Vehicle storage battery electric quantity management method and system and model training method
By utilizing an energy recovery prediction model and a DC-DC converter in the vehicle, suspension energy recovery information is calculated based on user information and driving behavior, and low-voltage battery power is precisely managed. This solves the problem of active suspension energy recovery and power management, and improves the vehicle's range.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-15
- Publication Date
- 2026-03-27
AI Technical Summary
How to more effectively recover energy from the vehicle's active suspension and manage the low-voltage battery charge based on the recovered energy in order to improve the vehicle's range.
By determining information such as user information, driving behavior, driving status, road characteristics, and suspension markings of the target vehicle, the energy recovery prediction model is used to calculate the energy recovery power and energy information of the active suspension. Combined with the low-voltage battery status parameters, the low-voltage battery power is precisely managed, including charging through a DC-DC converter.
It improves the accuracy of low-voltage battery power management, reduces power waste, and enhances vehicle range.
Smart Images
Figure CN121734178A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle battery power management technology, and in particular to a vehicle battery power management method and system, and a model training method. Background Technology
[0002] With the development of vehicle intelligence technology, there are more and more low-voltage electronic devices in vehicles. At the same time, with the increase of low-voltage side voltage (such as 48V platform), the application of active suspension technology and the development of all-domain intelligent electronic power distribution function, the power consumption of vehicles on the low-voltage side is increasing, and low-voltage power consumption will affect the vehicle's driving range.
[0003] With the increasing prevalence of electronically controlled active suspension, while improving driving comfort, active suspension can also recover some of the vehicle's Z-axis energy during road bumps using electromagnetic induction and control systems, which can then be used by the vehicle's low-voltage battery. How to rationally recover energy from the vehicle's active suspension and manage the low-voltage battery charge based on the recovered energy is crucial for improving the vehicle's range. Summary of the Invention
[0004] This application provides a vehicle battery power management method and system, and an energy recovery prediction model training method, to solve the problem of how to more rationally recover energy from the vehicle's active suspension and manage the low-voltage battery power based on the recovered energy, so as to improve the vehicle's range.
[0005] To address the aforementioned technical problems, in a first aspect, this application discloses a method for managing vehicle battery power. This method includes: determining target information during the vehicle's operation, including user information, user driving behavior information, driving status information, road characteristic information, active suspension identification information, and active suspension energy recovery history information; determining target energy recovery power information of the active suspension in the target vehicle based on the target information using a target energy recovery prediction model; determining target energy recovery information of the active suspension based on the target energy recovery power information and the target travel information corresponding to the target vehicle, where the target travel information is the travel distance from the starting point to the end point of the target travel distance; determining target battery power information corresponding to the low-voltage battery based on the battery state parameters and the target energy recovery information; and managing the battery power based on the target battery power information.
[0006] By employing the above technical solution, the target energy recovery power information of the active suspension of a target vehicle can be determined based on target information including user information, user driving behavior information, driving status information, driving road characteristic information, active suspension identification information, and active suspension energy recovery history information, as well as a target energy recovery prediction model. Then, based on the target energy recovery power information and the target travel information of the target vehicle, the target energy recovery information of the active suspension is determined. Finally, based on the battery state parameters of the low-voltage battery in the target vehicle and the target energy recovery information, the target charge information of the low-voltage battery is determined. The charge of the low-voltage battery is then managed based on the target charge information. This allows for more accurate determination of the target energy recovery information of the active suspension during vehicle operation, and the accurate target charge information of the low-voltage battery based on the battery state parameters and target energy recovery information. The charge of the low-voltage battery can then be managed based on the target charge information, such as charging the low-voltage battery through a DC-DC converter until the low-voltage battery reaches the target charge level. It can effectively manage the low-voltage battery power more rationally and accurately based on the energy recovery information of the vehicle's active suspension, reducing the waste of vehicle power and thus improving the vehicle's range.
[0007] According to another specific implementation of this application, the implementation of this application discloses a vehicle battery power management method, in which user driving behavior information is obtained based on the historical driving information of the target vehicle, driving status information includes vehicle speed information, which is obtained based on the target driving distance of the target vehicle and the road condition information corresponding to the target driving distance, and driving road characteristic information includes road bump index, which is obtained based on the target driving distance and the preset correspondence between driving distance and bump index.
[0008] By adopting the above technical solution, the accuracy of the obtained target information can be effectively improved, thereby improving the accuracy of the target vehicle's active suspension target energy recovery information.
[0009] According to another specific implementation of this application, the implementation of this application discloses a vehicle battery power management method, which determines the target energy recovery power information of the active suspension in the target vehicle based on target information, including: determining the initial energy recovery power information of the active suspension in the target vehicle based on the first information in the target information, the first information including user information, user driving behavior information, driving status information, driving road characteristic information and active suspension identification information; and verifying and correcting the initial energy recovery power information based on the second information in the target information to obtain the target energy recovery power information, the second information including the active suspension energy recovery history information.
[0010] Using the above technical solution, initial energy recovery power information is obtained based on user information, user driving behavior information, driving status information, road characteristic information, and active suspension identification information. Then, based on historical active suspension energy recovery information, the initial energy recovery power information is verified and corrected to obtain target energy recovery power information. Combining historical active suspension energy recovery information (such as the active suspension energy recovery information from the previous moment) to verify and correct the initial energy recovery power information effectively improves the accuracy of the obtained target energy recovery power information.
[0011] According to another specific implementation of this application, the implementation of this application discloses a vehicle battery power management method, wherein the target energy recovery power information includes a target energy recovery power spectrum, and the target energy recovery information of the active suspension is determined based on the target energy recovery power information and the target travel information corresponding to the target vehicle, including: determining the target energy recovery information of the active suspension based on the target energy recovery power spectrum and the target travel information.
[0012] By adopting the above technical solution, the target energy recovery information of the active suspension is more accurate based on the target energy recovery power spectrum and target travel information.
[0013] According to another specific implementation of this application, a vehicle battery power management method is disclosed in this implementation. The target energy recovery information includes a target energy recovery value. Based on the target energy recovery power spectrum and target travel information, the target energy recovery information of the active suspension is determined, including: determining the energy consumption power information of the low-voltage electronic devices included in the target vehicle corresponding to the target travel distance; determining the target energy recovery extreme power of the active suspension based on the target energy recovery power spectrum; and determining the target energy recovery value of the active suspension based on the target energy recovery extreme power, target travel information, and energy consumption power information.
[0014] By adopting the above technical solution, the target energy recovery extreme power of the active suspension is determined based on the target energy recovery power spectrum, and the energy consumption power information of the low-voltage electronic devices included in the target vehicle corresponding to the target driving distance is determined. Then, based on the target energy recovery extreme power, target travel information, and energy consumption power information, the determined target energy recovery value of the active suspension can be effectively improved, and the low-voltage battery power can be managed more rationally and accurately based on the energy recovery information of the vehicle's active suspension.
[0015] According to another specific implementation of this application, a vehicle battery power management method is disclosed in this implementation. Given that the target travel time is the target travel time required for the target vehicle to travel from the starting point to the end point of the target travel distance, the method includes determining the target energy recovery value of the active suspension using the following formula:
[0016] E bat_chrg =∫0 t (P regen -P veh_discharg )dt
[0017] Among them, E bat_chrg For the target energy recovery value, P regen For the target energy recovery extreme power, P veh_discharg This represents energy consumption power information, and t represents the target travel time.
[0018] According to another specific implementation of this application, the implementation of this application discloses a vehicle battery power management method, wherein the battery status parameter information includes the life information of the low-voltage battery and the battery temperature information.
[0019] By adopting the above technical solution, based on the lifespan and temperature information of the low-voltage battery, the target capacity information corresponding to the determined low-voltage battery can be effectively improved.
[0020] Secondly, the implementation of this application also discloses a model training method, which includes: determining a training dataset, the training dataset including multiple energy recovery power prediction training samples corresponding to the active suspension in the vehicle; inputting the training dataset into an initial energy recovery prediction model for training until the loss function corresponding to the initial energy recovery prediction model converges and the reward function meets the requirements, thereby obtaining a target energy recovery prediction model, which is applied to the vehicle battery power management method as described in any of the first aspects.
[0021] According to another specific implementation of this application, the model training method disclosed in this application further includes, during the training of the initial energy recovery prediction model: when the actual energy recovery value of the active suspension increases, a positive reward is given based on the reward function; when the difference between the actual energy recovery value and the predicted energy recovery value of the active suspension is greater than the difference threshold and / or the user's driving comfort does not meet the requirements, a negative reward is given based on the reward function.
[0022] By adopting the above technical solution, the accuracy of the energy recovery prediction model in predicting the energy recovery information of active suspension can be effectively improved.
[0023] Thirdly, this application also discloses a vehicle battery power management system. This system includes a server and a target vehicle. The server determines target information during the vehicle's operation. Based on this target information, it uses a target energy recovery prediction model to determine the target energy recovery power information of the active suspension in the target vehicle. Based on the target energy recovery power information and the target travel information corresponding to the target vehicle, it determines the target energy recovery information of the active suspension. Based on the battery state parameters and the target energy recovery information of the low-voltage battery in the target vehicle, it determines the target battery power information. The target information includes user information, user driving behavior information, driving status information, road characteristic information, active suspension identification information, and active suspension energy recovery history information. The target travel information is the travel information of the target vehicle from the starting point to the end point of the target travel distance. The target vehicle manages the battery power based on the target battery power information.
[0024] Fourthly, this application also discloses a model training device, comprising: a first processing module for determining a training dataset, the training dataset including multiple energy recovery power prediction training samples corresponding to the active suspension in a vehicle; and a second processing module for inputting the training dataset into an initial energy recovery prediction model for training until the loss function corresponding to the initial energy recovery prediction model converges and the reward function meets the requirements, thereby obtaining a target energy recovery prediction model, the target energy recovery prediction model being applied to the vehicle battery power management method as described in any one of the first aspects.
[0025] Fifthly, this application also discloses an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores a computer program; the processor executes the computer program stored in the memory to enable the electronic device to implement the corresponding processing in the vehicle battery power management method provided by any of the implementations of the first aspect above, or to implement the corresponding processing in the model training method provided by any of the implementations of the second aspect above.
[0026] Sixthly, an implementation of this application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it is used to implement the corresponding processing in the vehicle battery power management method provided by any of the implementations of the first aspect above, or to implement the corresponding processing in the model training method provided by any of the implementations of the second aspect above.
[0027] Seventhly, an implementation of this application provides a computer program product, including a computer program that, when executed by a processor, implements the corresponding processing in the vehicle battery power management method provided by any implementation of the first aspect above, or implements the corresponding processing in the model training method provided by any implementation of the second aspect above.
[0028] It is understandable that the beneficial effects of the third to fifth aspects mentioned above can also be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description
[0029] Figure 1 This is a schematic flowchart of a vehicle battery power management method provided in an embodiment of this application;
[0030] Figure 2 This is a flowchart illustrating how to determine the target energy recovery power information of the active suspension in a target vehicle based on target information, according to an embodiment of this application.
[0031] Figure 3 This is another flowchart illustrating how to determine the target energy recovery power information of the active suspension in a target vehicle based on target information, according to an embodiment of this application.
[0032] Figure 4 This is a schematic diagram of a process for determining the target energy recovery information of an active suspension according to an embodiment of this application;
[0033] Figure 5 This is an integral diagram illustrating the determination of the target recovered energy value of the active suspension based on the target energy recovery extreme power, target travel information, and energy consumption power information, provided in an embodiment of this application.
[0034] Figure 6 This is a flowchart illustrating a model training method provided in an embodiment of this application.
[0035] Figure 7 This is a schematic diagram of a target energy recovery prediction model provided in an embodiment of this application;
[0036] Figure 8 This is a schematic diagram of a vehicle battery power management system provided in an embodiment of this application;
[0037] Figure 9 This is a schematic diagram of the structure of the target vehicle provided in an embodiment of this application;
[0038] Figure 10 This is a schematic diagram of an electronic power distribution unit provided in an embodiment of this application;
[0039] Figure 11This is a schematic diagram of a vehicle-cloud coordinated low-voltage energy management method and management system provided in an embodiment of this application;
[0040] Figure 12 This is a schematic diagram of a vehicle-side low-voltage energy management system method and management system provided in an embodiment of this application;
[0041] Figure 13 This is a schematic diagram illustrating the correspondence between the low-voltage storage battery and the low-voltage grid voltage provided in an embodiment of this application;
[0042] Figure 14 This is a schematic diagram of a structure of an energy recovery prediction model training device provided in an embodiment of this application;
[0043] Figure 15 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0044] As mentioned earlier, how to more rationally recover energy from the vehicle's active suspension and manage the low-voltage battery charge based on the recovered energy to improve the vehicle's range has become an important issue in the existing technology.
[0045] Based on this, this application provides a vehicle battery power management method and system, which can more accurately determine the target energy recovery information of the active suspension during vehicle operation, and determine the accurate target power information corresponding to the low-voltage battery based on the battery state parameter information and target energy recovery information of the target vehicle's low-voltage battery. Based on the target power information, the power of the low-voltage battery is managed, reducing the waste of vehicle power and thus improving the vehicle's range.
[0046] Next, with reference to the accompanying drawings, the steps and advantages of the vehicle controller configuration method provided in this application will be described in detail.
[0047] In one implementation of this application, such as Figure 1 As shown, the vehicle battery power management method includes the following steps.
[0048] S100: Determine target information during the vehicle's movement.
[0049] The target information includes user information corresponding to the target vehicle, user driving behavior information, driving status information, driving road characteristic information, active suspension identification information, and active suspension energy recovery history information.
[0050] Among these, user information could include, for example, the account information of the user currently driving the target vehicle.
[0051] User driving behavior information can include the user's driving style. By collecting information such as the target vehicle's steering, acceleration, and braking, it can be determined whether the user's driving style is aggressive or conservative.
[0052] Driving status information, such as the target vehicle's speed, can be used.
[0053] Information about road characteristics can include, for example, the degree of bumpiness or the gradient of the road.
[0054] Active suspension identification information can include, for example, the active suspension number.
[0055] Historical information on active suspension energy recovery can include, for example, the energy recovery history data of a single target vehicle or the energy recovery history data of a fleet.
[0056] S200: Based on the target information, the target energy recovery prediction model determines the target energy recovery power information of the active suspension in the target vehicle.
[0057] For example, the target information can be input into the target energy recovery prediction model for prediction processing to obtain the target energy recovery power information of the active suspension in the target vehicle.
[0058] S300: Determine the target energy recovery information of the active suspension based on the target energy recovery power information and the target travel information of the target vehicle.
[0059] The target trip information refers to the journey information of the target vehicle from the starting point to the ending point of the target route, such as mileage and travel time. This information can be obtained through the vehicle's navigation software for trip planning, as well as real-time traffic congestion information and predicted conditions.
[0060] S400: Determine the target charge information corresponding to the low-voltage battery based on the battery state parameter information and target recovered energy information of the low-voltage battery in the target vehicle.
[0061] Target energy information could be, for example, the State of Charge (SOC) of a low-voltage battery. That is, based on the battery state parameters of the low-voltage battery in the target vehicle and the target recovered energy information, the SOC value is determined when the low-voltage battery can meet the vehicle's usage requirements during the target driving distance.
[0062] S500: Manages the power of low-voltage batteries based on target power information.
[0063] For example, based on the SOC value of the low-voltage battery, the high-voltage battery can be controlled to charge the low-voltage battery until the low-voltage battery reaches that SOC value.
[0064] The vehicle battery power management method provided in this application can determine the target energy recovery power information of the active suspension of a target vehicle based on target information including user information corresponding to the target vehicle, user driving behavior information, driving status information, driving road characteristic information, active suspension identification information, and active suspension energy recovery history information, as well as a target energy recovery prediction model. Then, based on the target energy recovery power information and the target travel information corresponding to the target vehicle, the target energy recovery information of the active suspension is determined. Finally, based on the battery state parameters and target energy recovery information of the low-voltage battery in the target vehicle, the target power information of the low-voltage battery is determined. Based on the target power information, the power of the low-voltage battery is managed. Therefore, it can more accurately determine the target energy recovery information of the active suspension during vehicle operation, and accurately determine the target power information of the low-voltage battery based on the battery state parameters and target energy recovery information of the target vehicle's low-voltage battery. Based on the target power information, the power of the low-voltage battery is managed, for example, by charging the low-voltage battery through a DC-DC converter until the low-voltage battery power reaches the target power information. It can effectively manage the low-voltage battery power more rationally and accurately based on the energy recovery information of the vehicle's active suspension, reducing the waste of vehicle power and thus improving the vehicle's range.
[0065] In one implementation of this application, such as Figure 2 As shown, a flowchart is provided to determine the target energy recovery power information of the active suspension in a target vehicle based on target information. The target energy recovery power information may be, for example, the target energy recovery power spectrum.
[0066] This process is also a process of predicting the power spectrum of travel energy recovery (i.e., the target power spectrum of energy recovery) through machine learning.
[0067] Firstly, based on historical data in the cloud (such as steering information, braking information, acceleration information, etc. corresponding to the target user), the user's driving style can be identified. Based on trip planning and road condition data (such as traffic congestion and expected conditions), the trip speed (i.e., vehicle speed information) can be predicted.
[0068] The active suspension control of the current target vehicle stores the road bump index to achieve the magic carpet suspension function, and this data is also used for road feature updates.
[0069] Then, based on the user's driving style, predicted trip speed, and road characteristics, the suspension energy recovery is predicted to obtain the active suspension energy recovery power spectrum.
[0070] Furthermore, performance can be verified and corrected using real-time energy recovery data from the active suspension. Simultaneously, to ensure data reliability, the active suspension energy recovery power spectrum can be updated based on the target vehicle's individual vehicle energy recovery history data and the fleet's energy recovery history data.
[0071] That is, in one implementation of this application, the user driving behavior information is obtained based on the historical driving information of the target vehicle, the driving status information includes vehicle speed information, the vehicle speed information is obtained based on the target driving distance of the target vehicle and the road condition information corresponding to the target driving distance, and the driving road feature information includes road bump index, the road bump index is obtained based on the target driving distance and the preset correspondence between the driving distance and the bump index.
[0072] In one implementation of this application, such as Figure 3 As shown, the target energy recovery power information of the active suspension in the target vehicle is determined based on the target information, including the following steps.
[0073] S210: Based on the first information in the target information, determine the initial energy recovery power information of the active suspension in the target vehicle.
[0074] The first information includes user information, user driving behavior information, driving status information, driving road characteristic information, and active suspension identification information.
[0075] S220: Based on the second information in the target information, the initial energy recovery power information is verified and corrected to obtain the target energy recovery power information.
[0076] The second piece of information includes historical information on active suspension energy recovery.
[0077] In one implementation of this application, the target energy recovery power information includes a target energy recovery power spectrum. Determining the target energy recovery information of the active suspension based on the target energy recovery power information and the target travel information corresponding to the target vehicle includes: determining the target energy recovery information of the active suspension based on the target energy recovery power spectrum and the target travel information.
[0078] In one implementation of this application, the target recovered energy information includes the target recovered energy value, such as... Figure 4 As shown, the target energy recovery information of the active suspension is determined based on the target energy recovery power spectrum and the target travel information, including the following steps.
[0079] S310: Determine the energy consumption power information of the low-voltage electronic devices included in the target vehicle corresponding to the target travel distance.
[0080] S320: Determine the target energy recovery extreme power of the active suspension based on the target energy recovery power spectrum.
[0081] S330: Determine the target energy recovery value of the active suspension based on the target energy recovery extreme power, target travel information, and energy consumption power information.
[0082] For example, such as Figure 5 As shown, the average low-voltage power consumption (energy consumption power information) of the low-voltage electronic devices included in the target vehicle corresponding to the target driving distance is determined, and the instantaneous energy recovery (W) is determined according to the active suspension energy recovery power (W) predicted by the model. According to the correspondence of energy consumption / recovery = power integral, the target recovered energy value of the active suspension is determined according to the integration time (s).
[0083] In one implementation of this application, when the target travel information is the target travel time required for the target vehicle to travel from the starting point to the ending point of the target travel distance, the method includes determining the target recovered energy value of the active suspension using the following formula:
[0084] E bat_chrg =∫0 t (P regen -P veh_discharg )dt
[0085] Among them, E bat_chrg For the target energy recovery value, P regen For the target energy recovery extreme power, P veh _ discharg This represents energy consumption power information, and t represents the target travel time.
[0086] In one implementation of this application, the battery state parameter information includes low-voltage battery life information and battery temperature information.
[0087] In one implementation of this application, such as Figure 6 As shown, a model training method is provided, which includes the following steps.
[0088] S10: Determine the training dataset.
[0089] The training dataset includes multiple training samples corresponding to the energy recovery power prediction of active suspension in vehicles.
[0090] Each power prediction training sample may include attributes such as historical user information, historical user driving behavior information, historical driving status information, historical driving road feature information, historical active suspension identification information, and historical active suspension energy recovery information.
[0091] S20: Input the training dataset into the initial energy recovery prediction model for training until the loss function corresponding to the initial energy recovery prediction model converges and the reward function meets the requirements, thus obtaining the target energy recovery prediction model.
[0092] This target energy recovery prediction model is applied to the aforementioned vehicle battery power management method.
[0093] In one implementation of this application, during the training of the initial energy recovery prediction model, the method further includes: providing a positive reward based on a reward function when the actual energy recovery value of the active suspension increases; and providing a negative reward based on a reward function when the difference between the actual energy recovery value and the predicted energy recovery value of the active suspension exceeds a difference threshold and / or the user's driving comfort does not meet the requirements.
[0094] For example, such as Figure 7 As shown, the suspension energy recovery prediction model estimates the predicted energy recovery power using an AI Agent. A goal-oriented reward function is designed to balance energy recovery efficiency and driving experience. Higher recovered energy values receive positive rewards, while reduced driving comfort (caused by sudden torque changes) and deviations from expectations (such as actual energy recovery not matching expectations) receive negative rewards, thus adjusting the suspension energy recovery prediction model parameters.
[0095] Among them, AIAgent is deployed in the cloud to be an entity or software that senses the environment and takes action to achieve goals, including predicting energy recovery power.
[0096] The state space is a collection of perceived environmental states, including driver behavior, expected travel speed, travel bump index, historical energy recovery data for individual vehicles, historical energy recovery data for the entire fleet, and real-time energy recovery data for the suspension.
[0097] Actions are behaviors taken to change the state of the environment, and energy recovery and DC-DC control are achieved by controlling the suspension torque.
[0098] The environment refers to the physical world and abstract information space in which the vehicle is located, including the vehicle's position, speed, driver behavior, vehicle vibration status, and actual vehicle status (such as suspension energy recovery).
[0099] In one implementation of this application, such as Figure 8As shown, a vehicle battery power management system is provided. The system includes a server and a target vehicle. The server is used to determine the target information during the driving process of the target vehicle. Based on the target information, the server determines the target energy recovery power information of the active suspension in the target vehicle through a target energy recovery prediction model. Based on the target energy recovery power information and the target trip information of the target vehicle, the server determines the target energy recovery information of the active suspension. Based on the battery state parameter information and the target energy recovery information of the low-voltage battery in the target vehicle, the server determines the target power information of the low-voltage battery. The target information includes user information, user driving behavior information, driving status information, driving road characteristic information, active suspension identification information, and active suspension energy recovery history information. The target trip information is the trip information of the target vehicle from the starting point to the ending point of the target driving distance.
[0100] The target vehicle is used to manage the power of the low-voltage battery based on the target power information.
[0101] In one implementation of this application, the vehicle battery power management system provided by this application includes a vehicle-side (i.e., the target vehicle) and a cloud-side (i.e., the server). The vehicle-side collects real-time data of the vehicle and uploads it to the cloud-side. The cloud-side records data over a long period of time and performs AI autonomous learning. The cloud-side sends AI-optimized instructions to the vehicle-side, and the vehicle-side controller executes the corresponding energy management strategy.
[0102] The cloud collects information on single and multiple vehicles, and uses machine learning and other methods to predict the instantaneous power and energy values of energy recovery for the current trip based on the driver's driving style.
[0103] The central computing unit (i.e., central control unit) at the vehicle end is used to control the low-voltage battery charging process and maintain the battery within an appropriate charge range. It also monitors the electronic power distribution and low-voltage power consumption status of the low-voltage loads through area controllers.
[0104] In one implementation of this application, such as Figure 9 As shown, the central control unit at the vehicle end includes zone controller 1 (i.e., ZONE1), zone controller 2 (i.e., ZONE2), and zone controller 3 (i.e., ZONE3). The electronic power distribution unit includes each zone controller, which is used to perform electronic power distribution and low-voltage power status monitoring of the low-voltage battery.
[0105] In one implementation of this application, such as Figure 10As shown, the electronic power distribution unit detects the power level of the low-voltage battery management system (LVBMS) through the zone controller and actuators, and replenishes the low-voltage battery by using DC-DC power supply circuit 1 and by using the energy recovered from the active suspension through the power supply circuit 3. The zone controller contains a metal-oxide-semiconductor (MOS) transistor.
[0106] The vehicle also includes a low-voltage battery system for low-voltage energy storage and battery management.
[0107] The vehicle also includes an on-board charging system that performs high-voltage to low-voltage energy conversion (DCDC).
[0108] The vehicle also includes an active suspension system, which controls the stiffness of the suspension and actively “intervenes” in vibrations through actuators. The active suspension recovers low-pressure energy from road bumps by using electromagnetic induction and control systems.
[0109] In one implementation of this application, the vehicle battery power management system provided in this application, namely a vehicle-cloud coordinated low-voltage energy management system, such as... Figure 11 As shown, the vehicle-cloud coordinated low-voltage energy management system predicts the power spectrum of active suspension energy recovery during travel by analyzing driver information (such as user information) and vehicle status. Based on the power spectrum and electronic power distribution monitoring, it monitors the vehicle's low-voltage power consumption to obtain the actual low-voltage load power consumption of the current vehicle (i.e., the target vehicle). It then calculates the extreme power of active suspension energy recovery and the travel-recovered energy value. Based on the extreme power of energy recovery and the recovered energy value, it calculates the SOC value that the low-voltage battery should maintain (i.e., reserved capacity, target SOC of the low-voltage battery) to meet the requirements of instantaneous charging power and travel energy storage. Finally, based on the target SOC of the low-voltage battery, it calculates the output voltage of the DC-DC converter and controls the DC-DC output voltage to charge the low-voltage battery to achieve the target SOC.
[0110] In one implementation of this application, the energy of the vehicle under driving conditions can be estimated based on the predicted active suspension energy recovery power spectrum and travel time, and the energy that can be recovered and stored during the entire journey can be predicted based on the actual low-pressure consumption of the vehicle.
[0111] Low-pressure energy recovery power: P bat_chrg =P regen -P veh_discharg
[0112] Low-pressure energy recovery energy: E bat_chrg =∫(P regen -Pveh_discharg )dt
[0113] Among them, P bat_chrg For low-voltage energy recovery power, E bat_chrg For low-pressure energy recovery (i.e., the target recovered energy value), P regen For the target energy recovery extreme power, P veh_discharg This represents energy consumption power information, and t represents the target travel time.
[0114] In one implementation of this application, such as Figure 12 As shown, the vehicle-side low-voltage energy management system adjusts the target output voltage value of the DC-DC converter based on the instantaneous maximum power value of energy recovery during the predicted trip and the current state of the battery (i.e., real-time status information) to achieve optimal management of battery power (e.g., management based on the expected battery SOC).
[0115] Specifically, based on the predicted maximum instantaneous power value of energy recovery during the trip, a portion of the battery capacity is reserved to meet instantaneous charging needs and prevent battery overvoltage. Another portion of the battery capacity is reserved to accommodate potential SOC increases due to short-term continuous power recovery, maximizing energy recovery. The minimum sustaining capacity is calculated based on battery life, battery temperature, and low-voltage power consumption data to ensure safe vehicle operation.
[0116] In one implementation of this application, such as Figure 13 The diagram illustrates the relationship between low-voltage battery and low-voltage grid voltage, allowing for real-time voltage adjustment based on battery aging status. Figure 13 It can be seen that the lower the SOC of a low-voltage battery, the lower the corresponding low-voltage grid voltage, and the safe SOC of the battery is lower than the target SOC and lower than 100% SOC.
[0117] The vehicle battery power management method and system provided in this application are based on an advanced EEA architecture and use AI technology and cloud big data to adjust the energy management strategy in real time for different users and trip plans. By optimizing the energy recovery and energy management strategy on the low-voltage side, the vehicle's driving range is increased.
[0118] In one implementation of this application, a model training device is provided, such as... Figure 14 As shown, it includes: a first processing module for determining a training dataset, which includes multiple training samples corresponding to the energy recovery power prediction of the active suspension in the vehicle; and a second processing module for inputting the training dataset into the initial energy recovery prediction model for training until the loss function corresponding to the initial energy recovery prediction model converges and the reward function meets the requirements, thereby obtaining a target energy recovery prediction model, which is applied to the aforementioned vehicle battery power management method.
[0119] Please see Figure 15 , Figure 15 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Figure 15 As shown, the electronic device may include: transceiver 121, processor 122, and memory 123.
[0120] In one implementation of this application, the electronic device may be, for example, the aforementioned cloud or server.
[0121] Processor 122 executes computer execution instructions stored in memory, causing processor 122 to execute the corresponding technical solutions in the vehicle battery power management method and / or energy recovery prediction model training method in the above embodiments. Processor 122 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0122] The memory 123 is connected to the processor 122 via the system bus and completes communication between them. The memory 123 is used to store computer program instructions.
[0123] For example, and not as a limitation, memory 123 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 123 may include removable or non-removable (or fixed) media. Transceiver 121 may be used to acquire the task to be run and its configuration information.
[0124] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. For ease of illustration, it is represented by only one thick line in the figure, but this does not mean that there is only one bus or one type of bus.
[0125] This application also provides a chip for executing instructions, which is used to execute the corresponding technical solutions in the vehicle battery power management method and / or model training method in the above embodiments.
[0126] This application also provides a computer-readable storage medium storing computer instructions. When these computer instructions are executed on the processor of an electronic device, the processor of the electronic device executes the corresponding technical solutions in the vehicle battery power management method and / or model training method of the above embodiments.
[0127] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the corresponding technical solutions in the vehicle battery power management method and / or model training method in the above embodiments.
[0128] This application is described with reference to flowchart illustrations and / or block diagrams of the methods, apparatus, and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable information processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable information processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable information processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0130] These computer program instructions may also be loaded onto a computer or other programmable information processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0131] It should be noted that, in addition to the specific embodiments described above, those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Although the description of this application is presented in conjunction with preferred embodiments, this does not mean that the features of this invention are limited to this implementation. On the contrary, the purpose of describing the invention in conjunction with the implementation is to cover other options or modifications that may be derived based on the claims of this application. To provide a thorough understanding of this application, many specific details are included in the above description, and this application may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of this application, some specific details will be omitted in the description. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.
[0132] It should be noted that in this specification, similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0133] Although this application has been illustrated and described with reference to certain preferred embodiments, those skilled in the art should understand that the above description is a further detailed explanation of the application in conjunction with specific implementations, and should not be construed as limiting the specific implementation of the application to these descriptions. Those skilled in the art can make various changes in form and detail, including some simple deductions or substitutions, without departing from the spirit and scope of this application.
Claims
1. A method for managing the power of a vehicle battery, characterized in that, The method includes: Determine target information during the driving process of the target vehicle. The target information includes user information, user driving behavior information, driving status information, driving road characteristic information, active suspension identification information, and active suspension energy recovery history information corresponding to the target vehicle. Based on the target information, the target energy recovery prediction model determines the target energy recovery power information of the active suspension in the target vehicle. Based on the target energy recovery power information and the target travel information corresponding to the target vehicle, the target energy recovery information of the active suspension is determined, wherein the target travel information is the travel information of the target vehicle from the starting point of the target travel distance to the end point of the target travel distance; Based on the battery status parameter information of the low-voltage battery in the target vehicle and the target recovered energy information, the target power information corresponding to the low-voltage battery is determined; The power of the low-voltage battery is managed based on the target power information.
2. The vehicle battery power management method as described in claim 1, characterized in that, The user driving behavior information is obtained based on the historical driving information of the target vehicle. The driving status information includes vehicle speed information, which is obtained based on the target driving distance of the target vehicle and the road condition information corresponding to the target driving distance. The driving road feature information includes road bump index, which is obtained based on the target driving distance and the preset correspondence between driving distance and bump index.
3. The vehicle battery power management method as described in claim 1 or 2, characterized in that, Based on the target information, the target energy recovery power information of the active suspension in the target vehicle is determined, including: Based on the first information in the target information, the initial energy recovery power information of the active suspension in the target vehicle is determined, wherein the first information includes the user information, the user driving behavior information, the driving status information, the driving road feature information, and the active suspension identification information; Based on the second information in the target information, the initial energy recovery power information is verified and corrected to obtain the target energy recovery power information, wherein the second information includes the active suspension energy recovery history information.
4. The vehicle battery power management method as described in any one of claims 1-3, characterized in that, The target energy recovery power information includes a target energy recovery power spectrum. Based on the target energy recovery power information and the target travel information corresponding to the target vehicle, the target energy recovery information of the active suspension is determined, including: The target energy recovery information of the active suspension is determined based on the target energy recovery power spectrum and the target travel information.
5. The vehicle battery power management method as described in claim 4, characterized in that, The target recovered energy information includes a target recovered energy value. The target recovered energy information of the active suspension is determined based on the target recovered energy power spectrum and the target travel information, including: Determine the energy consumption power information of the low-voltage electronic devices included in the target vehicle corresponding to the target travel distance; The target energy recovery extreme power of the active suspension is determined based on the target energy recovery power spectrum. The target energy recovery value of the active suspension is determined based on the target energy recovery extreme power, the target travel information, and the energy consumption power information.
6. The vehicle battery power management method as described in claim 5, characterized in that, When the target travel information is the target travel time required for the target vehicle to travel from the start point to the end point of the target travel distance, the method includes determining the target recovered energy value of the active suspension using the following formula: HAVE BEEN bat_chrg =∫0 t (P regen -P veh_discharg )dt Among them, E bat_chrg P represents the target energy recovery value. regen P is the target energy recovery extreme power. veh_discharg The energy consumption power information is given, and t is the target travel time.
7. The vehicle battery power management method according to any one of claims 1-6, characterized in that, The battery status parameter information includes the lifespan information and battery temperature information of the low-voltage battery.
8. A model training method, characterized in that, The method includes: Determine a training dataset, which includes multiple training samples corresponding to the energy recovery power prediction of active suspension in a vehicle; The training dataset is input into the initial energy recovery prediction model for training until the loss function corresponding to the initial energy recovery prediction model converges and the reward function meets the requirements, thereby obtaining the target energy recovery prediction model. The target energy recovery prediction model is applied to the vehicle battery power management method as described in any one of claims 1-7.
9. The model training method as described in claim 8, characterized in that, The method further includes the following steps during the training of the initial energy recovery prediction model: When the actual energy recovery value of the active suspension increases, a positive reward is given based on the reward function; If the difference between the actual energy recovery value and the predicted energy recovery value of the active suspension is greater than the difference threshold and / or the user's driving comfort does not meet the requirements, a negative reward is given based on the reward function.
10. A vehicle battery power management system, characterized in that, The system includes a server and a target vehicle, wherein, The server is used to determine target information during the driving process of the target vehicle. Based on the target information, the server determines the target energy recovery power information of the active suspension in the target vehicle using a target energy recovery prediction model. Based on the target energy recovery power information and the target travel information corresponding to the target vehicle, the server determines the target energy recovery information of the active suspension. Based on the battery state parameter information of the low-voltage battery in the target vehicle and the target energy recovery information, the server determines the target charge information corresponding to the low-voltage battery. The target information includes user information, user driving behavior information, driving status information, driving road characteristic information, active suspension identification information, and active suspension energy recovery history information corresponding to the target vehicle. The target travel information is the travel information of the target vehicle from the starting point of the target travel distance to the ending point of the target travel distance. The target vehicle is used to manage the power of the low-voltage battery based on the target power information.