Vehicle charging control method and system and vehicle

Abstract

The invention provides a vehicle charging control method and system and a vehicle, and the method comprises the steps: obtaining multi-source heterogeneous data of the vehicle, the multi-source heterogeneous data comprising user scene data, vehicle travel data and battery reference state data; respectively inputting the multi-source heterogeneous data into a pre-trained parking time length prediction model and a pre-trained travel demand prediction model, and correspondingly obtaining an expected available charging time length and an estimated minimum required electric quantity; constructing a constraint condition based on the expected available charging duration and the estimated minimum required electric quantity, and solving to obtain a charging power sequence by taking the minimum cumulative aging cost as an optimization target; and executing the charging power sequence to control a charging process of the vehicle. According to the method, the minimum estimated cumulative aging cost is taken as an optimization target, and the stress and aging of the battery in the high charge state can be remarkably reduced, so that the full life cycle of the battery system is prolonged.

Description

Technical Field

[0001] This invention relates to the field of intelligent charging and energy management technology for electric vehicles, specifically to a vehicle charging control method, system, and vehicle. Background Technology

[0002] With the increasing popularity of electric vehicles, achieving efficient, convenient, and battery-life-friendly intelligent charging has become a key aspect of technological development. Current mainstream charging control solutions have the following limitations:

[0003] Some solutions rely on a limited set of pre-defined, fixed charging strategy templates, from which to choose during actual charging. While these methods can adapt to different charging device capabilities, their strategy library is static and cannot generate highly customized charging curves for dynamic scenarios such as the user's next unique travel time and mileage requirements, resulting in insufficient strategy flexibility. Other solutions focus on using real-time sensor data (such as battery temperature) for single-dimensional online adjustments, such as dynamically adjusting power based on charger temperature to balance efficiency and safety. Although these methods have some real-time response capabilities, their optimization dimension is singular, mainly focusing on the instantaneous state of the charging process or device thermal management, without taking "extending the battery's entire lifespan" as a core optimization goal, nor systematically integrating the user's long-term driving habits and future travel intentions. In addition, some solutions focus on improving the physical preparation process before charging (such as battery preheating) to increase charging speed. Their core is to create conditions for fast charging, rather than continuously and dynamically planning power throughout the entire charging cycle based on a function that integrates multiple objectives such as battery health degradation and user time costs.

[0004] In summary, existing technologies have failed to construct an online dynamic optimization framework that proactively integrates predictions of future user scenarios and real-time battery health status, with the explicit mathematical objective of minimizing cumulative battery aging damage. This results in a charging strategy that struggles to achieve true optimal battery lifespan while simultaneously satisfying user convenience. Therefore, there is an urgent need to provide a vehicle charging control method, system, and vehicle that can achieve true optimal battery lifespan while meeting user convenience requirements. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle charging control method, system and vehicle to solve the technical problem in the prior art that the inability to actively integrate the prediction of future user scenarios and the aim of minimizing the cumulative aging damage of the battery leads to a short battery life.

[0006] To address the aforementioned technical problems, in a first aspect, the present invention provides a vehicle charging control method, comprising: Acquire multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data; The multi-source heterogeneous data is input into the pre-trained parking duration prediction model and trip demand prediction model respectively to obtain the expected available charging time and the estimated minimum required power. Based on the expected available charging time and the estimated minimum required power, constraints are constructed, and the charging power sequence is obtained by minimizing the cumulative aging cost as the optimization objective. The charging power sequence is executed to control the charging process of the vehicle.

[0007] In one possible implementation, the user scenario data includes vehicle location, current time, week type, holiday information, in-vehicle calendar schedule, and input temporary trip plan; the vehicle trip data includes historical trip energy consumption data, current remaining range, and maximum available power of the currently connected charging station; the battery baseline status data includes battery health status value, current state of charge, and average battery pack temperature.

[0008] In one possible implementation, the process for determining the expected available charging time is as follows: The multi-source heterogeneous data is input into the parking duration prediction model to obtain the departure time probability distribution; The cumulative probability is determined based on the exit time probability distribution, and the quantile time is determined based on the preset confidence level and the cumulative probability. Calculate the expected value of the probability distribution of the departure time, and take the later of the expected value and the quantile time as the expected available charging time.

[0009] In one possible implementation, the parking duration prediction model is a recurrent neural network model with an embedded attention mechanism, which is used to assign weights to the multi-source heterogeneous data during prediction.

[0010] In one possible implementation, the process for determining the estimated minimum required power is as follows: Determine if the user has set a navigation destination for their next trip; If already set, the baseline energy consumption prediction value is calculated based on the route information provided by the navigation system; If not set, contextual features related to trip prediction are extracted from the multi-source heterogeneous data, and similar trip patterns are matched from historical trip data based on the contextual features. The multi-source heterogeneous data and the matched trip pattern features are input into the trip demand prediction model to obtain the baseline energy consumption prediction value. The sum of the baseline energy consumption prediction and the preset safety margin is taken as the estimated minimum required power consumption.

[0011] In one possible implementation, the constraint is: Power demand constraint: When the vehicle finishes charging, the cumulative charging power is greater than or equal to the estimated minimum required power. Time constraint: The total charging time is less than or equal to the expected available charging time; Battery real-time health constraint: The charging power at any time is less than or equal to the instantaneous maximum allowable power, which refers to the upper limit of the charging power that can be safely applied; Hardware constraints: The charging power is less than or equal to the maximum available power of the charging pile, and the charging current and charging voltage are within the normal operating range.

[0012] In one possible implementation, the method further includes: Obtain the first charging duration, first aging rate, and first charging cost when charging with the current maximum allowed power; Obtain the second charging duration, second aging rate, and second charging cost based on the charging power sequence; The first charging time, the first aging rate, the first charging cost, the second charging time, the second aging rate, and the second charging cost are displayed on the vehicle's infotainment screen. The system responds to the vehicle's infotainment screen's selection command to charge using the current maximum allowed power or to charge based on the charging power sequence, and charges the vehicle using the selected charging method.

[0013] In one possible implementation, the method further includes: The actual parking time, actual power consumption, and battery response data after the vehicle charging process is completed are obtained, and the parking time prediction model, the trip demand prediction model, and the aging quantification model in the optimization objective are iteratively optimized based on the actual parking time, actual power consumption, and battery response data.

[0014] Secondly, the present invention also provides a vehicle charging control system, comprising: The data acquisition unit is used to acquire multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data. The charging time and required power prediction unit is used to input the multi-source heterogeneous data into the pre-trained parking time prediction model and trip demand prediction model respectively, and obtain the expected available charging time and the estimated minimum required power accordingly. The charging power sequence determination unit is used to construct constraints based on the expected available charging time and the estimated minimum required power, and solve for the charging power sequence with the optimization objective of minimizing the cumulative aging cost. A charging control unit is used to execute the charging power sequence to control the charging process of the vehicle.

[0015] Thirdly, the present invention also provides a vehicle, including a processor and a memory, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps of the vehicle charging control method described in any of the above possible implementations.

[0016] The beneficial effects of this invention are as follows: The vehicle charging control method provided by this invention, when solving for the charging power sequence, takes minimizing the estimated cumulative aging cost as the optimization objective, so that each charging plan directly aims to delay battery capacity degradation. Compared with traditional constant power or simple fast charging strategies, it can significantly reduce the stress and aging of the battery under high charge conditions, thereby extending the entire life cycle of the battery system.

[0017] Furthermore, constraints are constructed based on the expected available charging time and estimated minimum required power volume determined by multi-source heterogeneous data. This enables the resulting charging power sequence to predict user demand in advance and accurately, ensuring that the generated charging power sequence can meet the power demand of the user's next trip within the time window set or predicted by the user, fundamentally avoiding the risk of trip interruption due to insufficient charging. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic flowchart of an embodiment of the vehicle charging control method provided by the present invention; Figure 2 A schematic flowchart of an embodiment of the process for determining the expected available charging time provided by the present invention; Figure 3 A schematic flowchart of an embodiment of the process for determining the estimated minimum required power consumption provided by the present invention; Figure 4 This is a schematic flowchart of an embodiment of the present invention that provides an intuitive comparison of different charging strategies; Figure 5 A schematic diagram of an embodiment of the vehicle charging control system provided by the present invention; Figure 6 A schematic diagram of an embodiment of the vehicle provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] It should be understood that the illustrative drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] This invention provides a vehicle charging control method, system, and vehicle, which will be described below.

[0024] Figure 1 This is a schematic flowchart of an embodiment of the vehicle charging control method provided by the present invention, as shown below. Figure 1 As shown, the vehicle charging control method includes: S101. Obtain multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data.

[0025] User scenario data aims to depict vehicle usage scenarios, with the core being understanding user behavior and future intentions. This type of data is used to overcome the static nature of existing technological strategies. For example, without understanding a user's unique schedule and lifestyle, the generated charging strategy can only be a generic, rigid template. Only by integrating user scenarios can truly personalized predictions be achieved, providing a fundamental basis for generating personalized charging power sequences.

[0026] Vehicle trip data is designed to reflect a vehicle's recent energy consumption, current range, and available charging infrastructure. This data is used to establish accurate charging needs and charging capabilities.

[0027] Battery baseline state data is designed to reveal the long-term health status and real-time operating conditions of the battery pack.

[0028] In a specific embodiment of the present invention, user scenario data includes vehicle location, current time, week type, holiday information, in-vehicle calendar schedule, and input temporary trip plan; vehicle trip data includes historical trip energy consumption data, current remaining range, and maximum available power of the currently connected charging pile; battery baseline status data includes battery health status value, current state of charge, and average battery pack temperature.

[0029] Among them, vehicle location refers to the precise geographical location of the vehicle when it is parked and its semantic information (such as home, office, public charging station). The purpose of setting this is that location is one of the strongest features for identifying user parking behavior patterns (for example, parking at home is usually longer, while parking in a shopping mall is shorter), and it is also a key context for inferring the starting point of the next trip, providing a core basis for predicting available charging time and trip destination.

[0030] The current time, day of the week, and holiday information refer to the precise time when charging was initiated, the day of the week, and whether it falls on a public holiday. The purpose of setting this time-related information is to accurately capture the inherent periodicity and rhythm of user car usage behavior. Weekday and weekend travel patterns, as well as early morning and late night travel patterns, are drastically different; this data serves as the fundamental spatiotemporal anchor for building high-precision time series prediction models.

[0031] The in-car calendar schedule refers to the event arrangements in the electronic calendar synchronized with the user. The purpose of this setting is that the calendar represents the user's proactive expression of future intentions, providing highly confident future signals that transcend historical statistical patterns. For example, a "flight" event might directly predict a long-distance trip and an urgent departure time, thus greatly improving the foresight and accuracy of predictions.

[0032] User-input temporary trip plans refer to temporary trip reminders manually added by users through the vehicle's infotainment system or an app. The purpose of this feature is to compensate for temporary and unexpected needs not covered by the fixed calendar, enhance responsiveness to the user's latest intentions, and is an important component of human-computer interaction and decision-making, improving flexibility and reliability.

[0033] Historical trip energy consumption data refers to the actual mileage and average energy consumption of the vehicle during recent driving (especially the most recent one or several trips). The purpose of setting this is to establish an energy consumption baseline specific to each user. Actual energy consumption takes into account personalized factors such as driving habits, road conditions, and air conditioning load. Using this data, rather than the theoretical value of the vehicle model, to predict future demand ensures the accuracy and reliability of energy consumption prediction.

[0034] The remaining driving range refers to the estimated remaining driving distance based on the current battery level. The purpose of setting this parameter is to clarify the starting state of this charging task. Combined with the predicted required energy, the energy difference that needs to be replenished can be accurately calculated, becoming a fundamental input parameter for constructing a charging optimization problem.

[0035] The maximum available power of the currently connected charging station refers to the upper limit of power that the specific charging station currently connected can provide. The purpose of setting this is to define the physical capacity ceiling for this charging process. Any optimized charging power sequence must be subject to this hard constraint to ensure that the planned scheme can be successfully executed in reality.

[0036] The State of Health (SOH) value refers to the percentage of a battery's current usable capacity relative to its initial capacity. It is a comprehensive indicator for measuring the degree of long-term aging and is used to accurately characterize the estimated cumulative aging costs.

[0037] Current state of charge (SBC) refers to the current percentage of battery charge remaining, and is also used to accurately characterize the estimated cumulative aging costs.

[0038] Battery pack temperature refers to the key temperature monitoring value inside the battery pack. The purpose of this setting is that temperature is one of the most critical factors affecting battery safety and aging rate. It directly participates in determining the boundary of the instantaneous maximum permissible power and plays a significant role in the aging model, ensuring that the optimization strategy balances safety and durability under any operating conditions.

[0039] In other words, by acquiring data such as user habits reflecting future scenarios, vehicle energy consumption and range representing real-time status, and battery health defining safety and lifespan boundaries to determine the charging power sequence, not only can each charging plan be highly personalized, but the conflicting goals of ensuring vehicle convenience and extending battery life can also be unified within a quantifiable and solvable mathematical optimization framework. This enables proactive protection of battery health throughout its entire lifecycle while meeting user needs.

[0040] S102. Input the multi-source heterogeneous data into the pre-trained parking duration prediction model and trip demand prediction model respectively to obtain the expected available charging time and the estimated minimum required power.

[0041] In a specific embodiment of the present invention, the parking duration prediction model is a recurrent network model, such as an LSTM model, a Transformer time series encoder, or a Gaussian process regression model. The travel demand prediction model is a gradient boosting decision tree or a gradient boosting machine.

[0042] S103. Based on the expected available charging time and the estimated minimum required power, construct constraints and solve for the charging power sequence with the goal of minimizing the cumulative aging cost.

[0043] Specifically, the optimization objective can be expressed as:

[0044] In the formula, The inputs to the aging cost model are charging current, battery SOC, temperature, and SOH.

[0045] It should be noted that the optimization objective can be solved using algorithms such as Sequential Quadratic Programming (SQP), Dynamic Programming (DP), Interior Point Method, or Simulated Annealing.

[0046] S104. Execute the charging power sequence to control the vehicle's charging process.

[0047] It should be understood that the vehicle charging control method in this embodiment of the invention can be implemented in any device based on a vehicle charging control method, such as a vehicle's battery management system or other vehicle controller. Specifically, the vehicle charging control method is stored in the aforementioned device as a pre-programmed program, and when the device is started, the program is invoked, and the vehicle charging control method is implemented.

[0048] Compared with existing technologies, the vehicle charging control method provided in this invention optimizes the calculation of the charging power sequence by minimizing the estimated cumulative aging cost, ensuring that each charging plan directly aims to delay battery capacity degradation. Compared with traditional constant power or simple fast charging strategies, this significantly reduces battery stress and aging under high charge conditions, thereby extending the entire lifespan of the battery system.

[0049] Furthermore, constraints are constructed based on the expected available charging time and estimated minimum required power volume determined by multi-source heterogeneous data. This enables the resulting charging power sequence to predict user demand in advance and accurately, ensuring that the generated charging power sequence can meet the power demand of the user's next trip within the time window set or predicted by the user, fundamentally avoiding the risk of trip interruption due to insufficient charging.

[0050] The expected available charging time should be determined by the vehicle's departure time, which is essentially a random event. Using a fixed time point for planning is either too risky, leading to insufficient charging, or too conservative, wasting charging time.

[0051] To overcome this technical problem, in some embodiments of the present invention, such as... Figure 2 As shown, the process for determining the expected available charging time is as follows: S201. Input multi-source heterogeneous data into the parking duration prediction model to obtain the probability distribution of departure time; S202. Determine the cumulative probability based on the exit time probability distribution, and determine the quantile time based on the preset confidence level and cumulative probability; S203. Calculate the expected value of the probability distribution of departure time, and take the later of the expected value and the quantile time as the expected available charging time.

[0052] For example, suppose the model predicts the following probability distribution for a vehicle leaving the site within the next 5 hours:

[0053] Its expected value = 1×0.1 + 2×0.2 + 3×0.4 + 4×0.2 + 5×0.1 = 3.0 hours The cumulative probability is:

[0054] If the preset confidence level is 90%, then the quantile time is 4 hours (the minimum time point with a cumulative probability ≥ 0.9).

[0055] At this point, the quantile time of 4 hours is greater than the mathematical expectation of 3 hours, therefore, 4 hours is taken as the expected available charging time.

[0056] The embodiments of the present invention determine the expected available charging time based on mathematical expectation value and quantile time, so that subsequent planning can be based on a time window with confidence information. For example, if a higher quantile time is selected as a conservative planning basis, the risk of insufficient battery power during vehicle use due to prediction deviation is significantly reduced, and the practicality and reliability are improved.

[0057] Since there are many types of multi-source heterogeneous data in the embodiments of the present invention, treating all features equally will lead to a slow response to key mutation signals, thereby reducing prediction accuracy.

[0058] To address this technical problem, in some embodiments of the present invention, the parking duration prediction model is a recurrent neural network model with an embedded attention mechanism, which is used to assign weights to multi-source heterogeneous data during prediction.

[0059] For example, the weight of "flight" events in the in-vehicle calendar should be higher than that of "regular Tuesdays" to focus on features that have a more critical impact on parking duration.

[0060] The embodiments of the present invention can assign higher weights to key features, enabling the prediction model to not only learn general rules but also have the intelligent discrimination ability to handle special cases, thereby improving the accuracy of the expected available charging time and thus improving the precision and situational adaptability of vehicle charging control.

[0061] In practical applications, there are two scenarios: one with a clear destination and one with an unclear destination. To ensure accurate determination of the estimated minimum power requirement in both scenarios, some embodiments of the present invention, such as... Figure 3 As shown, the process for determining the estimated minimum required power is as follows: S301. Determine whether the user has set a navigation destination for the next trip; S302. If already set, the baseline energy consumption prediction value is calculated based on the route information provided by the navigation system. S303. If not set, extract context features related to trip prediction from multi-source heterogeneous data, match similar trip patterns from historical trip data based on context features, and input multi-source heterogeneous data and matched trip pattern features into the trip demand prediction model to obtain the baseline energy consumption prediction value.

[0062] Among them, contextual features include, but are not limited to, time features, location features, and vehicle state features.

[0063] S304. The sum of the baseline energy consumption prediction value and the preset safety margin is used as the estimated minimum required power consumption.

[0064] It should be understood that the safety margin can be set according to the actual application scenario, and no specific limit is made here.

[0065] When the navigation destination is clear, this invention can directly calculate an accurate baseline energy consumption prediction value based on the route information provided by the navigation system, avoiding unnecessary model calculations and ensuring reliable results. When the information is ambiguous, i.e., no navigation destination is set, it uses intelligent inference path based on machine learning to make full use of the context for estimation, ensuring functional continuity. In other words, this invention achieves the goal of accurately determining the estimated minimum power consumption in any usage scenario, ensuring prediction reliability across all scenarios.

[0066] In a specific embodiment of the present invention, the constraints include: Power demand constraint: When the vehicle is fully charged, the total amount of electricity charged must be greater than or equal to the estimated minimum required amount of electricity. Time constraint: Total charging time is less than or equal to the expected available charging time; Battery real-time health constraints: The charging power at any given time is less than or equal to the instantaneous maximum allowable power, which refers to the upper limit of the charging power that can be safely applied; Hardware constraints: The charging power is less than or equal to the maximum available power of the charging pile, and the charging current and charging voltage are within the normal operating range.

[0067] Based on the above constraints, the generated charging power sequence can be made more adaptive. For example: Scenario A (Ample time, average battery health): In this case, the charging power sequence is fast at first and then slows down, with a plateau charging curve. The current drops significantly in the middle, forming a long-term low-stress "plateau period".

[0068] Scenario B (Time is tight, battery health is good): In this case, the charging power sequence allows for maintaining high power for a long time, only ending quickly in the final stage.

[0069] To avoid the problem of users distrusting the vehicle control method proposed in the embodiments of the present invention, leading to implementation obstacles, in some embodiments of the present invention, such as Figure 4 As shown, the vehicle charging control method also includes: S401. Obtain the first charging duration, the first aging rate, and the first charging cost when charging with the current maximum allowed power. S402, Obtain the second charging duration, second aging rate, and second charging cost based on the charging power sequence; S403, Display the first charging time, first aging rate, first charging cost, second charging time, second aging rate, and second charging cost on the vehicle screen; S404 responds to the vehicle's infotainment screen's command to select between charging using the current maximum allowed power and charging based on a charging power sequence, and charges the vehicle using the selected charging method.

[0070] Specifically, the aging rate is determined based on the aging model, the charging cost is determined based on the electricity price and the required electrical energy, and the charging time is determined by the charging power and the required electrical energy.

[0071] It should be noted that, in addition to selecting commands, the vehicle's infotainment screen has a pop-up window where users can fine-tune the charging power sequence for personalized adjustments.

[0072] This invention generates and displays the charging time, charging cost, and aging rate corresponding to two strategies: optimal lifespan and fastest charging time. This transforms the advantages and disadvantages of different technologies into easily understandable time, cost, and lifespan metrics, improving the transparency of decision-making, user acceptance, and scenario adaptability. Users are no longer passively receiving instructions but can make proactive choices (adopt, reject, or fine-tune) based on clear information. This respects the user's autonomy and provides an emergency channel (choosing the fastest charging) for unexpected needs.

[0073] Since battery performance and vehicle performance change dynamically over time, in order to adapt various models to this dynamic change, in some embodiments of the present invention, the vehicle charging control method further includes: The system acquires data on the actual parking time, actual power consumption, and battery response after the vehicle charging process is completed. Based on this data, it iteratively optimizes the parking time prediction model, the trip demand prediction model, and the aging quantification model in the optimization objective.

[0074] The embodiments of the present invention set up dynamic updates for the parking duration prediction model, the trip demand prediction model, and the aging quantification model in the optimization target, so that the entire vehicle charging control method can dynamically adapt to long-term changes in users and vehicles, and maintain prediction accuracy and optimization effect over the long term.

[0075] Specifically, various models can be updated via OTA (Over-The-Air).

[0076] In summary, the vehicle charging control method proposed in this invention constructs a closed-loop process of perception-prediction-optimization-interaction-learning, deeply integrating previously fragmented information such as user behavior, vehicle status, and battery health. This achieves a fundamental leap from fixed strategy selection to dynamic scenario optimization. During each charging cycle, based on accurate predictions of the user's future journey and quantitative assessments of real-time battery health, a personalized flexible charging curve is dynamically generated. This curve, while strictly meeting the constraints of vehicle convenience, aims to minimize the cumulative cost of battery aging. This fundamentally and collaboratively resolves the contradiction in traditional charging strategies—extending battery life and ensuring vehicle usage needs—achieving proactive protection of battery health throughout its entire lifecycle and seamless optimization of a personalized driving experience.

[0077] On the other hand, embodiments of the present invention also provide a vehicle charging control system, such as Figure 5 As shown, the vehicle charging control system 500 includes: The data acquisition unit 501 is used to acquire multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data. The charging time and required power prediction unit 502 is used to input multi-source heterogeneous data into the pre-trained parking time prediction model and trip demand prediction model respectively, and obtain the expected available charging time and the estimated minimum required power accordingly. The charging power sequence determination unit 503 is used to construct constraints based on the expected available charging time and the estimated minimum required power, and to solve for the charging power sequence with the optimization objective of minimizing the cumulative aging cost. The charging control unit 504 is used to execute a charging power sequence to control the charging process of the vehicle.

[0078] The vehicle charging control system 500 provided in the above embodiments can realize the technical solutions described in the above vehicle charging control method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above vehicle charging control method embodiments, and will not be repeated here.

[0079] like Figure 6 As shown, the present invention also provides a vehicle 600. The vehicle 600 includes a processor 601, a memory 602, and a display 603. Figure 6 Only some components of vehicle 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0080] In some embodiments, processor 601 may be a microcontroller in a vehicle, used to run program code stored in memory 602 or process data, such as the vehicle charging control method of the present invention.

[0081] In some embodiments, memory 602 may be an internal storage unit of vehicle 600, such as a hard disk or memory of vehicle 600. In other embodiments, memory 602 may also be an external storage device of vehicle 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on vehicle 600.

[0082] Furthermore, the memory 602 may include both internal storage units of the vehicle 600 and external storage devices. The memory 602 is used to store application software and various types of data installed on the vehicle 600.

[0083] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 603 is used to display information about vehicle 600 and to display a visual user interface. Components 601-603 of vehicle 600 communicate with each other via a device bus.

[0084] In some embodiments of the present invention, when the processor 601 executes the vehicle charging control program in the memory 602, the following steps can be implemented: Acquire multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data; Multi-source heterogeneous data are input into pre-trained parking duration prediction models and trip demand prediction models respectively to obtain the expected available charging time and the estimated minimum required power. Based on the expected available charging time and the estimated minimum required power, constraints are constructed, and the charging power sequence is obtained by minimizing the cumulative aging cost as the optimization objective. Execute a charging power sequence to control the vehicle's charging process.

[0085] It should be understood that when the processor 601 executes the base vehicle charging control program in the memory 602, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0086] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0087] The present invention has provided a detailed description of a vehicle charging control method, system, and vehicle. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A vehicle charging control method, characterized in that, include: Acquire multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data; The multi-source heterogeneous data is input into the pre-trained parking duration prediction model and trip demand prediction model respectively to obtain the expected available charging time and the estimated minimum required power. Based on the expected available charging time and the estimated minimum required power, constraints are constructed, and the charging power sequence is obtained by minimizing the cumulative aging cost as the optimization objective. The charging power sequence is executed to control the charging process of the vehicle.

2. The vehicle charging control method according to claim 1, characterized in that, The user scenario data includes vehicle location, current time, week type, holiday information, in-vehicle calendar schedule, and input temporary travel plans; The vehicle trip data includes historical trip energy consumption data, current remaining driving range, and the maximum available power of the currently connected charging station; the battery baseline status data includes battery health status value, current state of charge, and average battery pack temperature.

3. The vehicle charging control method according to claim 1, characterized in that, The process for determining the expected available charging time is as follows: The multi-source heterogeneous data is input into the parking duration prediction model to obtain the departure time probability distribution; The cumulative probability is determined based on the exit time probability distribution, and the quantile time is determined based on the preset confidence level and the cumulative probability. Calculate the expected value of the probability distribution of the departure time, and take the later of the expected value and the quantile time as the expected available charging time.

4. The vehicle charging control method according to claim 1 or 3, characterized in that, The parking duration prediction model is a recurrent neural network model with an embedded attention mechanism, which is used to assign weights to the multi-source heterogeneous data during prediction.

5. The vehicle charging control method according to claim 1, characterized in that, The process for determining the estimated minimum required power is as follows: Determine if the user has set a navigation destination for their next trip; If already set, the baseline energy consumption prediction value is calculated based on the route information provided by the navigation system; If not set, contextual features related to trip prediction are extracted from the multi-source heterogeneous data, and similar trip patterns are matched from historical trip data based on the contextual features. The multi-source heterogeneous data and the matched trip pattern features are input into the trip demand prediction model to obtain the baseline energy consumption prediction value. The sum of the baseline energy consumption prediction and the preset safety margin is taken as the estimated minimum required power consumption.

6. The vehicle charging control method according to claim 1, characterized in that, The constraints include: Power demand constraint: When the vehicle finishes charging, the cumulative charging power is greater than or equal to the estimated minimum required power. Time constraint: The total charging time is less than or equal to the expected available charging time; Battery real-time health constraint: The charging power at any time is less than or equal to the instantaneous maximum allowable power, which refers to the upper limit of the charging power that can be safely applied; Hardware constraints: The charging power is less than or equal to the maximum available power of the charging pile, and the charging current and charging voltage are within the normal operating range.

7. The vehicle charging control method according to claim 1, characterized in that, The method further includes: Obtain the first charging duration, first aging rate, and first charging cost when charging with the current maximum allowed power; Obtain the second charging duration, second aging rate, and second charging cost based on the charging power sequence; The first charging time, the first aging rate, the first charging cost, the second charging time, the second aging rate, and the second charging cost are displayed on the vehicle's infotainment screen. The system responds to the vehicle's infotainment screen's selection command to charge using the current maximum allowed power or to charge based on the charging power sequence, and charges the vehicle using the selected charging method.

8. The vehicle charging control method according to claim 1, characterized in that, The method further includes: The actual parking time, actual power consumption, and battery response data after the vehicle charging process is completed are obtained, and the parking time prediction model, the trip demand prediction model, and the aging quantification model in the optimization objective are iteratively optimized based on the actual parking time, actual power consumption, and battery response data.

9. A vehicle charging control system, characterized in that, include: The data acquisition unit is used to acquire multi-source heterogeneous data of the vehicle, including user scenario data, vehicle trip data and battery baseline state data. The charging time and required power prediction unit is used to input the multi-source heterogeneous data into the pre-trained parking time prediction model and trip demand prediction model respectively, and obtain the expected available charging time and the estimated minimum required power accordingly. The charging power sequence determination unit is used to construct constraints based on the expected available charging time and the estimated minimum required power, and solve for the charging power sequence with the optimization objective of minimizing the cumulative aging cost. A charging control unit is used to execute the charging power sequence to control the charging process of the vehicle.

10. A vehicle, characterized in that, Including processor and memory, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps of the vehicle charging control method according to any one of claims 1 to 8.

Images