Electric vehicle thermal management method and system based on mileage prediction

Through machine learning, predicting user mileage and time, combined with user habits to selective heating and charging, the problem of inaccurate thermal management of existing electric vehicle batteries is solved, extending battery life and reducing battery consumption.

CN115742865BActive Publication Date: 2024-11-19JIANGSU ZENIO NEW ENERGY BATTERY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211355518.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-01
Publication Date
2024-11-19
Estimated Expiration
2042-11-01

AI Technical Summary

Technical Problem

The existing electric vehicle battery management system cannot conduct targeted thermal management based on users' driving habits, resulting in inaccurate battery temperature control and affecting battery performance and life.

Method used

By collecting historical driving habit data, the machine learning model is trained to predict the mileage and time that users will travel, and combine daily driving instructions and remote driving instructions to achieve selective heating and charging operations and optimize battery thermal management.

Benefits of technology

Real-time and targeted battery thermal management for different users is achieved, extending the battery life and reducing battery consumption and charging times.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115742865B_ABST
    Figure CN115742865B_ABST
Patent Text Reader

Abstract

The present invention relates to a method and system for thermal management of electric vehicles based on mileage prediction, the method comprising collecting historical data related to user driving habits as a training set, using the training set to train a machine learning model to obtain a trained machine learning model, acquiring real-time data related to user driving habits and using the trained machine learning model to predict the mileage and time that the user will travel, and performing energy-saving thermal management on the battery according to the mileage and time that the user will travel; the system comprises a prediction module, a control module and an energy-saving thermal management module. The present invention can achieve targeted battery optimization control for different customers and achieve effective thermal management of the battery, thereby extending the service life of the vehicle battery.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle thermal management, and in particular to an electric vehicle thermal management method and system based on mileage prediction. Background Art

[0002] With the strong support of the country for the new energy industry, the new energy vehicle industry continues to develop. For new energy vehicles, batteries are the power and the core, and batteries provide all the power for the car. The battery management system (BMS) is the core of the car control, which is used to protect the safe use of the battery and determine the customer's driving experience. During the use of electric vehicle batteries, it is necessary to monitor the temperature of the battery in real time to perform thermal management on the battery. When the battery temperature is lower than the applicable temperature of the battery, it needs to be heated. When the battery temperature is higher than the applicable temperature of the battery, it needs to be cooled, otherwise the battery performance and life will be affected. Due to the limitation of hardware computing resources, the BMS function is fixed when it leaves the factory, but different customers have different driving habits and driving environments, so the degree of battery use is also different. The fixed-function BMS cannot perform targeted optimization control for each customer.

[0003] Big data records driving data, charging data, and fault data, but the current BMS technology combined with big data does not fully utilize the data. At present, big data is only used as an auxiliary means for the fixed functions of traditional BMS. For example, based on the historical data of the car, it helps BMS to more accurately predict the battery SOX (full name State Of X, which is a description of the battery status, including SOH, SOC, SOP, SOE, H is Health in English, C is capacity, P is power, and E is energy), predict the remaining charging time, modify the battery model parameters, etc., but there is no relevant application for battery thermal management. At present, the BMS thermal management strategy function mainly adopts segmented control, which only considers the temperature of the battery pack itself and the temperature of the current state, and cannot realize effective thermal management of the battery in combination with the user's driving habits. Summary of the invention

[0004] To this end, the technical problem to be solved by the present invention is to overcome the deficiencies in the prior art and provide an electric vehicle thermal management method and system based on mileage prediction, which can achieve targeted battery optimization control for different customers and effective thermal management of the battery, thereby extending the service life of the vehicle battery.

[0005] In order to solve the above technical problems, the present invention provides an electric vehicle thermal management method based on mileage prediction, comprising:

[0006] Collect historical data related to the user's driving habits as a training set, use the training set to train a machine learning model to obtain a trained machine learning model, obtain real-time data related to the user's driving habits, and use the trained machine learning model to predict the mileage and time that the user will travel;

[0007] Energy-saving thermal management of the battery is performed according to the mileage and time that the user will travel.

[0008] As a preferred method, when performing energy-saving thermal management on the battery, two working modes, daily driving instructions and remote driving instructions, are set.

[0009] When the user selects daily driving instructions, the battery enters the energy-saving thermal management working mode; when the user selects long-distance driving instructions, the battery enters the normal thermal management working mode.

[0010] Preferably, energy-saving thermal management is performed on the battery according to the mileage and time that the user is going to travel, specifically:

[0011] S1: Determine whether the battery temperature needs to be heated at this time, if not, execute S2, if yes, execute S3;

[0012] S2: Keep the battery status and continue driving, and execute S1;

[0013] S3: Calculate the power consumed during driving Q3, the remaining power at the end of driving Q2, and the accumulated time t3 of heating the battery according to the predicted mileage and time that the user will travel,

[0014] Conduct a temperature rise test on the battery and obtain the heat exchange function of the battery based on the temperature rise test data;

[0015] Calculate the average battery temperature T4 when the vehicle is driving without turning on the heater according to the heat exchange function, and calculate the remaining battery capacity Q4 at the temperature T4;

[0016] The battery is selectively heated and charged based on the remaining battery power Q1 when the user selects daily driving instructions, the remaining battery power Q2 when driving ends, the power consumed during driving Q3, the cumulative time t3 for heating the battery, and the remaining battery power value Q4.

[0017] Preferably, the heat exchange function is:

[0018] △T=ae -bE-ct -d+μ,

[0019] Wherein, △T is the temperature rise, a, b, c, and d are parameters obtained by fitting, e is the natural constant, E represents the base of the power of 10, μ is the correction coefficient, t is the heat preservation time, t = t2 - t1, t2 is the starting time of driving, and t1 is the time when the user selects the daily driving instruction.

[0020] Preferably, the value range of the correction coefficient μ is 0 to 10.

[0021] Preferably, the calculation method of the average battery temperature T4 is as follows:

[0022] T4 = T1 + △T,

[0023] Wherein, T1 is the average battery temperature when the user selects the daily driving instruction.

[0024] Preferably, the remaining battery charge value Q4 when calculating the T4 temperature is specifically the remaining charge value Q4 obtained by inversely calculating the T4 temperature according to the battery SOE - OCV - T table.

[0025] Preferably, the selective heating and charging operations of the battery are performed by combining the remaining battery charge Q1 when the user selects the daily driving instruction, the remaining charge Q2 at the end of driving, the power consumption Q3 during driving, the cumulative heating time t3 of the battery, and the remaining battery charge value Q4, specifically as follows:

[0026] Calculate the power difference ΔQ1 = Q2 - Q1 - P2×t3, where P2 is the heating power of the battery;

[0027] If ΔQ1 > 0 and Q2 > Q3, heat the battery; if ΔQ1 > 0 and Q2 < Q3, charge the battery until the current remaining charge of the battery is greater than Q3 and stop charging;

[0028] If ΔQ1 < 0 and Q4 > Q3, do not heat the battery; if ΔQ1 < 0 and Q4 < Q3, charge the battery until the current remaining charge of the battery is greater than Q3 and stop charging.

[0029] Preferably, when performing energy-saving thermal management on the battery according to the mileage and time that the user is about to drive, obtain the temperature data of the next few hours and the current air velocity and predict the natural cooling temperature of the battery within the next few hours, and perform energy-saving thermal management on the battery in combination with the natural cooling temperature of the battery.

[0030] The present invention also provides an electric vehicle thermal management system based on driving mileage prediction, including a prediction module, a control module, and an energy-saving thermal management module.

[0031] The prediction module collects historical data related to the user's driving habits as a training set, uses the training set to train a machine learning model to obtain a trained machine learning model, obtains real-time data related to the user's driving habits, and uses the trained machine learning model to predict the mileage and time that the user will travel;

[0032] The control module includes a mobile client, in which two types of instructions, daily driving instructions and remote driving instructions, are provided. The control module controls the operation of the energy-saving thermal management module according to the instruction type selected by the user;

[0033] When the user selects the daily driving instruction, the energy-saving thermal management module performs energy-saving thermal management on the battery according to the mileage and time that the user will travel.

[0034] The above technical solution of the present invention has the following advantages compared with the prior art:

[0035] The present invention collects data related to historical user driving habits and predicts the mileage and time that the user will travel accordingly. On this basis, it performs selective energy-saving thermal management of the battery according to the user's needs, and effectively combines BMS and big data to achieve real-time and targeted battery optimization control for different customers. At the same time, without affecting user use, the battery power consumption is reduced in a single driving, and the number of battery charging times is reduced based on user habits, thereby achieving effective thermal management of the battery, thereby extending the service life of the car battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein

[0037] Figure 1 is a flow chart of the present invention,

[0038] Figure 2 It is the heat exchange function obtained by performing a temperature rise experiment on the battery in the embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0040] Reference Figure 1 As shown, the present invention discloses a thermal management method for electric vehicles based on mileage prediction, which is characterized by comprising:

[0041] Collect historical data related to user driving habits as a training set, use the training set to train the machine learning model to obtain a trained machine learning model, obtain real-time data related to user driving habits, and use the trained machine learning model to predict the mileage and time that the user will travel. The data collected from historical users' driving habits include the mileage, power, cell voltage, cell temperature, current, heater power consumption, fault records, battery pack SOH, etc. of the electric vehicle, and collect external feature data such as the day of the week, outside temperature, weather, holiday conditions, wind direction, and wind force. Obtain real-time data related to user driving habits, including the time the user has used the car, the amount of electricity consumed, the amount of electricity consumed by thermal management, and the temperature rise. Statistical data on driving time at different mileages, normal driving power consumption values, and temperature rise data. The formula used to calculate the cumulative amount of electricity Q consumed by the user on the day of use of the car using the battery power P1 is: t represents time. The voltage, temperature and other data used in this embodiment are all average data obtained by processing the acquired data, so as to reduce the adverse effects of abnormal points on prediction; the machine learning model used in this embodiment is a linear regression model.

[0042] Two instructions, daily driving instructions and remote driving instructions, are set. When the user selects the daily driving instructions, the battery enters the energy-saving thermal management working mode; when the user selects the remote driving instructions, the battery enters the normal thermal management working mode. The normal thermal management mode is a common conventional thermal management mode defined by the whole vehicle, and the energy-saving effect is not considered. When the user selects the remote driving instruction, it means that the user's next driving is not a daily car use, and energy saving is not considered. The data of this car use is not stored as data related to the user's daily driving habits, so as to improve the effectiveness of the training set and thus improve the prediction accuracy of daily car use behavior habits. In this embodiment, the two instructions of daily driving instructions and remote driving instructions can be set in the APP on the user's mobile phone. By selecting different instructions in the APP, the battery enters different working modes. By setting the two instructions of daily driving instructions and remote driving instructions in the car APP on the user's mobile phone, the interaction between the intelligent control of the car and the user's instructions is realized; in different modes, the user's choice is combined with targeted response, which can meet the user's occasional long-distance car use needs.

[0043] Energy-saving thermal management performs energy-saving thermal management on the battery based on the predicted mileage and time that the user will travel. The data related to the user's driving habits under energy-saving thermal management will also be added to the training set as historical data related to the user's driving habits, and will be used in the next training of the machine learning model, thereby improving the prediction accuracy of the machine learning model.

[0044] Energy-saving thermal management of the battery is performed according to the mileage and time that the user will drive, specifically:

[0045] S1: Determine whether the battery temperature needs to be heated at this time, if not, execute S2, if yes, execute S3;

[0046] S2: Keep the battery status and continue driving, and execute S1;

[0047] S3: The power consumed during driving Q3, the remaining power at the end of driving Q2 and the accumulated time t3 of heating the battery are calculated based on the predicted mileage and time that the user will travel. Q3, Q2 and t3 are calculated by the battery control system BMS.

[0048] Conduct a temperature rise experiment on the battery, and obtain the heat exchange function of the battery based on the temperature rise experiment data; specifically, fit the heat exchange function based on the insulation experiment data of the battery in a fixed temperature range. According to the different types of batteries used in driving, determine the temperature range in which different batteries can work normally. For example, the fixed temperature range of ternary lithium batteries is set to -20℃-50℃. Obtain the real-time temperature data of the battery in the insulation box within this temperature range, and fit the real-time temperature data to obtain the heat exchange function;

[0049] The method used in this embodiment to fit the heat exchange function is linear regression, and the heat exchange function is:

[0050] △T=ae -bE-ct -d+μ,

[0051] Wherein, △T is the temperature rise, a, b, c, d are the parameters obtained by fitting, e is a natural constant, E represents the cardinality of 10, μ is the correction coefficient, t is the heat preservation placement time, t=t2-t1, t2 is the time when driving starts, and t1 is the time when the user selects the daily driving instruction. The heat exchange function obtained in this embodiment is △T=41.445e -5E-5t -40+μ. When the outside temperature is different, the coefficient of heat exchange is different, so a correction coefficient μ is required. In this embodiment, the correction coefficient μ ranges from 0 to 10. In this embodiment, a battery pack with a temperature of 25°C and an 84-degree battery pack is placed in an incubator with a dustproof and waterproof grade standard of IP68, and the temperature of the incubator is -20°C. Monitor and record the temperature data of the battery pack until the temperature of the battery pack reaches -20°C and stop monitoring. The experimental data of temperature and time are as follows: Figure 2 As shown by the solid curve in the figure, the heat transfer function obtained by fitting the experimental data is △T = 41.09e -4E-05t .

[0052] According to the heat exchange function, the average battery temperature T4 when the heater is not turned on during driving is calculated, and the remaining battery power value Q4 at the temperature T4 is calculated;

[0053] The calculation method of the battery average temperature T4 is:

[0054] T4 = T1 + ΔT,

[0055] where T1 is the average battery temperature when the user selects the daily driving command.

[0056] The remaining battery charge value Q4 when calculating the T4 temperature is specifically the remaining charge value Q4 at the T4 temperature inversely deduced from the battery SOE - OCV - T table. SOE - OCV - T refers to a three - dimensional table of different temperatures, different voltages, and available battery energy under static conditions, obtained by testing the battery cells.

[0057] Based on the remaining battery charge Q1 when the user selects the daily driving command, the remaining charge Q2 at the end of driving, the power consumed during driving Q3, the cumulative heating time t3 of the battery, and the remaining battery charge value Q4, selective heating and charging operations are performed on the battery. Specifically:

[0058] Calculate the charge difference ΔQ1 = Q2 - Q1 - P2×t3, where P2 is the heating power of the battery;

[0059] If ΔQ1 > 0 and Q2 > Q3, heat the battery until ΔQ1 > 0 and Q2 > Q3 are no longer satisfied and then stop heating; if ΔQ1 > 0 and Q2 < Q3, charge the battery until the current remaining charge of the battery is greater than Q3 and then stop charging; if ΔQ1 < 0 and Q4 > Q3, do not heat the battery; if ΔQ1 < 0 and Q4 < Q3, charge the battery until the current remaining charge of the battery is greater than Q3 and then stop charging. The present invention obtains the temperature data for the next N hours and the current air flow rate based on intelligent networking technology, accurately predicts the natural cooling temperature of the battery within the next N hours according to experimental data, and N is determined according to the user's driving habits and the predicted time of using the vehicle. The working temperature of the battery is controlled within the optimal temperature to the greatest extent, and heating and cooling can be turned off immediately after reaching the expected temperature, minimizing the waste of electric energy.

[0060] The present invention also discloses an electric vehicle thermal management system based on mileage prediction, including a prediction module, a control module and an energy-saving thermal management module. The prediction module collects historical data related to user driving habits as a training set, uses the training set to train a machine learning model to obtain a trained machine learning model, obtains real-time data related to user driving habits and uses the trained machine learning model to predict the mileage and time that the user will travel. The control module includes a mobile client, and the mobile client is provided with two instructions, namely daily driving instructions and remote driving instructions. The control module controls the working mode of the energy-saving thermal management module according to the instruction type selected by the user. When the user selects the daily driving instruction, the energy-saving thermal management module performs energy-saving thermal management on the battery according to the mileage and time that the user will travel; when the user selects the remote driving instruction, the battery is not subjected to energy-saving thermal management.

[0061] As the competition intensity of new energy vehicles becomes increasingly fierce, thermal management of batteries of new energy vehicles based on user driving habits will be a future development trend. The emergence of big data provides means and basis for BMS specific control, which can continuously enrich the functions of BMS. The present invention collects historical data related to user driving habits and predicts the mileage and time that users will travel based on this data. On this basis, it selectively manages the energy-saving thermal management of the battery according to the needs of the user. Compared with the thermal management of the battery during driving in the prior art, which is either not heated or heated all the time, the present invention effectively combines BMS and big data to achieve real-time and targeted battery optimization control for different customers. At the same time, the thermal management of the battery by the present invention will not affect the normal use of the user, and can reduce the power consumption of the battery in a single driving. Based on user habits, the number of times the battery is charged is reduced, and effective thermal management of the battery is achieved, thereby extending the service life of the car battery. The present invention can break through the limitations of computing resources, improve the performance of BMS, and give BMS more functions.

[0062] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0063] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0066] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the protection scope of the invention.

Claims

1. A thermal management method for electric vehicles based on mileage prediction, characterized in that: Including: Collecting data related to historical driving habits of users as a training set, training a machine learning model using the training set to obtain a trained machine learning model, acquiring real-time data related to driving habits of users, and using the trained machine learning model to predict the mileage and time that the user is about to drive; Performing energy-saving thermal management on the battery according to the mileage and time that the user is about to drive; When performing energy-saving thermal management on the battery, setting two working modes: a daily driving instruction mode and a remote driving instruction mode; When the user selects the daily driving instruction, the battery enters the working mode of energy-saving thermal management; when the user selects the remote driving instruction, the battery enters the working mode of normal thermal management; Performing energy-saving thermal management on the battery according to the mileage and time that the user is about to drive, specifically: S1: Judging whether the temperature of the battery needs to be heated at this time. If not, execute S2; if so, execute S3; S2: Keep the battery in its current state and continue driving, and execute S1; S3: Calculating the power consumption Q3 during driving, the remaining power Q2 at the end of driving, and the cumulative heating time t3 of the battery according to the predicted mileage and time that the user is about to drive; Performing a temperature rise experiment on the battery, and obtaining a heat exchange function of the battery according to the temperature rise experiment data; Calculating the average battery temperature T4 during driving without a heater according to the heat exchange function, and calculating the remaining power value Q4 of the battery at the T4 temperature; Performing selective heating and charging operations on the battery by combining the remaining power Q1 of the battery when the user selects the daily driving instruction, the remaining power Q2 at the end of driving, the power consumption Q3 during driving, the cumulative heating time t3 of the battery, and the remaining power value Q4 of the battery; The heat exchange function is: △T=ae -bE-ct -d+μ, Where, △T is the temperature rise, a, b, c, d are fitting parameters, e is the natural constant, E represents the base of the power of 10, μ is the correction coefficient, t is the heat preservation time, t = t2 - t1, t2 is the start time of driving, and t1 is the time when the user selects the daily driving instruction.

2. The electric vehicle thermal management method based on mileage prediction according to claim 1, characterized in that: The value range of the correction coefficient μ is 0 to 10.

3. The electric vehicle thermal management method based on mileage prediction according to claim 1, characterized in that: The calculation method of the average battery temperature T4 is: T4 = T1 + △T, Where, T1 is the average battery temperature when the user selects the daily driving instruction.

4. The electric vehicle thermal management method based on mileage prediction according to claim 1, characterized in that: Calculating the remaining power value Q4 of the battery at the T4 temperature, specifically, inversely deducing the remaining power value Q4 at the T4 temperature according to the battery SOE-OCV-T table.

5. The electric vehicle thermal management method based on mileage prediction according to claim 1, characterized in that: Performing selective heating and charging operations on the battery by combining the remaining power Q1 of the battery when the user selects the daily driving instruction, the remaining power Q2 at the end of driving, the power consumption Q3 during driving, the cumulative heating time t3 of the battery, and the remaining power value Q4 of the battery, specifically: Calculating the power difference ΔQ1 = Q2 - Q1 - P2 × t3, where P2 is the heating power of the battery; If ΔQ1 > 0 and Q2 > Q3, heat the battery; if ΔQ1 > 0 and Q2 < Q3, charge the battery until the current remaining power of the battery is greater than Q3 to stop charging; If ΔQ1 < 0 and Q4 > Q3, the battery is not heated; if ΔQ1 < 0 and Q4 < Q3, the battery is charged until the current remaining battery power is greater than Q3 and then the charging stops.

6. The electric vehicle thermal management method based on mileage prediction according to any one of claims 1 to 5, characterized in that: When performing energy-saving thermal management on the battery according to the mileage and time that the user will travel, obtain the temperature data for the next few hours and the current air flow rate, and predict the natural cooling temperature of the battery within the next few hours. Combine the natural cooling temperature of the battery to perform energy-saving thermal management on the battery.

7. An electric vehicle thermal management system based on mileage prediction, characterized in that: It includes a prediction module, a control module, and an energy-saving thermal management module. The prediction module collects historical data related to the user's driving habits as a training set, uses the training set to train a machine learning model to obtain a trained machine learning model, obtains real-time data related to the user's driving habits, and uses the trained machine learning model to predict the mileage and time that the user will travel. The control module includes a mobile client. There are two types of instructions, namely, daily driving instructions and remote driving instructions, in the mobile client. The control module controls the energy-saving thermal management module to work according to the type of instruction selected by the user. When the user selects daily driving instructions, the energy-saving thermal management module performs energy-saving thermal management on the battery according to the mileage and time that the user will travel. When performing energy-saving thermal management on the battery, set two working modes: daily driving instructions and remote driving instructions. When the user selects daily driving instructions, the battery enters the working mode of energy-saving thermal management; when the user selects remote driving instructions, the battery enters the working mode of normal thermal management. Performing energy-saving thermal management on the battery according to the mileage and time that the user will travel specifically includes: S1: Determine whether the temperature of the battery needs to be heated at this time. If not, execute S2; if so, execute S3. S2: Keep the battery in its current state and continue driving, and execute S1. S3: Calculate the power consumption Q3 during driving, the remaining power Q2 at the end of driving, and the cumulative heating time t3 of the battery according to the predicted mileage and time that the user will travel. Conduct a temperature rise experiment on the battery, and obtain the heat exchange function of the battery according to the temperature rise experiment data. Calculate the average temperature T4 of the battery when driving without a heater during driving according to the heat exchange function, and calculate the battery remaining power value Q4 at the T4 temperature. Combine the battery remaining power Q1 when the user selects daily driving instructions, the remaining power Q2 at the end of driving, the power consumption Q3 during driving, the cumulative heating time t3 of the battery, and the battery remaining power value Q4 to perform selective heating and charging operations on the battery. The heat exchange function is: △T=ae -bE-ct -d+μ, Where, △T is the temperature rise, a, b, c, d are the fitted parameters, e is the natural constant, E represents the base of the power of 10, μ is the correction coefficient, t is the heat preservation placement time, t = t2 - t1, t2 is the start driving time, and t1 is the time when the user selects daily driving instructions.