first determining module 20 is further configured to:

determining a correlation coefficient score with a first type of early warning parameters according to the first type of correlation coefficient and the first type of system score;

and determining a second type of correlation coefficient and a second type of system score which are matched with the second type of early warning parameters, and determining the correlation coefficient score with the second type of early warning parameters according to the second type of correlation coefficient and the second type of system score.

In summary, the fire early warning system provided in the embodiment of the present application obtains a first-class early warning parameter related to the ignition of the battery core through the obtaining module, determines a second-class early warning parameter related to the ignition of the battery core according to the first-class early warning parameter, and determines the ignition probability of the target device based on the relevance coefficient score of the first-class early warning parameter and the relevance coefficient score of the second-class early warning parameter. Therefore, the embodiment of the application can directly acquire the measurement parameters and can not directly acquire the measurement parameters, and the fire early warning factor is more comprehensive; due to the adoption of the comprehensive scoring method with the relevance coefficient, different weights can be given to different fire influence factors, and the scoring rule is more scientific; due to the adoption of the concept of the ignition probability of the battery cell, the fire early warning of the battery cell is more intuitive.

In order to implement the foregoing embodiments, the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the fire early warning method of the foregoing embodiments is implemented.

It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware that is related to instructions of a program, and the program may be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.

In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.