Battery module temperature distribution inversion and inversion model construction method and device

Abstract

The invention discloses a battery module temperature distribution inversion method and device and an inversion model construction method and device. The method comprises the steps of establishing a geometric model based on geometric characteristics of an experimental battery pack, establishing a finite element temperature simulation model of the experimental battery module comprising the geometric model and an electrothermal coupling physical field, performing analog simulation on the operation state of the battery module based on the established simulation model, collecting surface and internal temperature data in the simulation process, and calculating the temperature of the battery module according to the surface and internal temperature data. And training an inversion model of the temperature of the power battery based on the obtained surface and internal temperature data to finally obtain a trained temperature distribution inversion model of the experimental battery module, and applying the temperature distribution inversion model to actual measurement. The internal temperature of the battery can be better predicted based on the surface temperature of the battery, a more accurate temperature prediction result can be obtained, the possible overheating state of the battery can be more timely and accurately predicted, the safety of the power battery is improved, and then the use safety of the electric vehicle is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicle equipment, and particularly to a method and device for inverting the temperature distribution of a battery module and constructing an inversion model. Background Art

[0002] As an energy storage device and power source for electric vehicles, the performance and lifespan of a power battery pack are greatly affected by temperature. The safe and stable operation of the battery pack is of great significance for the equipment safety and reliability of electric vehicles. Potential faults such as overheating and mechanical puncture during the storage, charging, and discharging of electric vehicle power battery packs may cause thermal runaway. Therefore, measuring the temperature of electric vehicle power battery packs and calculating their internal temperature distribution to evaluate the operating state of electric vehicles and avoid thermal runaway caused by faults such as battery overheating and mechanical puncture is of great significance for the operation and maintenance of electric vehicle power batteries.

[0003] In the prior art, the prediction of battery overheating faults is usually based on the current operating data of the battery pack using random forest regression technology for overheating probability prediction. For example, Chinese Patent Application No. CN115958957 titled "A Method and System for Predicting Overheating Faults in Charging of Power Batteries for Electric Vehicles" discloses a method and system for predicting overheating faults in charging of power batteries for electric vehicles. This method collects data on the current operation of the power battery pack, trains and constructs a random forest big data regression technology model based on a historical dataset of the operating states of power batteries under various charging conditions, predicts the battery operating data within a preset future time, and uses the future operating data as a discriminant index for faults to obtain the probability of the battery overheating fault within the preset future time. Summary of the Invention

[0004] Potential faults such as overheating and mechanical puncture during the storage, charging, and discharging of electric vehicle power battery packs may cause thermal runaway. The existing battery overheating fault prediction methods rely on pure data-driven, it is difficult to obtain a large amount of applicable and effective data during actual operation, and at the same time, the physical relationships between the battery operating principles and their various parameters are ignored, resulting in poor prediction accuracy and data utilization efficiency. At the same time, the existing methods are not applicable in the scenario where there is only a battery module without a corresponding battery management system. In summary, the battery pack overheating fault prediction methods in the prior art cannot accurately predict the overheating state of the battery, rely on the battery management system, have limited usage scenarios, and poor generality.

[0005] In view of the above problems, the present invention is proposed to provide a method and device for inverting the temperature distribution of a battery module that overcomes the above problems or at least partially solves the above problems.

[0006] In a first aspect, an embodiment of the present invention provides a method for constructing an inversion model of the temperature distribution of a battery module, including:

[0007] Obtain the temperature simulation results of simulating the temperature of the experimental battery module under multiple loading conditions of a preset working condition by using the finite element temperature simulation model of the experimental battery module; the finite element temperature simulation model includes the geometric model of the experimental battery pack and the electrothermal coupling physical field constructed based on the geometric model, and the electrothermal coupling physical field at least includes the electric field distribution relationship, the temperature distribution relationship, and the total cumulative heat determined based on the relationship;

[0008] Based on the temperature simulation results, obtain a temperature distribution data set including each set of loading conditions and the corresponding temperature distribution data; the temperature distribution data includes the surface temperature and the internal temperature of the battery module;

[0009] Use the temperature distribution data set to train the pre-established inversion model of the power battery temperature to obtain the temperature distribution inversion model of the experimental battery module.

[0010] In some optional embodiments, the process of establishing the finite element temperature simulation model of the experimental battery module is as follows:

[0011] Based on the geometric characteristics of the experimental battery module, construct the geometric model of the experimental battery module;

[0012] Perform mesh division on the geometric model of the battery module by using the mesh division method to obtain the mesh data of the geometric model;

[0013] Discretize the Maxwell equations and the solid heat transfer equation of the experimental battery module, and construct the electrothermal coupling physical field according to the mesh data, the discretized equations, and the discretized solid heat transfer equation.

[0014] In some optional embodiments, using the finite element temperature simulation model of the experimental battery module to simulate the temperature of the experimental battery module under multiple loading conditions of a preset working condition, and obtain the temperature simulation results, including:

[0015] Set the working conditions of the experimental battery module and multiple sets of loading conditions under different working conditions;

[0016] Simulate the operating state of the battery under different loading conditions through the finite element temperature simulation model of the experimental battery module; and collect the surface temperature and the internal temperature of the experimental battery module under the loading conditions to obtain the temperature distribution data of the experimental battery module under multiple loading conditions of the preset working condition;

[0017] The preset working condition includes at least one of a normal working condition and a fault working condition; the loading conditions include at least one of the simulation model ambient temperature, the internal short circuit fault condition, and the per unit value of the charging power.

[0018] In some alternative embodiments, a temperature distribution data set including each set of loading conditions and corresponding temperature distribution data is obtained, including:

[0019] Obtain the temperature distribution data of the experimental battery module under each set of loading conditions; the temperature distribution data includes the internal temperature of the experimental battery module and its corresponding surface temperature;

[0020] According to each set of loading conditions and the corresponding temperature distribution data, establish multiple groups of first temperature distribution arrays;

[0021] Construct a temperature distribution data set of the experimental battery module based on multiple groups of first temperature distribution arrays.

[0022] In some alternative embodiments, the above method further includes:

[0023] Normalize the temperature in each group of first temperature distribution arrays in the temperature distribution data set through the following formula: where is the normalized temperature data, T i is the temperature data at the selected temperature point; T max and T min are respectively the maximum temperature and the minimum temperature in the first temperature distribution array.

[0024] In some alternative embodiments, use the temperature distribution data set to train a pre-established inverse model of the power battery temperature to obtain an inverse model of the temperature distribution of the experimental battery module, including:

[0025] Divide the temperature distribution data set into N1 groups of first temperature distribution sub-arrays under normal conditions and N2 groups of first temperature distribution sub-arrays under fault conditions according to the accuracy requirements, and each group of first temperature distribution sub-arrays is represented by a feature quantity matrix composed of M data;

[0026] Input the N1 groups of first temperature distribution sub-arrays under normal conditions and the N2 groups of first temperature distribution sub-arrays under fault conditions into the pre-constructed inverse model of the power battery temperature based on the backpropagation neural network respectively, output the predicted value of the internal temperature of the experimental battery module, adjust the parameters of the inverse model based on the predicted value of the internal temperature and the internal temperature of the experimental battery module included in the temperature distribution data set, and repeat the process of model training until the model meets the preset convergence conditions, and obtain the trained inverse model of the power battery temperature as the inverse model of the temperature distribution of the test battery module.

[0027] In some alternative embodiments, adjust the parameters of the inverse model based on the predicted value of the internal temperature and the internal temperature of the experimental battery module included in the temperature distribution sub-array, and repeat the process of model training until the model meets the preset convergence conditions, including:

[0028] Calculate the error result between the predicted value of the internal temperature output by the inversion model and the measured value of the internal temperature of the experimental battery module included in the temperature distribution dataset according to the pre-constructed error function, and calculate the partial derivative of the error with respect to the initial weights of the inversion model to obtain the weight adjustment gradient of the inversion model, and update the weights according to the weight adjustment gradient; the error function of the inversion model is where O i is the predicted value of the internal temperature output by the inversion model, and t i is the measured value of the internal temperature of the experimental battery module obtained from the simulation model;

[0029] Repeat the process of model training and error calculation. After multiple iterations, until the error reaches the preset requirement, the training is completed.

[0030] In a second aspect, an embodiment of the present invention provides a method for inverting the temperature distribution of a battery module, including:

[0031] Collect the surface temperature distribution data of the experimental battery module to be predicted under the loading conditions of the preset working condition, and input the loading conditions of the preset working condition and the corresponding surface temperature distribution data into the temperature distribution inversion model of the trained experimental battery module to output the internal temperature of the experimental battery module under the preset working condition;

[0032] The temperature distribution inversion model is trained by using the above battery module temperature distribution inversion model construction method.

[0033] In some optional embodiments, collecting the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working condition includes:

[0034] When the experimental battery module is under the preset working condition and the preset loading condition, obtain the temperature at the surface points of the battery module measured by the temperature sensors arranged in the finite element temperature simulation model of the experimental battery module, and obtain the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working condition.

[0035] In some optional embodiments, the temperature sensors arranged in the finite element temperature simulation model of the experimental battery module include:

[0036] A temperature sensors arranged at the positive electrode of the battery, B temperature sensors arranged at the negative electrode of the battery, and C temperature sensors arranged on the side of the battery. The C temperature sensors arranged on the side of the battery are evenly arranged.

[0037] In a third aspect, an embodiment of the present invention provides a device for constructing a temperature distribution inversion model of a battery module, including:

[0038] A data acquisition module, configured to obtain temperature simulation results of simulating the temperature of an experimental battery module under multiple loading conditions of a preset working condition by using a finite element temperature simulation model of the experimental battery module; the finite element temperature simulation model includes an experimental battery pack geometric model and an electro-thermal coupling physical field constructed based on the geometric model, and the electro-thermal coupling physical field at least includes an electric field distribution relationship, a temperature distribution relationship, and a total accumulated heat determined based on the above relationships; a temperature distribution data set including each set of loading conditions and corresponding temperature distribution data is obtained based on the temperature simulation results; the temperature distribution data includes the surface temperature and the internal temperature of the battery module;

[0039] A model construction module, configured to use the temperature distribution data set to train a pre-established inverse model of the power battery temperature to obtain an inverse model of the temperature distribution of the experimental battery module.

[0040] In a fourth aspect, an embodiment of the present invention provides a device for inverting the temperature distribution of a battery module, including:

[0041] A data collection module, configured to collect surface temperature distribution data of the experimental battery module to be predicted under the loading conditions of a preset working condition;

[0042] A temperature prediction module, configured to input the loading conditions of the preset working condition and the corresponding surface temperature distribution data into the trained inverse model of the temperature distribution of the experimental battery module, and output the internal temperature of the experimental battery module under the preset working condition; the inverse model of the temperature distribution is trained by using the method for constructing the inverse model of the temperature distribution of the battery module.

[0043] An embodiment of the present invention provides a computer storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the method for constructing the inverse model of the temperature distribution of the battery module or the method for inverting the temperature distribution of the battery module is implemented.

[0044] An embodiment of the present invention provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method for constructing the inverse model of the temperature distribution of the battery module or the method for inverting the temperature distribution of the battery module is implemented.

[0045] The beneficial effects of the above technical solutions provided by the embodiments of the present invention at least include:

[0046] The method for constructing an inversion model of the temperature distribution of a battery module provided by an embodiment of the present invention establishes a geometric model based on the geometric characteristics of an experimental battery pack, and constructs a thermoelectric coupling physical field based on the geometric model to reflect the physical laws and battery operating states of the experimental battery pack. Finally, a finite element temperature simulation model of the experimental battery module including the geometric model and the thermoelectric coupling physical field is established. The operating state of the battery module is simulated and analyzed based on the constructed simulation model, and the surface and internal temperature data during the simulation process are collected. The temperature data obtained in this way can reflect the physical relationship between various battery parameters and is closer to the actual situation of the experimental battery pack. The inversion model of the power battery temperature is trained based on the obtained surface and internal temperature data. The trained model can better predict the battery internal temperature based on the battery surface temperature and obtain a more accurate temperature prediction result, and more timely and accurately predict the possible overheating state of the battery.

[0047] The method for inverting the temperature distribution of a battery module provided by an embodiment of the present invention predicts the internal temperature of an experimental battery pack based on the model obtained by the above training method and the surface temperature distribution data of the experimental battery pack under the loading conditions of a preset working condition. Thus, an accurate temperature prediction result can be obtained, the temperature change situation inside the battery can be predicted in a timely manner, and a timely warning can be given and corresponding measures can be taken when overheating may occur, so as to avoid accidents caused by overheating, improve the safety of the power battery, and further ensure the use safety of the electric vehicle.

[0048] Compared with the traditional method, the above method for constructing an inversion model of the temperature distribution of a battery module and the method for inverting the temperature distribution of a battery module have the characteristics driven by a physical model, can generate a large amount of data based on the physical model, avoid the disadvantages of limited or incomplete battery operating state data in the traditional method, and make the calculation result more accurate. At the same time, this method does not depend on the battery management system, has better applicability, is not limited to batteries with a battery management system, can obtain the battery temperature distribution characteristics through data analysis and realize the evaluation of the battery state, and has a wider applicable scenario.

[0049] Other features and advantages of the present invention will be described in the following specification, and in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written specification, claims, and drawings.

[0050] The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0051] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, but do not constitute a limitation to the present invention. In the drawings:

[0052] Figure 1 It is a flowchart of the method for constructing the battery module temperature distribution inversion model in Embodiment 1 of the present invention;

[0053] Figure 2 It is a flowchart of the training of the battery module temperature distribution inversion model in Embodiment 1 of the present invention;

[0054] Figure 3 It is a schematic structural diagram of the device for constructing the battery module temperature distribution inversion model in Embodiment 1 of the present invention;

[0055] Figure 4 It is a flowchart of the battery module temperature distribution inversion method in Embodiment 2 of the present invention;

[0056] Figure 5 It is an example diagram of the temperature change curve in Embodiment 2 of the present invention;

[0057] Figure 6 It is a schematic structural diagram of the battery module temperature distribution inversion device in Embodiment 2 of the present invention. Detailed implementation manners

[0058] As an energy storage device and power source of an electric vehicle, the performance and life of the power battery pack are greatly affected by temperature. The safe and stable operation of the battery pack is of great significance to the equipment safety and reliability of the electric vehicle. Therefore, it is of great significance to measure the temperature of the electric vehicle power battery pack, calculate and obtain its internal temperature distribution, so as to evaluate the operating state of the electric vehicle, avoid thermal runaway caused by battery overheating, mechanical puncture and other faults, and carry out operation and maintenance of the electric vehicle power battery.

[0059] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0060] The battery overheating fault prediction method in the prior art relies on pure data driving, and it is difficult to obtain a large amount of applicable and effective data during actual operation. At the same time, it ignores the battery operation principle and the physical relationship between its various parameters, and the prediction accuracy and data utilization efficiency are poor. At the same time, the existing methods are not applicable in the situation where there is only a battery module and no corresponding battery management system.

[0061] To solve the problems of inaccurate prediction, poor data utilization efficiency existing in the prior art, and inapplicability in the situation where there is only a battery module but lacking a corresponding battery management system, an embodiment of the present invention provides a method for inverting the temperature distribution of a battery module and constructing an inversion model.

[0062] Embodiment 1

[0063] An embodiment 1 of the present invention provides a method for constructing an inversion model of the temperature distribution of a battery module, and its process is as Figure 1 shown, including the following steps:

[0064] Step S101: Obtain the temperature simulation results of simulating the temperature of a plurality of loading conditions of a preset working condition of an experimental battery module by using a finite element temperature simulation model of the experimental battery module.

[0065] Step S102: Based on the temperature simulation results, obtain a temperature distribution data set including each group of loading conditions and the corresponding temperature distribution data.

[0066] Step S103: Use the temperature distribution data set to train a pre-established inversion model of the power battery temperature to obtain an inversion model of the temperature distribution of the experimental battery module.

[0067] Preferably, in the above step S101, the finite element temperature simulation model includes an experimental battery pack geometric model, an electro-thermal coupling physical field constructed based on the geometric model, and the electro-thermal coupling physical field at least includes an electric field distribution relationship, a temperature distribution relationship, and a total accumulated heat determined based on the relationship;

[0068] Preferably, a finite element temperature simulation model of the experimental battery module can be pre-established for use in temperature simulation and collecting temperature distribution data of the battery module under simulation conditions. The establishment process of the finite element temperature simulation model of the experimental battery module is as follows:

[0069] Based on the geometric characteristics of the experimental battery module, construct an experimental battery module geometric model;

[0070] Perform mesh division on the battery module geometric model by using a mesh generation method to obtain the mesh data of the geometric model;

[0071] Discretize the Maxwell equations and the solid heat transfer equation of the experimental battery module, and construct an electro-thermal coupling physical field according to the mesh data, the discretized equations, and the discretized solid heat transfer equation.

[0072] In this embodiment, a finite element temperature simulation model of a single lithium-ion battery module is established by the above method for establishing a finite element temperature simulation model of the experimental battery module:

[0073] Based on the geometric characteristics of the lithium-ion battery module, a geometric model of the experimental battery module is constructed, where the material and set parameters of the lithium-ion battery module in the set area are shown in Table 1;

[0074] Table 1

[0075]

[0076] The geometric model of the lithium-ion battery module is meshed by the mesh dissection method to obtain the mesh data of the geometric model of the lithium-ion battery module; the mesh dissection method can adopt the ANSYS Maxwell adaptive mesh dissection method, or other mesh dissection methods according to actual needs, and no specific restrictions are made here;

[0077] The Maxwell equations and the solid heat transfer equation of the lithium-ion battery module are discretized. Based on the mesh data of the geometric model of the lithium-ion battery module, the discretized equations, and the discretized solid heat transfer equation, an electro-thermal coupling physical field is constructed; the electro-thermal coupling physical field constructed based on the geometric model can reflect the physical laws and battery operating states during the operation of the experimental battery pack. Finally, a finite element temperature simulation model of the experimental battery module including the geometric model and the electro-thermal coupling physical field is established. This finite element temperature simulation model can take into account the physical relationships between various battery parameters, so that the temperature distribution data obtained based on the simulation model is closer to the real data during battery operation.

[0078] Preferably, the constructed electro-thermal coupling physical field includes at least the electric field distribution relationship, the temperature distribution relationship, and the total accumulated heat determined based on the above relationships.

[0079] Optionally, the relationship between ion concentration migration and current density can be added to the above electro-thermal coupling physical field to reflect the strength of the electric field, which can make the constructed electro-thermal coupling physical field more accurately and realistically reflect the operating state in the lithium-ion battery module and simulate more accurate temperature data.

[0080] According to the following formula, a coupling relationship between the solid active material phase and the electrolyte phase in the porous electrode is established:

[0081]

[0082]

[0083] where j loc represents the local current density; j 0 is the exchange current density, c surf represents the insertion exchange current on the surface of the active material; α a , α c represent the transfer coefficients at the anode and cathode; represents the solid-phase potential in the battery; Represents the liquid-phase potential in the battery; E OCP Represents the open-circuit voltage of the battery; F represents the Faraday constant; R represents the gas constant; a represents the specific area of the active material; j L Is the current density in the liquid phase, J n Represents the normal-phase current density, T is the temperature;

[0084] The migration relationship of lithium-ion concentration with time is established according to the following formula:

[0085]

[0086] Where c L Represents the lithium-ion concentration; t represents time; V m LiPF6 Represents the molar volume of LiPF 6 ; ε L Represents the dielectric constant of the battery liquid phase; β L Represents the Brigman constant in the liquid phase; D L Represents the diffusion coefficient in the liquid phase; The value is (0.28687×(c L / 1000)2 + 0.74678×(c L / 1000) + 0.44103) / (1 - t Li+ solv ); c solv Represents the lithium-ion concentration with respect to the solvent; c L tot Represents the total lithium-ion concentration; t Li+ solv Represents the lithium-ion transference number with respect to the solvent, j L Is the current density in the liquid phase; T is the temperature.

[0087] The mass transport of lithium in the positive and negative electrode active material particles is assumed to be diffusion along the particle radius / thickness and is described by Fick's second law.

[0088] Preferably, an energy balance is established based on the above electric field distribution relationship and temperature distribution relationship to determine the heat in the local area of the battery module, and the internal heat generation power of the battery is calculated according to the following formula: q cc / sc =(js) 2 / σ, where, j S Is the current density; σ is the electronic conductivity, q cc / scis the heating power of local domain Joule heat; the total accumulated heat inside the battery is determined by calculating the relationship between the heating power and the time variation during the battery operation. Further calculating the total accumulated heat inside the battery in the physical field with the electric field distribution relationship and the temperature distribution relationship can make the finally established finite element temperature simulation model more truly reflect the operation state of the battery, and the data obtained from this model will be more accurate.

[0089] Preferably, in the above step S101, the finite element temperature simulation model of the experimental battery module is used to simulate the temperature under multiple loading conditions of the preset working conditions of the experimental battery module, and the temperature simulation results are obtained, including:

[0090] Set the working conditions of the experimental battery module and multiple groups of loading conditions under different working conditions;

[0091] Simulate the operation state of the battery under different loading conditions through the finite element temperature simulation model of the experimental battery module; and collect the surface temperature and internal temperature of the experimental battery module under the loading conditions to obtain the temperature distribution data of the experimental battery module under multiple loading conditions of the preset working conditions;

[0092] The preset working conditions include at least one of normal working conditions and fault working conditions; the loading conditions include at least one of the simulation model environment temperature, internal short circuit fault conditions, and per unit value of charging power.

[0093] When the finite element temperature simulation model of the battery module is under different loading conditions, simulate the operation state of the battery, and obtain the temperature distribution data based on the simulation model. According to the finite element temperature simulation model, a large amount of accurate temperature data can be obtained, which can effectively improve the problem that it is difficult to obtain a large amount of applicable and effective data in the traditional method. The above loading conditions include at least one of the simulation model environment temperature, internal short circuit fault conditions, and per unit value of charging power. Among them, the internal short circuit fault conditions can be realized by setting the internal short circuit fault radius. When the internal short circuit fault radius is 0, it means that the battery module is operating under normal working conditions at this time. When the internal short circuit fault radius is other values, it is regarded as a fault working condition; the value of the per unit value of charging power depends on the ratio between the test charging power of this battery module and the full-load charging power under standard working conditions.

[0094] Preferably, in the above step S102, based on the temperature simulation results, a temperature distribution data set including each group of loading conditions and the corresponding temperature distribution data is obtained, including:

[0095] Obtain the temperature distribution data of the experimental battery module under each group of loading conditions; the temperature distribution data includes the internal temperature of the experimental battery module and its corresponding surface temperature;

[0096] Based on each set of loading conditions and the corresponding temperature distribution data, multiple sets of first temperature distribution arrays are established;

[0097] Based on multiple sets of first temperature distribution arrays, a temperature distribution data set of the experimental battery module is constructed.

[0098] Each set of loading conditions includes but is not limited to the environmental temperature of the simulation model, the internal short - circuit fault condition, and the per - unit value of the charging power. By changing the values of the loading conditions, multiple sets of loading conditions are obtained. The first temperature distribution arrays established include the temperature distribution data sets of each set of loading conditions and the corresponding temperature distribution data. For example, a set of first temperature distribution arrays can be expressed in the following form [T 0 , ……, T n , T = 0°C, R = 0um, C_rate = 1]. This array represents the temperature distribution data of the battery module obtained under the loading conditions of an environmental temperature of 0°C, an internal short - circuit fault radius of 0um, and a per - unit value of the charging power of 1. The working condition at this time is the normal working condition. Among them, T 0 ~T n represent the internal temperature of the battery module at the selected points and the corresponding temperature of the battery surface; the first temperature distribution array [T 0 , ……, T n , T = 0°C, R = 10um, C_rate = 1]. This array represents the temperature distribution data of the battery module obtained under the loading conditions of an environmental temperature of 0°C, an internal short - circuit fault radius of 10um, and a per - unit value of the charging power of 1. The working condition at this time is the fault working condition; among them, the environmental temperature of the simulation model, the internal short - circuit fault condition, and the per - unit value of the charging power can be changed according to requirements, and T 0 ~T n at different points can also be selected according to requirements. In this embodiment, the environmental temperature can be 0°C, 20°C, 40°C, ……, the internal short - circuit fault radius can be 0um, 10um, 20um, ……, the per - unit value of the charging power can be 1, 3, 5, …… Of course, the value of the loading conditions can also be specified according to actual needs. By changing the values of the loading conditions of the experimental battery module, temperature distribution data under multiple sets of loading conditions can be obtained.

[0099] Preferably, in the above step S102, it further includes:

[0100] Normalize the temperature in each set of first temperature distribution arrays in the temperature distribution data set through the following formula: where is the normalized temperature data, T i is the temperature data at the selected temperature point; T max and T minare the maximum temperature and the minimum temperature in the first temperature distribution array respectively. The purpose of normalization is to unify the numerical ranges between different features to the same scale, improving the training effect of the model and the accuracy of prediction.

[0101] Preferably, in the above step S103, the pre-established inversion model of the power battery temperature is trained using the temperature distribution data set to obtain the temperature distribution inversion model of the experimental battery module, including:

[0102] The temperature distribution data set is divided into the first temperature distribution sub-arrays of N1 groups under normal conditions and the first temperature distribution sub-arrays of N2 groups under fault conditions according to the accuracy requirement. Each first temperature distribution sub-array is represented by a feature quantity matrix composed of M data;

[0103] The first temperature distribution sub-arrays of N1 groups under normal conditions and the first temperature distribution sub-arrays of N2 groups under fault conditions are respectively input into the inversion model of the power battery temperature pre-constructed based on the backpropagation neural network, and the internal temperature prediction values of the experimental battery module are output. Based on the internal temperature prediction values and the internal temperature of the experimental battery module included in the temperature distribution data set, the parameters of the inversion model are adjusted, and the process of model training is repeated until the model meets the preset convergence condition, and the trained inversion model of the power battery temperature is obtained as the temperature distribution inversion model of the test battery module.

[0104] For example, it can be divided into the first temperature distribution sub-arrays of N1 groups under normal conditions and the first temperature distribution sub-arrays of N2 groups under fault conditions according to the time accuracy. Each first temperature distribution sub-array is represented by a feature quantity matrix composed of M data. In this embodiment, a feature quantity matrix composed of 11 data is adopted, including the temperature data of 8 temperature points and 3 data of loading conditions, such as in the following form: [T0,……, T7, T = 0℃, R = 0um, C_rate = 1], [T0,……, T7, T = 20℃, R = 10um, C_rate = 3], [T0,……, T7, T = 40℃, R = 20um, C_rate = 5],…… According to the value of the internal short-circuit fault radius R, the sub-arrays under N1 normal conditions and the sub-arrays under fault conditions in the first temperature distribution array can be determined. Since the working state of the battery is generally only normal operation and fault, it is necessary to divide the temperature distribution data under different conditions, and input the temperature distribution data under normal conditions and fault conditions into the power battery temperature reproduction model for training. In this way, the trained model will be more accurate, making the output data closer to the true value, thereby improving the accuracy of temperature prediction.

[0105] Preferably, based on the predicted internal temperature value and the internal temperature of the experimental battery module included in the temperature distribution sub-array, the inversion model is tuned, and the process of model training is repeatedly executed until the model meets the preset convergence conditions, including:

[0106] According to the pre-constructed error function, calculate the error result between the predicted value of the internal temperature output by the inversion model and the measured value of the internal temperature of the experimental battery module included in the temperature distribution dataset, and calculate the partial derivative of the error with respect to the initial weight of the inversion model, obtain the weight adjustment gradient of the inversion model, and update the weight according to the weight adjustment gradient; the error function of the inversion model is where O i is the predicted value of the internal temperature output by the inversion model, and t i is the measured value of the internal temperature of the experimental battery module obtained from the simulation model;

[0107] Repeat the process of model training and error calculation. After multiple iterations, until the error reaches the preset requirement, the training is completed.

[0108] During the process of model training, after giving the input data and initial weights of the model, the predicted value of the internal temperature can be output. However, whether this output value is true and effective needs to be judged by calculating the error function between the predicted value of the internal temperature output and the measured value of the internal temperature of the experimental battery module obtained from the simulation model. When the error is large, the weights need to be adjusted and the next training is carried out. Continuously adjust the calculation error and adjust the weights, so as to finally minimize the error and make the model fit better. The method of adjusting the weights is to calculate the partial derivative of the error with respect to the weights, obtain the adjustment gradient of the weights, and continuously update and adjust the weights according to the adjustment gradient during the iteration process. In this embodiment, the temperature distribution inversion model of the power battery is trained according to the temperature distribution data obtained from the temperature simulation model of the lithium battery. Therefore, the trained temperature distribution inversion model of the power battery is used as the temperature distribution inversion model of the battery module of the lithium battery, and then the temperature distribution inversion model of the battery module of the lithium battery is applied to the actual application.

[0109] Figure 2 FIG. is the flow chart of the training of the temperature distribution inversion model of the battery module. First, set the numerical values of different loading conditions, then input the loading conditions into the finite element temperature simulation model for temperature simulation. After obtaining the temperature distribution data, according to the loading conditions and the corresponding temperature distribution data, see the sample set of model training. Finally, through multiple iterations of training, until the model meets the training requirements, the trained temperature distribution inversion model of the experimental battery module is obtained.

[0110] Based on the same inventive concept, the embodiment of the present invention also provides a device for constructing a temperature distribution inversion model of a battery module. This device can be set in a device with the ability to process computer instructions. The structure of this device is asFigure 3 As shown in

[0111] a data acquisition module 11, configured to obtain temperature simulation results of simulating the temperature of an experimental battery module under multiple loading conditions of a preset working condition by using a finite element temperature simulation model of the experimental battery module; the finite element temperature simulation model includes an experimental battery pack geometric model and an electrothermal coupling physical field constructed based on the geometric model, and the electrothermal coupling physical field at least includes an electric field distribution relationship, a temperature distribution relationship, and a total accumulated heat determined based on the relationship; a temperature distribution data set including each group of loading conditions and corresponding temperature distribution data is obtained based on the temperature simulation results; the temperature distribution data includes the surface temperature and the internal temperature of the battery module;

[0112] a model construction module 12, configured to train an inverse model of the power battery temperature established in advance by using the temperature distribution data set to obtain an inverse model of the temperature distribution of the experimental battery module.

[0113] Preferably, the model construction module 12 is specifically configured to input the first temperature distribution sub-arrays of N1 groups of normal working conditions and the first temperature distribution sub-arrays of N2 groups of fault working conditions in the temperature distribution data set into the inverse model of the power battery temperature pre-constructed based on the backpropagation neural network respectively, output the predicted value of the internal temperature of the experimental battery module, adjust the parameters of the inverse model based on the predicted value of the internal temperature and the internal temperature of the experimental battery module included in the temperature distribution data set, and repeat the process of model training until the model meets the preset convergence condition, and obtain the trained inverse model of the power battery temperature as the inverse model of the temperature distribution of the test battery module.

[0114] Regarding the device for constructing the inverse model of the battery module temperature distribution in the above embodiment, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0115] In the above method and device of this embodiment, a geometric model is established based on the geometric characteristics of the experimental battery pack, and an electrothermal coupling physical field is constructed based on the geometric model to reflect the physical laws of the operation of the experimental battery pack and the battery operation state. Finally, a finite element temperature simulation model of the experimental battery module including the geometric model and the electrothermal coupling physical field is established. The operation state of the battery pack is simulated and analyzed based on the constructed simulation model, and the surface and internal temperature data during the simulation process are collected. The temperature data obtained in this way can reflect the physical relationship between the battery parameters and is closer to the actual situation of the experimental battery pack; the inverse model of the power battery temperature is trained based on the obtained surface and internal temperature data. The trained model can better predict the battery internal temperature based on the battery surface temperature and obtain more accurate temperature prediction results, and more timely and accurately predict the possible overheating state of the battery.

[0116] Embodiment 2

[0117] A specific implementation process of the battery module temperature distribution inversion method provided in the second embodiment of the present invention is as follows Figure 4 shown, including the following steps:

[0118] Step S201: Collect the surface temperature distribution data of the experimental battery module to be predicted under the loading conditions of the preset working conditions;

[0119] Step S202: Input the loading conditions of the preset working conditions and the corresponding surface temperature distribution data into the temperature distribution inversion model of the trained experimental battery module, and output the internal temperature of the experimental battery module under the preset working conditions;

[0120] Preferably, in the above step S201, collecting the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working conditions includes:

[0121] When the experimental battery module is under the preset working conditions and preset loading conditions, obtain the temperature at the surface points of the battery module measured by the temperature sensors arranged in the finite element temperature simulation model of the experimental battery module, and obtain the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working conditions.

[0122] Preferably, after obtaining the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working conditions, establish a second temperature distribution array according to the loading conditions of the preset working conditions and the corresponding surface temperature distribution data.

[0123] Preferably, the temperature sensors arranged in the finite element temperature simulation model of the experimental battery module include: A temperature sensors arranged at the positive electrode of the battery, B temperature sensors arranged at the negative electrode of the battery, and C temperature sensors arranged on the side of the battery. The C temperature sensors arranged on the side of the battery are evenly arranged.

[0124] For example, when collecting the surface temperature distribution data of a lithium battery under normal working conditions, the loading conditions can be set as T = 20°C, R = 0um, C_rate = 1. Measure the temperature of the area on the battery surface through 1 temperature sensor arranged at the positive electrode of the battery, 1 temperature sensor arranged at the negative electrode of the battery, and 6 temperature sensors arranged on the side of the battery. The 6 temperature sensors arranged on the side of the battery are evenly arranged, and the distance between the temperature sensors can be set, for example, it can be 776um. Mark the measured temperatures as T1 - T8 in sequence, and construct the second temperature distribution array [T1, T2,..., T8, T = 20°C, R = 0um, C_rate, R = 1].

[0125] Preferably, in the above step S202, the loading conditions of the preset working conditions and the corresponding surface temperature distribution data are input into the temperature distribution inversion model of the trained experimental battery module, and the internal temperature of the experimental battery module under the preset working conditions is output; wherein the temperature distribution inversion model of the experimental battery module is obtained by the battery module temperature distribution inversion model construction method in Embodiment 1. The trained temperature distribution inversion model of the experimental battery module can predict the internal temperature of the battery according to the battery surface temperature, can evaluate the battery state without relying on the battery management system, and can obtain the battery temperature distribution characteristics through data analysis. The applicable scenarios are more extensive. The temperature distribution inversion model obtained in this embodiment is for the battery module of lithium batteries, and the temperature distribution inversion models of other battery modules can be retrained according to actual situations.

[0126] Preferably, the above step S202 further includes:

[0127] Fit the internal temperature of the experimental battery module under the preset working conditions output, and obtain a temperature change curve.

[0128] As time goes by, the temperature of the lithium battery will change continuously. Therefore, the temperature measured at the battery surface points at each moment is constantly changing. Since the internal heat generation of the battery causes the temperature to be measured on the battery surface, the internal temperature is also constantly changing. By fitting the internal temperatures of the experimental battery module under the preset working conditions output at multiple moments, a temperature change curve can be obtained. From the temperature change curve, it can be determined at what time the temperature will reach the highest value. When the internal temperature of the battery is about to reach the highest temperature value, a high-temperature warning prompt is issued, thereby avoiding the thermal runaway phenomenon and improving the equipment safety and reliability of the electric vehicle.

[0129] Figure 5 is an example diagram of the temperature change curve. This curve is obtained under normal working conditions with an ambient temperature of 20°C and a per-unit value of the charging power of 1 for multiple groups of second temperature distribution arrays. The data in the multiple groups of second temperature distribution arrays are input into the temperature distribution inversion model of the battery module of the lithium battery, and the internal temperature of the lithium battery at multiple moments is output. The temperature change curve fitted according to the internal temperatures at multiple moments is composed of Figure 5 It can be seen that when the battery module of the lithium battery is working normally, when the ambient temperature is 20°C and the per-unit value of the charging power is 1, as time increases, the temperature gradually rises, and after reaching the highest value of 58°C at 0.008 s, the internal temperature of the battery module tends to be stable.

[0130] Steps S201 to S202 realize the prediction of the internal temperature of the experimental battery pack based on the trained temperature distribution inversion model of the experimental battery module and the surface temperature distribution data of the experimental battery pack under the loading conditions of the preset working conditions, so as to obtain accurate temperature prediction results.

[0131] Based on the same inventive concept, an embodiment of the present invention further provides a device for inverting the temperature distribution of a battery module. This device can be arranged in a device with the ability to process computer instructions, and the structure of the device is as follows Figure 6 shown, including:

[0132] A data acquisition module 21, configured to acquire the surface temperature distribution data of an experimental battery module to be predicted under the loading conditions of a preset working condition;

[0133] A temperature prediction module 22, configured to input the loading conditions of the preset working condition and the corresponding surface temperature distribution data into the trained temperature distribution inversion model of the experimental battery module, and output the internal temperature of the experimental battery module under the preset working condition; the temperature distribution inversion model is trained by using the method for constructing a temperature distribution inversion model of a battery module.

[0134] Preferably, the temperature prediction module 22 is further configured to fit the internal temperature of the experimental battery module under the preset working condition output, to obtain a temperature change curve.

[0135] Regarding the device for inverting the temperature distribution of the battery module in the above embodiment, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0136] The above method and device of the embodiment of the present invention predict the internal temperature of the experimental battery pack based on the trained temperature distribution inversion model of the battery module and the surface temperature distribution data of the experimental battery pack under the loading conditions of the preset working condition, so as to obtain accurate temperature prediction results, timely predict the temperature change situation inside the battery, give a warning prompt in time when overheating may occur and perform corresponding processing, avoid accidents caused by overheating, improve the safety of power batteries, and thus ensure the use safety of electric vehicles.

[0137] Unless otherwise specifically stated, terms such as processing, calculating, computing, determining, displaying, etc. may refer to the actions and / or processes of one or more processing or computing systems, or similar devices, which operate on and transform data represented as physical (such as electronic) quantities in the registers or memories of the processing system into other data similarly represented as physical quantities in the memories, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different technologies and methods. For example, the data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0138] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of the present disclosure. The appended method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy recited.

[0139] In the foregoing detailed description, various features are combined in a single embodiment to simplify the present disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are expressly recited in each claim. Rather, as reflected in the appended claims, the invention lies in less than all of the features of a single disclosed embodiment. Accordingly, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0140] Those skilled in the art should also understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments herein can be implemented as electronic hardware, computer software, or combinations thereof. To clearly illustrate the interchangeability of hardware and software, the various illustrative components, blocks, modules, circuits, and steps have been generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in a variety of ways for each particular application, but such implementation decisions should not be interpreted as departing from the scope of the present disclosure.

[0141] The steps of a method or algorithm described in connection with the embodiments herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination thereof. The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also exist as discrete components in a user terminal.

[0142] For software implementation, the techniques described in this application can be implemented by modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is communicatively coupled to the processor via various means, which are well known in the art.

[0143] The above description includes examples of one or more embodiments. Of course, it is not possible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but those of ordinary skill in the art should recognize that the various embodiments can be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Further, with respect to the term "comprising" used in the specification or claims, the word is intended to be construed in a manner similar to the term "including" as interpreted when "including" is used as a transitional word in a claim. Additionally, any use of the term "or" in the claims or specification is to mean "non-exclusive or".

Claims

1. A method for constructing an inversion model of the temperature distribution of a battery module, characterized in that, it includes: Obtain the temperature simulation results of simulating the temperature under multiple loading conditions of the preset working conditions of the experimental battery module by using the finite element temperature simulation model of the experimental battery module; The finite element temperature simulation model includes an experimental battery pack geometric model and an electro-thermal coupling physical field constructed based on the geometric model. The electro-thermal coupling physical field at least includes the electric field distribution relationship, the temperature distribution relationship, and the total accumulated heat determined based on the relationship; Based on the temperature simulation results, obtain a temperature distribution data set including each group of loading conditions and the corresponding temperature distribution data; the temperature distribution data includes the surface temperature and the internal temperature of the battery module; Use the temperature distribution data set to train the pre-established inversion model of the power battery temperature to obtain the temperature distribution inversion model of the experimental battery module.

2. The method according to claim 1, characterized in that, The process of establishing the finite element temperature simulation model of the experimental battery module is as follows: Based on the geometric characteristics of the experimental battery module, construct the experimental battery module geometric model; Perform mesh division on the battery module geometric model by using the mesh division method to obtain the mesh data of the geometric model; Discretize the Maxwell equations and the solid heat transfer equation of the experimental battery module, and construct an electro-thermal coupling physical field according to the mesh data, the discretized equations, and the discretized solid heat transfer equation.

3. The method according to claim 1, characterized in that, The process of using the finite element temperature simulation model of the experimental battery module to simulate the temperature under multiple loading conditions of the preset working conditions of the experimental battery module and obtain the temperature simulation results includes: Set the working conditions of the experimental battery module and multiple groups of loading conditions under different working conditions; Simulate the operating state of the battery under different loading conditions through the finite element temperature simulation model of the experimental battery module; and collect the surface temperature and the internal temperature of the experimental battery module under the loading conditions to obtain the temperature distribution data of the experimental battery module under multiple loading conditions of the preset working conditions; The preset working conditions include at least one of normal working conditions and fault working conditions; the loading conditions include at least one of the simulation model environment temperature, internal short circuit fault conditions, and per unit value of charging power.

4. The method according to claim 1, characterized in that, Based on the temperature simulation results, obtain a temperature distribution data set including each group of loading conditions and the corresponding temperature distribution data; it includes: Obtain the temperature distribution data of the experimental battery module under each group of loading conditions; the temperature distribution data includes the internal temperature of the experimental battery module and its corresponding surface temperature; According to each group of loading conditions and the corresponding temperature distribution data, establish multiple groups of first temperature distribution arrays; Construct a temperature distribution data set of the experimental battery module according to the multiple groups of first temperature distribution arrays.

5. The method according to claim 4, characterized in that, It further includes: Normalize the temperatures in each group of the first temperature distribution arrays in the temperature distribution dataset using the following formula: where is the normalized temperature data, T i is the temperature data at the selected temperature point; T max and T min are the maximum temperature and the minimum temperature in the first temperature distribution array, respectively.

6. The method according to claim 1, characterized in that, The process of using the temperature distribution data set to train the pre-established inversion model of the power battery temperature to obtain the temperature distribution inversion model of the experimental battery module includes: Divide the temperature distribution dataset into the first temperature distribution sub-arrays of N1 groups under normal conditions and the first temperature distribution sub-arrays of N2 groups under faulty conditions according to the accuracy requirements, and each group of the first temperature distribution sub-arrays is represented by a feature quantity matrix composed of M data; Input the first temperature distribution sub-arrays of N1 groups under normal conditions and the first temperature distribution sub-arrays of N2 groups under faulty conditions into the inversion model of the power battery temperature pre-constructed based on the backpropagation neural network, output the predicted values of the internal temperature of the experimental battery module, adjust the parameters of the inversion model based on the predicted values of the internal temperature and the internal temperature of the experimental battery module included in the temperature distribution dataset, and repeat the process of model training until the model meets the preset convergence conditions, and obtain the trained inversion model of the power battery temperature as the temperature distribution inversion model of the test battery module.

7. The method according to claim 6, characterized in that, Adjusting the parameters of the inversion model based on the predicted values of the internal temperature and the internal temperature of the experimental battery module included in the temperature distribution sub-array, and repeating the process of model training until the model meets the preset convergence conditions, including: Calculate the error result between the predicted value of the internal temperature output by the inversion model and the measured value of the internal temperature of the experimental battery module included in the temperature distribution dataset according to the pre-constructed error function, and calculate the partial derivative of the error with respect to the initial weights of the inversion model to obtain the weight adjustment gradient of the inversion model, and update the weights according to the weight adjustment gradient; the error function of the inversion model is where O i is the predicted value of the internal temperature output by the inversion model, and t i is the measured value of the internal temperature of the experimental battery module obtained by the simulation model; Repeating the process of model training and error calculation, and after multiple iterations, until the error reaches the preset requirements, the training is completed.

8. A method for inverting the temperature distribution of a battery module, characterized in that, including: Collect the surface temperature distribution data of the experimental battery module to be predicted under the loading conditions of the preset working conditions, input the loading conditions of the preset working conditions and the corresponding surface temperature distribution data into the trained temperature distribution inversion model of the experimental battery module, and output the internal temperature of the experimental battery module under the preset working conditions; The temperature distribution inversion model is trained by using the battery module temperature distribution inversion model construction method according to any one of claims 1-7.

9. The method according to claim 8, characterized in that, The collecting the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working conditions includes: When the experimental battery module is under the preset working conditions and the preset loading conditions, obtain the temperature at the surface points of the battery module measured by the temperature sensors arranged in the finite element temperature simulation model of the experimental battery module, and obtain the surface temperature distribution data of the experimental battery module under the preset loading conditions of the preset working conditions.

10. The method according to claim 9, characterized in that, The temperature sensors arranged in the finite element temperature simulation model of the experimental battery module include: A temperature sensors arranged at the positive electrode of the battery, B temperature sensors arranged at the negative electrode of the battery, and C temperature sensors arranged on the side of the battery, and the C temperature sensors arranged on the side of the battery are evenly arranged.

11. A device for constructing a temperature distribution inversion model of a battery module, characterized in that, including: A data acquisition module, configured to obtain temperature simulation results of simulating the temperature of an experimental battery module under multiple loading conditions of a preset working condition by using a finite element temperature simulation model of the experimental battery module; the finite element temperature simulation model includes an experimental battery pack geometric model and an electro-thermal coupling physical field constructed based on the geometric model, and the electro-thermal coupling physical field at least includes an electric field distribution relationship, a temperature distribution relationship, and a total accumulated heat determined based on the relationship. A temperature distribution data set including each set of loading conditions and corresponding temperature distribution data is obtained based on the temperature simulation results; the temperature distribution data includes the surface temperature and the internal temperature of the battery module. A model construction module, configured to train an inversion model of the power battery temperature established in advance by using the temperature distribution data set to obtain an inversion model of the temperature distribution of the experimental battery module.

12. A device for inverting the temperature distribution of a battery module Characterized in that It includes: A data acquisition module, configured to acquire surface temperature distribution data of an experimental battery module to be predicted under a loading condition of a preset working condition. A temperature prediction module, configured to input the loading condition of the preset working condition and the corresponding surface temperature distribution data into the trained inversion model of the temperature distribution of the experimental battery module, and output the internal temperature of the experimental battery module under the preset working condition; the temperature distribution inversion model is trained by using the method for constructing an inversion model of the temperature distribution of a battery module according to any one of claims 1-7.

13. A computer storage medium Characterized in that The computer storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the method for constructing an inversion model of the temperature distribution of a battery module according to any one of claims 1-7 or the method for inverting the temperature distribution of a battery module according to claims 8-10 is implemented.

14. A computer device Characterized in that It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method for constructing an inversion model of the temperature distribution of a battery module according to any one of claims 1-7 or the method for inverting the temperature distribution of a battery module according to claims 8-10 is implemented.

Images