Battery thermal management optimization method and system based on driving habits

Abstract

The invention relates to the technical field of battery thermal management optimization, and discloses a battery thermal management optimization method and system based on driving habits. According to the battery thermal management optimization method and system based on the driving habits, the whole vehicle driving condition data, the battery system data and the user side data are collected and sorted in real time through the cloud platform, the driving behaviors are recognized and classified through the machine learning algorithm, and the relation between the driving habits and battery thermal management is deeply analyzed; a personalized battery thermal management optimization strategy is generated, the strategy can be dynamically adjusted according to different driving habits, accurate control over the battery temperature, optimization of the battery life and improvement of the energy utilization efficiency are achieved, and meanwhile, by uploading vehicle operation data in real time and continuously monitoring the execution effect of the optimization strategy through a cloud platform, the energy utilization efficiency is improved. It is ensured that thermal management measures are matched with actual requirements, the user experience and the overall performance of the vehicle are finally improved, and the limitation of a traditional BMS in thermal management control is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery thermal management optimization, and specifically to a method and system for optimizing battery thermal management based on driving habits. Background Art

[0002] For currently commonly used new energy power batteries, whether it is a lithium iron phosphate battery with good safety or a ternary lithium battery with high energy density, they all have strict requirements for operating temperature. In order to ensure that the battery is always in a suitable temperature operating range, usually when designing a power battery pack, a battery heating and cooling system will be designed, including a battery pack cooling circuit, a PTC heating circuit, an air-conditioning cooling circuit, etc. When necessary, the battery pack is heated or cooled to ensure the operating safety and life of the battery.

[0003] Whether it is heating the battery pack by PTC or cooling the battery pack by an air-conditioning compressor, the energy used comes from the battery pack itself. Battery thermal management energy consumption is one of the main energy consumptions of the whole vehicle except for driving energy consumption, and thermal management energy consumption is also one of the main reasons for the reduction of the cruising range of electric vehicles in winter and summer.

[0004] The battery management system (BMS) usually outputs parameters such as the inlet temperature of the cooling water of the battery pack and the cooling water flow rate to the vehicle thermal management control system according to the current maximum temperature, minimum temperature, temperature difference, SOC, etc. of the power battery cells, and the vehicle thermal management control system controls the PTC power, air compressor power, water pump speed, and three-way valve opening degree, etc. to achieve temperature control of the battery cells.

[0005] Currently, most of the conventional battery management system (BMS) thermal management control algorithms are controlled based on the current state of the battery pack, without considering future driving conditions and the driving habits of users. At the same time, due to the large heat capacity of the battery pack, there is a large lag in temperature control, which usually leads to overheating or overcooling of the battery pack, resulting in unnecessary energy loss. On the other hand, in extreme cases, due to excessive thermal management requests of the battery system, it affects the power distribution of vehicle heating or cooling, resulting in insufficient power distribution for heating or cooling the passenger compartment and affecting the user experience. Summary of the Invention

[0006] Aiming at the problem of the limitations of BMS in thermal management control in the prior art, the present invention provides a battery thermal management optimization method and system based on driving habits. The present invention collects and collates vehicle driving condition data, battery system data, and user-end data in real time through a cloud platform, uses machine learning algorithms to identify and classify driving behaviors, deeply analyzes the relationship between driving habits and battery thermal management, generates personalized battery thermal management optimization strategies, which can be dynamically adjusted according to different driving habits, realizes precise control of battery temperature, optimizes battery life, and improves energy utilization efficiency. At the same time, by uploading vehicle operation data in real time, the cloud platform continuously monitors the execution effect of the optimization strategy to ensure that the thermal management measures match the actual needs, ultimately improving the user experience and the overall performance of the vehicle.

[0007] To achieve the above object, the present invention provides the following technical solutions: A battery thermal management optimization method based on driving habits, comprising the following steps: S1. Collect vehicle driving condition data through a cloud platform, including speed, acceleration, braking, and steering angle, and obtain battery system data and user-end data in real time. The battery system data includes the temperature, voltage, and charge and discharge state of the battery, and the user-end data includes the user's login information and operation habits; S2. Clean the collected vehicle driving condition data, battery system data, and user-end data, remove noise data and outliers, and integrate the vehicle driving condition data, battery system data, and user-end data into a unified data format; S3. Use machine learning algorithms to identify and classify the driving behaviors of drivers, analyze the relationship between driving habits and battery thermal management, and extract data affecting battery temperature and performance; S4. According to the analysis results, combined with the battery temperature control under different driving habits, conduct battery life assessment. After the assessment, the cloud generates corresponding battery thermal management optimization strategies and pushes the battery thermal management optimization strategies to the vehicle local system and the user's mobile phone through the network; S5. During the vehicle's driving process, upload vehicle operation data, battery system operation data, and user operation records to the cloud in real time. The cloud platform monitors the execution effect of the optimization strategy and analyzes whether the optimization result reaches the expected goal; S6. The user receives the optimization strategy pushed by the cloud on the mobile phone side and confirms whether to perform algorithm optimization.

[0008] Preferably, the formula for data denoising is as follows:

[0009] In the formula, represents the data value after denoising and smoothing, Represents the values of the vehicle driving condition data, battery system data, and user - end data at the time point . Represents the size of the filtering window.

[0010] Preferably, the formula for removing outliers from the data is as follows:

[0011] When a data point meets the following conditions, then this point is considered an outlier: Or

[0012] Where is the inter - quartile range, representing the degree of dispersion of the data, is the first quartile, indicating that 25% of the data points are less than this value, is the third quartile, indicating that 75% of the data points are less than this value.

[0013] Preferably, the formula for integrating the data into a unified data format is as follows:

[0014] In the formula, represents the integrated unified data set, in the format of a set of tuples, represents the vehicle driving condition data, represents the battery system data, represents the user - end data.

[0015] Preferably, the formula for identifying the driving behavior of the driver is as follows:

[0016] In the formula, represents the change in the acceleration feature, represents the acceleration at the current time point , represents the acceleration at the previous time point .

[0017] Preferably, the formula for classifying the driving behavior of the driver is as follows:

[0018] In the formula, represents the center of the th cluster, represents the number of samples belonging to the cluster , represents the set of samples in the cluster , represents the sample point.

[0019] Preferably, the formula for controlling the battery temperature is as follows:

[0020] In the formula, represents the controlled temperature, represents the target battery temperature, represents the temperature adjustment coefficient, represents the current battery temperature.

[0021] Preferably, the formula for evaluating the battery life is as follows:

[0022] In the formula, represents the battery life, represents the maximum battery capacity, represents the current battery capacity, represents the capacity attenuation rate.

[0023] Preferably, the formula for analyzing whether the optimization result reaches the expected goal is as follows:

[0024] In the formula, represents the target achievement rate, represents the optimization index actually observed by the system, represents the set optimization target value of the system.

[0025] A battery thermal management optimization system based on driving habits includes a data collection module, a data cleaning and integration module, a driving behavior recognition and analysis module, an optimization strategy generation module, a data upload module, and a user confirmation optimization module; The data collection module collects the vehicle running condition data through the cloud platform, including speed, acceleration, braking, and steering angle, and obtains the battery system data and user-side data in real time. The battery system data includes the temperature, voltage, and charge and discharge state of the battery, and the user-side data includes the user's login information and operation habits; The data cleaning and integration module cleans the collected vehicle running condition data, battery system data, and user-side data, removes noise data and outliers, and integrates the vehicle running condition data, battery system data, and user-side data into a unified data format; The driving behavior recognition and analysis module uses machine learning algorithms to identify and classify the driver's driving behavior, analyzes the relationship between driving habits and battery thermal management, and extracts the data affecting the battery temperature and performance; Based on the analysis results, the optimization strategy generation module combines the battery temperature control under different driving habits to evaluate the battery life. After the evaluation, the cloud generates the corresponding battery thermal management optimization strategy and pushes the battery thermal management optimization strategy to the vehicle local system and the user's mobile phone through the network; The data upload module uploads the vehicle operation data, battery system operation data, and user operation records to the cloud in real time. The cloud platform monitors the execution effect of the optimization strategy and analyzes whether the optimization result meets the expected goal; The user confirmation optimization module receives the optimization strategy pushed by the cloud on the mobile phone side, and the user confirms whether to perform algorithm optimization.

[0026] Compared with the prior art, the present invention provides a battery thermal management optimization method and system based on driving habits, having the following beneficial effects: The present invention uses the cloud platform to collect and organize the vehicle driving condition data, battery system data, and user-side data in real time, uses machine learning algorithms to identify and classify driving behaviors, deeply analyzes the relationship between driving habits and battery thermal management, and generates personalized battery thermal management optimization strategies. This strategy can be dynamically adjusted according to different driving habits to achieve precise control of the battery temperature, optimize the battery life, improve the energy utilization efficiency. At the same time, by uploading the vehicle operation data in real time, the cloud platform continuously monitors the execution effect of the optimization strategy to ensure that the thermal management measures match the actual needs, ultimately improving the user experience and the overall performance of the vehicle, and effectively solving the limitations of traditional BMS in thermal management control. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic flow chart of the battery thermal management optimization method based on driving habits of the present invention.

[0028] Figure 2 It is a schematic flow chart of the battery thermal management optimization system based on driving habits of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0030] In view of the fact that most of the current conventional battery management system (BMS) thermal management control algorithms are based on the current state of the battery pack for control, without considering future driving conditions and users' driving habits. At the same time, due to the large heat capacity of the battery pack, there is a large lag in temperature control, which usually leads to overheating or overcooling of the battery pack, resulting in unnecessary energy loss. Therefore, an optimized method for battery thermal management based on driving habits is proposed. Please refer to Figure 1 , and this method includes the following steps: S1. Collect the vehicle driving condition data through the cloud platform, including speed, acceleration, braking, and steering angle, and obtain the battery system data and user-side data in real time. The battery system data includes the temperature, voltage, and charge and discharge state of the battery, and the user-side data includes the user's login information and operation habits; Through the cloud platform, the Internet of Things (IoT) technology is used to collect the vehicle driving condition data in real time, including speed, acceleration, braking force, and steering angle. In this process, on-vehicle sensors and data acquisition modules are used to quickly transmit the information to the cloud to ensure the high frequency and real-time nature of the data. At the same time, the system also obtains the battery system data in real time, such as the temperature, voltage, and charge and discharge state of the battery. These data are monitored and analyzed through the battery management system (BMS). In addition, the user-side data is also included in the monitoring scope, including the user's login information and behavior patterns. Through the integration of the user interface and data analysis functions, it helps to deeply understand and analyze the user's operation habits; S2. Clean the collected vehicle driving condition data, battery system data, and user-side data, remove the noise data and outliers, and integrate the vehicle driving condition data, battery system data, and user-side data into a unified data format; Among them, the formula for data denoising is as follows:

[0031] The process of data denoising can significantly improve the quality of the data, making the data on which the model is based more real and reliable. By removing invalid or incorrect data points, it ensures that the analysis and decision-making are based on high-quality information. In the formula, represents the denoised and smoothed data value, represents the values of the vehicle driving condition data, battery system data, and user-side data at time point , represents the size of the filtering window. The denoised data helps to improve the performance of machine learning algorithms. Noise data often leads to errors in the training process of the algorithm, thus reducing the prediction accuracy of the model. And the cleaned data can better reflect the real system state and optimize the training effect of the algorithm; The formula for data outlier removal is as follows:

[0032] When a data point meets the following conditions, then this point is considered an outlier: or

[0033] where is the interquartile range, representing the dispersion degree of the data, is the first quartile, indicating that 25% of the data points are less than this value, is the third quartile, indicating that 75% of the data points are less than this value; In battery management and thermal control decisions, accurate data is crucial. After removing outliers, the state of the battery can be better evaluated, more reasonable decisions can be made based on real data, management mistakes caused by incorrect data can be reduced, and by eliminating data that may cause confusion to the system, resources can be more effectively allocated, ensuring that the battery and the vehicle operate in the best state, reducing energy waste and unnecessary maintenance costs; The formula for integrating data into a unified data format is as follows:

[0034] After integrating the vehicle driving condition data, battery system data, and user - end data into a unified data format, it is more convenient for interaction and comparison. This provides a good basis for data analysis, enabling data from different sources to be interrelated. In the formula, represents the integrated unified data set, in the format of a set of tuples, represents the vehicle driving condition data, represents the battery system data, represents the user - end data. The unified data format allows for comprehensive analysis of multi - dimensional information, enabling a more comprehensive understanding of the impact of driving behavior on battery performance and helping to formulate more accurate optimization strategies; S3. Use machine learning algorithms to identify and classify the driving behavior of drivers, analyze the relationship between driving habits and battery thermal management, and extract data that affects battery temperature and performance; The formula for identifying the driving behavior of drivers is as follows:

[0035] By identifying the driving behavior of drivers, a deeper understanding of the impact of different driving styles on battery efficiency and thermal management can be obtained. This provides basic data for personalized optimization, making the management strategy more targeted. In the formula, represents the change in acceleration characteristics, represents the current time point of the acceleration, represents the previous time point For the acceleration, behavior recognition enables the system to intelligently adapt to the characteristics of different drivers, thus realizing a more flexible thermal management strategy to adjust the battery thermal control measures according to the driver's behavior during driving; The formula for classifying the driver's driving behavior is as follows:

[0036] By classifying the driving behavior, drivers can be divided into different groups, such as "aggressive driving" and "smooth driving". This enables the battery management strategy to be optimized for specific groups, contributing to improving the overall energy efficiency. In the formula, represents the center of the th cluster, represents the number of samples belonging to cluster , represents the set of samples in cluster , represents the sample point. The classified information helps to provide personalized optimization strategies for different driving habits. For example, more energy recovery functions can be provided during aggressive driving to improve energy utilization efficiency; S4. According to the analysis results, combined with the battery temperature control under different driving habits, conduct battery life assessment. After the assessment, the cloud generates the corresponding battery thermal management optimization strategy and pushes the battery thermal management optimization strategy to the vehicle local system and the user's mobile phone through the network; The formula for battery temperature control is as follows:

[0037] Reasonable temperature control can prevent the battery from working at too high or too low temperatures, thus extending the battery life. Good thermal management can reduce the risk of thermal degradation and enable the battery to operate in good condition. In the formula, represents the controlled temperature, represents the target battery temperature, represents the temperature adjustment coefficient, represents the current battery temperature. When the battery works within an appropriate temperature range, the charging efficiency is relatively high, which means that charging can be completed in a shorter time, thus improving the user experience and the vehicle's usability; The formula for battery life assessment is as follows:

[0038] Battery life assessment provides visual information on the battery health status, enabling maintenance personnel to carry out regular maintenance and replacement plans based on the data, avoiding failures and reducing maintenance costs. In the formula, represents the battery life, represents the maximum battery capacity, represents the current battery capacity, represents the capacity decay rate. The battery life assessment provides a scientific basis for operation decisions, helping enterprises and individuals to conduct the best cost-benefit analysis during use; S5. During the vehicle's driving process, the vehicle's overall operation data, battery system operation data, and user operation records are uploaded to the cloud in real time. The cloud platform monitors the execution effect of the optimization strategy and analyzes whether the optimization result reaches the expected goal; The formula for analyzing whether the optimization result reaches the expected goal is as follows:

[0039] Through the comparative analysis of the optimization result and the expected goal, the effectiveness of the adopted optimization strategy can be effectively evaluated, and deficiencies can be timely discovered and adjusted. In the formula, represents the goal achievement rate, represents the optimization index actually observed by the system, represents the set optimization target value of the system. Analyzing the optimization result can provide a theoretical basis for the next improvement and adjustment, ensuring that the system continuously develops towards a better effect and realizing dynamic optimization; S6. The user receives the optimization strategy pushed by the cloud on the mobile phone side and confirms whether to perform algorithm optimization; The cloud big data will establish a vehicle historical operation data table based on the operation data uploaded by the vehicle as a whole. According to this historical operation data table, the relationships between the predicted operation time, predicted temperature rise, and related potential factors are established, that is:

[0040] Among them, represents the predicted driving cycle time for this time, represents the predicted average power of this driving cycle, represents the predicted temperature rise of this driving cycle, represents the start time of the driving cycle, represents the driving cycle , represents the start temperature of the driving cycle, represents the current temperature of the driving cycle, represents the working condition prediction model; The big data platform iteratively updates the above model based on the historical data of each vehicle (each user account) operation every week (the time can be calibrated) to improve the accuracy of the prediction model and at the same time pushes the updated prediction model to the vehicle. After obtaining the user's consent, this prediction model will be applied to the thermal management control strategy of the local battery management system; The thermal management strategy of the traditional battery pack local battery management system (BMS) usually depends on the current highest temperature and lowest temperature of the battery cells, Calculate thermal management control parameters such as the target temperature of the cooling water and the target flow rate based on parameters such as the ambient temperature. In addition to considering the above factors, the optimized thermal management algorithm also needs to consider the driving habits of users, including potential factors such as the estimated time of the current driving cycle, the estimated temperature rise of the battery cells, the estimated maximum power, and the average power, and dynamically adjust the thermal management control parameters to prevent unnecessary energy consumption; The local thermal management strategy consists of three parts: A. The operating condition prediction model sent from the cloud to the local battery management system (BMS) This model predicts the possible duration of the current driving cycle, the average power demand, the maximum power demand, the temperature rise, etc. based on parameters such as the start time of the current driving cycle, the starting ambient temperature, and the battery cell temperature.

[0041] B. The battery operating condition prediction model This model predicts the possible operating conditions during the current driving cycle, including the highest temperature, the lowest temperature after the end of the operating condition, and the optimal temperature range to meet the power demand of the driving condition.

[0042] C. The battery thermal management control model This model calculates thermal management control parameters such as the cooling water temperature, flow rate, and cooling or heating level by combining the current battery system state and the prediction of future operating conditions.

[0043] Please refer to Figure 2 A battery thermal management optimization system based on driving habits, including a data collection module, a data cleaning and integration module, a driving behavior recognition and analysis module, an optimization strategy generation module, a data upload module, and a user confirmation optimization module; The data collection module collects the vehicle driving condition data through the cloud platform, including speed, acceleration, braking, and steering angle, and obtains the battery system data and user-side data in real time. The battery system data includes the temperature, voltage, and charge and discharge state of the battery, and the user-side data includes the user's login information and operation habits; The data cleaning and integration module cleans the collected vehicle driving condition data, battery system data, and user-side data, removes noise data and outliers, and integrates the vehicle driving condition data, battery system data, and user-side data into a unified data format; The driving behavior recognition and analysis module uses machine learning algorithms to identify and classify the driver's driving behavior, analyzes the relationship between driving habits and battery thermal management, and extracts data that affect battery temperature and performance; Based on the analysis results, the optimization strategy generation module combines the battery temperature control under different driving habits to evaluate the battery life. After the evaluation, the cloud generates the corresponding battery thermal management optimization strategy and pushes the battery thermal management optimization strategy to the vehicle local system and the user's mobile phone through the network; The data upload module uploads the vehicle operation data, battery system operation data, and user operation records to the cloud in real time. The cloud platform monitors the execution effect of the optimization strategy and analyzes whether the optimization result meets the expected goal; The user confirmation optimization module receives the optimization strategy pushed by the cloud on the mobile phone side, and the user confirms whether to perform algorithm optimization.

[0044] Through the comprehensive application of the above methods and systems, personalized battery thermal management optimization strategies are generated. These strategies can be dynamically adjusted according to different driving habits, achieving precise control of the battery temperature, optimizing the battery life, and improving the energy utilization efficiency. At the same time, by uploading the vehicle operation data in real time, the cloud platform continuously monitors the execution effect of the optimization strategy to ensure that the thermal management measures match the actual needs, ultimately enhancing the user experience and the overall performance of the vehicle.

[0045] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A battery thermal management optimization method based on driving habits, characterized in that: The following steps are involved: S1. Collect vehicle driving condition data, including speed, acceleration, braking and steering angle, through the cloud platform, and obtain battery system data and user-end data in real time. Battery system data includes battery temperature, voltage and charge and discharge status, and user-end data includes user login information and operating habits; S2. Clean the collected vehicle driving condition data, battery system data and user-end data, remove noise data and abnormal values, and integrate the vehicle driving condition data, battery system data and user-end data into a unified data format; S3. Use machine learning algorithms to identify and classify drivers’ driving behaviors, analyze the relationship between driving habits and battery thermal management, and extract data that affects battery temperature and performance; S4. Based on the analysis results and combined with the battery temperature control under different driving habits, the battery life is evaluated. After the evaluation is completed, the cloud generates the corresponding battery thermal management optimization strategy, which is pushed to the vehicle local system and the user's mobile phone through the network; S5. During driving, the vehicle uploads the vehicle operation data, battery system operation data and user operation records to the cloud in real time. The cloud platform monitors the execution effect of the optimization strategy and analyzes whether the optimization results meet the expected goals. S6. The user receives the optimization strategy pushed from the cloud on the mobile phone and confirms whether to perform algorithm optimization.

2. The battery thermal management optimization method based on driving habits according to claim 1, characterized in that: The formula for data denoising is as follows: In the formula, represents the data value after denoising and smoothing, Indicates vehicle driving condition data, battery system data, and user-side data at a time point The value of Indicates the size of the filter window.

3. The battery thermal management optimization method based on driving habits according to claim 2, characterized in that: The formula for removing outliers from the data is as follows: When a data point If the following conditions are met, the point is considered an outlier: or in is the interquartile range, which indicates the spread of the data. is the first quartile, indicating that 25% of the data points are smaller than this value. The third quartile means that 75% of the data points are smaller than this value.

4. The battery thermal management optimization method based on driving habits according to claim 3, characterized in that: The formula for integrating the data into a unified data format is as follows: In the formula, Represents the integrated unified data set, in the form of a tuple set. Indicates the vehicle driving condition data, Indicates battery system data, Represents user-side data.

5. The battery thermal management optimization method based on driving habits according to claim 4, characterized in that: The formula for identifying the driver's driving behavior is as follows: In the formula, represents the change in acceleration characteristics, Indicates the current time point The acceleration of Indicates the previous time point acceleration.

6. The battery thermal management optimization method based on driving habits according to claim 5, characterized in that: The formula for classifying the driver's driving behavior is as follows: In the formula, Indicates The center of the cluster, Indicates that it belongs to a cluster The number of samples, Representation clustering The sample set in Represents the sample points.

7. The battery thermal management optimization method based on driving habits according to claim 6, characterized in that: The formula for battery temperature control is as follows: In the formula, Indicates temperature control. Indicates the target battery temperature, represents the temperature adjustment coefficient, Indicates the current battery temperature.

8. The battery thermal management optimization method based on driving habits according to claim 7, characterized in that: The formula for battery life evaluation is as follows: In the formula, Indicates battery life. Indicates the maximum capacity of the battery. Indicates the current capacity of the battery. Indicates the capacity decay rate.

9. The battery thermal management optimization method based on driving habits according to claim 8, characterized in that: The formula for analyzing whether the optimization result reaches the expected goal is as follows: In the formula, represents the target achievement rate, represents the optimization metric actually observed by the system, Indicates the optimization target value set by the system.

10. A battery thermal management optimization system based on driving habits, characterized in that: It includes data collection module, data cleaning and integration module, driving behavior recognition and analysis module, optimization strategy generation module, data upload module and user confirmation optimization module; The data collection module collects vehicle driving condition data, including speed, acceleration, braking and steering angle, through the cloud platform, and obtains battery system data and user-end data in real time. The battery system data includes battery temperature, voltage and charge and discharge status, and the user-end data includes user login information and operating habits. The data cleaning and integration module cleans the collected vehicle driving condition data, battery system data and user end data, removes noise data and abnormal values, and integrates the vehicle driving condition data, battery system data and user end data into a unified data format; The driving behavior recognition and analysis module uses a machine learning algorithm to recognize and classify the driver's driving behavior, analyze the relationship between driving habits and battery thermal management, and extract data that affects battery temperature and performance; The optimization strategy generation module evaluates the battery life according to the analysis results and the battery temperature control under different driving habits. After the evaluation, the cloud generates the corresponding battery thermal management optimization strategy, and pushes the battery thermal management optimization strategy to the vehicle local system and the user's mobile phone through the network; The data upload module uploads the vehicle operation data, battery system operation data and user operation records to the cloud in real time. The cloud platform monitors the execution effect of the optimization strategy and analyzes whether the optimization result reaches the expected goal. The user confirmation optimization module receives the optimization strategy pushed from the cloud on the mobile phone, and the user confirms whether to perform algorithm optimization.

Images