Charging control method, electronic equipment and storage medium

Abstract

The invention discloses a charging control method, electronic equipment and a storage medium, and the method comprises the steps: obtaining battery state information and a historical charging strategy corresponding to a battery in the equipment, and determining a plurality of initial charging strategies based on the historical charging strategy; performing battery performance parameter prediction on the plurality of initial charging strategies based on the battery state information to obtain predicted battery performance parameters corresponding to the plurality of initial charging strategies; predicting battery performance parameters and battery state information based on the plurality of initial charging strategies, and determining a plurality of candidate charging strategies output by the multi-target optimization model; and sending the plurality of candidate charging strategies to the equipment, so that the equipment charges the battery according to one target charging strategy in the plurality of candidate charging strategies.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery charging, in particular to a charging control method, an electronic device and a storage medium. BACKGROUND

[0002] As the core component of charging equipment such as electric vehicles, robots and other equipment, lithium ion batteries have the problem of long charging time due to the limitation of their own electrochemical properties. Overcurrent charging control can shorten the service life of the battery and even cause fire and explosion accidents. Therefore, a reasonable charging strategy needs to be set to achieve effective charging control of lithium batteries.

[0003] At present, traditional charging strategies mainly include constant current charging, constant voltage charging, pulse charging and the like. The traditional charging strategy is simple and easy to implement and is most widely used. However, due to the unstable charging time, in the constant current stage, a high current level can cause the battery temperature to rise, and in the constant voltage stage, part of the energy is wasted in maintaining the constant voltage state, resulting in energy waste, and there are problems of low charging control efficiency and low charging flexibility of the battery. SUMMARY

[0004] The present application provides a charging control method, which aims to improve the charging control efficiency and charging flexibility of the battery.

[0005] In a first aspect, a charging control method is provided, comprising the following steps: Obtaining battery state information and historical charging strategies corresponding to the battery in the equipment, and determining a plurality of initial charging strategies based on the historical charging strategies; Based on the battery state information, performing battery performance parameter prediction on the plurality of initial charging strategies to obtain predicted battery performance parameters corresponding to the plurality of initial charging strategies respectively; Based on the plurality of initial charging strategies, the predicted battery performance parameters and the battery state information, determining a plurality of candidate charging strategies output by a multi-objective optimization model; Sending the plurality of candidate charging strategies to the equipment, so that the equipment charges the battery according to a target charging strategy in the plurality of candidate charging strategies.

[0006] In one embodiment, based on the historical charging strategies, the plurality of initial charging strategies are determined, comprising: Based on the current location corresponding to the equipment, the historical charging strategies are screened to obtain target historical charging strategies; Based on the target historical charging strategies, the plurality of initial charging strategies are determined.

[0007] In the embodiment, the target historical charging strategy is screened according to the current position of the device, so that the target historical charging strategy can meet the current charging demand of the device, the effectiveness of the target historical charging strategy is ensured, and the accuracy of the initial charging strategy is improved.

[0008] In one embodiment, based on the battery state information, the battery performance parameters of the plurality of initial charging strategies are predicted to obtain the predicted battery performance parameters corresponding to the plurality of initial charging strategies, including: The battery state information and the plurality of initial charging strategies are input into the electro-thermal-aging coupling model. The battery performance parameters of the plurality of initial charging strategies are predicted based on the battery state information under the safety constraint boundary by the electro-thermal-aging coupling model, to obtain the predicted battery performance parameters corresponding to the plurality of initial charging strategies.

[0009] In the embodiment, the predicted battery performance parameters of the plurality of initial charging strategies are predicted by the electro-thermal-aging coupling model, so that the accuracy of the predicted battery performance parameters can be ensured.

[0010] In one embodiment, the charging control method further includes: The predicted battery performance parameters corresponding to the historical charging strategy and the actual battery performance parameters of the battery charged according to the historical charging strategy in the historical time period are obtained. When the difference between the predicted battery performance parameters corresponding to the historical charging strategy and the actual battery performance parameters is greater than a preset difference threshold, the electro-thermal-aging coupling model is updated to obtain an updated electro-thermal-aging coupling model. The battery state information and the plurality of initial charging strategies are input into the electro-thermal-aging coupling model, including: The battery state information and the plurality of initial charging strategies are input into the updated electro-thermal-aging coupling model.

[0011] In the embodiment, when the difference between the predicted battery performance parameters corresponding to the historical charging strategy and the actual battery performance parameters is greater than a preset difference threshold, the electro-thermal-aging coupling model is updated, and the predicted battery performance parameters of the initial charging strategy are predicted using the updated electro-thermal-aging coupling model, so that the accuracy of the predicted battery performance parameters can be ensured.

[0012] In one embodiment, the battery state information includes a battery health state, and the charging control method further includes: When the battery health state is less than a preset health state threshold, the safety constraint boundary is updated to obtain an updated safety constraint boundary. The battery performance parameters are predicted for the multiple initial charging strategies based on the battery state information under the safety constraint boundary through the electro-thermal-aging coupling model, including: The battery performance parameters are predicted for the multiple initial charging strategies based on the battery state information under the updated safety constraint boundary through the electro-thermal-aging coupling model.

[0013] In this embodiment, the parameters of the electro-thermal-aging coupling model are calibrated by analyzing the deviation, and the output of the electro-thermal-aging coupling model is ensured to conform to the actual aging trajectory of the battery. Meanwhile, the safety constraint boundary of the electro-thermal-aging coupling model is dynamically adjusted according to the current state of health SOH of the battery, so that the new safety constraint boundary can adapt to the attenuation change of the battery performance, thereby ensuring the accuracy of the predicted battery performance parameters output by the electro-thermal-aging coupling model.

[0014] In one embodiment, based on the multiple initial charging strategies, the predicted battery performance parameters and the battery state information, multiple candidate charging strategies output by a multi-objective optimization model are determined, including: Based on the predicted battery performance parameters, multiple charging targets for charging control of the battery are determined, and the multiple charging targets include at least two of a target charging time, a target battery temperature and a target capacity attenuation; The multiple initial charging strategies, the predicted battery performance parameters, the multiple charging targets and the battery state information are input into the multi-objective optimization model for strategy optimization, and multiple candidate charging strategies are output.

[0015] In this embodiment, when the multi-objective optimization problem model is constructed and the NSGA-II algorithm is run, the real-time SOH is taken as the model input and the optimization constraint condition, so that the non-dominated optimal solution set (Pareto front) that best balances the charging time, the maximum temperature and the capacity attenuation is dynamically generated for the battery with different health degrees, that is, the candidate charging strategies, the adaptability of the charging strategy to the battery aging is realized, the overcharging risk and the life acceleration caused by ignoring the battery attenuation are effectively avoided, and the safety of the charging process and the long-term effectiveness of the strategy are significantly improved.

[0016] In one embodiment, the charging control method further includes: obtaining a custom weight corresponding to a specified charging target in the multiple charging targets sent by the device; performing first weight updating on the multiple charging targets based on the custom weight corresponding to the specified charging target, to obtain a custom charging target; inputting the multiple initial charging strategies, the predicted battery performance parameters, the custom charging target and the battery state information into the multi-objective optimization model for strategy optimization, and outputting multiple custom charging strategies; The plurality of customized charging strategies are sent to the device to enable the device to charge the battery according to a target charging strategy in the plurality of customized charging strategies.

[0017] In this embodiment, by receiving the customized weight corresponding to the charging target and updating the customized charging target, the multi-objective optimization model outputs the customized charging strategy based on the customized charging target, which realizes the user's self-defined optimization target and meets the diversified demand of the battery charging strategy.

[0018] In one embodiment, the customized weight corresponding to the charging target is a customized weight corresponding to a target charging time; and the charging control method further includes: The capacity attenuation corresponding to each of the plurality of customized charging strategies is obtained. When there is a capacity attenuation greater than a preset capacity attenuation threshold, the second weight update is performed on the customized charging target to obtain an updated customized charging target. The plurality of initial charging strategies, the predicted battery performance parameters, the updated customized charging target and the battery state information are input into the multi-objective optimization model for strategy optimization, and a plurality of optimized customized charging strategies are output. The plurality of optimized customized charging strategies are sent to the device to enable the device to charge the battery according to a target charging strategy in the plurality of optimized customized charging strategies.

[0019] In this embodiment, when the customized charging strategy has a greater impact on the battery life, the customized charging target is automatically adjusted, and the optimized customized charging strategy is determined according to the updated customized charging target, which can prevent damage to the battery and realize personalized charging under the premise of safety.

[0020] In a second aspect, the application also provides a charging control device, which includes: The data processing module is configured to obtain the battery state information and the historical charging strategy corresponding to the battery in the device, and determine a plurality of initial charging strategies based on the historical charging strategy. The performance prediction module is configured to perform battery performance parameter prediction on the plurality of initial charging strategies based on the battery state information, and obtain predicted battery performance parameters corresponding to each of the plurality of initial charging strategies. The multi-objective optimization module is configured to determine a plurality of candidate charging strategies output by a multi-objective optimization model based on the plurality of initial charging strategies, the predicted battery performance parameters and the battery state information. The strategy output module is configured to send the plurality of candidate charging strategies to the device to enable the device to charge the battery according to a target charging strategy in the plurality of candidate charging strategies.

[0021] In a third aspect, the present application also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is configured to control the processor to perform the method in any of the above-mentioned aspects or embodiments.

[0022] In a fourth aspect, the present application also provides a computer-readable storage medium, comprising computer instructions, and the computer instructions are configured to perform the method in any of the above-mentioned aspects or embodiments when executed by a processor.

[0023] In a fifth aspect, the present application provides a computer program product, and the computer program product is configured to perform the method in any of the above-mentioned aspects or embodiments when executed by a processor.

[0024] Advantages: by obtaining the battery state information and the historical charging strategy of the battery in the device, and determining a plurality of initial charging strategies according to the historical charging strategy, the charging strategy with the reference property meeting the charging demand of the device can be provided based on the historical charging strategy, and the effectiveness of the initial charging strategy is ensured; then the predicted battery performance parameters corresponding to the initial charging strategy are predicted according to the battery state information, and a plurality of candidate charging strategies output by the multi-objective optimization model are determined according to the initial charging strategy, the predicted battery performance parameters and the battery state information, so as to realize effective optimization of the initial charging strategy, obtain the candidate charging strategy meeting the multi-objective optimization, and further improve the charging control effectiveness and accuracy of the candidate charging strategy. Furthermore, the plurality of candidate charging strategies are sent to the device, so that the device charges the battery according to a target charging strategy in the plurality of candidate charging strategies, thereby ensuring the charging control effectiveness and accuracy of the battery according to the target charging strategy, and realizing the charging flexibility of the device. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 is a flowchart of the charging control method provided by the exemplary embodiment of the present disclosure; Figure 2 is a schematic diagram of the electro-thermal-aging coupling model provided by the exemplary embodiment of the present disclosure; Figure 3 is a logic architecture diagram for optimizing the charging current based on the NSGA-II algorithm provided by the exemplary embodiment of the present disclosure; Figure 4is a schematic diagram of a charging strategy system based on multi-objective optimization provided by an example embodiment of the present disclosure; Figure 5 is an application flow schematic diagram of a charging strategy system provided by an example embodiment of the present disclosure; Figure 6 is a structural schematic diagram of a charging control device provided by an example embodiment of the present disclosure; Figure 7 is an internal schematic diagram of an electronic device provided by an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0028] In the description of the present application, it should be understood that the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited. The word "exemplary" is used to mean "serving as an example, instance, or illustration." Any embodiment described as "exemplary" in the present application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can realize the present application without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the present application with unnecessary detail. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope consistent with the principles and features disclosed herein.

[0029] This application provides a charging control method, an electronic device, and a storage medium. The electronic device can be a server or a terminal, and the terminal may include, but is not limited to, computers and laptops. In one embodiment, the server obtains battery state information and historical charging strategies corresponding to the battery in the device, and determines multiple initial charging strategies based on the historical charging strategies. Based on the battery state information, the server predicts battery performance parameters for the multiple initial charging strategies, obtaining predicted battery performance parameters corresponding to each initial charging strategy. Based on the multiple initial charging strategies, predicted battery performance parameters, and battery state information, the server determines multiple candidate charging strategies output by a multi-objective optimization model. The server sends the multiple candidate charging strategies to the device, so that the device charges the battery according to one of the target charging strategies from the multiple candidate charging strategies. The device may include, but is not limited to, electric vehicles, robots, and other devices with batteries and charging systems. The server may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, big data, and artificial intelligence platforms. The server and device can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0030] On the one hand, this embodiment provides a charging control method, such as Figure 1 As shown, it includes the following steps: S101, obtain the battery status information and historical charging strategies corresponding to the battery in the device, and determine multiple initial charging strategies based on the historical charging strategies.

[0031] Battery status information refers to the real-time status information collected from the battery in the device, such as battery voltage, internal resistance, state of charge, and health status. Historical charging strategy refers to the charging strategy implemented by the device on the battery over a historical period. A charging strategy represents the charging control sequence for charging the battery; specifically, it can be the battery's charging current curve or a charging current sequence, used to specify that the device charges the battery according to the corresponding charging current at each time point in the charging strategy. The initial charging strategy is the charging strategy to be optimized based on the historical charging strategies.

[0032] For example, when a charging command is triggered, the device sends a charging strategy retrieval request to the server. The request carries the real-time battery status information of the battery in the device, as well as the historical charging strategies of the battery within a preset historical time period. This device can be an electric vehicle, a robot, an aircraft, or similar equipment.

[0033] The server receives a charging strategy retrieval request and generates multiple initial charging strategies based on the historical charging strategies carried. Specifically, it may extract the charging features and charging constraint features corresponding to the historical charging strategies. The charging features may include charging power, charging time, and SOC (State of Charge) range. Among these, the charging time of the historical charging strategy can be used as the maximum charging time in the charging constraint features, and / or the SOC range of the historical charging strategy can be used as the SOC range in the charging constraint features. These constraints are used to ensure that the charging features of the generated initial charging strategies meet the charging constraint features of the historical charging strategies, such as the charging time of the initial charging strategy being less than or equal to the charging time of the historical charging strategies.

[0034] Then, based on the charging characteristics of historical charging strategies, multiple initial charging strategies that conform to the charging constraint characteristics are generated. For example, the charging characteristics and charging constraint characteristics are input into a pre-trained learning model, and the learning model outputs multiple initial charging strategies that conform to the charging constraint characteristics.

[0035] S102, based on battery state information, predict battery performance parameters for multiple initial charging strategies to obtain predicted battery performance parameters corresponding to each initial charging strategy.

[0036] Among them, the predicted battery performance parameters refer to the battery performance parameters predicted by the initial charging strategy. They can be understood as the predicted performance parameters of the battery during the charging process according to the initial charging strategy, such as battery temperature and capacity decay.

[0037] For example, after obtaining multiple initial charging strategies, the server calls the corresponding battery performance prediction model. The multiple initial charging strategies and battery state parameters are input into the battery performance prediction model. The model then predicts the performance parameters of the multiple initial charging strategies based on the battery state parameters, obtaining the predicted battery performance parameters corresponding to each initial charging strategy. Specifically, the battery performance prediction model can be an electro-thermal-aging coupled model.

[0038] S103 determines multiple candidate charging strategies output by the multi-objective optimization model based on multiple initial charging strategies, predicted battery performance parameters, and battery state information.

[0039] The multi-objective optimization model refers to a mathematical model that simultaneously handles multiple conflicting optimization objectives and outputs a series of optimal compromise solutions (i.e., a Pareto optimal solution set). This model is used to output a candidate charging strategy that achieves a balance among multiple charging objectives in this embodiment. The multiple charging objectives include at least two of the following: target charging time, target battery temperature, and target capacity decay.

[0040] For example, the server determines multiple charging targets for charging control of the battery based on predicted battery performance parameters. For instance, based on the predicted battery performance parameters including charging time, battery temperature, and capacity decay, the multiple charging targets include at least two of the following: minimum charging time (target charging time), maximum battery temperature (target battery temperature), and maximum capacity decay (target capacity decay).

[0041] Then, multiple initial charging strategies, predicted battery performance parameters, multiple charging targets, and battery state information are input into a multi-objective optimization model for strategy optimization, and multiple candidate charging strategies are output.

[0042] S104, send multiple candidate charging strategies to the device so that the device charges the battery according to a target charging strategy among the multiple candidate charging strategies.

[0043] The target charging strategy refers to the charging strategy used to actually charge the device among multiple candidate charging strategies.

[0044] For example, after receiving multiple candidate charging strategies, the server sends these strategies to the device. The device then determines the target charging strategy from among the candidate strategies based on the current charging requirements. For instance, it matches the battery performance parameters corresponding to each candidate strategy based on current charging performance demand data. The successfully matched candidate strategy is then adopted as the target charging strategy, and the battery is charged according to the target strategy. The battery performance parameters corresponding to each candidate charging strategy can be the battery performance parameters of the candidate charging strategies output along with the multiple candidate charging strategies by a multi-objective optimization model.

[0045] In an exemplary embodiment, when the device is an electric vehicle, the server sends multiple candidate charging strategies to the corresponding vehicle terminal. The vehicle terminal then generates a displayable charging mode list based on these candidate strategies. The charging mode list includes charging modes such as "fast charging," "battery life protection charging," and "equalization charging." Specifically, the vehicle terminal obtains the charging performance indicators corresponding to each of the multiple preset charging modes. For example, the charging performance indicator for the "fast charging" mode is the shortest charging time. Based on these performance indicators, the server matches the battery performance parameters of the multiple candidate charging strategies. The successfully matched candidate charging strategies are then identified as the charging strategies corresponding to the respective preset charging modes. Finally, a charging mode list is generated based on these preset charging modes.

[0046] Then, the vehicle terminal displays the charging mode list on the interactive interface, including multiple preset charging modes. The vehicle terminal responds to the target charging mode selected by the user among the multiple preset charging modes through the interactive interface, obtains the target charging strategy corresponding to the target charging mode, and charges the battery according to the target charging strategy.

[0047] In this embodiment, by acquiring the battery state information and historical charging strategies of the battery in the device, and determining multiple initial charging strategies based on the historical charging strategies, a reference charging strategy that meets the charging needs of the device can be provided based on the historical charging strategies, ensuring the effectiveness of the initial charging strategies. Then, the predicted battery performance parameters corresponding to the initial charging strategies are predicted based on the battery state information. Based on the initial charging strategies, the predicted battery performance parameters, and the battery state information, multiple candidate charging strategies output by the multi-objective optimization model are determined, enabling effective optimization of the initial charging strategies and obtaining candidate charging strategies that satisfy multi-objective optimization, further improving the charging control effectiveness and accuracy of the candidate charging strategies. Furthermore, the multiple candidate charging strategies are sent to the device so that the device charges the battery according to one of the target charging strategies. This ensures the effectiveness and accuracy of charging control according to the target charging strategy while also achieving charging flexibility for the device.

[0048] In one embodiment, multiple initial charging strategies are determined based on historical charging strategies, including: Based on the current location of the device, historical charging strategies are filtered to obtain the target historical charging strategy; Based on the target historical charging strategy, multiple initial charging strategies are determined.

[0049] The current location refers to the geographical location of the device at the current moment.

[0050] For example, the charging strategy acquisition request also carries the device's current location. The server determines the current charging scenario and the corresponding current charging type based on the current location, and obtains the charging type corresponding to historical charging strategies. The charging type corresponding to historical charging strategies can be obtained by pre-marking historical charging strategies. Then, based on the current charging type, the server filters for target historical charging strategies that match the charging type. For instance, when the device is an electric vehicle, if the electric vehicle's current location is a service area, the current charging scenario is determined to be a service area fast charging scenario, and the corresponding current charging type is fast charging. Then, the server filters for target historical charging strategies that are also fast charging. Finally, based on the target historical charging strategy, multiple initial charging strategies under the fast charging type are determined.

[0051] In this embodiment, by filtering the target historical charging strategy according to the current location of the device, the target historical charging strategy can meet the current charging needs of the device, ensuring the effectiveness of the target historical charging strategy and thus improving the accuracy of the initial charging strategy.

[0052] In an exemplary embodiment, the charging type of the device can also be determined based on the device's current location and current time. For example, when the device is an electric vehicle, and the electric vehicle's current location is a charging station, and the current time is 21:00, and the distance between the location of the charging station and the owner's residence is detected to be less than a preset distance threshold, the current charging scenario of the electric vehicle is determined to be a nighttime charging scenario, and the current charging type corresponding to the nighttime charging scenario is a balanced charging type. The balanced charging type indicates a charging type that aims to protect battery life, that is, to minimize the capacity decay of the battery during charging.

[0053] In an exemplary embodiment, the server determines the current charging type of the current charging scenario based on the device's current location and current time, obtains the charging performance parameter threshold corresponding to the current charging type, and determines the charging performance parameter range corresponding to the current charging type based on a preset threshold range. The charging performance parameter range may include charging performance parameter thresholds corresponding to other charging types. For example, if the current charging type is fast charging, the server obtains the charging performance parameter threshold corresponding to fast charging, and also obtains the charging performance parameter thresholds corresponding to other charging types such as balanced charging. The difference between the charging performance parameter thresholds corresponding to balanced charging and fast charging is used as the preset threshold range, and the charging performance parameter range corresponding to fast charging is determined based on this preset threshold range.

[0054] Then, obtain the charging performance parameters corresponding to the historical charging strategies. Based on the charging performance parameter range and the charging performance parameters corresponding to the historical charging strategies, determine the target historical charging strategy. Specifically, the target historical charging strategy can be the historical charging strategy whose charging performance parameters are within the charging performance parameter range.

[0055] In this embodiment, historical charging strategies are filtered by setting a range of charging performance parameters. This ensures the relevance of the target historical charging strategy to the current charging scenario while also increasing the diversity of the target historical strategy set. This improves the coverage of the initial charging strategy for different charging scenarios and enhances the generalization performance of the candidate charging strategies output by the multi-objective optimization model.

[0056] In one embodiment, based on battery state information, battery performance parameters are predicted for multiple initial charging strategies to obtain predicted battery performance parameters corresponding to each initial charging strategy, including: Battery state information and multiple initial charging strategies are input into the electro-thermal-aging coupled model; By using an electro-thermal-aging coupled model under safety constraints, battery performance parameters are predicted for multiple initial charging strategies based on battery state information, resulting in predicted battery performance parameters for each initial charging strategy.

[0057] For example, the server pre-sets an electro-thermal-aging coupling model for predicting battery performance parameters. After obtaining multiple initial charging strategies, the server inputs the battery state information and the multiple initial charging strategies into the electro-thermal-aging coupling model. Under safety constraints, the electro-thermal-aging coupling model predicts the battery performance parameters of the multiple initial charging strategies based on the battery state information, thereby obtaining the predicted battery performance parameters corresponding to the multiple initial charging strategies.

[0058] Specifically, such as Figure 2 The diagram shows a schematic of the electro-thermal-aging coupling model. This model is constructed by coupling an electrical model, a thermal model, and an aging model. The electrical model is a second-order RC equivalent circuit model. This is the battery open-circuit voltage. This refers to the battery terminal voltage. It is the ohmic internal resistance of the battery, corresponding to The ohmic voltage on is , , These are the polarization capacitors on the two RC circuits, , These are the polarization resistors on the two RC circuits, and the corresponding voltages across the two parallel RC circuits are the polarization voltages. and I is the current of the battery (negative for discharge and positive for charging). The battery temperature T is calculated according to Kirchhoff's current and voltage laws. The mathematical model expression of its electrical model is shown in formulas (1)-(3).

[0059] (1) The open-circuit voltage is mainly determined by the battery temperature and the amount of remaining charge, as shown in formula (2).

[0060] (2) in, The remaining usable power of the battery can be obtained from formula (3).

[0061] (3) in, For the initial stage of lithium-ion batteries , For Coulomb efficiency, This refers to the battery's rated capacity.

[0062] Then, based on Kirchhoff's laws, a lumped parameter battery thermal model is constructed, as shown in formulas (4)-(5).

[0063] (4) The internal heat source Q can be calculated using the heat generation rate equation proposed by Bernardi: (5) in, , These are the internal and external heat capacities of the battery, respectively. , These represent the internal thermal resistance and surface thermal resistance of the battery, respectively. , These are the battery's internal temperature and surface temperature, respectively. The ambient temperature.

[0064] Then, the battery temperature output from the battery thermal model, i.e., the internal heat source Q, is input into the battery semi-empirical aging model (referred to as the aging model) to calculate the battery capacity degradation. .

[0065] After receiving multiple initial charging strategies, the server inputs these strategies and battery state information into the electro-thermal-aging coupled model. The model simulates the dynamic characteristics of the battery during charging and outputs the charging time. Maximum battery temperature and battery capacity degradation This yields the predicted battery performance parameters corresponding to multiple initial charging strategies.

[0066] In this embodiment, the predicted battery performance parameters of multiple initial charging strategies are predicted using an electro-thermal-aging coupling model, which ensures the accuracy of the predicted battery performance parameters.

[0067] In one embodiment, the charging control method further includes: Obtain the predicted battery performance parameters corresponding to the historical charging strategy, as well as the actual battery performance parameters obtained by charging the battery according to the historical charging strategy during the historical time period. When the difference between the predicted battery performance parameters and the actual battery performance corresponding to the historical charging strategy is greater than the preset difference threshold, the parameter of the electric-thermal-aging coupling model is updated to obtain the updated electric-thermal-aging coupling model. Battery state information and multiple initial charging strategies are input into the electro-thermal-aging coupled model, including: Battery state information and multiple initial charging strategies are input into the updated electro-thermal-aging coupled model.

[0068] For example, the charging strategy acquisition request also carries the actual battery performance parameters corresponding to the historical charging strategy. These actual battery performance parameters are the battery performance parameters collected by the device during the charging process according to the historical charging strategy within a historical time period.

[0069] After receiving a charging strategy retrieval request, the server retrieves historical charging strategies and corresponding actual battery performance parameters from the request, and also obtains the predicted battery performance parameters corresponding to the historical charging strategies from its local storage. These predicted battery performance parameters are obtained by using an electro-thermal-aging coupling model to predict battery performance parameters for historical charging strategies over a historical time period.

[0070] The server calculates the difference between the predicted battery performance parameters corresponding to historical charging strategies and the actual battery performance. When the difference is less than a preset difference threshold, the battery state information and multiple initial charging strategies are input into the electro-thermal-aging coupling model. Under the safety constraint boundary, the electro-thermal-aging coupling model predicts the battery performance parameters of multiple initial charging strategies based on the battery state information, and obtains the predicted battery performance parameters corresponding to each of the multiple initial charging strategies.

[0071] When the difference is greater than or equal to a preset difference threshold, the parameter of the electro-thermal-aging coupling model is updated to obtain the updated electro-thermal-aging coupling model. Then, the battery state information and multiple initial charging strategies are input into the updated electro-thermal-aging coupling model. Under the safety constraint boundary, the updated electro-thermal-aging coupling model predicts the battery performance parameters of multiple initial charging strategies based on the battery state information, and obtains the predicted battery performance parameters corresponding to the multiple initial charging strategies.

[0072] In this embodiment, when the difference between the predicted battery performance parameters corresponding to the historical charging strategy and the actual battery performance is greater than a preset difference threshold, the parameters of the electro-thermal-aging coupling model are updated, and the updated electro-thermal-aging coupling model is used to predict the predicted battery performance parameters of the initial charging strategy, thus ensuring the accuracy of the predicted battery performance parameters.

[0073] In one embodiment, battery status information includes battery health status; the charging control method further includes: When the battery health status is less than the preset health status threshold, the safety constraint boundary is updated to obtain the updated safety constraint boundary. Under safety constraints, a coupled electro-thermal-aging model is used to predict battery performance parameters for multiple initial charging strategies based on battery state information, including: Using an electro-thermal-aging coupled model, battery performance parameters are predicted for multiple initial charging strategies based on battery state information under updated safety constraints.

[0074] For example, the battery status information also includes the current battery health status of the battery in the device. After receiving the charging policy retrieval request, the server retrieves the battery health status from the battery status information and compares the battery health status with a preset health status threshold.

[0075] When the battery health status is greater than or equal to a preset health status threshold, the battery status information and multiple initial charging strategies are input into the electro-thermal-aging coupling model. Under the safety constraint boundary, the electro-thermal-aging coupling model predicts the battery performance parameters of multiple initial charging strategies based on the battery status information, and obtains the predicted battery performance parameters corresponding to each of the multiple initial charging strategies.

[0076] When the battery's state of health (SOH) falls below a preset threshold, it indicates a significant decline in SOH, signifying accelerated aging. Consequently, its ability to withstand high-current charging and high temperatures weakens. Therefore, the safety constraint boundary is updated, for example, by tightening the safety boundary threshold for the charging current, resulting in the updated safety constraint boundary. Then, the battery state information and multiple initial charging strategies are input into the electro-thermal-aging coupled model. Under the updated safety constraint boundary, the electro-thermal-aging coupled model predicts battery performance parameters for each initial charging strategy based on the battery state information, yielding the predicted battery performance parameters for each initial charging strategy.

[0077] In an exemplary embodiment, when the server detects that the difference between the predicted battery performance parameters corresponding to historical charging strategies and the actual battery performance is greater than a preset difference threshold, and the battery health status is less than a preset health status threshold, the server updates the parameters of the electro-thermal-aging coupling model to obtain an updated electro-thermal-aging coupling model, and updates the safety constraint boundary to obtain an updated safety constraint boundary. Then, the battery state information and multiple initial charging strategies are input into the updated electro-thermal-aging coupling model. Under the updated safety constraint boundary, the updated electro-thermal-aging coupling model predicts the battery performance parameters of the multiple initial charging strategies based on the battery state information, obtaining the predicted battery performance parameters corresponding to each of the multiple initial charging strategies.

[0078] In this embodiment, the parameters of the electro-thermal-aging coupling model are calibrated by analyzing deviations to ensure that the output of the electro-thermal-aging coupling model conforms to the actual aging trajectory of the battery. Simultaneously, based on the battery's current state of health (SOH), the safety constraint boundaries of the electro-thermal-aging coupling model are dynamically adjusted so that the new safety constraint boundaries can adapt to changes in battery performance degradation, thereby ensuring the accuracy of the predicted battery performance parameters output by the electro-thermal-aging coupling model.

[0079] In one embodiment, based on multiple initial charging strategies, predicted battery performance parameters, and battery state information, multiple candidate charging strategies output by a multi-objective optimization model are determined, including: Based on predicted battery performance parameters, multiple charging targets for battery charging control are determined, including at least two of target charging time, target battery temperature, and target capacity decay. Multiple initial charging strategies, predicted battery performance parameters, multiple charging targets, and battery state information are input into a multi-objective optimization model for strategy optimization, and multiple candidate charging strategies are output.

[0080] Here, the charging target refers to the multi-dimensional performance indicators that the charging strategy aims to optimize. Target charging time, target battery temperature, and target capacity decay refer to the degree that needs to be optimized to achieve, such as minimum charging time, minimum battery temperature, and minimum capacity decay.

[0081] For example, after obtaining the predicted battery performance parameters corresponding to multiple initial charging strategies, the server determines multiple charging targets based on the charging time, battery temperature, and capacity decay included in the predicted battery performance parameters. These targets include at least two of the following: minimum charging time (target charging time), maximum battery temperature (target battery temperature), and maximum capacity decay (target capacity decay). Then, the multiple initial charging strategies, predicted battery performance parameters, multiple charging targets, and battery state information are input into a multi-objective optimization model for strategy optimization, outputting multiple candidate charging strategies.

[0082] Specifically, based on the predicted battery performance parameters output by the electro-thermal-aging coupling model, multiple charging targets are determined, and a multi-objective optimization model is constructed, the mathematical expression of which is shown in formula (6).

[0083] (6) Wherein, objective function This indicates minimizing the charging time simultaneously. Maximum battery temperature and total capacity decay Then, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to optimize the objective optimization model and output multiple candidate charging strategies. Specifically, under the constraints of set safety boundaries, such as maximum temperature and lithium plating boundary, a global search and iterative evolution of the current magnitude and duration of each stage in the initial charging strategy is performed, ultimately outputting a set of non-dominated optimal solutions, namely the Pareto Front. Each solution in this set represents a charging strategy that achieves the best trade-off between charging time, battery temperature, and battery life degradation.

[0084] In one exemplary embodiment, such as Figure 3 The diagram shows the logic architecture for optimizing charging current based on the NSGA-II algorithm. The multi-objective optimization model aims to achieve shorter charging time, lower temperature rise, and less lifetime degradation (i.e., capacity decay), and sets constraints including maximum and minimum current limits, maximum temperature rise limits, cutoff current limits, and lithium plating boundary limits. The multi-objective optimization model then considers multiple initial charging strategies and predicted battery performance parameters, including input battery state information such as initial battery temperature, ambient temperature, and charging SOC range [SOC]. k-1 SOC k The NSGA-II algorithm is used to optimize the multi-objective optimization model and output a cluster of charging strategies when the battery is in different health states, i.e., multiple candidate charging strategies.

[0085] In this embodiment, by constructing a multi-objective optimization problem model and running the NSGA-II algorithm, the real-time SOH is used as the model input and optimization constraint. This dynamically generates a set of non-dominated optimal solutions (Pareto front) that achieves the best balance between charging time, maximum temperature, and capacity decay for batteries with different health levels. These are candidate charging strategies, which realize the adaptability of the charging strategy to battery aging. This effectively avoids the risk of overcharging and accelerated lifespan shortening caused by ignoring battery decay, and significantly improves the safety of the charging process and the long-term effectiveness of the strategy.

[0086] In one embodiment, the charging control method further includes: Get the custom weight corresponding to a specified charging target among multiple charging targets sent by the device; Based on the custom weights corresponding to the specified charging target, the first weights of multiple charging targets are updated to obtain the custom charging target; Multiple initial charging strategies, predicted battery performance parameters, custom charging targets, and battery state information are input into a multi-objective optimization model for strategy optimization, and multiple custom charging strategies are output. Multiple custom charging strategies are sent to the device so that the device charges the battery according to a target charging strategy among the multiple custom charging strategies.

[0087] For example, when sending a charging strategy acquisition request, the device can also simultaneously send a custom weight corresponding to a specified charging target among multiple charging targets. This custom weight can be generated by the device based on user instructions. For instance, the device can provide the user with a custom weight editing control for setting multiple charging targets through an interactive interface, and obtain the custom weight input by the user for the specified charging target among multiple charging targets using this custom weight editing control.

[0088] The server updates the weights of multiple charging targets based on custom weights corresponding to a specified charging target. For example, it replaces the original weights of the specified charging target with the custom weights to obtain the custom charging target. Simultaneously, it updates the constraints of the multi-objective optimization model based on the custom weights. For instance, when the user increases the weight of charging time (indicating a shorter charging time), it relaxes the maximum temperature rise limit or the maximum current limit. Then, multiple initial charging strategies, predicted battery performance parameters, custom charging targets, and battery state information are input into the multi-objective optimization model for strategy optimization, outputting multiple custom charging strategies. These custom charging strategies represent the charging strategies output by the multi-objective optimization model under the custom charging target.

[0089] Then, multiple custom charging strategies are sent to the device so that the device charges the battery according to a target charging strategy among the multiple custom charging strategies.

[0090] In an exemplary embodiment, after obtaining multiple candidate charging strategies output by the multi-objective optimization model, the server sends the multiple candidate charging strategies to the device and receives custom weights from the device for a specified charging target among the multiple charging targets of the multiple candidate charging strategies. For example, the device provides the user with a custom weight editing control for setting multiple charging targets for multiple candidate charging strategies through an interactive interface, and obtains the custom weights input by the user for a specified charging target among the multiple charging targets using the custom weight editing control.

[0091] Then, based on the custom weights corresponding to the specified charging target, the first weights of multiple charging targets are updated to obtain the custom charging target. From multiple candidate charging strategies, the custom charging strategy that matches the custom charging target is determined. The updated candidate charging strategy is then sent to the device so that the device charges the battery according to one of the target charging strategies in the updated candidate strategy. Specifically, the server performs local optimization based on the original Pareto solution set (i.e., candidate charging strategies) according to the custom charging target. This optimization can be achieved using a simplified model coupled with a first-order RC circuit model, a single-node lumped parameter battery thermal model, and an aging model. The server then generates a custom charging strategy for the custom charging target and sends it to the device.

[0092] In this embodiment, by receiving the custom weight corresponding to the specified charging target and updating it to the custom charging target, the multi-objective optimization model outputs a custom charging strategy based on the custom charging target, realizing the user's custom setting of optimization targets and meeting the diversified needs of battery charging strategies.

[0093] In one embodiment, the custom weight corresponding to the charging target is specified as the custom weight corresponding to the target charging time; the charging control method further includes: Obtain the capacity decay corresponding to multiple custom charging strategies; When the capacity decay exceeds the preset capacity decay threshold, the custom charging target is updated with a second weight to obtain the updated custom charging target. Multiple initial charging strategies, predicted battery performance parameters, updated custom charging targets, and battery state information are input into a multi-objective optimization model for strategy optimization, and multiple optimized custom charging strategies are output. Multiple optimized custom charging strategies are sent to the device so that the device charges the battery according to a target charging strategy among the multiple optimized custom charging strategies.

[0094] For example, when the custom weight corresponding to the specified charging target is the same as the custom weight corresponding to the target charging time, the server obtains the custom charging strategy and corresponding capacity decay output by the multi-objective optimization model based on the custom charging target.

[0095] When the capacity decay of a custom charging strategy exceeds the preset capacity decay threshold, it indicates that the candidate charging strategy output based on the custom target obtained by the user-set custom weights will seriously affect battery life. It is necessary to optimize the weights of the custom target to protect battery life. The server then performs a second weight update on the custom charging target, such as reducing the custom weight corresponding to the specified charging target, or increasing the weights of other charging targets among multiple charging targets, except for the specified charging target, to obtain the updated custom charging target.

[0096] Multiple initial charging strategies, predicted battery performance parameters, updated custom charging targets, and battery state information are input into a multi-objective optimization model for strategy optimization, outputting multiple optimized custom charging strategies. These optimized custom charging strategies are then sent to the device, enabling the device to charge the battery according to one of the target charging strategies.

[0097] In this embodiment, when the custom charging strategy has a significant impact on battery life, the custom charging target is automatically adjusted, and the optimized custom charging strategy is determined based on the updated custom charging target. This can prevent damage to the battery and achieve personalized charging under the premise of safety.

[0098] In one exemplary embodiment, such as Figure 4 The diagram illustrates a charging strategy system based on multi-objective optimization. This system can be specifically applied to electric vehicles and includes an onboard intelligent platform (integrating a battery management system, vehicle-side processing center, and other modules), a cloud control platform, and a vehicle-side processing center (including user-defined modules). Through the collaboration of the onboard intelligent platform, cloud control platform, and vehicle-side processing center, a complete closed loop of data acquisition, optimization calculation, and charging strategy execution is formed.

[0099] The vehicle-side processing center is used to collect real-time battery status parameters and ambient temperature data from the batteries in electric vehicles. Meanwhile, the battery management system at the vehicle-side processing center continuously monitors the battery's State of Charge (SOC) and State of Health (SOH). The vehicle-side processing center uploads the collected battery status information to the cloud control platform via the vehicle network. Furthermore, the vehicle-side processing center also receives and executes optimal charging current commands issued by the cloud control platform or selected by the user. This refers to the target charging strategy. Specifically, when the vehicle-side processing center uploads battery status information to the cloud control platform, it also includes the current command executed in the previous cycle. This refers to the historical charging strategy, which serves as status feedback and is uploaded to the cloud control platform along with the currently collected real-time data.

[0100] After receiving the above data, the cloud control platform will implement the historical current strategy. The actual battery performance parameters are compared with the predicted battery performance parameters. The parameters of the electro-thermal-aging coupling model (i.e., the battery model) are calibrated by analyzing the deviation. When the current state of health (SOH) of the battery is greater than the preset state of health threshold, the safety constraint boundary of the electro-thermal-aging coupling model is dynamically adjusted so that the new safety constraint boundary and the calibrated electro-thermal-aging coupling model can adapt to the degradation of battery performance.

[0101] When the cloud control platform enters the multi-objective optimization calculation phase, it follows the current command. Multiple initial charging strategies are determined, and the charging time is output for each initial charging strategy using a battery model. Maximum battery temperature and battery capacity degradation Then, a multi-objective optimization model is constructed: The non-dominated sorting genetic algorithm (NSGA-II) is used to optimize the multi-objective optimization model, generating a set of non-dominated optimal solutions for the current battery state, i.e., multiple candidate charging strategies. This set of non-dominated optimal solutions is then sent to the vehicle-side processing center. Through the user-defined module in the vehicle-side processing center, the set of non-dominated optimal solutions is transformed into diverse charging strategies available to the user through the user interface.

[0102] Once the user selects a specific strategy based on current needs, the vehicle-side control system of the in-vehicle intelligent platform begins to execute the new optimized current command. At the same time, the charging strategy executed this time is saved as the basis for the state feedback of the next cycle.

[0103] In one exemplary embodiment, such as Figure 5 The diagram illustrates an application flow of a charging strategy system, including the following steps: S1 acquires battery status data and user operation data in real time through the vehicle-side data acquisition module, including battery SOC, SOH, temperature parameters and user historical strategy selection records, and uploads the data to the cloud control platform. S2, through the multi-objective optimization module of the cloud control platform, uses the NSGA-II algorithm based on the uploaded data to solve the multi-objective optimization problem of charging time, temperature rise and capacity decay, and generates a non-dominated optimal solution set for the current battery state; S3 transforms the non-dominated optimal solution set distributed from the cloud into a visual strategy menu through a user-defined module. Users can select preset modes or custom charging thresholds according to real-time needs. The system triggers rapid re-optimization to generate personalized charging strategies based on user selections. S4 executes the user-selected optimized charging strategy through the vehicle-side control module, continuously monitors changes in battery status during the charging process, and uploads the strategy execution effect as status feedback data to the cloud.

[0104] This completes a full "collection-feedback-optimization-execution" closed loop, enabling the charging strategy to continuously and intelligently adjust itself according to changes in battery status. This allows the charging strategy to not only adapt to users' personalized needs but also consistently match the actual health condition of the battery, achieving adaptive optimization throughout its entire lifecycle. Furthermore, compared to traditional charging strategies, the charging strategy in this embodiment, which considers battery health status, significantly shortens charging time while preventing overheating and lithium plating, achieving ultra-fast charging of the power battery and meeting the rapid energy replenishment needs of electric vehicles. Moreover, users can choose different charging strategies from multiple performance frontiers to meet diverse and multi-scenario user requirements.

[0105] In an exemplary embodiment, the electric vehicle is equipped with a user-defined module. The electric vehicle receives multiple candidate charging strategies from the server, and the device presents a "strategy list" of multiple candidate charging strategies in a visual form, such as including options like "fast charging mode," "battery life protection mode," "equalization charging mode," "user-defined mode," and "user preference mode." Each option corresponds to a specific solution in the solution set (i.e., the charging current of a candidate charging strategy). sequence).

[0106] Users can choose the target charging strategy that best suits their needs from the strategy list, based on their current application scenario (e.g., emergency charging on a highway, overnight charging at home), their level of concern for battery life, or personal preferences. After the user completes the selection, the electric vehicle will charge according to the target strategy. The sequence is sent to the vehicle control system, which then processes it according to... Sequential charging equipment charges batteries.

[0107] In one exemplary embodiment, the electric vehicle receives multiple candidate charging strategies from the server and generates a real-time interactive power setting slider on a visual interface. When the user sets a target power threshold by dragging the slider, the vehicle-side control system uses the current curves of the multiple candidate charging strategies (i.e., The system performs real-time calculations and updates the display of key parameters for multiple candidate charging strategies, including the time required to reach the target battery level, the predicted maximum temperature, and the lifespan impact coefficient. For example, when a user adjusts the target battery level from 90% to 85%, the interface immediately displays a comparison: "Fast charging mode: 14 minutes to 85%, peak temperature 41°C; Balanced charging mode: 18 minutes to 85%, peak temperature 37°C."

[0108] In one exemplary embodiment, when a user selects the same configuration more than three times in a specific scenario, an intelligent recommendation mechanism is triggered: First, a personalized solution suggestion is generated, which is saved as a customized mode after user confirmation, while recording relevant scenario characteristics. Subsequently, when a similar scenario is detected, this personalized solution is prioritized and clearly marked "Recommended based on your habits" on the interface. For example, if a user repeatedly selects "charge to 90%+ long lifespan mode" on Thursday evenings, the system will create a "Thursday Reserve" personalized solution, store it in the "User Preference Mode," and record relevant scenario characteristics (time, location, travel planning, etc.). When a similar scenario is detected again, this solution will appear as a priority recommendation in the strategy menu. For temporary policy changes by users, abnormal context information is recorded, and the emergency scenario strategy library is gradually improved through machine learning algorithms.

[0109] To ensure system feasibility, multiple safeguards are implemented: computational tasks are processed in layers, and a simplified model is used for re-optimization triggered by threshold changes; user habit data is compressed using feature encoding, with single-user data storage not exceeding 100KB; all automatic recommendation strategies require user confirmation before execution; in special circumstances such as network anomalies, the system automatically switches to a safety strategy generated by the cloud during the last successful charging cycle, which has been verified by the vehicle-side battery management system to have not triggered safety boundaries such as voltage, temperature, and lithium plating.

[0110] This embodiment ensures both the intelligence level of charging strategy optimization and reliable operation under various working conditions. Simultaneously, it achieves a shift from passive response to proactive service, forming an intelligent charging management ecosystem that continuously interacts with users and evolves together.

[0111] In one exemplary embodiment, a bidirectional calibration mechanism is established within the data loop between the vehicle and the cloud. The vehicle continuously collects battery SOH (State of Harshness) degradation data and strategy execution performance. When a drift in key parameters is detected, a recalibration of the cloud model is automatically triggered. Specifically, after receiving real-vehicle data, the cloud dynamically corrects the parameters of the electrical-thermal-aging model by comparing historical strategy predictions with actual measurements. This model update mechanism, based on real-vehicle verification, ensures that the cloud model remains synchronized with the physical battery. For example, when a 15% increase in battery internal resistance is detected, the charging strategy system not only adjusts the current strategy but also updates the internal resistance parameters in the cloud model, providing a more accurate benchmark for subsequent optimization calculations for all vehicles.

[0112] Within the closed-loop strategy between the cloud and the user, the charging strategy system enables the continuous evolution of personalized services. The cloud analyzes users' historical selection patterns to establish a mapping relationship between charging scenarios and charging strategies, and feeds this information back to the strategy generation stage. For example, in the "balanced mode" for commuting scenarios, the system outputs an optimized current curve corresponding to the balanced mode, ensuring a better balance between charging speed and battery life. Simultaneously, the charging strategy system incorporates validated personalized strategies into the standard strategy library, enriching the range of subsequent strategy choices.

[0113] Within the closed-loop execution between the user and the vehicle, the charging strategy system provides real-time strategy adjustment capabilities. For example, the vehicle displays an optimized strategy set based on the latest battery status to the user, while the user's selection data is fed back to the cloud via the vehicle, driving the next round of strategy optimization. When the user adjusts charging parameters according to real-time needs, the charging strategy system immediately initiates rapid recalculation, generating a customized strategy that meets individual needs while ensuring safety. This instant response mechanism ensures that the system is always synchronized with the user's actual needs.

[0114] To ensure the stable operation of the ternary closed-loop charging strategy system, a hierarchical decision-making mechanism is employed: the vehicle is responsible for execution and safety monitoring, the cloud handles core computation and model optimization, and the user has the final decision-making power. This architecture allows the system to continuously optimize over time, ultimately achieving optimal performance management throughout the battery's entire lifecycle.

[0115] In this embodiment, the cloud control platform solves the computing power bottleneck and complex optimization problems, user-defined modules meet diverse needs, and the vehicle-cloud closed loop achieves precise and adaptive strategy execution. This effectively transforms abstract multi-objective optimization theory into practical functions that are perceptible and selectable by the user, maximizing charging efficiency and user experience while ensuring battery safety and lifespan.

[0116] On the other hand, this embodiment provides a charging control device. Figure 6 This is a schematic diagram of a battery life prediction device according to an embodiment of this application, such as... Figure 6 As shown, the charging control device 600 includes: a data processing module 601, a performance prediction module 602, a multi-objective optimization module 603, and a strategy output module 604. The device will be described below.

[0117] The data processing module 601 is used to obtain the battery status information and historical charging strategies corresponding to the batteries in the device, and to determine multiple initial charging strategies based on the historical charging strategies. The performance prediction module 602 is used to predict battery performance parameters for multiple initial charging strategies based on battery state information, and obtain the predicted battery performance parameters corresponding to the multiple initial charging strategies respectively. The multi-objective optimization module 603 is used to determine multiple candidate charging strategies output by the multi-objective optimization model based on multiple initial charging strategies, predicted battery performance parameters and battery state information. The strategy output module 604 is used to send multiple candidate charging strategies to the device so that the device charges the battery according to a target charging strategy among the multiple candidate charging strategies.

[0118] In one embodiment, the data processing module 601 is used to filter historical charging strategies based on the current location of the device to obtain a target historical charging strategy; and to determine multiple initial charging strategies based on the target historical charging strategy.

[0119] In one embodiment, the performance prediction module 602 is further configured to input battery state information and multiple initial charging strategies into the electro-thermal-aging coupling model; and, under safety constraints, predict battery performance parameters for multiple initial charging strategies based on battery state information through the electro-thermal-aging coupling model to obtain the predicted battery performance parameters corresponding to each of the multiple initial charging strategies.

[0120] In one embodiment, the charging control device 600 is further configured to acquire the predicted battery performance parameters corresponding to historical charging strategies, and the actual battery performance parameters obtained by charging the battery according to the historical charging strategies during a historical time period; when the difference between the predicted battery performance parameters corresponding to the historical charging strategies and the actual battery performance is greater than a preset difference threshold, the parameter of the electro-thermal-aging coupling model is updated to obtain the updated electro-thermal-aging coupling model; inputting battery state information and multiple initial charging strategies into the electro-thermal-aging coupling model includes: inputting battery state information and multiple initial charging strategies into the updated electro-thermal-aging coupling model.

[0121] In one embodiment, the battery state information includes the battery health state; the charging control device 600 is further configured to update the safety constraint boundary when the battery health state is less than a preset health state threshold, to obtain the updated safety constraint boundary; and to predict battery performance parameters for multiple initial charging strategies based on the battery state information under the safety constraint boundary using an electro-thermal-aging coupling model, including: predicting battery performance parameters for multiple initial charging strategies based on the battery state information under the updated safety constraint boundary using an electro-thermal-aging coupling model.

[0122] In one embodiment, the multi-objective optimization module 603 is further configured to determine multiple charging objectives for charging control of the battery based on predicted battery performance parameters, wherein the multiple charging objectives include at least two of target charging time, target battery temperature, and target capacity decay; input multiple initial charging strategies, predicted battery performance parameters, multiple charging objectives, and battery state information into the multi-objective optimization model for strategy optimization, and output multiple candidate charging strategies.

[0123] In one embodiment, the charging control device 600 is further configured to: acquire a custom weight corresponding to a specified charging target among multiple charging targets sent by the device; update the weights of the multiple charging targets based on the custom weights corresponding to the specified charging target to obtain a custom charging target; input multiple initial charging strategies, predicted battery performance parameters, custom charging targets, and battery state information into a multi-objective optimization model for strategy optimization, and output multiple custom charging strategies; and send the multiple custom charging strategies to the device so that the device charges the battery according to one of the target charging strategies among the multiple custom charging strategies.

[0124] In one embodiment, the custom weight corresponding to the specified charging target is the custom weight corresponding to the target charging time; the charging control device 600 is further configured to obtain the capacity decay corresponding to multiple custom charging strategies respectively; when there is a capacity decay greater than a preset capacity decay threshold, the custom charging target is updated with a second weight to obtain the updated custom charging target; multiple initial charging strategies, predicted battery performance parameters, updated custom charging targets and battery state information are input into a multi-objective optimization model for strategy optimization, and multiple optimized custom charging strategies are output; the multiple optimized custom charging strategies are sent to the device so that the device charges the battery according to one of the target charging strategies among the multiple optimized custom charging strategies.

[0125] Each module in the aforementioned charging control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0126] Thirdly, this embodiment provides an electronic device, including a memory and a processor. The memory stores computer instructions, and when the computer instructions are executed by the processor, they implement the method of any of the above embodiments.

[0127] In one embodiment, this embodiment also provides an electronic device, which may be a server, and its internal structure diagram may be as follows. Figure 7As shown, this electronic device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer instructions, and a database. The internal memory provides the environment for the operation of the operating system and computer instructions stored in the non-volatile storage media. The database stores data involved in business data processing methods. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer instructions are executed by the processor, a battery life prediction method is implemented.

[0128] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0129] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions thereon, which are loaded by a processor to execute the arrangements in any of the methods described above. In embodiments of this application, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0130] Fifthly, embodiments of this application provide a computer program product, including a computer program or instructions, which are executed by a processor to implement the steps of any of the methods described above.

[0131] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0132] The charging control method, electronic device, and computer-readable storage medium provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A charging control method, characterized in that, Includes the following steps: Obtain battery status information and historical charging strategies corresponding to the batteries in the device, and determine multiple initial charging strategies based on the historical charging strategies; Based on the battery state information, battery performance parameters are predicted for multiple initial charging strategies to obtain predicted battery performance parameters corresponding to each of the multiple initial charging strategies. Based on the initial charging strategies, the predicted battery performance parameters, and the battery state information, multiple candidate charging strategies output by the multi-objective optimization model are determined. Multiple candidate charging strategies are sent to the device so that the device charges the battery according to a target charging strategy among the multiple candidate charging strategies.

2. The method according to claim 1, characterized in that, The determination of multiple initial charging strategies based on the historical charging strategies includes: Based on the current location of the device, historical charging strategies are filtered to obtain the target historical charging strategy; Based on the target historical charging strategy, multiple initial charging strategies are determined.

3. The method according to claim 1, characterized in that, Based on the battery state information, the battery performance parameters of the plurality of initial charging strategies are predicted to obtain the predicted battery performance parameters corresponding to each of the plurality of initial charging strategies, including: The battery state information and multiple initial charging strategies are input into the electro-thermal-aging coupling model; Under safety constraints, the electro-thermal-aging coupling model is used to predict battery performance parameters for multiple initial charging strategies based on the battery state information, thereby obtaining the predicted battery performance parameters corresponding to each of the multiple initial charging strategies.

4. The method according to claim 3, characterized in that, The method further includes: Obtain the predicted battery performance parameters corresponding to the historical charging strategy, and the actual battery performance parameters obtained by charging the battery according to the historical charging strategy during the historical time period; When the difference between the predicted battery performance parameters and the actual battery performance corresponding to the historical charging strategy is greater than a preset difference threshold, the parameter of the electro-thermal-aging coupling model is updated to obtain the updated electro-thermal-aging coupling model. The step of inputting the battery state information and multiple initial charging strategies into the electro-thermal-aging coupling model includes: The battery state information and multiple initial charging strategies are input into the updated electro-thermal-aging coupling model.

5. The method according to claim 3, characterized in that, The battery status information includes the battery health status; the method further includes: When the battery health status is less than a preset health status threshold, the safety constraint boundary is updated to obtain the updated safety constraint boundary. The process of predicting battery performance parameters for multiple initial charging strategies based on battery state information using the electro-thermal-aging coupling model under safety constraints includes: Under the updated safety constraints, the electro-thermal-aging coupling model predicts battery performance parameters for multiple initial charging strategies based on the battery state information.

6. The method according to claim 1, characterized in that, The process of determining multiple candidate charging strategies output by a multi-objective optimization model based on multiple initial charging strategies, predicted battery performance parameters, and battery state information includes: Based on the predicted battery performance parameters, multiple charging targets for charging control of the battery are determined, and the multiple charging targets include at least two of target charging time, target battery temperature, and target capacity decay. The initial charging strategies, the predicted battery performance parameters, the charging targets, and the battery state information are input into a multi-objective optimization model for strategy optimization, and multiple candidate charging strategies are output.

7. The method according to claim 6, characterized in that, The method further includes: Obtain the custom weight corresponding to a specified charging target among the multiple charging targets sent by the device; Based on the custom weights corresponding to the specified charging target, the first weights of the multiple charging targets are updated to obtain the custom charging target; The initial charging strategies, the predicted battery performance parameters, the custom charging targets, and the battery state information are input into a multi-objective optimization model for strategy optimization, and multiple custom charging strategies are output. Multiple custom charging strategies are sent to the device so that the device charges the battery according to a target charging strategy among the multiple custom charging strategies.

8. The method according to claim 7, characterized in that, The custom weight corresponding to the specified charging target is the custom weight corresponding to the target charging time; the method further includes: Obtain the capacity decay corresponding to each of the multiple custom charging strategies; When the capacity decay exceeds the preset capacity decay threshold, the custom charging target is updated with a second weight to obtain the updated custom charging target. The initial charging strategies, the predicted battery performance parameters, the updated custom charging target, and the battery state information are input into a multi-objective optimization model for strategy optimization, and multiple optimized custom charging strategies are output. Multiple optimized custom charging strategies are sent to the device so that the device charges the battery according to a target charging strategy among the multiple optimized custom charging strategies.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing a computer program configured to be executed by the processor to implement the steps of the method according to any one of claims 1 to 8.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer program configured to be executed by a processor to implement the method of any one of claims 1 to 8.

Images