Adaptive control method and device for battery management system, medium, and program product

Abstract

Provided in the present application are an adaptive control method and device for a battery management system, a medium, and a program product. The method comprises: by means of a cloud battery management system, acquiring real-time data of a target vehicle; analyzing the real-time data to determine the real-time operating condition of the target vehicle and a target control strategy; and adapting the target control strategy to a target cloud platform having a mapping relationship with the real-time operating condition, such that the target cloud platform controls battery systems of all vehicles in a vehicle set associated therewith.

Description

Battery management system adaptive control methods, devices, media, and program products Cross-references to related applications

[0001] This application claims priority to Chinese patent application No. 202411432590.5, filed on October 14, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to, but is not limited to, the field of battery control system technology, and in particular to an adaptive control method, device, medium, and program product for a battery management system. Background Technology

[0003] Currently, the battery control system in vehicles typically consists of a Cell Monitor Unit (CMU) and a Battery Management System (BMS). The CMU collects data on various parameters such as voltage, current, and temperature, and transmits this data to the BMS. The BMS estimates the data transmitted by the CMU; if abnormal data is found, it performs fault diagnosis according to the fault diagnosis strategy defined in the BMS, and then protects the battery based on the diagnosed fault level and corresponding fault measures. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] According to a first aspect of the embodiments of this application, an adaptive control method for a battery management system is provided, applied to a cloud-based battery management system (BMS). The method includes: acquiring real-time data of a target vehicle; analyzing the real-time data to determine the real-time operating conditions and a target control strategy for the target vehicle, wherein the target control strategy is a control strategy adaptively matched based on a base strategy in the cloud-based BMS and combined with the real-time operating conditions; and adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in a vehicle set associated with it, the vehicle set including the target vehicle.

[0006] This application also provides an adaptive control method for a battery management system, wherein the vehicle set includes vehicles equipped with a physical BMS and vehicles not equipped with a physical BMS.

[0007] This application also provides an adaptive control method for a battery management system, wherein adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, includes: for vehicles that are not equipped with a physical BMS, controlling the battery system of the vehicle through control software matched with the target cloud platform; wherein the control software is adapted to the target control strategy.

[0008] This application also provides an adaptive control method for a battery management system, wherein the target control strategy is adapted to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, including: for vehicles equipped with a physical BMS, controlling the physical BMS through the target cloud platform, so that the physical BMS controls the vehicle's battery system through a CAN bus.

[0009] This application also provides an adaptive control method for a battery management system. After adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, the method further includes: receiving information fed back by the vehicles to expand the operating condition identification scenario of the cloud-based BMS.

[0010] This application also provides an adaptive control method for a battery management system. After adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, the method further includes: obtaining the vehicle-side health status (SOH) values ​​of all vehicles with the same set driving mileage as the target vehicle; verifying the vehicle-side SOH values ​​with the theoretical SOH values, and issuing a warning to vehicles with vehicle-side SOH values ​​lower than the theoretical SOH values; wherein the theoretical SOH values ​​are determined based on the vehicle-side SOH values ​​uploaded by vehicles with the same set driving mileage as the target vehicle and equipped with a physical BMS.

[0011] This application also provides an adaptive control method for a battery management system. The process of determining the theoretical SOH value includes: receiving the vehicle-side SOH value and related data uploaded by a vehicle equipped with a physical BMS, wherein the related data includes driving mileage data; grouping the vehicles according to a preset mileage interval based on a set mileage threshold to obtain multiple vehicle groups corresponding to multiple mileage intervals; determining the average SOH value of each vehicle group; and using the average SOH value of the vehicle group corresponding to the mileage interval that matches the set driving mileage as the theoretical SOH value.

[0012] This application also provides an adaptive control method for a battery management system. The process of determining the theoretical SOH value further includes: training a cloud-based SOH model using the vehicle-side SOH values ​​and related data of vehicles in multiple vehicle groups corresponding to multiple mileage intervals; and determining the theoretical SOH value of the vehicle when it reaches the set driving mileage based on the cloud-based SOH model.

[0013] This application also provides an adaptive control method for a battery management system, wherein the vehicle-side SOH value includes the vehicle-side SOH value of vehicles not equipped with the physical BMS, and the step of obtaining the vehicle-side SOH values ​​of all vehicles with the same set driving mileage as the target vehicle includes: receiving the vehicle-side SOH value uploaded by the target cloud platform corresponding to the vehicle not equipped with the physical BMS, wherein the vehicle-side SOH value is calculated based on the real-time operating data of the vehicle not equipped with the physical BMS obtained by software mapping from the target cloud platform corresponding to the vehicle not equipped with the physical BMS.

[0014] This application also provides an adaptive control method for a battery management system. After issuing a warning to the vehicle with a vehicle-side SOH value lower than the theoretical SOH value, the method further includes: adapting an SOH compensation strategy from the cloud-based BMS to the target cloud platform to which the vehicle with the warning belongs, and performing SOH compensation on the vehicle with the warning through the target cloud platform.

[0015] This application also provides an adaptive control method for a battery management system, wherein the SOH compensation strategy includes an active balancing strategy.

[0016] This application also provides an adaptive control method for a battery management system. After issuing a warning for the vehicle corresponding to the vehicle-side SOH value that is lower than the theoretical SOH value, the method further includes: obtaining the real-time SOH value of the vehicle corresponding to the vehicle-side SOH value that is lower than the theoretical SOH value; and analyzing the cause of the SOH anomaly based on the real-time SOH value.

[0017] This application also provides an adaptive control method for a battery management system. After issuing a warning for vehicles with a vehicle-side SOH value lower than the theoretical SOH value, the method further includes: acquiring full-lifecycle verification SOH data of vehicles with the same mileage as the vehicles with a vehicle-side SOH value lower than the theoretical SOH value; and analyzing the causes of SOH anomalies based on the real-time SOH data of the vehicles with a vehicle-side SOH value lower than the theoretical SOH value and the verification SOH data.

[0018] This application also provides an adaptive control device for a battery management system, comprising: at least one processor; and at least one memory communicatively connected to the at least one processor, the at least one memory storing computer-executable instructions, the at least one processor being configured to read the computer-executable instructions from the at least one memory and execute the computer-executable instructions to implement the adaptive control method for the battery management system as described above.

[0019] This application also provides a non-transitory computer-readable storage medium storing computer-executable instructions thereon, which, when executed by at least one processor, implement the adaptive control method of the battery management system as described above.

[0020] This application also provides a computer program product, including a computer program that, when executed by at least one processor, implements the adaptive control method of the battery management system as described above.

[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Other aspects will become clear after reading and understanding the accompanying drawings and detailed description. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0023] Figure 1 is a schematic diagram of the framework of an adaptive control method for a battery management system according to an exemplary embodiment of this application.

[0024] Figure 2 is a schematic flowchart illustrating an adaptive control method for a battery management system according to an exemplary embodiment of this application.

[0025] Figure 3 is a schematic diagram of an adaptive control device for a battery management system according to an exemplary embodiment of this application.

[0026] Figure 4 is a schematic block diagram of an adaptive control device for a battery management system according to an exemplary embodiment of this application. Detailed Implementation

[0027] The embodiments (or "implementations") of this application will be clearly and completely described herein with reference to the accompanying drawings. In the following description, when referring to the drawings, unless otherwise indicated, the same reference numerals in different drawings denote the same or similar elements.

[0028] If the embodiments of this application contain terms relating to directional indications or positional relationships (such as up, down, left, right, front, back, inside, outside, top, bottom, center, vertical, horizontal, longitudinal, transverse, length, width, counterclockwise, clockwise, axial, radial, circumferential, etc.), such terms are only used to explain the relative positional relationships and movement of the components in a specific posture (as shown in the attached figures); if the specific posture changes, the directional indications or positional relationships will also change accordingly. Furthermore, the terms "first" and "second" used in the embodiments of this application are only for descriptive convenience and should not be construed as indicating or implying relative importance.

[0029] Currently, most vehicle battery management systems (BMS) rely on fixed strategies and parameters to manage batteries, lacking the ability to adapt to different operating conditions. For example, battery performance varies significantly under different conditions such as high temperature, low temperature, mountainous terrain, and plains, but existing BMSs often cannot adjust their strategies in a timely manner to adapt to these changes. Moreover, vehicles without physical BMSs lack effective battery management methods.

[0030] Therefore, embodiments of this application provide an adaptive control method and device for a battery management system, a storage medium, and a program product. The embodiments of this application will be described in detail below with reference to the accompanying drawings. Unless otherwise specified, the features of the following embodiments and implementations can be combined with each other.

[0031] By collecting vehicle data from vehicles equipped with physical BMS and uploading it to cloud BMS, various operating conditions can be identified through cloud analysis without occupying vehicle-side / onboard BMS resources. Based on existing base strategies, the optimal response strategy / calibration parameters can be adaptively matched and used to control the battery system of each vehicle through the cloud platform.

[0032] In the embodiments of this application, the battery system refers to a system used to manage and control the battery, which includes a battery pack, sensors, data transmission modules, etc. Both vehicles equipped with a physical BMS and vehicles without a physical BMS have a battery system. Vehicles without a physical BMS can collect battery-related parameter data (such as voltage, current, temperature, etc.) through existing vehicle sensors, control systems (such as onboard electronic control units (ECUs), charging systems, etc.), and this data can be uploaded to a cloud platform via the vehicle's communication modules (such as Bluetooth, Wi-Fi, or mobile communication networks). Vehicles equipped with a physical BMS collect battery-related parameter data via a CAN (Controller Area Network) bus and upload it to the cloud platform.

[0033] Figure 1 is a schematic diagram of the framework of an adaptive control method for a battery management system provided in an embodiment of this application.

[0034] First, the cloud-based BMS receives vehicle data collected and uploaded by vehicles equipped with physical BMS systems. This vehicle data is generated during vehicle operation, including battery voltage, temperature, current, vehicle speed, acceleration, road condition information, and more. The physical BMS can accurately collect this data and upload it completely and accurately to the cloud.

[0035] Next, after receiving this wealth of vehicle data, the cloud-based BMS analyzes it, such as identifying various operating conditions. Vehicles encounter various operating conditions during operation, including mountainous terrain, plains, low-temperature environments, high-temperature environments, and normal-temperature environments. The cloud-based BMS can deeply mine and analyze the massive amounts of data generated by these operating conditions, accurately identifying the characteristics and patterns of each condition.

[0036] Then, based on the existing base strategy of the cloud-based BMS and combined with user needs, the optimal response strategy / calibration parameters are adaptively matched. For example, in low-temperature weather, battery performance will be affected, and the cloud-based BMS will adjust parameters such as charging current and voltage based on collected data to optimize battery charging efficiency and lifespan. Under high-speed driving conditions, the cloud-based BMS will adjust the battery discharge strategy to ensure the vehicle's power output and continuous range.

[0037] In each operating condition, only some vehicles are equipped with a physical Battery Management System (BMS), while other vehicles are controlled via a cloud platform. The strategies optimized by the cloud-based BMS are adapted to different cloud platforms (1 / 2 / 3...n) to meet the needs of different operating conditions. The cloud platform sends control commands back to the vehicle wirelessly, and the vehicle receives the commands and controls the battery system. For example, it might adjust the parameters of the vehicle's charging equipment to control the charging current, or adjust the vehicle's power output to limit the discharge power. For vehicles without a physical BMS, commands are translated into control operations on the battery system through software mapping, thus achieving battery system control.

[0038] In this embodiment, vehicle data can be collected and analyzed via a cloud-based BMS. This allows for the identification of various operating conditions without consuming onboard BMS resources, saving on the capacity and load of the onboard BMS. It avoids the problem of excessive computational load that might occur when the onboard BMS handles numerous real-time tasks, thus preventing issues that could affect the operational efficiency and stability of the vehicle's battery system. Furthermore, the method of analyzing and calculating vehicle data via a cloud-based BMS offers scalability and continuous optimization capabilities. For unmet user scenarios and market demands, the cloud platform's compatibility allows for full coverage of all vehicles.

[0039] Figure 2 is a flowchart illustrating an adaptive control method for a battery management system provided in an embodiment of this application. As shown in Figure 2, this method is applied to a cloud-based battery management system (BMS) and includes the following steps S100 to S300.

[0040] In step S100, real-time data of the target vehicle is acquired.

[0041] The real-time data mentioned in this article refers to the data generated during vehicle operation.

[0042] The target vehicle mentioned in this article can be a vehicle equipped with a physical BMS or a vehicle that is not equipped with a physical BMS.

[0043] In step S200, the real-time data is analyzed to determine the real-time operating conditions and target control strategy of the target vehicle. The target control strategy is a control strategy adaptively matched based on the base strategy in the cloud-based BMS and the real-time operating conditions.

[0044] The cloud-based BMS identifies various operating conditions through cloud analytics, including operating scenarios, user needs, and cell configurations. After identifying the operating conditions, the system optimizes and adjusts the corresponding strategies / calibration parameters based on existing base strategies.

[0045] The base strategy described in this article is a fundamental strategy applicable to controlling vehicle battery systems under all operating conditions. It is a preliminary strategy developed through extensive theoretical research, experimental data, and real-vehicle data, conducted in a laboratory environment to deeply study the performance and characteristics of batteries. Furthermore, the base strategy can also be set with reference to industry standards, product technology applications, and vehicle manufacturer design requirements and objectives.

[0046] Based on the base strategy, a target control strategy is adaptively matched by incorporating the identified real-time operating conditions. Regarding calibration parameters, such as adjusting battery internal resistance compensation parameters and capacity estimation parameters according to different operating conditions, battery management becomes more precise and effective.

[0047] For example, the base strategy specifies the battery charging and discharging strategy under normal driving conditions, but when the cloud-based BMS identifies that the vehicle is in a long-term high-speed driving condition, it will adaptively adjust the battery charging and discharging strategy to a more suitable strategy for high-speed driving, such as increasing the charging cut-off voltage to increase the driving range.

[0048] In some embodiments, the following is an example of adaptively matching the optimal response strategy / calibration parameters based on the base strategy.

[0049] For example, in one example, the response strategy / calibration parameters include: calibration tables with different adaptation parameters for different operating conditions such as high temperature, low temperature, normal temperature, plains, and mountainous areas; different operating conditions have a significant impact on the performance and lifespan of vehicle batteries, so different adaptation parameters are formulated for each operating condition and presented in the form of calibration tables to facilitate more accurate battery management by the cloud-based BMS. For example, in high-temperature environments, the battery's heat dissipation requirements increase, and charging and discharging parameters need to be adjusted to prevent overheating; another example is that road conditions are relatively stable in plains areas, while in mountainous areas there are frequent uphill and downhill sections, and these two operating conditions have different requirements for battery functional output and energy recovery.

[0050] For example, in another example, the response strategy / calibration parameters include: cell configuration, and adapting the cell's BOL (Beginning Of Life) and EOL (End Of Life) parameters. BOL and EOL represent different life stages of the cell. Because the performance of a cell differs significantly between its new state and near the end of its lifespan, appropriate adaptation parameters need to be configured for it.

[0051] For example, in another example, the strategy / calibration parameters include shallow charge / discharge (20%-85%), which avoids fully charging or depleting the battery during charging and discharging, instead maintaining it within a partial capacity range (e.g., 20%-85%). This strategy adapts to different battery cells and periodically reminds the user to fully charge. Shallow charge / discharge helps extend battery life, but different types of battery cells perform differently in this mode. By adapting to the characteristics of different battery cells, determining the optimal management strategy within the 20%-85% charging range, while periodically reminding the user to fully charge, helps calibrate the battery's capacity.

[0052] For example, in another example, the response strategy / calibration parameters include a strategy for users who habitually fast charge (those who don't use slow charging even when available, have range anxiety, and only charge when a fast charging station is available). That is, a corresponding strategy is formed based on the identified user's charging habits (habitual fast charging). In this strategy, the charging rate is set in segments: a higher charging rate is used when the battery is low to quickly replenish the battery, and the rate is reduced when the battery is nearly fully charged to protect it.

[0053] For example, in another example, the strategy / calibration parameters include a strategy for low temperatures in northern regions (below 0°C, fast and slow charging, requiring heating), in which the battery needs to be preheated. Preheating the battery before charging can improve charging efficiency and reduce damage to the battery.

[0054] For example, in another example, the strategy / calibration parameters include a strategy for charging under high-temperature conditions and / or after high-speed driving (where current is limited when fast charging is needed at high temperatures). In this strategy, the battery needs to be cooled down in advance. After high-temperature and high-speed driving, the battery temperature is usually high. If fast charging is performed at this time, it will accelerate battery aging and even cause safety problems. By cooling down in advance, such as by activating a cooling system, the battery temperature can be reduced to a safe range before charging, and the charging current can be limited, which can effectively protect the battery.

[0055] In this application embodiment, a target control strategy is matched according to different operating scenarios, user needs and cell configurations to maximize battery performance and extend battery life.

[0056] In step S300, the target control strategy is adapted to the target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, the vehicle set including the target vehicle.

[0057] The cloud-based BMS adapts the target control strategy to the corresponding cloud platform. As shown in Figure 1, the cloud platform has a mapping relationship with real-time operating conditions. After collecting vehicle data uploaded by vehicles equipped with physical BMS, the cloud-based BMS identifies various operating conditions based on this data and adapts these conditions to cloud platforms 1, 2, ..., n. Therefore, after determining the real-time operating conditions based on the vehicle's real-time data, the corresponding target cloud platform is determined based on the real-time operating conditions. All vehicles in the vehicle set under that target cloud platform are then controlled through the target cloud platform. In this embodiment, the vehicle set includes vehicles equipped with physical BMS and vehicles not equipped with physical BMS.

[0058] For vehicles equipped with a physical BMS, the target cloud platform controls the physical BMS, enabling it to control the vehicle's battery system via the CAN bus. Specifically, after receiving control commands from the target cloud platform, the physical BMS communicates with the vehicle's battery system via the CAN bus to perform control operations such as charging and discharging management, status monitoring, and fault diagnosis. For example, based on the vehicle's operating conditions and battery status, the cloud platform sends control commands, such as adjusting the charging current, to the physical BMS. The physical BMS then transmits these commands to the battery system via the CAN bus, ensuring the battery system operates safely and efficiently under various conditions.

[0059] For vehicles without a physical BMS, the vehicle's battery system is controlled via control software matched with the target cloud platform; this control software is adapted to the target control strategy. In this way, when the cloud-based BMS matches the optimal control strategy, it wirelessly transmits the corresponding control software (executable instruction set) to the vehicle, thereby achieving remote control of the vehicle's battery system. This means that even if the vehicle itself does not have physical BMS hardware, it can still receive control commands from the cloud-based BMS or issued through the cloud platform, thus controlling the vehicle's battery system.

[0060] In this embodiment, only some vehicles are equipped with a physical BMS. For other vehicles that are not equipped with a physical BMS, the cloud-based BMS parses the data and allocates the target control strategy to the cloud platform according to the operating conditions to control their battery system, which greatly reduces the cost of the physical BMS.

[0061] It's worth noting that the target control strategy matched by the cloud-based BMS is the optimal control strategy obtained based on real-time operating conditions. When the vehicle changes to a new operating condition, the cloud platform corresponding to the new condition is switched, and the vehicle is controlled based on the corresponding control software. For example, when switching from urban road driving conditions to highway driving conditions, or from a high-temperature environment to a low-temperature environment, the cloud-based BMS will re-identify and match a new target control strategy, and send the corresponding control software to the vehicle through the cloud platform corresponding to that operating condition. The vehicle then switches to the new control mode.

[0062] In this embodiment of the application, this method of dynamically switching between different cloud platform controls can ensure that the vehicle's battery system always operates in an optimized state and adapts to various complex and changing working conditions.

[0063] In some embodiments, after adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, the method further includes: receiving information fed back by the vehicles to expand the operating condition identification scenario of the cloud-based BMS.

[0064] In this embodiment of the application, because different cloud platforms collect feedback from different operating conditions during the control process, the cloud platform will upload this feedback to the cloud BMS, thereby enriching the cloud BMS's collection of different operating conditions and requirements, thus forming a closed loop of control.

[0065] This application provides an adaptive control method and device for a battery management system, as well as a storage medium and program product. Compared to current battery management systems that cannot adjust their strategies in a timely manner to adapt to various operating conditions and lack effective battery management methods for vehicles without a physical BMS, this application acquires real-time data of the target vehicle through a cloud-based battery management system. The real-time data is analyzed to determine the real-time operating conditions and target control strategy of the target vehicle. By collecting and analyzing data through the cloud-based battery management system, the capacity and load of the vehicle-side battery management system are saved. The optimal control strategy is adaptively matched based on the vehicle data to adapt to different operating conditions. Furthermore, the cloud-based battery control system adapts the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, enabling the target cloud platform to control the battery systems of all vehicles in its associated vehicle set, including battery management for vehicles without a physical battery management system, thereby achieving full-scenario coverage for all vehicles.

[0066] Based on the above embodiments, this application further proposes another embodiment of the adaptive control method for a battery management system. This other embodiment is used to predict the battery's State of Health (SOH) under the adaptive control method of the battery management system, so as to improve the accuracy of SOH prediction.

[0067] Specifically, after adapting the target control strategy to the target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, the method further includes steps S400 and S500.

[0068] In step S400, the vehicle-side SOH values ​​of all vehicles with the same set mileage as the target vehicle are obtained.

[0069] Improving the accuracy of battery SOH prediction is particularly important for extending battery life. Therefore, it is necessary to monitor the SOH of vehicle batteries in real time, and the monitoring targets are vehicles equipped with physical BMS and vehicles without physical BMS.

[0070] For vehicles equipped with a physical BMS, the vehicle-side SOH value is uploaded to the cloud-based BMS. The data uploaded to the cloud-based BMS includes the actual battery health status information of the vehicle at different mileages, as well as relevant data such as the vehicle's driving conditions and usage habits.

[0071] In step S500, the vehicle-side SOH value is compared with the theoretical SOH value, and a warning is issued for vehicles with vehicle-side SOH values ​​lower than the theoretical SOH value.

[0072] In this embodiment of the application, the theoretical SOH value is determined based on the vehicle-side SOH value uploaded by a vehicle equipped with a physical BMS under the same set mileage.

[0073] Based on the theoretical SOH at the same mileage, the vehicle-side SOH value is verified with the theoretical SOH to accurately assess the vehicle's battery health. The system can issue an early warning for vehicles with a vehicle-side SOH value lower than the theoretical SOH value, so that the owner or relevant personnel can be informed in advance of potential problems with the vehicle's battery and take timely measures, such as arranging inspections or repairs.

[0074] In some embodiments, the process of determining the theoretical SOH value includes steps S511 to S514.

[0075] In step S511, the vehicle-side SOH value and related data uploaded by the vehicle equipped with a physical BMS are received, including mileage data.

[0076] In step S512, the vehicles are grouped according to a preset mileage interval based on a set mileage threshold, resulting in multiple vehicle groups corresponding to multiple mileage intervals. For example, if the set mileage threshold is from 100,000 km to 800,000 km, the vehicles are grouped at intervals of 100,000 km to obtain multiple mileage intervals, and then the vehicles are grouped according to the mileage intervals to obtain multiple vehicle groups.

[0077] In step S513, the average SOH value of each vehicle group is determined. After receiving this data uploaded by the vehicles in each vehicle group, the cloud-based BMS calculates the average SOH value at a specific mileage (e.g., 300,000 km), and simultaneously obtains the vehicle-side SOH value of vehicles with a lower average SOH value. By comparing and verifying these two values, the health status of the vehicle battery can be more accurately assessed.

[0078] Specifically, the average SOH value at a specific mileage can be calculated using the following formula: SOH avr =f(s,m,SOH) 车端 ), where SOH avr The average SOH value; s is the specific mileage mentioned above, in ten thousand kilometers; m is the total number of vehicles used to calculate the average SOH value; SOH 车端 This represents the SOH value at the vehicle end of a single vehicle.

[0079] In step S514, the average SOH value of the vehicle group corresponding to the mileage interval that matches the set driving mileage is taken as the theoretical SOH value.

[0080] In other embodiments, the vehicle-side SOH value includes the vehicle-side SOH value of a vehicle that is not equipped with the physical BMS.

[0081] For vehicles not equipped with the physical BMS, obtaining the vehicle-side SOH value of all vehicles with the same set mileage as the target vehicle includes: receiving the vehicle-side SOH value uploaded by the cloud platform corresponding to the vehicle not equipped with the physical BMS, wherein the vehicle-side SOH value is calculated based on the real-time operating data of the vehicle obtained by the cloud platform corresponding to the vehicle not equipped with the physical BMS through software mapping.

[0082] In this embodiment, for vehicles without a physical BMS, the cloud platform obtains relevant vehicle data through software mapping, and then estimates the current vehicle-side SOH value based on a specific algorithm or model (such as a cloud-based BMS model). The vehicle-side SOH value is then compared with the theoretical SOH value, and a warning is issued for vehicles with a vehicle-side SOH value lower than the theoretical SOH value.

[0083] In the embodiments of this application, the process of determining the theoretical SOH value further includes steps S521 to S524.

[0084] In step S521, the vehicle-side SOH value and related data of the vehicle without a physical BMS are obtained by software mapping. The related data includes mileage data.

[0085] In step S522, the vehicles are grouped according to a preset mileage threshold and a preset mileage interval to obtain multiple vehicle groups corresponding to multiple mileage intervals.

[0086] In step S523, a cloud-based SOH model is trained using the vehicle-side SOH values ​​and related data from the vehicles in the multiple vehicle groups corresponding to the multiple mileage intervals. The cloud-based BMS trains the cloud-based SOH model corresponding to the same mileage based on the vehicle-side SOH value calculated by the cloud platform, which is used to estimate the theoretical SOH value for that mileage. This cloud-based SOH model comprehensively considers the general patterns of many factors, such as the impact of different mileages, different operating conditions, and different usage habits on battery health, aiming to provide a reference value for the SOH level that a vehicle should have at a specific mileage under ideal or average conditions, i.e., the theoretical SOH value.

[0087] In step S524, the theoretical SOH value when the vehicle reaches the set driving mileage is determined according to the cloud SOH model, and the cloud BMS will dynamically estimate the theoretical SOH value of the vehicle at the corresponding mileage.

[0088] For vehicles without a physical BMS, the vehicle-side SOH value calculated by the cloud platform is verified against the theoretical SOH value. For vehicles with a vehicle-side SOH value lower than the theoretical SOH value, it indicates that the vehicle's battery health status is not as expected and there may be some problems affecting battery performance. Therefore, timely warnings can be issued or reminders can be sent to users, suggesting adjustments to driving habits to extend battery life.

[0089] In other embodiments, for vehicles with SOH values ​​lower than the average SOH value, a real-time longitudinal comparison of SOH values ​​is performed (i.e., comparing the vehicle's own SOH value over time, etc.), and an alarm is triggered when the change in SOH value exceeds a preset threshold deviation, in order to investigate the cause of the difference in the vehicle's SOH value. For example, the vehicle's SOH value decays over time, and an alarm is triggered for the corresponding vehicle when the decay change of the SOH value exceeds a preset threshold.

[0090] Specifically, after issuing a warning to vehicles with vehicle-side SOH values ​​lower than the theoretical SOH value, the method further includes: obtaining the real-time SOH value of the vehicle with vehicle-side SOH values ​​lower than the theoretical SOH value.

[0091] Specifically, the real-time SOH value can be calculated using the following formula: SOH act =∫(I i *Δt) / ΔSOC / 125Ah / 3600; where I i Δt is the charging current value at time i; Δt is the time change value; 125Ah is the rated capacitance of the battery; 3600 is the unit conversion between seconds (s) and hours (h); ΔSOC is the SOC (State of Charge) change value of a single charging behavior.

[0092] Based on real-time data, such as the real-time SOH value, the causes of SOH anomalies are analyzed. Specifically, for vehicles with SOH values ​​lower than the average SOH value, a longitudinal comparison of real-time SOH values ​​is performed to analyze the battery health status of the vehicle at different time points as usage time and mileage increase. By monitoring the long-term performance changes of the vehicle's battery, the impact of key events at different usage stages on battery health status is analyzed, and the causes of SOH anomalies are comprehensively analyzed.

[0093] In some embodiments, a predictive model is established by longitudinally analyzing the battery data of a vehicle in the past to estimate the battery health status of the vehicle at a future time point. If the deviation between the real-time SOH value at the current time point and the estimated SOH value at the future time point is large, the SOH at the current time point is analyzed to determine the cause of the SOH abnormality.

[0094] In other embodiments, the verified State of Health (SOH) data for the entire lifecycle of vehicles with the same mileage as the vehicle that has received a warning is acquired. Based on the real-time SOH data of the vehicle that received the warning and the verified SOH data, the cause of the SOH anomaly is analyzed. Specifically, the cloud-based BMS collects vehicle data uploaded by each vehicle, recording the vehicle's mileage, SOH value, and related usage data at different points in time. As time progresses and mileage increases, the trend of the vehicle's SOH value is analyzed, and the vehicle's SOH value is compared with the SOH values ​​of other vehicles with similar usage histories to determine the cause of the vehicle's SOH anomaly.

[0095] In this embodiment, by comparing the cloud-based SOH values ​​of vehicles with similar mileage ranges, a real-time longitudinal comparison of the SOH values ​​of vehicles with vehicle-side SOH values ​​lower than the average SOH value is performed. An alarm is triggered when the change in SOH value exceeds a preset threshold deviation, so as to investigate the reasons for the difference in vehicle SOH values ​​and introduce corresponding SOH compensation strategies. This method is targeted and predictive, and can improve the service life of battery products.

[0096] After issuing a warning to vehicles with a vehicle-side SOH value lower than the theoretical SOH value, the method further includes: adapting the SOH compensation strategy from the cloud-based BMS to the cloud platform to which the vehicle that has been warned belongs, and performing SOH compensation on the vehicle that has been warned through the cloud platform.

[0097] The cloud platform imports SOH compensation strategies from the cloud-based BMS. These compensation strategies include adjusting vehicle charging parameters, such as reducing charging current to avoid overcharging and optimizing energy recovery strategies to reduce battery wear.

[0098] For example, after a vehicle without a physical BMS has traveled a certain mileage, the cloud platform calculates an actual vehicle-side SOH (State of Health) value of 70%, while the theoretical SOH value for that mileage, calculated according to the cloud-based SOH model, is 75%. In this case, the cloud-based BMS will adapt the SOH compensation strategy to the cloud platform of the vehicle that issued the warning, and the cloud platform will compensate for the vehicle's SOH. For instance, it might adjust the vehicle's charging mode to make the charging process gentler, slowing down battery degradation and improving the vehicle's battery health.

[0099] In some embodiments, the SOH compensation strategy includes an active balancing strategy. Active balancing is an important method for improving battery pack performance and extending battery life, typically employing energy transfer methods to achieve balance between individual cells within the battery pack. Specifically, energy is transferred from high-capacity cells to low-capacity cells to achieve balance.

[0100] This SOH compensation strategy can improve the performance and lifespan of the battery pack.

[0101] Based on the same application concept as the above method, this application embodiment also provides a battery management system adaptive control device.

[0102] As shown in Figure 3, the device includes: a data acquisition module 602 configured to acquire real-time data of the target vehicle; a data analysis module 604 configured to analyze the real-time data to determine the real-time operating conditions and target control strategy of the target vehicle, wherein the target control strategy is a control strategy adaptively matched based on the base strategy in the cloud-based BMS and combined with the real-time operating conditions; and a vehicle control module 606 configured to adapt the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in its associated vehicle set, the vehicle set including the target vehicle.

[0103] The implementation process of the functions and roles of each module / submodule / unit in the above device is detailed in the implementation process of the corresponding steps in the above method. The above device can achieve the same technical effect as the above method, and will not be repeated here.

[0104] Figure 4 illustrates a schematic diagram of the physical structure of an adaptive control device for a battery management system. As shown in Figure 4, the adaptive control device for the battery management system may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. The processor 810, communication interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute the aforementioned adaptive control method for the battery management system.

[0105] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by at least one processor, it can execute the adaptive control method of the battery management system provided in the above embodiments.

[0107] In another aspect, embodiments of this application also provide a non-transitory computer-readable storage medium storing computer-executable instructions thereon, which, when executed by at least one processor, can execute the adaptive control method of the battery management system provided in the above embodiments.

[0108] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware (e.g., a processor), and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiments can be implemented in hardware, such as by using an integrated circuit to implement its corresponding function, or it can be implemented in the form of a software functional module, such as by a processor executing a program / instruction stored in memory to implement its corresponding function. This application is not limited to any particular combination of hardware and software.

[0109] It should be noted that the technical solutions or features described in the above embodiments can be combined or complemented by each other without conflict. The scope of protection of this application is not limited to the precise structures described in the above embodiments and shown in the accompanying drawings. All modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An adaptive control method for a battery management system, applied to a cloud-based battery management system (BMS), the method comprising: Obtain real-time data of the target vehicle; The real-time data is analyzed to determine the real-time operating conditions and target control strategy of the target vehicle. The target control strategy is an adaptively matched control strategy based on the base strategy in the cloud-based BMS and combined with the real-time operating conditions. The target control strategy is adapted to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in the vehicle set associated with it, the vehicle set including the target vehicle.

2. The adaptive control method for a battery management system as described in claim 1, wherein, The vehicle set includes vehicles equipped with a physical BMS and vehicles not equipped with a physical BMS.

3. The adaptive control method for a battery management system as described in claim 2, wherein, The step of adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in its associated vehicle set, includes: For vehicles that are not equipped with a physical BMS, the vehicle's battery system is controlled by control software that matches the target cloud platform; The control software is adapted to the target control strategy.

4. The adaptive control method for a battery management system as described in claim 2, wherein, The step of adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in its associated vehicle set, includes: For the vehicle equipped with a physical BMS, the physical BMS is controlled through the target cloud platform so that the physical BMS controls the vehicle's battery system via the CAN bus.

5. The adaptive control method for a battery management system as described in any one of claims 1 to 4, wherein, After adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in its associated vehicle set, the method further includes: The system receives information from the vehicle to expand the operational condition recognition scenarios of the cloud-based BMS.

6. The adaptive control method for a battery management system as described in any one of claims 1 to 5, wherein, After adapting the target control strategy to a target cloud platform that has a mapping relationship with the real-time operating conditions, so that the target cloud platform controls the battery systems of all vehicles in its associated vehicle set, the method further includes: Obtain the vehicle health status (SOH) values ​​of all vehicles with the same set mileage as the target vehicle; The vehicle-side SOH value is verified against the theoretical SOH value, and a warning is issued for vehicles whose vehicle-side SOH value is lower than the theoretical SOH value. The theoretical SOH value is determined based on the vehicle-side SOH value uploaded by a vehicle with the same set mileage as the target vehicle and equipped with a physical BMS.

7. The adaptive control method for a battery management system as described in claim 6, wherein, The process of determining the theoretical SOH value includes: Receive vehicle-side SOH values ​​and related data uploaded by vehicles equipped with physical BMS, including mileage data; Based on the set mileage threshold, the vehicles are grouped at preset mileage intervals to obtain multiple vehicle groups corresponding to multiple mileage intervals. Determine the average SOH value for each of the vehicle groups; The average SOH value of the vehicle group corresponding to the mileage interval that matches the set driving mileage is used as the theoretical SOH value.

8. The adaptive control method for a battery management system as described in claim 7, wherein, The process of determining the theoretical SOH value also includes: A cloud-based SOH model is trained using the vehicle-side SOH values ​​and related data of vehicles in multiple vehicle groups corresponding to multiple mileage intervals. The theoretical SOH value when the vehicle reaches the set driving mileage is determined based on the cloud-based SOH model.

9. The adaptive control method for a battery management system as described in any one of claims 6 to 8, wherein, The vehicle-side SOH value includes the vehicle-side SOH value of vehicles that are not equipped with the physical BMS. The step of obtaining the vehicle-side SOH values ​​of all vehicles with the same set mileage as the target vehicle includes: The system receives the vehicle-side SOH value uploaded by the target cloud platform corresponding to the vehicle that is not equipped with the physical BMS. The vehicle-side SOH value is calculated based on the real-time operating data of the vehicle that is not equipped with the physical BMS, obtained through software mapping on the target cloud platform corresponding to the vehicle.

10. The adaptive control method for a battery management system as described in any one of claims 6 to 9, wherein, After issuing a warning for vehicles with a vehicle-end SOH value lower than the theoretical SOH value, the method further includes: The SOH compensation strategy is adapted from the cloud-based BMS to the target cloud platform to which the vehicle that has been warned belongs, and the SOH compensation is performed on the vehicle that has been warned through the target cloud platform.

11. The adaptive control method for a battery management system as described in claim 10, wherein, The SOH compensation strategy includes an active balancing strategy.

12. The adaptive control method for a battery management system as described in any one of claims 6 to 11, wherein, After issuing a warning for vehicles with a vehicle-end SOH value lower than the theoretical SOH value, the method further includes: Obtain the real-time SOH value of the vehicle corresponding to the vehicle-side SOH value that is lower than the theoretical SOH value; Based on the real-time SOH value, the causes of SOH abnormalities were analyzed.

13. The adaptive control method for a battery management system as described in any one of claims 6 to 12, wherein, After issuing a warning for vehicles with a vehicle-end SOH value lower than the theoretical SOH value, the method further includes: Obtain the full lifecycle verification SOH data of vehicles with the same mileage as the vehicle-end SOH value corresponding to the vehicle-end SOH value that is lower than the theoretical SOH value; Based on the real-time SOH data of the vehicle corresponding to the vehicle-side SOH value that is lower than the theoretical SOH value and the verification SOH data, the cause of the SOH anomaly is analyzed.

14. An adaptive control device for a battery management system, comprising: At least one processor; as well as At least one memory, communicatively connected to the at least one processor, the at least one memory storing computer-executable instructions, the at least one processor being configured to read the computer-executable instructions from the at least one memory and execute the computer-executable instructions to implement the battery management system adaptive control method as described in any one of claims 1-13.

15. A non-transitory computer-readable storage medium, wherein, The non-transitory computer-readable storage medium stores computer-executable instructions, which, when executed by at least one processor, implement the adaptive control method of the battery management system as described in any one of claims 1-13.

16. A computer program product comprising a computer program that, when executed by at least one processor, implements the adaptive control method of a battery management system as described in any one of claims 1 to 13.

Images