Vehicle end charging method and device, vehicle and storage medium

Abstract

The invention relates to the technical field of vehicle charging control, in particular to a vehicle end charging method and device, a vehicle and a storage medium. The method comprises the following steps: acquiring historical charging data of a current vehicle and a current battery health state value; based on the historical charging data, calculating an optimal charging curve by using a preset battery life prediction model and a preset optimization search algorithm, and generating an optimized charging MAP based on the optimal charging curve; and determining a current charging strategy based on the optimized charging MAP and the current battery health state value, and charging the current vehicle based on the current charging strategy. Therefore, the optimal charging curve is calculated based on the historical charging data of the vehicle, the problem that potential safety hazards exist in the fast charging process due to the fact that a standard charging MAP in the prior art cannot be dynamically adjusted according to the actual aging state of the battery and the use working condition of the vehicle is solved, the service life of the battery is prolonged, heat accumulation in a battery cell during fast charging is reduced, and the charging efficiency is improved. And the battery safety is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle charging control technology, and in particular to a vehicle-side charging method, device, vehicle, and storage medium. Background Technology

[0002] With the rapid development of new energy vehicles and their increasing ownership, the reduction in driving range and the safe use of power batteries have become key concerns for users. The performance of the power battery directly affects the vehicle's range and lifespan, and the charging process is one of the critical factors influencing battery performance. Therefore, optimizing battery management during charging to extend battery life and improve its safety has become an important direction for the technological development of new energy vehicles.

[0003] In related technologies, charging management for new energy vehicles typically relies on a standard charging MAP (charging curve), which is designed based on the battery's initial performance and general operating conditions. However, in actual use, the standard charging MAP cannot be dynamically adjusted according to the actual aging state of the battery and the vehicle's operating conditions, leading to safety hazards during fast charging, which urgently needs to be addressed. Summary of the Invention

[0004] This application provides a vehicle-side charging method, device, vehicle, and storage medium to solve the problem that the standard charging MAP of the prior art cannot be dynamically adjusted according to the actual aging state of the battery and the usage conditions of the vehicle, resulting in safety hazards during fast charging, thereby extending battery life, reducing heat accumulation inside the battery cell during fast charging, and improving battery safety.

[0005] To achieve the above objectives, the first aspect of this application proposes a vehicle-side charging method, comprising the following steps: Obtain the vehicle's historical charging data and current battery health status value; Based on the historical charging data, the optimal charging curve is calculated using a preset battery life prediction model and a preset optimization search algorithm, and an optimized charging MAP is generated based on the optimal charging curve. Based on the optimized charging MAP and the current battery health status value, a current charging strategy is determined, and the current vehicle is charged based on the current charging strategy.

[0006] According to one embodiment of this application, generating the optimized charging MAP based on the optimal charging curve includes: Based on the optimal charging curve, the charging process is evenly divided into multiple preset time steps, and the charging parameters for each preset time step are obtained. Determine at least one battery health state interval to be managed, and calibrate an initial smart MAP for the interval endpoints of each battery health state interval to be managed. Based on each of the battery health status intervals to be managed, the charging parameters for each preset time step are mapped to the corresponding initial smart MAP to generate the optimized charging MAP.

[0007] According to one embodiment of this application, determining the current charging strategy based on the optimized charging MAP and the current battery health state value includes: Determine whether the current battery health status value conforms to any of the battery health status intervals to be managed; If the current battery health status value meets any of the battery health status intervals to be managed, a target battery health status interval corresponding to the current battery health status value is determined from the optimized post-charge MAP. Determine whether the current battery health status value is within the range of the target battery health status interval to be managed; If the current battery health status value is within the range of the target battery health status interval, then the target charging parameters corresponding to the current battery health status value are calculated using linear interpolation, and the current charging strategy is obtained based on the target charging parameters.

[0008] According to one embodiment of this application, after determining whether the current battery health state value is within the range of the endpoints of the target battery health state range to be managed, the method further includes: If the current battery health status value is not within the range of the target battery health status interval, then the target charging parameter is determined based on the range of the target battery health status interval, and the current charging strategy is obtained based on the target charging parameter.

[0009] According to one embodiment of this application, after generating the optimized charging MAP from the optimal charging curve, the method further includes: Determine if there is a pre-defined charging map update requirement; If there is a preset charging MAP update requirement, at least one smart MAP in the optimized charging MAP is updated to obtain at least one updated smart MAP.

[0010] According to one embodiment of this application, before calculating the optimal charging curve using the preset battery life prediction model and the preset optimization search algorithm, the method further includes: Acquire historical charging datasets, actual battery life data, and battery health status values ​​corresponding to each historical charging process for multiple target vehicles, wherein the historical charging datasets are charging data for multiple historical charging processes for each target vehicle; Target data is obtained based on the historical charging datasets of the multiple target vehicles, the actual battery lifespan data, and the battery health status value corresponding to each historical charging process of each target vehicle. The target data is preprocessed, and the preprocessed target data is divided into a training set and a validation set; The preset neural network is trained using the training set to obtain an initial neural network model, and the initial neural network model is verified using the validation set until the initial neural network model meets the preset criteria. Then, the iterative training of the preset neural network ends to obtain the preset battery life prediction model. Otherwise, the hyperparameters of the model are adjusted and iterative training continues.

[0011] The vehicle-side charging method proposed in this application calculates the optimal charging curve based on the vehicle's historical charging data, using a preset battery life prediction model and a preset optimization search algorithm. An optimized charging map is then generated based on this optimal charging curve. Based on the optimized charging map and the current battery health status value, a current charging strategy is determined, and the vehicle is charged according to this strategy. Therefore, by calculating the optimal charging curve based on historical vehicle charging data, the method solves the problem that existing standard charging maps cannot dynamically adjust according to the actual aging state of the battery and the vehicle's operating conditions, leading to safety hazards during fast charging. This extends battery life, reduces internal heat buildup during fast charging, and improves battery safety.

[0012] To achieve the above objectives, a second aspect of this application provides a vehicle-side charging device, comprising: The acquisition module is used to acquire the historical charging data and current battery health status value of the current vehicle; The generation module is used to calculate the optimal charging curve based on the historical charging data, using a preset battery life prediction model and a preset optimization search algorithm, and generate an optimized charging MAP based on the optimal charging curve. The determination module is used to determine the current charging strategy based on the optimized charging MAP and the current battery health status value, and to charge the current vehicle based on the current charging strategy.

[0013] According to one embodiment of this application, the generation module is specifically used for: Based on the optimal charging curve, the charging process is evenly divided into multiple preset time steps, and the charging parameters for each preset time step are obtained. Determine at least one battery health state interval to be managed, and calibrate an initial smart MAP for the interval endpoints of each battery health state interval to be managed. Based on each of the battery health status intervals to be managed, the charging parameters for each preset time step are mapped to the corresponding initial smart MAP to generate the optimized charging MAP.

[0014] According to one embodiment of this application, the determining module includes: The first judgment unit is used to determine whether the current battery health status value conforms to any of the battery health status intervals to be managed. The determining unit is configured to determine, from the optimized post-charge MAP, a target battery health state interval corresponding to the current battery health state value when the current battery health state value conforms to any of the battery health state intervals to be managed. The second judgment unit is used to determine whether the current battery health status value is between the interval values ​​of the target battery health status interval to be managed; The calculation unit is used to calculate the target charging parameters corresponding to the current battery health state value using linear interpolation when the current battery health state value is between the end values ​​of the target battery health state range to be managed, and to obtain the current charging strategy based on the target charging parameters.

[0015] According to one embodiment of this application, the second determining unit is further configured to: If the current battery health status value is not within the range of the target battery health status interval to be managed, the target charging parameter is determined based on the range of the target battery health status interval to be managed, and the current charging strategy is obtained based on the target charging parameter.

[0016] According to one embodiment of this application, after generating the optimized charging MAP from the optimal charging curve, the generation module is further configured to: Determine if there is a pre-defined charging map update requirement; If there is a preset charging MAP update requirement, at least one smart MAP in the optimized charging MAP is updated to obtain at least one updated smart MAP.

[0017] According to one embodiment of this application, before calculating the optimal charging curve using the preset battery life prediction model and the preset optimization search algorithm, the charging module is further configured to: Acquire historical charging datasets, actual battery life data, and battery health status values ​​corresponding to each historical charging process for multiple target vehicles, wherein the historical charging datasets are charging data for multiple historical charging processes for each target vehicle; Target data is obtained based on the historical charging datasets of the multiple target vehicles, the actual battery lifespan data, and the battery health status value corresponding to each historical charging process of each target vehicle. The target data is preprocessed, and the preprocessed target data is divided into a training set and a validation set; The preset neural network is trained using the training set to obtain an initial neural network model, and the initial neural network model is verified using the validation set until the initial neural network model meets the preset criteria. Then, the iterative training of the preset neural network ends to obtain the preset battery life prediction model. Otherwise, the hyperparameters of the model are adjusted and iterative training continues.

[0018] The vehicle-side charging device proposed in this application calculates the optimal charging curve based on the vehicle's historical charging data, using a preset battery life prediction model and a preset optimization search algorithm. An optimized charging map is then generated based on this optimal charging curve. Based on the optimized charging map and the current battery health status value, a current charging strategy is determined, and the vehicle is charged according to this strategy. Therefore, by calculating the optimal charging curve based on the vehicle's historical charging data, the problem of existing standard charging maps being unable to dynamically adjust according to the actual aging state of the battery and the vehicle's operating conditions, leading to safety hazards during fast charging, is solved. This extends battery life, reduces internal heat buildup during fast charging, and improves battery safety.

[0019] To achieve the above objectives, a third aspect of this application provides a vehicle comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle-side charging method as described in the above embodiments.

[0020] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the vehicle-side charging method as described in the above embodiments.

[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a vehicle-side charging method provided according to an embodiment of this application; Figure 2 This is a schematic diagram illustrating data transmission via vehicle-to-cloud connectivity according to an embodiment of this application; Figure 3 This is a schematic diagram of a smart MAP according to an embodiment of this application; Figure 4 This is a block diagram of a vehicle-side charging device provided according to an embodiment of this application; Figure 5 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following description, with reference to the accompanying drawings, outlines a vehicle-side charging method, apparatus, vehicle, and storage medium according to embodiments of this application. First, the vehicle-side charging method according to embodiments of this application will be described with reference to the accompanying drawings.

[0025] Figure 1 This is a flowchart of a vehicle-side charging method according to an embodiment of this application.

[0026] For example, such as Figure 1 As shown, the vehicle-side charging method includes the following steps: In step S101, the historical charging data and current battery health status value of the current vehicle are obtained.

[0027] Understandably, each charge generates a large amount of data (charging data) during vehicle use, including battery voltage, current, temperature, battery health status, charging time, charging power, charging cycle, charging environmental parameters, charging fault information, and battery status at the end of charging. This data is recorded and stored by the vehicle's Battery Management System (BMS), forming the vehicle's historical charging data to reflect the battery's actual performance under different operating conditions. Meanwhile, the State of Health (SOH) is a crucial indicator of battery performance, reflecting the ratio of the battery's current actual capacity to its rated capacity, usually expressed as a percentage. A higher SOH value indicates that the battery performance is closer to that of a new battery; a lower SOH value indicates a higher degree of battery aging. Therefore, by acquiring the vehicle's historical charging data and current battery health value, fundamental information can be provided for optimizing subsequent charging strategies.

[0028] In step S102, based on historical charging data, the optimal charging curve is calculated using a preset battery life prediction model and a preset optimization search algorithm, and an optimized charging MAP is generated based on the optimal charging curve.

[0029] Understandably, the preset battery life prediction model is a mathematical model built upon the battery's physicochemical characteristics, aging mechanism, and historical charging data. This model can predict the battery's lifespan trend under different charging strategies. By inputting historical charging data into the preset battery life prediction model, it's possible to analyze which factors (such as charging rate and charging temperature) have a significant impact on battery life during past charging processes, thus enabling battery life prediction under different charging conditions, for example, predicting the remaining battery life under a certain charging strategy. The preset optimization search algorithm, based on the preset battery life prediction model, uses mathematical optimization methods to find the optimal charging curve. The algorithm aims to maximize battery lifespan and improve battery safety while ensuring charging efficiency. The algorithm's input includes the output of the preset battery life prediction simulation model and some constraints, such as charging time, charging power, and battery temperature. The algorithm's output is the optimal charging curve, which, under given constraints, represents the charging current and voltage changes over time that maximize battery lifespan. By comprehensively considering factors such as battery temperature rise, degradation boundary, and lithium plating safety boundary, an optimal charging curve is found through iterative calculations under the constraints of the current battery health state and historical charging data. The optimal charging curve defines the changes in charging current and voltage over time under different battery states and charging conditions. Specifically, the curve can include the following parameters: charging current (I), the charging current value changing over time; charging voltage (V), the charging voltage value changing over time; time (t), the time axis of the charging process; battery temperature (T), the battery temperature during charging; and battery state of health (SOH), the battery's health state, usually expressed as a percentage.

[0030] Furthermore, after obtaining the optimal charging curve, it can be transformed into a specific charging parameter mapping table (i.e., the optimized charging MAP). A MAP is a multi-dimensional parameter table that can include the following dimensions: State of Health (SOH) of the battery, charging strategies under different health states; charging stages, different stages of the charging process (such as constant current charging, constant voltage charging, etc.); and time step, time division points of the charging process. Each dimension combination corresponds to a set of charging parameters. It specifies the specific values ​​of parameters such as charging current and voltage under different battery states and operating conditions. The optimized charging MAP can guide the vehicle to charge according to the optimal charging curve during the charging process, thereby achieving refined battery management.

[0031] To facilitate understanding, the following details how to generate an optimized charging MAP based on the optimal charging curve.

[0032] As one possible implementation, in some embodiments, generating an optimized charging MAP based on the optimal charging curve includes: dividing the charging process evenly into multiple preset time steps based on the optimal charging curve, and obtaining the charging parameters for each preset time step; determining at least one battery health state interval to be managed, and calibrating an initial smart MAP for the interval endpoints of each battery health state interval to be managed; and mapping the charging parameters for each preset time step to the corresponding initial smart MAP based on each battery health state interval to be managed, thereby generating an optimized charging MAP.

[0033] Specifically, based on the optimal charging curve, the entire charging process can be divided along a time dimension. That is, the entire charging process from start to finish is evenly divided into multiple preset time steps (e.g., every 5 minutes or every 10 minutes). Within each time step, charging parameters (including charging current, charging voltage, and battery health status) may vary according to the requirements of the optimal charging curve. In this way, the complex charging process can be decomposed into multiple small, easily managed and controlled stages. For example, the optimal charging curve may require a higher charging current in the early stages of charging to quickly increase battery capacity, while reducing the charging current in the middle and later stages to avoid overcharging and accelerated battery aging. By dividing the process into time steps, the charging parameters for each stage can be accurately obtained, thereby achieving fine-grained control of the charging process. These charging parameters will serve as the basis for generating the optimized charging MAP.

[0034] Since a higher State of Health (SOH) value indicates that the battery performance is closer to that of a new battery, several health state intervals need to be defined to better adapt to the charging requirements of the battery under different health states. For example, the interval with SOH ≥ 80% can be divided into several sub-intervals, such as [95%, 100%], [90%, 95%), [85%, 90%), [80%, 85%), etc. For each health state interval to be managed, an initial intelligent MAP can be calibrated for the interval's endpoints (i.e., the upper and lower limits of the interval). These initial intelligent MAPs are generated based on the battery's optimal charging curve within that health state interval, reflecting the battery's optimal charging parameters within that interval. For example, for the interval with SOH ≥ 80%, an initial intelligent MAP is calibrated every 5% (calibrated value) of SOH, namely MAP0 (corresponding to 80%), MAP1 (corresponding to 85%), MAP2 (corresponding to 90%), MAP3 (corresponding to 95%), and MAP4 (corresponding to 100%). These initial intelligent MAPs can provide targeted charging strategies for batteries in different health states. The initial intelligent MAP (MAP0~MAP4) can be used as the initial charging current parameters preset when the vehicle leaves the factory and stored in the non-volatile memory FLASH for the initial charging strategy of the vehicle.

[0035] To achieve dynamic optimization of the charging strategy, embodiments of this application can also modify (update) the initial smart MAPs (MAP0~MAP4) stored in FLASH, such as... Figure 2 As shown, through vehicle-to-cloud connectivity, the cloud can perform one-to-one correction (update) of the initial smart MAP based on historical charging data and battery health status transmitted from the vehicle, resulting in EEMAP0~EEMAP4, as follows. Figure 3 As shown, the corrected (updated) EEMAP0~EEMAP4 are then downloaded to the vehicle's EEPROM (Electrically Erasable Programmable Read-Only Memory) for storage. During system initialization, the initial values ​​of EEMAP0~EEMAP4 in the EEPROM are exactly the same as those in the FLASH memory. As the vehicle is used and charging data accumulates, the cloud can dynamically correct (update) these EEMAPs (EEMAP0~EEMAP4) based on the vehicle's historical charging data and battery health status. At this point, the corrected (updated) EEMAP0~EEMAP4 constitute the latest optimized charging MAP.

[0036] Optionally, during the one-to-one correction (update) of the initial smart MAP, after determining the initial smart MAP corresponding to each battery health state interval and its interval endpoints, the charging parameters for each preset time step can be mapped to the corresponding initial smart MAP. That is, the charging parameters for each preset time step calculated based on the optimal charging curve, combined with the battery's current state of health (SOH), are used to find the corresponding initial smart MAP, and these charging parameters are stored in that initial smart MAP, thus obtaining the corrected (updated) EEMAP. For example, assuming the battery's current SOH is 90%, the charging parameters of the initial smart MAP2 can be corrected (updated). If the optimal charging curve has a charging current of 10A and a voltage of 3.5V within a certain preset time step, then these parameters will be mapped to the corresponding time step position in the initial smart MAP2, resulting in the corrected (updated) EEMAP2.

[0037] In step S103, based on the optimized charging MAP and the current battery health status value, the current charging strategy is determined, and the current vehicle is charged based on the current charging strategy.

[0038] In other words, the optimized charging MAP and the current battery health status are key factors in determining the current charging strategy. Ultimately, the vehicle's battery management system can control parameters such as current and voltage during the charging process based on the determined current charging strategy to achieve vehicle charging. This approach not only extends battery life but also improves charging safety and efficiency, providing users with a superior charging experience.

[0039] As one possible implementation, in some embodiments, the current charging strategy is determined based on the optimized charging MAP and the current battery health state value, including: determining whether the current battery health state value conforms to any managed battery health state interval; if the current battery health state value conforms to any managed battery health state interval, determining the target managed battery health state interval corresponding to the current battery health state value from the optimized post-charging MAP; determining whether the current battery health state value is between the interval endpoints of the target managed battery health state interval; if the current battery health state value is between the interval endpoints of the target managed battery health state interval, then using linear interpolation to calculate the target charging parameters corresponding to the current battery health state value, and obtaining the current charging strategy based on the target charging parameters.

[0040] Specifically, during vehicle charging, when determining the current charging strategy, the first step is to check if the current battery health status value falls within any managed battery health status interval (i.e., any sub-interval of SOH ≥ 80%). If the current battery health status value does not fall within any managed battery health status interval (i.e., SOH < 80%), then the default charging strategy (such as the standard fast charging MAP strategy) can be used to charge the vehicle. If the current battery health status value falls within one of the managed battery health status intervals (i.e., SOH ≥ 80%), after determining the corresponding target managed battery health status interval, it can be further determined whether the current battery health status value is located between the endpoints of that interval. For example, assuming the current battery health status value is 92%, it indicates that the current battery health status value is between the endpoints of the target managed battery health status interval [90%, 95%). Since there is no directly corresponding smart MAP for the battery health status value of 92%, linear interpolation can be used to calculate the target charging parameters corresponding to the current battery health status value.

[0041] For example, regarding the calculation of charging current, MAP2 corresponds to a charging current of 8A with a state of health (SOH) of 90%, and MAP3 corresponds to a charging current of 10A with a SOH of 95%. Given a current battery health status of 92%, the charging current corresponding to 92% can be calculated using linear interpolation. Target charging current = MAP1 charging current + (current battery health status value - upper limit SOH value of the target battery health status range) / (lower limit SOH value of the target battery health status range - upper limit SOH value of the target battery health status range) × (MAP2 charging current - MAP1 charging current); That is, the target charging current = 10A + (92% - 95%) / (95% - 90%) × (8A - 10A) = 10A + (-3%) / (5%) × (-2A) = 10A + 1.2A = 8.8A.

[0042] Therefore, through the above calculations, the target charging current corresponding to the current battery health status (92%) is 8.8A. Similarly, other charging parameters (such as charging voltage) can be calculated.

[0043] Ultimately, based on these target charging parameters, a current charging strategy can be determined, and the vehicle can be charged according to this strategy. By dynamically adjusting charging parameters according to the actual health status of the battery, battery life can be extended, and charging safety and efficiency can be improved.

[0044] Optionally, in other embodiments, after determining whether the current battery health status value is within the range of the endpoints of the target battery health status range, the method further includes: if the current battery health status value is not within the range of the endpoints of the target battery health status range, then determining the target charging parameters based on the endpoints of the target battery health status range, and obtaining the current charging strategy based on the target charging parameters.

[0045] In other words, if the current battery health status value meets one of the managed battery health status intervals (i.e., SOH ≥ 80%), after determining the corresponding target managed battery health status interval, it is further determined whether the current battery health status value is within the interval's endpoints. For example, assuming the current battery health status value is 90%, indicating that the current battery health status value is not within the endpoints of the target managed battery health status interval [90%, 95%), then the intelligent MAP corresponding to the current battery health status value of 90% can be directly obtained. That is, the charging parameters corresponding to MAP2 are used as the target charging parameters to determine the current charging strategy and charge the vehicle according to this strategy.

[0046] Furthermore, in some embodiments, after generating the optimized charging MAP from the optimal charging curve, the method further includes: determining whether there is a preset charging MAP update requirement; if there is a preset charging MAP update requirement, updating at least one smart MAP in the optimized charging MAP to obtain at least one updated smart MAP.

[0047] Understandably, during vehicle use, the battery's state changes over time and with the number of charge / discharge cycles. Furthermore, the vehicle's operating environment (such as temperature and charging frequency) also affects battery performance. Therefore, it's necessary to periodically assess whether there's a need to update the charging map (i.e., a pre-defined charging map update requirement). The criteria for determining this update requirement can include current vehicle usage (such as mileage, number of charges, charging duration, and ambient temperature), changes in battery state (i.e., changes in battery health), and historical charging data. If a pre-defined charging map update requirement is identified, at least one smart map (EEMAP0~EEMAP4) in the optimized charging map can be updated based on the latest vehicle usage and battery state data. That is, all EEMAP0, EEMAP1, EEMAP2, EEMAP3, and EEMAP4 can be updated, or any single EEMAPi can be updated, resulting in at least one updated smart map.

[0048] Specifically, such as Figure 2 As shown, the TBOX (Telematics Box, Vehicle Communication Terminal) is the interface between the vehicle and the cloud. Currently, the vehicle can upload its usage and battery status data to the cloud via the TBOX, and receive commands and data from the cloud. After receiving the data from the vehicle, the cloud can use a preset battery life prediction model and a preset optimization search algorithm, combined with the vehicle's historical charging data, to recalculate the optimal charging curve and generate a new smart MAP. The cloud then downloads the new smart MAP to the vehicle's EEPROM, replacing the original EEPROM. After the update, the vehicle's BMS can read the updated smart MAP from the EEPROM and execute charging control based on the charging parameters in the MAP. The updated smart MAP can better adapt to the current state of the battery, achieving fast charging while protecting the battery.

[0049] To make it easier to understand, the following explains in detail how to obtain the preset battery life prediction model.

[0050] Furthermore, in some embodiments, before calculating the optimal charging curve using a preset battery life prediction model and a preset optimization search algorithm, the method further includes: acquiring historical charging datasets of multiple target vehicles, actual battery life data, and battery health status values ​​corresponding to each historical charging process of each target vehicle, wherein the historical charging dataset is the charging data of multiple historical charging processes for each target vehicle; obtaining target data based on the historical charging datasets of multiple target vehicles, actual battery life data, and battery health status values ​​corresponding to each historical charging process of each target vehicle; preprocessing the target data and dividing the preprocessed target data into a training set and a validation set; training a preset neural network using the training set to obtain an initial neural network model, and validating the initial neural network model using the validation set until the initial neural network model meets a preset standard, ending the iterative training of the preset neural network to obtain the preset battery life prediction model; otherwise, adjusting the hyperparameters of the model and continuing iterative training.

[0051] The target vehicle refers to the vehicle participating in the data collection. The historical charging dataset contains detailed charging data for each target vehicle across multiple historical charging processes (such as charging start and end times; charging current, voltage, and power; ambient temperature during charging; charging duration; battery temperature changes during charging, etc.). This data is typically recorded by the vehicle's Battery Management System (BMS) and uploaded to the cloud via the Onboard Module Box (TBOX). Actual battery lifespan data refers to the time or number of cycles from when the battery is put into use until its performance degrades to the point where it can no longer meet usage requirements (e.g., capacity falls below 80% of rated capacity).

[0052] Specifically, historical charging datasets, actual battery lifespan data, and State of Health (SOH) values ​​from multiple target vehicles are matched and integrated to obtain target data for subsequent model training and validation. Then, the target data undergoes preprocessing (e.g., outlier removal, missing value imputation, and data format standardization), and is divided into training and validation sets. Subsequently, a pre-defined neural network is trained using the training set, and the network weights are adjusted via backpropagation to enable the model to predict battery lifespan. The performance of the initial neural network model is evaluated using the validation set to ensure good performance even on unseen data. If the initial neural network model's performance on the validation set does not meet the pre-defined criteria, hyperparameters are adjusted, and the model is retrained and validated. Training ends when the model's performance on the validation set meets the pre-defined criteria, resulting in the pre-defined battery lifespan prediction model. Thus, in this way, a model capable of accurately predicting battery lifespan can be obtained, providing a basis for subsequent charging strategy optimization.

[0053] The vehicle-side charging method proposed in this application calculates the optimal charging curve based on the vehicle's historical charging data, using a preset battery life prediction model and a preset optimization search algorithm. An optimized charging map is then generated based on this optimal charging curve. Based on the optimized charging map and the current battery health status value, a current charging strategy is determined, and the vehicle is charged according to this strategy. Therefore, by calculating the optimal charging curve based on historical vehicle charging data, the method solves the problem that existing standard charging maps cannot dynamically adjust according to the actual aging state of the battery and the vehicle's operating conditions, leading to safety hazards during fast charging. This extends battery life, reduces internal heat buildup during fast charging, and improves battery safety.

[0054] Next, the vehicle-side charging device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0055] Figure 4 This is a block diagram of a vehicle-side charging device according to an embodiment of this application.

[0056] like Figure 4 As shown, the vehicle-side charging device 10 includes: an acquisition module 100, a generation module 200, and a determination module 300.

[0057] Among them, the acquisition module 100 is used to acquire the historical charging data and current battery health status value of the current vehicle; The generation module 200 is used to calculate the optimal charging curve based on historical charging data, using a preset battery life prediction model and a preset optimization search algorithm, and generate an optimized charging MAP based on the optimal charging curve. The determination module 300 is used to determine the current charging strategy based on the optimized charging MAP and the current battery health status value, and to charge the current vehicle based on the current charging strategy.

[0058] Optionally, in some embodiments, the generation module 200 is specifically used for: Based on the optimal charging curve, the charging process is evenly divided into multiple preset time steps, and the charging parameters for each preset time step are obtained. Identify at least one health state interval of the battery to be managed, and label an initial smart MAP for the interval endpoints of each health state interval of the battery to be managed. Based on the health status range of each battery to be managed, the charging parameters of each preset time step are mapped to the corresponding initial smart MAP to generate an optimized charging MAP.

[0059] Optionally, in some embodiments, the determining module 300 includes: The first judgment unit is used to determine whether the current battery health status value conforms to any health status interval of the battery to be managed. The determining unit is used to determine the target battery health state interval corresponding to the current battery health state value from the optimized post-charge MAP, provided that the current battery health state value meets any battery health state interval to be managed. The second judgment unit is used to determine whether the current battery health status value is between the interval values ​​of the target battery health status range to be managed; The calculation unit is used to calculate the target charging parameters corresponding to the current battery health state value by using linear interpolation when the current battery health state value is between the end values ​​of the target battery health state range to be managed, and to obtain the current charging strategy based on the target charging parameters.

[0060] Optionally, in some embodiments, the second determining unit is further configured to: If the current battery health status value is not within the range of the target battery health status interval, the target charging parameters are determined based on the range of the target battery health status interval, and the current charging strategy is obtained based on the target charging parameters.

[0061] Optionally, in some embodiments, after generating the optimized charging MAP from the optimal charging curve, the generation module 200 is further configured to: Determine if there is a pre-defined charging map update requirement; If there is a preset charging MAP update requirement, at least one smart MAP in the optimized charging MAP is updated to obtain at least one updated smart MAP.

[0062] According to one embodiment of this application, before calculating the optimal charging curve using a preset battery life prediction model and a preset optimization search algorithm, the charging module is further configured to: Acquire historical charging datasets, actual battery life data, and battery health status values ​​for each historical charging process of each target vehicle for multiple target vehicles. The historical charging dataset contains charging data for multiple historical charging processes of each target vehicle. Target data is obtained based on historical charging datasets of multiple target vehicles, actual battery life data, and battery health status values ​​corresponding to each historical charging process of each target vehicle. The target data is preprocessed, and the preprocessed target data is divided into training set and validation set; The initial neural network model is obtained by training the preset neural network using the training set, and the initial neural network model is verified using the validation set until the initial neural network model meets the preset criteria. Then the iterative training of the preset neural network ends and the preset battery life prediction model is obtained. Otherwise, the hyperparameters of the model are adjusted and iterative training continues.

[0063] It should be noted that the foregoing explanation of the vehicle-side charging method embodiment also applies to the vehicle-side charging device of this embodiment, and will not be repeated here.

[0064] The vehicle-side charging device proposed in this application calculates the optimal charging curve based on the vehicle's historical charging data, using a preset battery life prediction model and a preset optimization search algorithm. An optimized charging map is then generated based on this optimal charging curve. Based on the optimized charging map and the current battery health status value, a current charging strategy is determined, and the vehicle is charged according to this strategy. Therefore, by calculating the optimal charging curve based on the vehicle's historical charging data, the problem of existing standard charging maps being unable to dynamically adjust according to the actual aging state of the battery and the vehicle's operating conditions, leading to safety hazards during fast charging, is solved. This extends battery life, reduces internal heat buildup during fast charging, and improves battery safety.

[0065] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0066] When the processor 502 executes the program, it implements the vehicle-side charging method provided in the above embodiments.

[0067] Furthermore, the vehicle also includes: Communication interface 503 is used for communication between memory 501 and processor 502.

[0068] The memory 501 is used to store computer programs that can run on the processor 502.

[0069] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0070] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0071] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0072] The processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0073] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described vehicle-side charging method.

[0074] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0075] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0076] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle-side charging method, characterized in that, Includes the following steps: Obtain the vehicle's historical charging data and current battery health status value; Based on the historical charging data, the optimal charging curve is calculated using a preset battery life prediction model and a preset optimization search algorithm, and an optimized charging MAP is generated based on the optimal charging curve. Based on the optimized charging MAP and the current battery health status value, a current charging strategy is determined, and the current vehicle is charged based on the current charging strategy.

2. The method according to claim 1, characterized in that, The process of generating an optimized charging MAP based on the optimal charging curve includes: Based on the optimal charging curve, the charging process is evenly divided into multiple preset time steps, and the charging parameters for each preset time step are obtained. Determine at least one battery health state interval to be managed, and calibrate an initial smart MAP for the interval endpoints of each battery health state interval to be managed. Based on each of the battery health status intervals to be managed, the charging parameters for each preset time step are mapped to the corresponding initial smart MAP to generate the optimized charging MAP.

3. The method according to claim 2, characterized in that, The step of determining the current charging strategy based on the optimized charging MAP and the current battery health status value includes: Determine whether the current battery health status value conforms to any of the battery health status intervals to be managed; If the current battery health status value meets any of the battery health status intervals to be managed, a target battery health status interval corresponding to the current battery health status value is determined from the optimized post-charge MAP. Determine whether the current battery health status value is within the range of the target battery health status interval to be managed; If the current battery health status value is within the range of the target battery health status interval, then the target charging parameters corresponding to the current battery health status value are calculated using linear interpolation, and the current charging strategy is obtained based on the target charging parameters.

4. The method according to claim 3, characterized in that, After determining whether the current battery health status value is within the range of the target battery health status interval to be managed, the method further includes: If the current battery health status value is not within the range of the target battery health status interval, then the target charging parameter is determined based on the range of the target battery health status interval, and the current charging strategy is obtained based on the target charging parameter.

5. The method according to claim 2, characterized in that, After generating the optimized charging MAP from the optimal charging curve, the process further includes: Determine if there is a pre-defined charging map update requirement; If there is a preset charging MAP update requirement, at least one smart MAP in the optimized charging MAP is updated to obtain at least one updated smart MAP.

6. The method according to claim 1, characterized in that, Before calculating the optimal charging curve using the preset battery life prediction model and the preset optimization search algorithm, the process further includes: Acquire historical charging datasets, actual battery life data, and battery health status values ​​corresponding to each historical charging process for multiple target vehicles, wherein the historical charging datasets are charging data for multiple historical charging processes for each target vehicle; Target data is obtained based on the historical charging datasets of the multiple target vehicles, the actual battery lifespan data, and the battery health status value corresponding to each historical charging process of each target vehicle. The target data is preprocessed, and the preprocessed target data is divided into a training set and a validation set; The preset neural network is trained using the training set to obtain an initial neural network model, and the initial neural network model is verified using the validation set until the initial neural network model meets the preset criteria. Then, the iterative training of the preset neural network ends to obtain the preset battery life prediction model. Otherwise, the hyperparameters of the model are adjusted and iterative training continues.

7. A vehicle-mounted charging device, characterized in that, include: The acquisition module is used to acquire the historical charging data and current battery health status value of the current vehicle; The generation module is used to calculate the optimal charging curve based on the historical charging data, using a preset battery life prediction model and a preset optimization search algorithm, and generate an optimized charging MAP based on the optimal charging curve. The determination module is used to determine the current charging strategy based on the optimized charging MAP and the current battery health status value, and to charge the current vehicle based on the current charging strategy.

8. The apparatus according to claim 7, characterized in that, The generation module is specifically used for: Based on the optimal charging curve, the charging process is evenly divided into multiple preset time steps, and the charging parameters for each preset time step are obtained. Determine at least one battery health state interval to be managed, and calibrate an initial smart MAP for the interval endpoints of each battery health state interval to be managed. Based on each of the battery health status intervals to be managed, the charging parameters for each preset time step are mapped to the corresponding initial smart MAP to generate the optimized charging MAP.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle-side charging method as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the vehicle-side charging method as described in any one of claims 1-6.

Images