Battery thermal runaway early warning and safety protection system and method based on edge computing

Abstract

The application relates to a battery thermal runaway early warning and safety protection system and method based on edge computing, relates to the technical field of battery management, and is characterized in that a three-dimensional physical model of a battery pack and a packaging structure thereof is constructed, corresponding gas parameters and temperature parameters are obtained, a three-dimensional simulation model is obtained by using CFD software, predicted gas parameters under different environmental conditions are obtained, a gas prediction model is constructed, corrected temperature parameters at corresponding moments are obtained according to the gas parameters and the temperature parameters at the same moment, predicted corrected temperature parameters are obtained in combination with the gas prediction model, a warning signal is generated according to the predicted corrected temperature parameters, and the battery pack is pre-adjusted; the influence of the gas itself on temperature monitoring can be corrected, and effective prediction of subsequent temperature changes can be realized.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of battery management, and in particular to a battery thermal runaway early warning and safety protection system and method based on edge computing. BACKGROUND

[0002] Battery thermal runaway refers to the rapid accumulation of heat in a battery pack during operation due to internal or external factors, which leads to a rapid rise in temperature and loss of control. This phenomenon is usually accompanied by a sharp decline in battery performance, gas release, and even fire or explosion, which poses a serious threat to the battery system and the surrounding environment. Therefore, the early warning technology for thermal runaway is a research focus in the field of battery safety.

[0003] In the prior art, the gas released by thermal runaway has more or less influence on temperature monitoring, which leads to the fact that the temperature monitored by the sensor cannot accurately reflect the temperature of the battery itself. Moreover, as the external environment changes, the gas will also change, which makes the subsequent thermal runaway early warning more complex. The prior art lacks technical means to solve this problem. In view of the deficiencies of the prior art, the application provides a battery thermal runaway early warning and safety protection system and method based on edge computing. SUMMARY

[0004] The purpose of the application is to provide a battery thermal runaway early warning and safety protection system and method based on edge computing.

[0005] The purpose of the application can be achieved by the following technical solution: a battery thermal runaway early warning and safety protection system based on edge computing, comprising the following modules:

[0006] A data acquisition module is used to acquire physical parameters of a battery pack and its packaging structure, and to construct a three-dimensional physical model thereof. Different acquisition units are set for the battery pack and its packaging structure, and corresponding gas parameters and temperature parameters are acquired.

[0007] A gas prediction module is used to simulate the three-dimensional physical model by using CFD software to obtain a corresponding three-dimensional simulation model. In the three-dimensional simulation model, the predicted gas parameters of different gas parameters under different environmental conditions are obtained, and a gas prediction model inside the packaging structure is constructed.

[0008] A temperature correction module is used to acquire correction temperature parameters at a corresponding time according to gas parameters and temperature parameters at the same time, and to acquire predicted correction temperature parameters in combination with the gas prediction model.

[0009] A safety protection module is used to set a security unit, generate an early warning signal according to the predicted correction temperature parameters, and control the security unit to pre-adjust the battery pack.

[0010] Further, the process of acquiring the physical parameters of the battery pack and its packaging structure and constructing the three-dimensional physical models of both includes:

[0011] The packaging structure refers to the structure system that combines multiple battery monomers together and provides mechanical protection and electrical connection, and the physical parameters of the battery pack include the type and specification of the battery monomers, the number and connection mode;

[0012] The physical parameters of the packaging structure include the shell, air inlet, air outlet, internal frame, battery unit arrangement, electrical connector, thermal management component, and battery management system, and the three-dimensional physical models of the battery pack and its packaging structure are constructed by using three-dimensional modeling software according to the physical parameters of both.

[0013] Further, different acquisition units are set for the battery pack and its packaging structure, and the corresponding gas parameters and temperature parameters are acquired respectively, and the process includes:

[0014] A concentration acquisition unit is set, and the concentrations of various gases inside the packaging structure, including carbon monoxide concentration, hydrogen concentration, and methane concentration, are acquired in real time by the concentration acquisition unit, and the gas parameters refer to the concentrations of carbon monoxide, hydrogen, and methane inside the packaging structure at the same time;

[0015] A temperature acquisition unit is set for each battery monomer, and the temperature values of each battery monomer are acquired in real time by the temperature acquisition unit, and the temperature parameters refer to the temperature values of each battery monomer inside the packaging structure at the same time.

[0016] Further, the three-dimensional physical model is simulated by using CFD software to obtain the corresponding three-dimensional simulation model, and the process of obtaining the predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation model includes:

[0017] The corresponding environmental conditions are set at the air inlet and air outlet of the packaging structure of the three-dimensional physical model, including the air inlet speed and air inlet volume of the air inlet and the air outlet speed and air outlet volume of the air outlet;

[0018] The initial gas parameters inside the packaging structure of the three-dimensional physical model are preset, and the CFD software is used to simulate the gas change inside the three-dimensional physical model to obtain the corresponding three-dimensional simulation model;

[0019] An evaluation period is set, and the current environmental conditions and gas parameters are continuously adjusted to obtain the predicted gas parameters inside the packaging structure after an evaluation period.

[0020] Further, the process of constructing the gas prediction model inside the packaging structure includes:

[0021] According to different environmental conditions and gas parameters and corresponding predicted gas parameters, a gas prediction set is generated, and the obtained gas prediction model is divided into a training set and a test set;

[0022] A convolutional neural network is constructed, different environmental conditions and gas parameters in the training set are taken as input data of the convolutional neural network, and corresponding predicted gas parameters in the training set are taken as output data of the convolutional neural network, the convolutional neural network is trained to obtain an initial convolutional neural network;

[0023] The initial convolutional neural network is verified by using the test set, and the initial convolutional neural network with an output less than or equal to a preset test error threshold is taken as a gas prediction model inside the packaging structure.

[0024] Further, the process of obtaining a predicted correction temperature parameter according to the gas parameter, the temperature parameter at the same time and the gas prediction model includes:

[0025] According to the carbon monoxide concentration G a , the hydrogen concentration G b , the methane concentration G c and the temperature value W q of a single battery monomer inside the packaging structure at the current time, a correction temperature value W h of the single battery monomer at the current time is obtained.

[0026]

[0027] α and β are respectively a preset first compensation coefficient and a second compensation coefficient, G p is a comprehensive concentration of the carbon monoxide concentration, the hydrogen concentration and the methane concentration at the current time, is a comprehensive concentration change rate in a preset fixed time length, and t is the preset fixed time length.

[0028] G p = ω1G a + ω2G b + ω3G c ;

[0029] ω1, ω2 and ω3 are preset weight values, according to the temperature value W q of the single battery monomer at the current time and the temperature value W g before a preset fixed time length, a predicted temperature value W y of the single battery monomer after an evaluation period is obtained.

[0030]

[0031] The air inlet and the air outlet of the packaging structure in the actual application scene are provided with an air flow collection unit for obtaining actual environment conditions, including actual air inlet speed, actual air inlet volume of the air inlet, and actual air outlet speed, actual air outlet volume of the air outlet;

[0032] The current actual environment condition and the gas parameter are input into the gas prediction model to obtain a predicted gas parameter after an evaluation period, and the predicted temperature value and the predicted gas parameter after the evaluation period are substituted into the obtaining formula of the corrected temperature value to obtain a predicted corrected temperature value after the evaluation period;

[0033] The corrected temperature value of each battery monomer at the current moment is taken as the corrected temperature parameter of the battery pack thereof, and the predicted corrected temperature value of each battery monomer after an evaluation period is taken as the predicted corrected temperature parameter of the battery pack thereof.

[0034] Further, a security unit is arranged, a warning signal is generated according to the predicted corrected temperature parameter, and the process of pre-adjusting the battery pack by the security unit includes:

[0035] A temperature warning threshold is set, the predicted corrected temperature value of each battery monomer is compared with the temperature warning threshold respectively, to obtain a battery monomer with a risk of thermal runaway, and a warning signal is generated;

[0036] A security unit is arranged, and the pre-adjustment refers to spraying a cooling agent on the corresponding battery monomer by the security unit when the warning signal appears, and disconnecting the corresponding battery monomer from the battery pack, and feeding back the warning signal to relevant personnel.

[0037] In the embodiments of the present application, a battery thermal runaway early warning and safety protection method based on edge computing is also included, which comprises the following steps:

[0038] Step S1: obtaining physical parameters of a battery pack and a packaging structure thereof, and constructing three-dimensional physical models of the two, setting different collection units for the battery pack and the packaging structure, and respectively obtaining corresponding gas parameters and temperature parameters;

[0039] Step S2: simulating the three-dimensional physical model by using a CFD software to obtain a corresponding three-dimensional simulation model, obtaining predicted gas parameters of different gas parameters under different environment conditions in the three-dimensional simulation model, and constructing a gas prediction model inside the packaging structure;

[0040] Step S3: obtaining a corrected temperature parameter at a corresponding moment according to the gas parameter and the temperature parameter at the same moment, and obtaining a predicted corrected temperature parameter in combination with the gas prediction model;

[0041] Step S4: setting a security unit, generating a warning signal according to the predicted corrected temperature parameter, and controlling the security unit to pre-adjust the battery pack.

[0042] Compared with the prior art, the present application has the following advantages:

[0043] The present application can obtain the changes of different gas parameters under different environmental conditions by constructing a three-dimensional simulation model of the battery pack and its packaging structure, and can construct a corresponding gas prediction model, which is beneficial to obtaining the predicted gas parameters after a period of time according to the current gas parameters and environmental conditions, and can effectively predict the changes of subsequent gas concentration.

[0044] By obtaining the corrected temperature parameters at the corresponding time according to the gas parameters and temperature parameters at the same time, the influence of the gas itself on temperature monitoring can be corrected, so that the obtained temperature is more consistent with the actual temperature of the battery monomer, and by combining the predicted gas parameters after a period of time, the predicted corrected temperature parameters can be obtained, which can effectively predict the subsequent temperature changes, and thus the battery monomers that may have a risk of thermal runaway can be protected in advance. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The present application is a schematic diagram. DETAILED DESCRIPTION

[0046] As shown in Figure 1 The battery thermal runaway early warning and safety protection system based on edge computing includes the following modules:

[0047] The data acquisition module is used to obtain the physical parameters of the battery pack and its packaging structure, and to construct their three-dimensional physical models. Different acquisition units are set for the battery pack and its packaging structure, and the corresponding gas parameters and temperature parameters are obtained.

[0048] The gas prediction module is used to simulate the three-dimensional physical model by using CFD software to obtain the corresponding three-dimensional simulation model, and to obtain the predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation model, and to construct the gas prediction model inside the packaging structure.

[0049] The temperature correction module is used to obtain the corrected temperature parameters at the corresponding time according to the gas parameters and temperature parameters at the same time, and to obtain the predicted corrected temperature parameters by combining the gas prediction model.

[0050] The safety protection module is used to set the security unit, generate the early warning signal according to the predicted corrected temperature parameters, and control the security unit to pre-adjust the battery pack.

[0051] It should be further pointed out that in the specific implementation process, the process of obtaining the physical parameters of the battery pack and its packaging structure and constructing their three-dimensional physical models includes:

[0052] In the embodiments of the present application, the packaging structure refers to a structure system that combines multiple battery monomers together and provides mechanical protection and electrical connection, and a certain ventilation space exists inside the structure system, and the physical parameters refer to the relevant structure information of the battery pack and the packaging structure thereof;

[0053] For the battery pack, the physical parameters include the type and specification of the battery monomer, the number and connection mode, and for the packaging structure, the physical parameters include the shell, the air inlet, the air outlet, the internal frame, the battery unit arrangement, the electrical connector, the thermal management component, and the battery management system, and the three-dimensional physical models of the battery pack and the packaging structure thereof are constructed according to the obtained physical parameters of the battery pack and the packaging structure thereof by using a three-dimensional modeling software.

[0054] It needs to be further explained that, in the specific implementation process, the process of setting different acquisition units for the battery pack and the packaging structure thereof and respectively acquiring the corresponding gas parameters and temperature parameters includes:

[0055] Since the present application is to realize early warning for battery thermal runaway, it is necessary to monitor various gases that may be generated by battery thermal runaway, including carbon monoxide (CO), hydrogen (H2), and methane (CH4), and corresponding concentration acquisition units are respectively set for the above-mentioned various gases;

[0056] The concentration acquisition units are used to acquire the concentrations of various gases inside the packaging structure in real time, including the concentrations of carbon monoxide, hydrogen, and methane, and the gas parameters refer to the concentrations of carbon monoxide, hydrogen, and methane inside the packaging structure at the same time;

[0057] Another important parameter for early warning of battery thermal runaway is the temperature of each battery monomer included in the battery pack, and a corresponding temperature acquisition unit is respectively set for each battery monomer, and the temperature values of each battery monomer are respectively acquired in real time by the temperature acquisition units, and the temperature parameters refer to the temperature values of each battery monomer inside the packaging structure at the same time.

[0058] It needs to be further explained that, in the specific implementation process, the three-dimensional physical model is simulated by using a CFD software to obtain a corresponding three-dimensional simulation model, and the process of acquiring the predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation model includes:

[0059] Corresponding environmental conditions are respectively set for the air inlets and air outlets of the packaging structure of the three-dimensional physical model, and for the air inlets, the environmental conditions include the air inlet speed and the air inlet amount, and for the air outlets, the environmental conditions include the air outlet speed and the air outlet amount;

[0060] preset initial gas parameters inside the packaging structure of the three-dimensional physical model, and simulate the gas changes inside the three-dimensional physical model by using a CFD software to obtain a corresponding three-dimensional simulation model;

[0061] An evaluation period is set, and the gas parameters inside the packaging structure after the evaluation period are obtained by continuously adjusting the current environmental conditions and gas parameters, and are marked as the predicted gas parameters corresponding to the current environmental conditions and gas parameters.

[0062] It should be further explained that, in the specific implementation process, the process of constructing the gas prediction model inside the packaging structure includes:

[0063] The corresponding predicted gas parameters under different environmental conditions and different gas parameters are obtained by using the three-dimensional simulation model, a gas prediction set is generated according to different environmental conditions and gas parameters and the corresponding predicted gas parameters, and the obtained gas prediction model is divided into a training set and a test set;

[0064] A convolutional neural network is constructed, different environmental conditions and gas parameters in the training set are taken as input data of the convolutional neural network, and the corresponding predicted gas parameters in the training set are taken as output data of the convolutional neural network, the convolutional neural network is trained to obtain an initial convolutional neural network;

[0065] The initial convolutional neural network is verified by using the test set, and the initial convolutional neural network with an output less than or equal to a preset test error threshold is taken as the gas prediction model inside the packaging structure, and the gas prediction model is used for evaluating the predicted gas parameters.

[0066] It should be further explained that, in the specific implementation process, the process of obtaining the corrected temperature parameter at the corresponding time according to the gas parameter and the temperature parameter at the same time includes:

[0067] The carbon monoxide concentration, the hydrogen concentration and the methane concentration inside the packaging structure at the current time are respectively marked as G a , G b , and G c , the temperature value of a single battery monomer inside the packaging structure at the current time is marked as W q , and the corrected temperature value W h of the single battery monomer at the current time is obtained.

[0068]

[0069] α and β are respectively a preset first compensation coefficient and a second compensation coefficient, and the value ranges of the two are respectively 0.002-0.005 and 0.001-0.003, G pThis represents the combined concentration of carbon monoxide, hydrogen, and methane at the current moment. The comprehensive concentration change rate within the most recent preset fixed time period is t, where t is the preset fixed time period.

[0070] G p =ω1G a +ω2G b +ω3G c ;

[0071] ω1, ω2, and ω3 are preset weight values, and their sum equals 1;

[0072] Based on the temperature value W of the single battery cell at the current moment. q A temperature value W before a preset fixed time period. g Obtain the predicted temperature value W of the single battery cell after one evaluation cycle. y ;

[0073]

[0074] In practical application scenarios, an airflow acquisition unit is set at the air inlet and air outlet of the encapsulation structure to obtain the actual air inlet velocity and actual air inlet volume of the air inlet and the actual air outlet velocity and actual air outlet volume of the air outlet, and use them as actual environmental conditions.

[0075] The current actual environmental conditions and gas parameters are input into the gas prediction model. The gas prediction model outputs the predicted gas parameters after one evaluation period. The predicted temperature value and predicted gas parameters after one evaluation period are substituted into the formula for obtaining the corrected temperature value to obtain the predicted corrected temperature value after one evaluation period.

[0076] The corrected temperature value of each individual battery cell at the current moment is used as the corrected temperature parameter of its battery pack, and the predicted corrected temperature value of each individual battery cell after one evaluation cycle is used as the predicted corrected temperature parameter of its battery pack.

[0077] It should be further explained that, in the specific implementation process, the process of setting up a security unit, generating an early warning signal based on predicted and corrected temperature parameters, and controlling the security unit to pre-adjust the battery pack includes:

[0078] Set a temperature warning threshold, compare the predicted corrected temperature value of each battery cell with the temperature warning threshold respectively. If the predicted corrected temperature value is greater than or equal to the temperature warning threshold, it is determined that the corresponding battery cell has a risk of thermal runaway and a warning signal is generated. If it is less than, no other operation is performed on it.

[0079] The security unit is arranged, the pre-adjustment refers to when the early warning signal appears, the security unit sprays the coolant on the corresponding battery monomer, disconnects the corresponding battery monomer and the battery pack, and feeds back the early warning signal to the relevant personnel, to prompt the corresponding battery monomer to be operated and maintained in time.

[0080] In the embodiments of the present application, the battery thermal runaway early warning and safety protection method based on edge computing comprises the following steps:

[0081] Step S1: obtain the physical parameters of the battery pack and its packaging structure, and construct three-dimensional physical models of the two, set different collection units for the battery pack and its packaging structure, and obtain corresponding gas parameters and temperature parameters;

[0082] Step S2: simulate the three-dimensional physical model by using CFD software to obtain the corresponding three-dimensional simulation model, obtain the predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation model, and construct a gas prediction model inside the packaging structure;

[0083] Step S3: obtain the corrected temperature parameter at the corresponding time according to the gas parameter and the temperature parameter at the same time, and obtain the predicted corrected temperature parameter in combination with the gas prediction model;

[0084] Step S4: set a security unit, generate an early warning signal according to the predicted corrected temperature parameter, and control the security unit to pre-adjust the battery pack.

[0085] The above embodiments are only used to illustrate the technical method of the present application and are not limited. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

Claims

1. A battery thermal runaway early warning and safety protection system based on edge computing, characterized in that, The method comprises the following modules: a data acquisition module, configured to acquire physical parameters of a battery pack and a packaging structure thereof, and to construct three-dimensional physical models of the battery pack and the packaging structure thereof, to set different acquisition units for the battery pack and the packaging structure thereof, and to acquire corresponding gas parameters and temperature parameters; a gas prediction module, configured to simulate the three-dimensional physical models by using a CFD software to acquire corresponding three-dimensional simulation models, to acquire predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation models, and to construct a gas prediction model inside the packaging structure; a temperature correction module, configured to acquire correction temperature parameters at corresponding time points according to the gas parameters and the temperature parameters at the same time points, and to acquire predicted correction temperature parameters in combination with the gas prediction model; a safety protection module, configured to set a security unit, to generate an early warning signal according to the predicted correction temperature parameters, and to control the security unit to pre-adjust the battery pack; the process of acquiring the correction temperature parameters and the predicted correction temperature parameters in combination with the gas prediction model comprises: According to the carbon monoxide concentration G inside the package structure at the current time a , the hydrogen concentration G b , the methane concentration G c , and the temperature value W of the single battery cell q , the corrected temperature value W of the single battery cell at the current time is obtained h ; ； These are the preset first compensation coefficient and second compensation coefficient, respectively, G p This represents the combined concentration of carbon monoxide, hydrogen, and methane at the current moment. The comprehensive concentration change rate within the most recent preset fixed time period is t, where t is the preset fixed time period. ； is a preset weight value, the temperature value W q of the single battery cell at the current time g , and a temperature value W y of the single battery cell before a preset fixed time length ; ； setting air flow acquisition units for acquiring actual environmental conditions at air inlets and air outlets of the packaging structure in an actual application scenario, wherein the actual environmental conditions comprise actual air inlet velocity, actual air inlet volume at the air inlets and actual air outlet velocity, actual air outlet volume at the air outlets; inputting current actual environmental conditions and gas parameters into the gas prediction model to acquire predicted gas parameters after an evaluation period, and substituting the predicted temperature values and the predicted gas parameters after the evaluation period into an acquisition formula of the correction temperature values to acquire predicted correction temperature values after the evaluation period; taking correction temperature values of each battery monomer at a current time point as correction temperature parameters of a battery pack of the battery monomer, and taking predicted correction temperature values of each battery monomer after an evaluation period as predicted correction temperature parameters of a battery pack of the battery monomer.

2. The edge computing based battery thermal runaway early warning and safety protection system according to claim 1, characterized in that, The process of constructing the three-dimensional physical models of the battery pack and the packaging structure thereof comprises: the packaging structure refers to a structural system in which a plurality of battery monomers are combined together and mechanical protection and electrical connection are provided, and the physical parameters of the battery pack comprise types and specifications of the battery monomers, quantity and connection modes; the physical parameters of the packaging structure comprise an outer shell, air inlets, air outlets, an internal frame, battery unit arrangement, electrical connecting pieces, a thermal management assembly and a battery management system, and three-dimensional physical models of the battery pack and the packaging structure thereof are constructed by using three-dimensional modeling software according to the physical parameters of the battery pack and the packaging structure thereof.

3. The edge computing based battery thermal runaway early warning and safety protection system according to claim 2, characterized in that, The process of setting the acquisition units and acquiring the gas parameters and the temperature parameters respectively comprises: setting a concentration acquisition unit, and acquiring concentrations of various gases inside the packaging structure in real time through the concentration acquisition unit, wherein the gases comprise carbon monoxide, hydrogen and methane, and the gas parameters refer to concentrations of carbon monoxide, hydrogen and methane inside the packaging structure at the same time point; setting one temperature acquisition unit for each battery monomer, and acquiring temperature values of each battery monomer in real time through the temperature acquisition unit, wherein the temperature parameters refer to temperature values of each battery monomer inside the packaging structure at the same time point.

4. The edge computing based battery thermal runaway early warning and safety protection system according to claim 3, characterized in that, The process of acquiring predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation models comprises: The corresponding environmental conditions are arranged at the air inlet and the air outlet of the packaging structure of the three-dimensional physical model, including the air inlet velocity, the air inlet volume of the air inlet, and the air outlet velocity, the air outlet volume of the air outlet; The initial gas parameters are preset in the packaging structure of the three-dimensional physical model, and the CFD software is used to simulate the gas change in the three-dimensional physical model to obtain the corresponding three-dimensional simulation model; An evaluation period is set, and the current environmental conditions and gas parameters are continuously adjusted to obtain the predicted gas parameters in the packaging structure after the evaluation period.

5. The edge computing based battery thermal runaway early warning and safety protection system according to claim 4, characterized in that, The process of constructing the gas prediction model in the packaging structure includes: According to different environmental conditions and gas parameters and their corresponding predicted gas parameters, a gas prediction set is generated, and the obtained gas prediction model is divided into a training set and a test set; A convolutional neural network is constructed, different environmental conditions and gas parameters in the training set are taken as input data of the convolutional neural network, and the corresponding predicted gas parameters in the training set are taken as output data of the convolutional neural network, the convolutional neural network is trained to obtain an initial convolutional neural network; The initial convolutional neural network is verified by the test set, and the initial convolutional neural network with an output less than or equal to a preset test error threshold is taken as the gas prediction model in the packaging structure.

6. The edge computing based battery thermal runaway early warning and safety protection system according to claim 5, wherein, The process of generating a warning signal and controlling the security unit to pre-adjust the battery pack includes: A temperature warning threshold is set, the predicted corrected temperature value of each battery monomer is compared with the temperature warning threshold respectively to obtain the battery monomer with a risk of thermal runaway, and a warning signal is generated; A security unit is set, the pre-adjustment refers to when the warning signal appears, the security unit sprays coolant on the corresponding battery monomer, disconnects the corresponding battery monomer from the battery pack, and feeds back the warning signal to the relevant personnel.

7. The battery thermal runaway early warning and safety protection method based on edge computing is implemented based on the battery thermal runaway early warning and safety protection system of any one of claims 1-6, characterized in that, The method includes: Step S1: obtaining the physical parameters of the battery pack and its packaging structure, and constructing three-dimensional physical models of the two, setting different collection units for the battery pack and its packaging structure, and obtaining corresponding gas parameters and temperature parameters; Step S2: simulating the three-dimensional physical model by using the CFD software to obtain the corresponding three-dimensional simulation model, obtaining the predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation model, and constructing the gas prediction model in the packaging structure; Step S3: obtaining the corrected temperature parameter at the corresponding time according to the gas parameter and the temperature parameter at the same time, and obtaining the predicted corrected temperature parameter in combination with the gas prediction model; Step S4: setting a security unit, generating a warning signal according to the predicted corrected temperature parameter, and controlling the security unit to pre-adjust the battery pack.

Images