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

Abstract

The invention discloses a battery thermal runaway early warning and safety protection system and method based on edge calculation, and relates to the technical field of battery management. A three-dimensional physical model of a battery pack and a packaging structure thereof is constructed, corresponding gas parameters and temperature parameters are respectively obtained, a three-dimensional simulation model is obtained by using CFD software, predicted gas parameters of different gas parameters under different environment conditions are obtained, and a gas prediction model is constructed; acquiring corrected temperature parameters at corresponding moments according to the gas parameters and the temperature parameters at the same moment, acquiring predicted corrected temperature parameters in combination with the gas prediction model, generating early warning signals according to the predicted corrected temperature parameters, and pre-adjusting the battery pack; the influence of gas on temperature monitoring can be corrected, and the subsequent temperature change condition can be effectively predicted.

Description

Technical Field

[0001] The present invention relates to the field of battery management technology, and specifically to a battery thermal runaway warning and safety protection system and method based on edge computing. Background Art

[0002] Battery thermal runaway refers to the phenomenon in which a battery pack experiences rapid heat accumulation during operation due to internal or external factors, resulting in a rapid and uncontrolled temperature rise. This phenomenon is often accompanied by a sharp drop in battery performance, gas release, and even fire or explosion, posing a serious threat to the battery system and the surrounding environment. Therefore, 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 will have more or less impact on temperature monitoring, which means that the temperature monitored by the sensor cannot accurately reflect the temperature of the battery itself. As the external environment changes, the gas will also change accordingly, which makes the subsequent thermal runaway warning more complicated. The prior art lacks technical means to solve this problem. In response to the shortcomings of the prior art, the present invention provides a battery thermal runaway warning and safety protection system and method based on edge computing. Summary of the Invention

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

[0005] The purpose of the present invention can be achieved through the following technical solution: a battery thermal runaway warning and safety protection system based on edge computing, including the following modules:

[0006] The data acquisition module is used to obtain the physical parameters of the battery pack and its packaging structure, and to build a three-dimensional physical model of the two. Different acquisition units are set for the battery pack and its packaging structure, and the corresponding gas parameters and temperature parameters are obtained respectively;

[0007] The gas prediction module is used to simulate the three-dimensional physical model using CFD software to obtain a 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 build a gas prediction model inside the packaging structure;

[0008] The temperature correction module is used to obtain the corrected temperature parameters at the corresponding moment based on the gas parameters and temperature parameters at the same moment, and obtain the predicted corrected temperature parameters in combination with the gas prediction model;

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

[0010] Furthermore, the process of obtaining the physical parameters of the battery pack and its packaging structure and constructing a three-dimensional physical model of the two includes:

[0011] The packaging structure refers to a structural system that combines multiple battery cells and provides mechanical protection and electrical connections. The physical parameters of the battery pack include the type and specifications, quantity and connection method of the battery cells;

[0012] The physical parameters of the packaging structure include the outer shell, air inlet, air outlet, internal frame, battery cell arrangement, electrical connectors, thermal management components, and battery management system. Three-dimensional modeling software is used to construct a three-dimensional physical model of the battery pack and its packaging structure based on the physical parameters of the battery pack.

[0013] Furthermore, the process of setting different acquisition units for the battery pack and its packaging structure and respectively acquiring corresponding gas parameters and temperature parameters includes:

[0014] A concentration acquisition unit is provided to acquire the concentrations of various gases inside the packaging structure in real time, including carbon monoxide concentration, hydrogen concentration, and methane concentration. The gas parameters refer to the carbon monoxide concentration, hydrogen concentration, and methane concentration inside the packaging structure at the same time.

[0015] A temperature acquisition unit is provided for each battery cell, and the temperature value of each battery cell is acquired in real time through the temperature acquisition unit. The temperature parameter refers to the temperature value of each battery cell inside the packaging structure at the same time.

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

[0017] 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 volume, and the air outlet speed and air volume;

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

[0019] An evaluation cycle is set, and the predicted gas parameters inside the package structure after one evaluation cycle are obtained by continuously adjusting the current environmental conditions and gas parameters.

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

[0021] Generate a gas prediction set based on different environmental conditions and gas parameters and their corresponding predicted gas parameters, and divide the obtained gas prediction model into a training set and a test set;

[0022] Construct a convolutional neural network, use different environmental conditions and gas parameters in the training set as input data of the convolutional neural network, use the corresponding predicted gas parameters in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network;

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

[0024] Furthermore, the process of obtaining the corrected temperature parameter at the corresponding moment according to the gas parameter and temperature parameter at the same moment and obtaining the predicted corrected temperature parameter in combination with the gas prediction model includes:

[0025] According to the carbon monoxide concentration G inside the packaging structure at the current moment a , hydrogen concentration G b , methane concentration G c And the temperature value W of a single battery cell q , obtain the corrected temperature value W of the single battery cell at the current moment h ;

[0026]

[0027] α and β are the preset first compensation coefficient and second compensation coefficient respectively, G p is the comprehensive concentration of carbon monoxide concentration, hydrogen concentration, and methane concentration at the current moment, is the comprehensive concentration change rate within the most recent preset fixed time period, and t is the preset fixed time period;

[0028] G p =ω1G a +ω2G b +ω3G c ;

[0029] ω1, ω2, and ω3 are preset weight values, which are calculated based on the temperature value W of the single battery cell at the current moment. q and a temperature value W before a preset fixed time g , obtain the predicted temperature value W of the single battery cell after one evaluation cycle y ;

[0030]

[0031] An air flow collection unit for obtaining actual environmental conditions is provided at the air inlet and air outlet of the packaging structure in an actual application scenario. The actual environmental conditions include the actual inlet air speed and actual inlet air volume of the air inlet and the actual outlet air speed and actual outlet air volume of the air outlet;

[0032] Inputting the current actual environmental conditions and gas parameters into the gas prediction model to obtain the predicted gas parameters after one evaluation cycle, substituting the predicted temperature value and the predicted gas parameters after one evaluation cycle into the formula for obtaining the corrected temperature value to obtain the predicted corrected temperature value after one evaluation cycle;

[0033] The corrected temperature value of each 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 battery cell after one evaluation cycle is used as the predicted corrected temperature parameter of its battery pack.

[0034] Furthermore, a security unit is provided to generate an early warning signal according to the predicted and corrected temperature parameters, and the process of controlling the security unit to pre-condition the battery pack includes:

[0035] Set a temperature warning threshold and compare the predicted corrected temperature value of each battery cell with the temperature warning threshold to identify battery cells at risk of thermal runaway and generate a warning signal;

[0036] A security unit is set up, and the pre-adjustment means that when an early warning signal appears, the security unit is controlled to spray coolant on the corresponding battery cell and disconnect the corresponding battery cell from the battery pack, and at the same time, the early warning signal is fed back to relevant personnel.

[0037] An embodiment of the present invention also includes a battery thermal runaway warning and safety protection method based on edge computing, comprising the following steps:

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

[0039] Step S2: Using CFD software to simulate the three-dimensional physical model to obtain a corresponding three-dimensional simulation model, obtaining predicted gas parameters of different gas parameters under different environmental 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 based on the gas parameters and temperature parameters 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 to generate an early warning signal according to the predicted and corrected temperature parameters, and controlling the security unit to pre-condition the battery pack.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] By constructing a three-dimensional simulation model of the battery pack and its packaging structure, the present invention can obtain the changes in different gas parameters under different environmental conditions and build a corresponding gas prediction model. This is conducive to obtaining the predicted gas parameters after a period of time based on the current gas parameters and environmental conditions, and can effectively predict the subsequent changes in gas concentration.

[0044] By obtaining the corrected temperature parameters at the corresponding moment based on the gas parameters and temperature parameters at the same moment, 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 cell. 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 provide safety protection in advance for battery cells that may be at risk of thermal runaway. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0046] like Figure 1 As shown in the figure, the battery thermal runaway 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 build a three-dimensional physical model of the two. Different acquisition units are set for the battery pack and its packaging structure, and the corresponding gas parameters and temperature parameters are obtained respectively;

[0048] The gas prediction module is used to simulate the three-dimensional physical model using CFD software to obtain a 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 build a gas prediction model inside the packaging structure;

[0049] The temperature correction module is used to obtain the corrected temperature parameters at the corresponding moment based on the gas parameters and temperature parameters at the same moment, and obtain the predicted corrected temperature parameters in combination with the gas prediction model;

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

[0051] It should be further explained that, in a specific implementation process, the process of obtaining the physical parameters of the battery pack and its packaging structure and constructing a three-dimensional physical model of the two includes:

[0052] In the embodiments of the present invention, the packaging structure refers to a structural system that combines multiple battery cells and provides mechanical protection and electrical connections, with a certain amount of ventilation space inside. The physical parameters refer to relevant structural information of the battery pack and its packaging structure.

[0053] For the battery pack, its physical parameters include the type and specifications, quantity and connection method of the battery cells; for the packaging structure, its physical parameters include the outer shell, air inlet, air outlet, internal frame, battery cell arrangement, electrical connectors, thermal management components, and battery management system. 3D modeling software is used to construct 3D physical models of the battery pack and its packaging structure based on the obtained physical parameters.

[0054] It should be further explained that, in a specific implementation process, different acquisition units are set for the battery pack and its packaging structure, and the process of respectively obtaining the corresponding gas parameters and temperature parameters includes:

[0055] Since the present invention aims to provide 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). Corresponding concentration collection units are set for each of the above gases.

[0056] The concentration acquisition unit is used to obtain the concentrations of various gases inside the packaging structure in real time, including carbon monoxide concentration, hydrogen concentration, and methane concentration. The gas parameters refer to the carbon monoxide concentration, hydrogen concentration, and methane concentration 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 cell contained in the battery pack. A corresponding temperature acquisition unit is set for each battery cell, and the temperature value of each battery cell is obtained in real time through the temperature acquisition unit. The temperature parameter refers to the temperature value of each battery cell inside the packaging structure at the same time.

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

[0059] Corresponding environmental conditions are set at the air inlet and air outlet of the packaging structure of the three-dimensional physical model. For the air inlet, the environmental conditions include inlet air speed and inlet air volume, and for the air outlet, the environmental conditions include outlet air speed and outlet air volume;

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

[0061] An evaluation cycle is set, and the gas parameters inside the packaging structure after one evaluation cycle are obtained by continuously adjusting the current environmental conditions and gas parameters, and are marked as 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 building the gas prediction model inside the packaging structure includes:

[0063] Using a three-dimensional simulation model to obtain corresponding predicted gas parameters under different environmental conditions and different gas parameters, a gas prediction set is generated based on different environmental conditions and gas parameters and their corresponding predicted gas parameters, and the obtained gas prediction model is divided into a training set and a test set;

[0064] Construct a convolutional neural network, use different environmental conditions and gas parameters in the training set as input data of the convolutional neural network, use the corresponding predicted gas parameters in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network;

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

[0066] It should be further explained that, in a specific implementation process, the process of obtaining the corrected temperature parameter at the corresponding moment based on the gas parameter and temperature parameter at the same moment and obtaining the predicted corrected temperature parameter in combination with the gas prediction model includes:

[0067] The carbon monoxide concentration, hydrogen concentration, and methane concentration inside the package structure at the current moment are marked as G a , G b , G c , mark the temperature value of a single battery cell inside the packaging structure at the current moment as W q , obtain the corrected temperature value W of the single battery cell at the current moment h ;

[0068]

[0069] α and β are the preset first compensation coefficient and the second compensation coefficient, respectively, and their value ranges are 0.002-0.005 and 0.001-0.003, respectively. pis the comprehensive concentration of carbon monoxide concentration, hydrogen concentration, and methane concentration at the current moment. is the comprehensive concentration change rate within the most recent preset fixed time period, and 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 the sum of the three is equal to 1;

[0072] According to the temperature value W of the single battery cell at the current moment q and a temperature value W before a preset fixed time g , obtain the predicted temperature value W of the single battery cell after one evaluation cycle y ;

[0073]

[0074] In actual application scenarios, an airflow collection unit is set at the air inlet and air outlet of the packaging structure to obtain the actual air inlet speed and actual air volume of the air inlet and the actual air outlet speed and actual air volume of the air outlet, and use them as the actual environmental conditions;

[0075] Input the current actual environmental conditions and gas parameters into the gas prediction model, use the gas prediction model to output the predicted gas parameters after one evaluation cycle, substitute the predicted temperature value and predicted gas parameters after one evaluation cycle into the formula for obtaining the corrected temperature value to obtain the predicted corrected temperature value after one evaluation cycle;

[0076] The corrected temperature value of each 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 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 a specific implementation process, a security unit is set up to generate an early warning signal based on the predicted and corrected temperature parameters, and the process of controlling the security unit to pre-condition the battery pack includes:

[0078] Set a temperature warning threshold and compare the predicted corrected temperature value of each battery cell with the temperature warning threshold. If the predicted corrected temperature value is greater than or equal to the temperature warning threshold, the corresponding battery cell is judged to have a thermal runaway risk and a warning signal is generated. If it is less than the predicted corrected temperature value, no other action is taken.

[0079] A security unit is set up. The pre-adjustment means that when an early warning signal appears, the security unit is controlled to spray coolant on the corresponding battery cell and disconnect the corresponding battery cell from the battery pack. At the same time, the early warning signal is fed back to the relevant personnel to prompt them to perform operation and maintenance on the corresponding battery cell in a timely manner.

[0080] An embodiment of the present invention also includes a battery thermal runaway warning and safety protection method based on edge computing, comprising the following steps:

[0081] Step S1: obtaining physical parameters of the battery pack and its packaging structure, and constructing a three-dimensional physical model of the two, setting different acquisition units for the battery pack and its packaging structure, and obtaining corresponding gas parameters and temperature parameters respectively;

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

[0083] Step S3: obtaining a corrected temperature parameter at a corresponding moment based on the gas parameters and temperature parameters at the same moment, and obtaining a predicted corrected temperature parameter in combination with the gas prediction model;

[0084] Step S4: Setting a security unit to generate an early warning signal according to the predicted and corrected temperature parameters, and controlling the security unit to pre-condition the battery pack.

[0085] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The battery thermal runaway warning and safety protection system based on edge computing is characterized by: Includes the following modules: The data acquisition module is used to obtain the physical parameters of the battery pack and its packaging structure, and to build a three-dimensional physical model of the two. Different acquisition units are set for the battery pack and its packaging structure, and the corresponding gas parameters and temperature parameters are obtained respectively; The gas prediction module is used to simulate the three-dimensional physical model using CFD software to obtain a 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 build a gas prediction model inside the packaging structure; The temperature correction module is used to obtain the corrected temperature parameters at the corresponding moment based on the gas parameters and temperature parameters at the same moment, and obtain the predicted corrected temperature parameters in combination with the gas prediction model; The safety protection module is used to set the security unit, generate an early warning signal according to the predicted and corrected temperature parameters, and control the security unit to pre-condition the battery pack.

2. The battery thermal runaway warning and safety protection system based on edge computing according to claim 1 is characterized in that: The process of building a 3D physical model of the battery pack and its packaging structure includes: The packaging structure refers to a structural system that combines multiple battery cells and provides mechanical protection and electrical connections. The physical parameters of the battery pack include the type and specifications, quantity and connection method of the battery cells; The physical parameters of the packaging structure include the outer shell, air inlet, air outlet, internal frame, battery cell arrangement, electrical connectors, thermal management components, and battery management system. Three-dimensional modeling software is used to construct a three-dimensional physical model of the battery pack and its packaging structure based on the physical parameters of the battery pack.

3. The battery thermal runaway warning and safety protection system based on edge computing according to claim 2 is characterized in that: The process of setting up the acquisition unit and obtaining gas parameters and temperature parameters separately includes: A concentration acquisition unit is provided to acquire the concentrations of various gases inside the packaging structure in real time, including carbon monoxide concentration, hydrogen concentration, and methane concentration. The gas parameters refer to the carbon monoxide concentration, hydrogen concentration, and methane concentration inside the packaging structure at the same time. A temperature acquisition unit is provided for each battery cell, and the temperature value of each battery cell is acquired in real time through the temperature acquisition unit. The temperature parameter refers to the temperature value of each battery cell inside the packaging structure at the same time.

4. The battery thermal runaway warning and safety protection system based on edge computing according to claim 3 is characterized in that: The process of obtaining predicted gas parameters for different gas parameters under different environmental conditions in a 3D simulation model includes: 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 volume, and the air outlet speed and air volume; Initial gas parameters are preset inside the packaging structure of the three-dimensional physical model, and CFD software is used to simulate the gas changes inside the three-dimensional physical model to obtain a corresponding three-dimensional simulation model; An evaluation cycle is set, and the predicted gas parameters inside the package structure after one evaluation cycle are obtained by continuously adjusting the current environmental conditions and gas parameters.

5. The battery thermal runaway warning and safety protection system based on edge computing according to claim 4 is characterized in that: The process of building a gas prediction model inside a package structure includes: Generate a gas prediction set based on different environmental conditions and gas parameters and their corresponding predicted gas parameters, and divide the obtained gas prediction model into a training set and a test set; Construct a convolutional neural network, use different environmental conditions and gas parameters in the training set as input data of the convolutional neural network, use the corresponding predicted gas parameters in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network; The initial convolutional neural network is model verified using the test set, and the output of the initial convolutional neural network that is less than or equal to the preset test error threshold is used as the gas prediction model inside the packaging structure.

6. The battery thermal runaway warning and safety protection system based on edge computing according to claim 5 is characterized in that: The process of obtaining the corrected temperature parameters and combining them with the gas prediction model to obtain the predicted corrected temperature parameters includes: According to the carbon monoxide concentration G inside the packaging structure at the current moment a , hydrogen concentration G b , methane concentration G c And the temperature value W of a single battery cell q , obtain the corrected temperature value W of the single battery cell at the current moment h ; α and β are the preset first compensation coefficient and the second compensation coefficient respectively, G p is the comprehensive concentration of carbon monoxide concentration, hydrogen concentration, and methane concentration at the current moment. is the comprehensive concentration change rate within the most recent preset fixed time period, and t is the preset fixed time period; G p =ω1G a +ω2G b +ω3G c ; ω1, ω2, and ω3 are preset weight values, which are calculated based on the temperature value W of the single battery cell at the current moment. q and a temperature value W before a preset fixed time g , obtain the predicted temperature value W of the single battery cell after one evaluation cycle y ; An air flow collection unit for obtaining actual environmental conditions is provided at the air inlet and air outlet of the packaging structure in an actual application scenario. The actual environmental conditions include the actual inlet air speed and actual inlet air volume of the air inlet and the actual outlet air speed and actual outlet air volume of the air outlet; Inputting the current actual environmental conditions and gas parameters into the gas prediction model to obtain the predicted gas parameters after one evaluation cycle, substituting the predicted temperature value and the predicted gas parameters after one evaluation cycle into the formula for obtaining the corrected temperature value to obtain the predicted corrected temperature value after one evaluation cycle; The corrected temperature value of each 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 battery cell after one evaluation cycle is used as the predicted corrected temperature parameter of its battery pack.

7. The battery thermal runaway warning and safety protection system based on edge computing according to claim 6 is characterized in that: The process of generating an early warning signal and controlling the security unit to pre-condition the battery pack includes: Set a temperature warning threshold and compare the predicted corrected temperature value of each battery cell with the temperature warning threshold to identify battery cells at risk of thermal runaway and generate a warning signal; A security unit is set up, and the pre-adjustment means that when an early warning signal appears, the security unit is controlled to spray coolant on the corresponding battery cell and disconnect the corresponding battery cell from the battery pack, and at the same time, the early warning signal is fed back to relevant personnel.

8. A battery thermal runaway warning and safety protection method based on edge computing, which is implemented based on the battery thermal runaway warning and safety protection system according to any one of claims 1 to 7, characterized in that: The method comprises: Step S1: obtaining physical parameters of the battery pack and its packaging structure, and constructing a three-dimensional physical model of the two, setting different acquisition units for the battery pack and its packaging structure, and obtaining corresponding gas parameters and temperature parameters respectively; Step S2: Using CFD software to simulate the three-dimensional physical model to obtain a corresponding three-dimensional simulation model, obtaining predicted gas parameters of different gas parameters under different environmental conditions in the three-dimensional simulation model, and constructing a gas prediction model inside the packaging structure; Step S3: obtaining a corrected temperature parameter at a corresponding moment based on the gas parameters and temperature parameters at the same moment, and obtaining a predicted corrected temperature parameter in combination with the gas prediction model; Step S4: Setting a security unit to generate an early warning signal according to the predicted and corrected temperature parameters, and controlling the security unit to pre-condition the battery pack.

Images