Battery thermal management control method and system based on user driving habits

Abstract

The invention discloses a battery thermal management control method and system based on user driving habits. The method comprises the steps of judging whether a user has a commuting mode or not according to historical driving habits of the user on a vehicle cloud platform, and if yes, counting commuting historical data to obtain commuting mode feature data belonging to the user; obtaining current driving information of a user, commuting mode feature data, weather forecast and a battery thermal model for battery temperature prediction; and when the user is currently in the commuting mode, according to the current driving information of the user, the feature data of the commuting mode and the battery thermal model, making a control decision of a battery thermal management system before driving, in the driving process and after driving. Based on the driving habit of the user, dynamic control over battery thermal management is achieved, the energy efficiency and the user experience are remarkably improved, the method is particularly suitable for fixed commuting people, and a more efficient, energy-saving and personalized battery thermal management solution is provided for the user.

Description

Technical Field

[0001] This invention belongs to the field of battery thermal management. Specifically, this invention relates to a battery thermal management control method and system based on user driving habits. Background Technology

[0002] Current battery thermal management strategies employ a "one-size-fits-all" approach, such as activating heating at a fixed temperature threshold. This approach has significant drawbacks. For short-distance users, this fixed mode leads to energy waste because the battery may not require continuous heating during short trips. However, the fixed threshold mode cannot flexibly adjust according to actual needs, resulting in unnecessary energy consumption. For long-distance users, the fixed mode may not meet their high demands for battery performance, leading to insufficient battery performance and impacting the vehicle's range and driving efficiency.

[0003] Current technology cannot provide personalized and precise battery temperature control based on a user's specific driving behavior and habits (such as commuting mileage, driving time, battery status, etc.). Different users have different driving needs and habits, but existing thermal management strategies cannot adapt to these differences and cannot provide users with the most suitable battery temperature management solution for their individual needs, thus affecting user experience and overall vehicle performance.

[0004] In existing battery thermal management systems, although vehicles generate a large amount of data, this data is not fully utilized. Without analyzing user behavior through vehicle cloud big data to dynamically adjust thermal management strategies, it is impossible to achieve refined management and optimization of battery temperature, or predict future usage needs based on historical and real-time user data. Consequently, it is impossible to take appropriate thermal management measures in advance to further improve battery performance and energy efficiency.

[0005] While patent CN116598660A can optimize battery thermal management to some extent, it only provides a single time-series data stream without historical data analysis, thus failing to achieve predictive effects and proactive control. Patent CN116729203A focuses on historical storage of road information and requires navigation to determine whether the current driving conforms to historical driving habits. If navigation is not activated, the thermal management activation method is similar to that of patent CN116598660A, relying on real-time judgment based on actual road conditions. Furthermore, all of the above patents only address thermal management during driving and do not cover functions such as temperature warnings when the user is parked or pre-driving preheating management.

[0006] Therefore, this invention proposes a battery thermal management control method and system based on user driving habits. Summary of the Invention

[0007] This invention aims to overcome the shortcomings of existing technologies and proposes a battery thermal management control method and system based on user driving habits to achieve the following objectives: to realize dynamic control of battery thermal management based on user driving habits, significantly improve energy efficiency and user experience, especially suitable for fixed commuters, and provide users with a more efficient, energy-saving and personalized battery thermal management solution.

[0008] To achieve the above objectives, the technical solution adopted by the present invention is: a battery thermal management control method based on user driving habits, the method comprising:

[0009] Step S1: Based on the user's historical driving habits on the vehicle cloud platform, determine whether the user has a commuting mode. If so, continue to the next step and collect historical commuting data to obtain commuting mode characteristic data belonging to the user, including estimated commuting time, estimated commuting route and trip, estimated commuting time period, and estimated energy consumption.

[0010] Step S2: Obtain the user's current driving information, commuting mode feature data, weather forecast, and battery thermal model for battery temperature prediction; determine whether the user is currently in commuting mode, and if so, proceed to the next step;

[0011] Step S3: Based on the user's current driving information, commuting mode feature data, and battery thermal model, determine the opening and closing of the battery thermal management system before driving and during driving, and evaluate the effectiveness of turning on the battery thermal management system. After driving, combine the weather forecast to determine the opening and closing of the battery thermal management system for the next day.

[0012] Preferably, in step S1, the repetition rate of users' fixed routes on weekdays, the stability of travel time periods, and the similarity of vehicle energy consumption characteristics are obtained based on the users' historical driving habits on the vehicle cloud platform; when the following conditions are met simultaneously within a consecutive preset number of days:

[0013] The repetition rate of fixed routes on weekdays exceeds the preset repetition rate threshold;

[0014] The stability during the travel period is greater than the preset stability threshold;

[0015] The energy consumption feature similarity is greater than the preset similarity threshold;

[0016] Then it determines that the user is in commuting mode and collects commuting mode characteristic data.

[0017] Preferably, step S3 includes: before or during driving, inputting the user's current driving information and commuting mode feature data into the battery thermal model to predict the temperature change of the battery during commuting under the current conditions; if the prediction result shows that the battery temperature will exceed the preset operating temperature range within the expected commuting time or the remaining commuting time, then it is determined that the battery thermal management system needs to be turned on; otherwise, the battery thermal management system is turned off.

[0018] Preferably, evaluating the effectiveness of activating the battery thermal management system includes: obtaining the current battery SOC and remaining commute distance, and determining whether the current battery SOC can complete the remaining commute distance under the premise that the battery thermal management system is activated; if so, the activation of the battery thermal management system is considered effective; otherwise, the battery thermal management system is kept off.

[0019] Preferably, step S3 further includes: inputting the battery status at the end of the trip, the ambient temperature prediction information for the next day in the weather forecast, and commuting mode characteristic data into the battery thermal model for simulation prediction; if the prediction result shows that the battery temperature will exceed the preset operating temperature range during the commuting process on the second day, it is determined that the battery thermal management system needs to be turned on; otherwise, the battery thermal management system is turned off; at the same time, the prediction result is saved.

[0020] Preferably, the method further includes: during the driving process in commuting mode, detecting in real time whether the user leaves commuting mode, and when the user leaves commuting mode, switching to the battery thermal management system control strategy in non-commuting mode.

[0021] Preferred methods for detecting whether a user has left commuting mode include:

[0022] When any of the following conditions are met:

[0023] The route deviation of the expected path in commuting mode is greater than the preset deviation threshold.

[0024] The standard deviation of vehicle acceleration is greater than the preset standard deviation threshold.

[0025] This is considered as the user leaving commuting mode.

[0026] Preferably, the battery thermal management system control strategy in non-commuting mode includes battery thermal management by setting a fixed temperature threshold.

[0027] Preferably, the method further includes: establishing a predictive model for the start and stop times of the battery thermal management system, wherein the model takes current user driving information, commuting mode feature data and battery thermal model output data as input, and learns and trains through historical data to predict the optimal start and stop times of the battery thermal management system under different operating conditions.

[0028] This application also proposes a battery thermal management control system based on user driving habits, wherein the system uses a battery thermal management control method based on user driving habits according to any one of claims 1-9.

[0029] The technical effects of this invention are as follows:

[0030] 1. Personalized and Precise Temperature Control: By analyzing users' specific driving habits and behaviors through vehicle cloud big data, the system dynamically adjusts battery thermal management strategies to achieve personalized and precise temperature control. This is particularly beneficial for users with fixed commuting patterns. For example, for short-distance users, it avoids the energy waste caused by the previous fixed temperature threshold heating mode. The system can accurately predict when and for how long heating or cooling is needed based on the user's historical commuting data, thereby significantly improving energy efficiency and extending the vehicle's driving range.

[0031] 2. Enhanced User Experience: The application of battery thermal models enables real-time and accurate prediction of battery temperature changes during driving. This allows the system to more accurately assess reasonable energy and power demands, thus providing users with a better battery thermal management experience. Furthermore, pre-trip warm-up management and post-trip temperature warnings further enhance the user experience. Users no longer need to worry about battery performance falling short of expectations due to improper thermal management, and can receive more accurate reminders and suggestions when battery status may affect the driving experience.

[0032] 3. Improved Data Utilization Efficiency: Unlike existing technologies that only use real-time data or limited historical data, this application fully utilizes vehicle-generated data through cloud analytics. By analyzing historical and real-time data, the system can more accurately predict future user needs and take corresponding thermal management measures in advance. This not only optimizes battery performance and energy utilization efficiency but also reduces the burden on the cloud platform. For example, there is no need to store large amounts of thermal management on / off threshold information in the cloud, thereby saving cloud storage resources and improving the overall efficiency of the system.

[0033] 4. Adapts to different driving modes: The system automatically switches between commuting and non-commuting modes based on the user's driving behavior. When the user is in commuting mode, no user intervention is required; the thermal management strategy optimizes according to commuting conditions. When the user is not in commuting mode, the system automatically switches to non-commuting mode thermal management, ensuring that battery thermal management is always in the most suitable state for the current driving conditions, further improving vehicle performance and energy efficiency. Attached Figure Description

[0034] Figure 1 A flowchart of a battery thermal management control method based on user driving habits is provided for an embodiment of the present invention. Detailed Implementation

[0035] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. This is to help those skilled in the art to have a more complete, accurate, and in-depth understanding of the inventive concept and technical solutions of the present invention, and to facilitate its implementation. It should be noted that the terms "first," "second," etc., used in this application are only for the convenience of describing the technical solutions and to distinguish components; the corresponding component configurations may be the same or different, and are not intended to limit the scope of this application. To make the technical solutions of the present invention clearer, the present invention will be explained and illustrated through the following embodiments.

[0036] This embodiment provides a battery thermal management control method based on user driving habits, such as... Figure 1 As shown, the method includes:

[0037] Step S1: Based on the user's historical driving habits on the vehicle cloud platform, determine whether the user has a commuting mode. If so, continue to the next step and collect historical commuting data to obtain commuting mode characteristic data belonging to the user, including estimated commuting time, estimated commuting route and trip, estimated commuting time period, and estimated energy consumption.

[0038] Step S2: Obtain the user's current driving information, commuting mode feature data, weather forecast, and battery thermal model for battery temperature prediction; determine whether the user is currently in commuting mode, and if so, proceed to the next step;

[0039] Step S3: Based on the user's current driving information, commuting mode feature data, and battery thermal model, determine the opening and closing of the battery thermal management system before driving and during driving, and evaluate the effectiveness of turning on the battery thermal management system. After driving, combine the weather forecast to determine the opening and closing of the battery thermal management system for the next day.

[0040] Specifically, refer to step S1, where the vehicle cloud platform serves as the core data aggregation hub, responsible for collecting rich historical driving data from users in real time. The collected data mainly includes:

[0041] Daily Travel Time Distribution: This feature accurately records the start and end times of users' daily trips, as well as the specific time periods for each trip segment. In-depth analysis of this data provides clear insights into user travel activity at different times. For example, it can determine whether users concentrate their travel during weekday morning and evening rush hours or exhibit specific travel time preferences on weekends. Based on statistical analysis of extensive historical data, detailed and accurate daily travel time distribution curves can be generated.

[0042] Mileage Accumulation Features: Continuously tracks the mileage of each user's trip and accumulates the total mileage daily, weekly, and monthly. Mileage accumulation features not only intuitively reflect the frequency of a user's trips but also show the overall distance traveled, helping to determine the user's travel purpose. For example, a longer and more stable daily mileage may suggest that the user has a fixed commuting route, while short and frequent trips may be related to daily shopping, leisure travel, or other activities.

[0043] Acceleration / Deceleration Frequency Statistics: Utilizing data from various built-in vehicle sensors, this system monitors the vehicle's acceleration and deceleration in real time. It provides detailed statistics on the number of accelerations / decelerations per unit time, as well as the frequency distribution of different acceleration / deceleration levels, such as rapid acceleration, gradual acceleration, rapid deceleration, and gradual deceleration. Acceleration / deceleration frequency is a crucial indicator of driving style and road conditions. Frequent acceleration / deceleration often indicates driving in congested areas, while a smooth acceleration / deceleration pattern may suggest driving on a free-flowing highway. This data is of paramount importance for understanding user driving behavior and the vehicle's actual operating environment.

[0044] In this embodiment, based on the collected data, advanced data analysis algorithms and machine learning techniques are used to identify user commuting patterns. Specifically, based on users' historical driving habits on the vehicle cloud platform, the repetition rate of users' fixed routes on weekdays, the stability of travel times, and the similarity of vehicle energy consumption characteristics are obtained. This data lays a solid foundation for identifying user commuting patterns.

[0045] Weekday fixed route repetition rate: By comparing users' driving route data on different weekdays, Geographic Information System (GIS) technology is used to convert driving routes into a series of precise latitude and longitude coordinates. Then, string matching algorithms or path similarity-based algorithms (such as Dynamic Time Warping (DTW)) are used to accurately calculate the similarity between routes on different weekdays. A high weekday fixed route repetition rate is usually an important indicator that users have a fixed commuting route.

[0046] Travel Time Stability (Error ±15 minutes): In-depth analysis of user travel time stability on weekdays. Taking daily travel start time as an example, the deviation of travel start time across different weekdays is precisely calculated. Travel time stability refers to the proportion of days in which the deviation of travel start time remains within ±15 minutes across multiple weekdays, which is also one of the significant characteristics of commuting patterns.

[0047] Energy Consumption Similarity: A vehicle's energy consumption is closely related to its driving mode. Under the same vehicle and road conditions, different driving modes can lead to drastically different energy consumption performance. By carefully analyzing energy consumption data from users on the same commuting segments across different workdays, the similarity of energy consumption characteristics is calculated. Energy consumption characteristics can include key indicators such as energy consumption per unit distance and average power consumption. Similar energy consumption characteristics reflect a high degree of consistency in users' driving behavior on similar commuting trips, further providing strong support for the accurate identification of commuting patterns.

[0048] Specifically, the following conditions must be met simultaneously within a consecutive preset number of days:

[0049] The repetition rate of fixed routes on weekdays exceeds the preset repetition rate threshold;

[0050] The stability during the travel period is greater than the preset stability threshold;

[0051] The energy consumption feature similarity is greater than the preset similarity threshold;

[0052] The system then determines that the user is in a commuting mode and collects commuting mode characteristic data. For example, if the combined similarity of three indicators—weekday fixed route repetition rate, time period stability, and energy consumption characteristic similarity—is greater than 85% for five consecutive days, the user can be determined to be in a commuting mode.

[0053] Referring to step S2, after determining that the user is in a commuting mode, in order to achieve intelligent control of the battery thermal management system, it is also necessary to acquire and integrate data from multiple sources in real time, including:

[0054] Current driving information: Through various vehicle sensors, real-time data on the vehicle's current driving status is collected, including vehicle speed, acceleration, real-time state of charge (SOC) of the battery, and real-time temperature distribution of the battery pack. This information provides a clear picture of the vehicle's current operating status and the battery's real-time working condition.

[0055] Commuting mode characteristic data: By statistically analyzing relevant data from users' commuting patterns, we obtain personalized commuting mode characteristic data for each user, including estimated commuting time, estimated commuting route and journey, estimated commuting time period, estimated energy consumption, and historical ambient temperature changes during commuting patterns. This commuting mode characteristic data is of significant reference value for analyzing users' battery usage patterns and thermal management needs in commuting scenarios.

[0056] Battery Thermal Model: This section describes an existing battery thermal model built upon the battery's physical characteristics, heat conduction principles, and extensive experimental data. The model accurately simulates battery temperature changes under various operating conditions and the effectiveness of the battery thermal management system. By inputting parameters such as the current battery state, ambient temperature, and vehicle driving conditions, the battery thermal model can predict the battery's temperature trend over a future period.

[0057] Weather forecast data: Obtain weather data such as ambient temperature for the current day and the following day.

[0058] In a preferred embodiment of this application, a predictive model for the start and stop times of the battery thermal management system is established based on existing time series analysis algorithms, machine learning regression algorithms, etc. This model takes current user driving information, commuting mode characteristic data, and battery thermal model output data as input, and learns and trains using a large amount of historical data to predict the optimal start and stop times of the battery thermal management system under different operating conditions, thereby improving the intelligent control effect and enhancing the user experience. For example, when it is predicted that the battery temperature will exceed the upper limit of the suitable operating temperature range in the future, the model outputs a signal that the battery thermal management system needs to be turned on and provides the expected start time; conversely, when it is predicted that the battery temperature will drop to the lower limit of the suitable operating temperature range, the model outputs a signal that the battery thermal management system needs to be turned off and provides the expected stop time.

[0059] After acquiring and integrating data from various sources, the first step in implementation is to determine whether the user is currently in commuting mode. The determination method is similar to the determination of whether commuting mode exists: if the similarity between the current driving route and the expected route in commuting mode is greater than a preset path similarity threshold, and the driving time is also within the expected commuting time range in commuting mode, and the similarity between the energy consumption characteristics and the expected energy consumption characteristics in commuting mode is also greater than a preset energy consumption characteristic similarity threshold, then the user is determined to be in commuting mode; otherwise, the user is in non-commuting mode.

[0060] Referring to step S3, in this embodiment, the battery thermal management system is intelligently controlled before driving, during driving, and after driving in commuting mode.

[0061] Specifically, before or during driving, the user's current driving information and commuting mode feature data are input into the battery thermal model to predict the battery temperature change during commuting under the current conditions. If the prediction result shows that the battery temperature will exceed the preset operating temperature range within the expected commuting time or the remaining commuting time, it is determined that the battery thermal management system needs to be turned on to ensure battery performance and extend vehicle range; otherwise, the battery thermal management system is turned off to avoid unnecessary consumption of resources.

[0062] This embodiment further evaluates the effectiveness of activating the battery thermal management system, including: obtaining the current battery SOC and remaining commuting distance, and determining whether the current battery SOC can complete the remaining commuting distance under the premise of activating the battery thermal management system; if so, the activation of the battery thermal management system is considered effective; otherwise, the battery thermal management system remains off. For example, the average vehicle energy consumption (kWh / km) when the battery thermal management system is activated is obtained through historical data. The product of the average vehicle energy consumption and the remaining commuting distance yields the required battery SOC. If the current battery SOC is greater than the required battery SOC, the remaining commuting distance is considered achievable; otherwise, the remaining commuting distance is considered unachievable.

[0063] At the end of the trip, the battery status at the end of the trip, the ambient temperature prediction information for the next day in the weather forecast, and the commuting mode characteristic data are input into the battery thermal model for simulation and prediction. If the prediction result shows that the battery temperature will exceed the preset operating temperature range during the commuting process the next day, it is determined that the battery thermal management system needs to be turned on; otherwise, the battery thermal management system is turned off. At the same time, the prediction results are saved for reference when the user prepares to travel the next day.

[0064] Furthermore, in practical applications, users cannot always remain in commuting mode. Therefore, during commuting mode driving, this embodiment also detects in real time whether the user leaves commuting mode. When the user leaves commuting mode, the battery thermal management system control strategy switches to non-commuting mode. Conversely, in non-commuting mode, it also monitors in real time whether the user switches back to commuting mode.

[0065] The methods for detecting whether a user has left commuting mode include: when any of the following conditions are met:

[0066] The route deviation of the expected path in commuting mode is greater than the preset deviation threshold.

[0067] The standard deviation of vehicle acceleration is greater than the preset standard deviation threshold.

[0068] If the user leaves the commuting mode, the battery thermal management system control strategy will switch to the non-commuting mode, including battery thermal management by setting a fixed temperature threshold.

[0069] Through the battery thermal management control method based on user driving habits described above, this embodiment can achieve precise and efficient control of the battery thermal management system, effectively improve battery performance and lifespan, and reduce energy consumption, providing users with a better electric vehicle experience.

[0070] This embodiment also provides a battery thermal management control system based on user driving habits, wherein the system uses the above-described battery thermal management control method based on user driving habits.

[0071] The present invention has been described above by way of example with reference to the accompanying drawings. Obviously, the specific implementation of the present invention is not limited to the above-described manner. Any non-substantial improvements made using the inventive concept and technical solution; or the direct application of the inventive concept and technical solution to other situations without modification, are all within the protection scope of the present invention.

Claims

1. A battery thermal management control method based on user driving habits, characterized by: The method comprises: Step S1, judging whether the user has a commuting mode according to the historical driving habits of the user on the vehicle cloud platform, if so, continue to execute the next step, and count the commuting history data to obtain the commuting mode characteristic data belonging to the user, including the expected commuting time, the expected commuting path and journey, the expected commuting time period, and the expected energy consumption; Step S2, obtaining the current driving information of the user, the commuting mode characteristic data, the weather forecast, and the battery thermal model for battery temperature prediction; determining whether the user is currently in the commuting mode, if so, executing the next step; Step S3, judging the opening and closing of the battery thermal management system before and during driving respectively according to the current driving information of the user, the commuting mode characteristic data, and the battery thermal model, and evaluating the effectiveness of opening the battery thermal management system, and after driving, combining the weather forecast to judge the opening and closing of the battery thermal management system the next day. 2.The battery thermal management control method based on user driving habits according to claim 1, wherein: In the step S1, the user's daily fixed route repetition rate, travel time period stability, and vehicle energy consumption characteristic similarity are obtained according to the historical driving habits of the user on the vehicle cloud platform; when the following conditions are met simultaneously within a continuous preset number of days: The daily fixed route repetition rate is greater than a preset repetition rate threshold; The travel time period stability is greater than a preset stability threshold; The energy consumption characteristic similarity is greater than a preset similarity threshold; It is judged that the user is in the commuting mode, and the commuting mode characteristic data is counted. 3.The battery thermal management control method based on user driving habits of claim 1, wherein: The step S3 comprises: inputting the current driving information of the user and the commuting mode characteristic data into the battery thermal model to predict the temperature change of the battery during the commuting process under the current conditions before or during driving, if the prediction result shows that the battery temperature will exceed the preset working temperature range within the expected commuting time or the remaining commuting time, it is determined that the battery thermal management system needs to be turned on, otherwise the battery thermal management system is turned off.

4. The battery thermal management control method based on user driving habits according to claim 3, characterized in that: Evaluating the effectiveness of opening the battery thermal management system comprises: obtaining the current battery SOC and the remaining commuting journey, and determining whether the current battery SOC can complete the remaining commuting journey under the premise of opening the battery thermal management system; if so, it is considered that the opening of the battery thermal management system is effective; otherwise, the battery thermal management system remains closed. 5.The battery thermal management control method based on user driving habits according to claim 1, characterized in that: The step S3 further comprises: inputting the battery state at the end of driving, the environmental temperature prediction information of the next day in the weather forecast, and the commuting mode characteristic data into the battery thermal model for simulation prediction, if the prediction result shows that the battery temperature will exceed the preset working temperature range during the commuting process the next day, it is determined that the battery thermal management system needs to be turned on, otherwise the battery thermal management system is turned off; at the same time, the prediction result is saved. 6.The battery thermal management control method based on user driving habits according to claim 1, characterized in that: The method further comprises: during the driving process in the commuting mode, detecting whether the user has deviated from the commuting mode in real time, when the user deviates from the commuting mode, switching to the battery thermal management system control strategy in the non-commuting mode.

7. The battery thermal management control method based on user driving habits according to claim 6, characterized in that: The detection method of whether the user has deviated from the commuting mode comprises: When any of the following conditions is met: The route deviation from the commuting mode is greater than a preset deviation threshold; The vehicle acceleration standard deviation is greater than a preset standard deviation threshold; It is considered that the user has deviated from the commuting mode. 8.The battery thermal management control method based on user driving habits of claim 9, wherein: The battery thermal management system control strategy in the non-commuting mode includes battery thermal management by setting a fixed temperature threshold. 9.The battery thermal management control method based on user driving habits of claim 1, wherein: The method further comprises: establishing a prediction model of the opening and closing time of the battery thermal management system, the model taking the current user driving information, the commuting mode feature data and the battery thermal model output data as input, and learning and training through historical data to predict the optimal opening and closing time point of the battery thermal management system under different working conditions.

10. A battery thermal management control system based on user driving habits, characterized by: The system uses a battery thermal management control method based on user driving habits according to any one of claims 1-9.

Images