Vehicle endurance management method, device, storage medium and system
By collecting and analyzing data in the vehicle endurance management system, using machine learning algorithms to predict charging demand, and realizing energy sharing between vehicles through wireless energy transmission, the problems of single energy management strategies and prediction deviation in the existing technology are solved, and electric power is improved The car's endurance and charging efficiency.
Patent Information
- Application Number
- CN202410911270.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-09
AI Technical Summary
The existing vehicle endurance management system cannot fully collect and analyze users' driving behavior, charging history and real-time road conditions data, resulting in a single and limited energy management strategy, unable to adapt to complex and changeable actual use environments, and the charging demand forecast deviation is large, which affects the impact of The effectiveness of charging strategies.
Through vehicle sensors and Internet of Vehicles, historical charging data, real-time power status and user behavior data are collected, machine learning algorithms are used to predict charging demand, and energy sharing between vehicles is realized through wireless energy transmission technology, and charging scheduling and energy distribution strategies are dynamically adjusted. Combining the charging station status, vehicle power and driving paths, we generate the optimal charging and energy distribution strategy.
It realizes accurate prediction and energy management of vehicle charging needs, extends range, improves charging efficiency and energy utilization efficiency, reduces user waiting time, and improves the overall endurance and operational efficiency of electric vehicles.
Smart Images

Figure CN118469249B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle range storage management, and in particular to a vehicle range management method, device, storage medium and system. Background Art
[0002] With the widespread use of electric vehicles around the world, how to effectively manage the battery life of electric vehicles has become an urgent problem to be solved. During the driving process, electric vehicles often have insufficient battery life due to limited battery capacity, imperfect charging facilities and uneven energy consumption.
[0003] Existing vehicle endurance management systems mainly rely on the on-board battery management system (BMS) for power monitoring. This method cannot fully collect and analyze data such as user driving behavior, charging history, and real-time road conditions, resulting in a single and limited energy management strategy that cannot adapt to the complex and changing actual usage environment.
[0004] Existing charging demand prediction methods are usually based on simple historical data analysis, which cannot accurately capture the dynamic characteristics of user behavior and environmental changes, resulting in large deviations in prediction results and affecting the effectiveness of charging strategies. In addition, when charging station resources are limited, the charging scheduling strategies in the existing technology lack intelligence and dynamic adjustment capabilities and cannot be optimized according to real-time needs. Based on this, a new vehicle endurance management method, device, storage medium and system are proposed. Summary of the invention
[0005] To achieve the above object, the present invention provides the following solution: a vehicle endurance management method, comprising the following management steps:
[0006] Step a: The vehicle's historical charging data, real-time power status, and user behavior data are collected through on-board sensors and the Internet of Vehicles system. The vehicle's charging demand is predicted using a machine learning algorithm to generate a predicted value for future charging demand. The charging schedule is dynamically adjusted based on the predicted results to ensure optimal allocation of charging resources. The predicted results are used for subsequent energy allocation and collaborative optimization. The prediction formula is:
[0007]
[0008] in, For the moment The predicted value of charging demand, For the charging needs of the last moment, Charging data for history, User behavior data;
[0009] Step b: Based on the charging demand predicted in step a, the excess energy is stored in neighboring vehicles, and energy sharing between vehicles is achieved through wireless energy transmission technology. The energy allocation strategy is dynamically optimized according to the real-time charging demand prediction result generated in step a to optimize energy utilization efficiency, where the energy sharing formula is:
[0010]
[0011] in, For the moment The shared energy is the energy distribution coefficient, For the The real-time power of the vehicle is used to achieve efficient use of energy, thereby increasing overall energy utilization and driving range;
[0012] Step c: Integrate the data in step a and step b, use the collaborative optimization algorithm to integrate the charging station status, vehicle power, driving path and energy demand, and use the real-time charging demand prediction and energy sharing data to calculate and generate the optimal charging and energy allocation strategy. Specifically, the collaborative optimization is performed by integrating the following factors: the available status of the charging station, the power level of each vehicle, the current driving path and the real-time energy demand. The collaborative optimization formula is:
[0013]
[0014] in, is the overall performance indicator, Choose a weight for the charging station, is the predicted value of charging demand, is the energy sharing weight, To share energy;
[0015] It is used to achieve overall optimization of charging and energy storage, obtain the best energy management plan when the vehicle is driving, and increase the driving range and driving efficiency.
[0016] Furthermore, the historical charging data includes the vehicle's charging frequency, the amount of electricity charged each time, the charging time and the charging location;
[0017] The charging frequency is given by the formula Calculate, where For the moment The charging frequency, For the The data is used to predict the vehicle's future charging needs.
[0018] Furthermore, the real-time power status includes the remaining battery power, battery health status and current energy consumption rate;
[0019] The remaining battery capacity is measured by voltage and current sensors and is calculated using the formula Calculate, where The remaining battery power. is the battery voltage, is the current, For time.
[0020] Furthermore, the user behavior data includes the user's driving habits, driving speed and braking frequency;
[0021] By classifying user driving habits, clustering algorithms are used to divide driving habits into conservative, normal, and aggressive types, and each type of user behavior is modeled to improve the accuracy of charging demand prediction;
[0022]
[0023] in, For the moment User behavior data, is the average speed, is the braking frequency, is the acceleration;
[0024] User behavior data is combined with historical charging data and real-time power status.
[0025] Furthermore, the wireless energy transmission technology is an electromagnetic induction coupling technology, which is used to transmit energy between vehicles;
[0026] By establishing electromagnetic induction coupling between vehicles, efficient energy transmission is achieved. The energy transmission efficiency is calculated by the formula Calculate, where is the energy transfer efficiency, is the output power, The electromagnetic induction coupling is used to establish an energy transmission path between vehicles to realize the effective sharing of excess energy between vehicles.
[0027] In addition, the present invention also provides a vehicle endurance management device, the device comprising:
[0028] Data collection module, used to collect historical charging data, real-time power status and user behavior data of the vehicle;
[0029] A prediction module, communicating with the data acquisition module, predicting the charging demand of the vehicle using a machine learning algorithm and generating a predicted value of future charging demand;
[0030] A scheduling module, communicating with the prediction module, dynamically adjusting charging scheduling according to the prediction results to ensure optimal allocation of charging resources;
[0031] Energy storage and sharing module, which is used to realize distributed energy storage between vehicles, store excess energy in neighboring vehicles through wireless energy transmission technology, and dynamically adjust energy distribution strategy according to real-time demand;
[0032] The collaborative optimization module communicates with the energy storage and sharing module, comprehensively considers the charging station status, vehicle power, driving path and energy demand, and calculates and generates the optimal charging and energy distribution strategy.
[0033] Furthermore, the machine learning algorithm used by the prediction module includes a long short-term memory network LSTM, which improves the accuracy of charging demand prediction by combining historical data and real-time data;
[0034] The wireless energy transmission technology in the energy storage and sharing module adopts high-frequency modulation technology to optimize the propagation efficiency of electromagnetic waves, making energy transmission more efficient and with lower losses, and is suitable for short-distance energy sharing environments between vehicles.
[0035] In addition, the present invention also provides a storage medium for vehicle range management, wherein the storage medium stores a computer program, and when the computer program is executed by one or more processors, the vehicle range management method is implemented, including:
[0036] Collect historical charging data, real-time power status and user behavior data of vehicles;
[0037] Use machine learning algorithms to predict vehicle charging needs and generate forecasts of future charging needs;
[0038] Dynamically adjust charging scheduling based on prediction results to ensure optimal allocation of charging resources;
[0039] Distributed energy storage is realized between vehicles, excess energy is stored in neighboring vehicles through wireless energy transmission technology, and the energy distribution strategy is dynamically adjusted according to real-time demand.
[0040] In addition, the present invention also provides a vehicle endurance management system, the system comprising:
[0041] At least one vehicle is equipped with sensors for collecting historical charging data, real-time power status and user behavior data of the vehicle;
[0042] A processor, executing the vehicle endurance management method;
[0043] a communicator for communicating data between vehicles and between a vehicle and a charging station;
[0044] An energy management module, including a device and an algorithm for realizing energy transmission and sharing between vehicles, the device including an electromagnetic induction coupling device and a high-frequency modulation technology;
[0045] The optimization control module is used to dynamically adjust the charging and energy distribution strategies according to the prediction and scheduling results generated by the processor to achieve overall optimization of vehicle endurance management.
[0046] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0047] 1. The present invention accurately predicts the charging demand of vehicles and generates a predicted value of future charging demand. It dynamically adjusts the charging schedule according to the predicted results to ensure the optimal allocation of charging resources. At the same time, through distributed energy storage and management, excess energy is stored in neighboring vehicles, and energy sharing between vehicles is achieved through wireless energy transmission technology. On the basis of real-time monitoring and dynamic scheduling, it can achieve optimized charging and energy management and extend the vehicle's cruising range.
[0048] 2. The present invention adopts collaborative optimization to comprehensively optimize the status of charging stations, the power level of each vehicle, the current driving path and the real-time energy demand to generate the optimal charging and energy distribution strategy. By minimizing the overall performance indicators, the charging priority and energy sharing strategy are dynamically adjusted to ensure that each vehicle can obtain the best energy support during driving, improve charging efficiency and energy utilization efficiency, effectively reduce user waiting time, and greatly improve the overall endurance and operational efficiency of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0050] Figure 1 A flowchart of the vehicle endurance management method of the present invention;
[0051] Figure 2 It is a block diagram of the system modules of the present invention;
[0052] Figure 3 This is a diagram of the vehicle endurance management device of the present invention. DETAILED DESCRIPTION
[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0055] like Figure 1 As shown, a vehicle range management method in this embodiment includes the following management steps:
[0056] Step a: Collect the historical charging data, real-time power status and user behavior data of the vehicle through the on-board sensors and the Internet of Vehicles system, use the machine learning algorithm to predict the charging demand of the vehicle, generate the predicted value of future charging demand, and dynamically adjust the charging scheduling according to the predicted results to ensure the optimal allocation of charging resources:
[0057] The machine learning algorithm uses the long short-term memory network LSTM, which can process time series data and capture the complex relationship between historical data and real-time data. Specifically:
[0058] First, extract features from the collected historical charging data, real-time power status, and user behavior data;
[0059] For historical charging data, extract the charging frequency, the amount of electricity charged each time, and the charging time characteristics;
[0060] For real-time power status, extract the remaining battery power, battery health status and current energy consumption rate characteristics;
[0061] For user behavior data, driving habits, driving speed and braking frequency features are extracted.
[0062] Secondly, the extracted feature data is used to train the LSTM model. The LSTM model can handle long-term dependencies and is suitable for predicting future charging demand. The input of the model is the time series of historical charging data, real-time power status and user behavior data, and the output is the predicted value of charging demand at a future moment. ,The loss function of the model usually selects the mean square error (MSE), and the model parameters are optimized through the back-propagation algorithm;
[0063] Then, after the training is completed, the model is verified and adjusted. Through cross-validation and grid search techniques, the model's hyperparameters are adjusted to obtain the best performance. The validation data set is used to evaluate the model's prediction accuracy and generalization ability to avoid overfitting.
[0064] Finally, after the model training and verification are completed, the model is deployed in the vehicle system to achieve real-time prediction. Based on the real-time collected data, the model calculates and outputs the future charging demand prediction value in real time. , guiding the dynamic adjustment of charging scheduling;
[0065] The prediction results are used for subsequent energy allocation and collaborative optimization. The prediction formula is:
[0066]
[0067] in, For the moment The predicted value of charging demand, For the charging needs of the last moment, Charging data for history, User behavior data;
[0068] According to the future charging demand predicted by the machine learning model, the charging schedule is dynamically adjusted to ensure the optimal allocation of charging resources. The specific implementation is:
[0069] According to the real-time power status of the vehicle and the predicted value of charging demand, the charging priority is set. Vehicles with high priority will be given priority to obtain charging resources when charging resources are tight. The specific implementation steps are as follows:
[0070] Get the vehicle's power status in real time, including remaining power, battery health status, and current energy consumption rate. , calculate the charging priority of each vehicle, where is the remaining power, is the total battery capacity, Rate the battery health status, For the predicted charging demand, , , is the weight parameter, and all vehicles are assigned the calculated priority Sort by priority, and vehicles with high priority will be given priority to obtain charging resources when charging resources are scarce;
[0071] Next, use the predicted charging demand data to optimize the charging strategy, including selecting the most appropriate charging time and charging location, to reduce charging waiting time and improve charging efficiency. The specific implementation steps are as follows:
[0072] According to the grid load, choose to charge during the period when the grid load is low. The grid load prediction formula is: ,in For the moment The predicted value of grid load, is the historical load data, is the current load data, , is the weight coefficient. Continue to select the most suitable charging location based on the vehicle location and the usage of the charging pile. Use the predicted usage of the charging pile and the vehicle's driving path to calculate the charging efficiency score of each charging location. , the formula is ,in is the current utilization rate of charging piles, is the distance from the vehicle to the charging location, , is the weight coefficient;
[0073] When allocating charging resources among multiple vehicles, consider the charging needs and real-time power status of each vehicle and allocate energy reasonably. The specific implementation steps are as follows:
[0074] Based on the real-time charging needs of each vehicle and charging priority , dynamically adjust the charging power of each vehicle , the formula is ,in, For the The charging power of the vehicle, is the total charging power, For the The charging priority of the vehicle is to select the most suitable charging pile according to the charging needs of the vehicle and the load of the charging pile.
[0075] By predicting the real-time power status and charging needs of vehicles, and combining multiple factors such as grid load, charging pile usage and vehicle driving path, dynamic adjustment and optimal allocation of charging resources can be achieved. Specifically, by real-time monitoring of the vehicle's power status and user behavior data, the key factors affecting charging demand can be captured, and by accurately predicting future charging needs, the charging strategy and charging priority setting can be optimized to ensure that the needs of vehicles that need charging the most are met first when charging resources are tight. In addition, by reasonably allocating charging power and selecting the most suitable charging location, charging efficiency can be improved and user waiting time can be reduced.
[0076] Historical charging data includes the vehicle’s charging frequency, the amount of electricity charged each time, the charging time and the charging location;
[0077] The charging frequency is given by the formula Calculate, where For the moment The charging frequency, For the The interval between charges, the power of each charge records the amount of power input during each charging process to ensure effective management of the battery capacity, the charging time records the start and end time of each charge, and the charging location information helps to understand the user's charging behavior pattern, such as whether they often charge at a fixed location or have multiple charging locations;
[0078] Real-time power status includes remaining battery power, battery health status and current energy consumption rate;
[0079] The remaining battery capacity is measured by voltage and current sensors and is calculated using the formula Calculate, where is the remaining power, is the battery voltage, is the current, For time;
[0080] The battery health status is evaluated by monitoring parameters such as battery voltage, current and temperature. The battery management system (BMS) is used to monitor and analyze data in real time. The current energy consumption rate reflects the energy consumption of the vehicle under current driving conditions.
[0081] By classifying user driving habits, clustering algorithms are used to divide driving habits into conservative, normal, and aggressive types, and each type of user behavior is modeled to improve the accuracy of charging demand prediction;
[0082]
[0083] in, For the moment User behavior data, is the average speed, is the braking frequency, is the acceleration;
[0084] By performing cluster analysis on these data, different types of driving behaviors can be identified and the energy consumption under different driving behaviors can be predicted accordingly.
[0085] Step b: Based on the charging demand predicted in step a, the excess energy is stored in neighboring vehicles, and energy sharing between vehicles is achieved through wireless energy transmission technology. The energy allocation strategy is dynamically optimized according to the real-time charging demand prediction result generated in step a to optimize energy utilization efficiency, where the energy sharing formula is:
[0086]
[0087] in, For the moment The shared energy is the energy distribution coefficient, For the The real-time power of the vehicle is used to achieve efficient use of energy, increase overall energy utilization and range. Through on-board sensors and the Internet of Vehicles system, the vehicle's power status is collected in real time, including remaining power, battery health status and current energy consumption rate, to identify which vehicles have excess energy and which vehicles need additional energy support, ensuring that energy is efficiently shared and used among vehicles;
[0088] At every point in time , calculate the remaining energy of each vehicle through real-time data , when the remaining energy of a vehicle exceeds its preset threshold When the remaining energy of a vehicle is lower than the preset threshold, the vehicle is marked as an energy demand vehicle and is ready to obtain energy from the neighboring energy supply vehicle.
[0089] Then, according to the real-time charging demand forecast results generated in step a, the energy allocation strategy will be dynamically adjusted to calculate the charging demand of each vehicle at time The energy distribution coefficient ;
[0090] in, Indicates The distribution ratio of vehicles in energy sharing ensures the fairness and efficiency of energy distribution. The wireless energy transmission technology is electromagnetic induction coupling technology, which is used to transmit energy between vehicles. The energy supply vehicle starts the energy transmission device to generate a magnetic field; the energy demand vehicle receives the magnetic field and converts it into electrical energy, monitors the state of energy transmission in real time, and dynamically adjusts the transmission power according to the transmission efficiency and transmission time. The energy transmission efficiency is calculated by the formula Calculate, where is the energy transfer efficiency, is the output power, For input power, electromagnetic induction coupling is used to establish an energy transfer path between vehicles, enabling efficient sharing of excess energy between vehicles.
[0091] Step c: Integrate the data in step a and step b, use the collaborative optimization algorithm to integrate the charging station status, vehicle power, driving path and energy demand, and use the real-time charging demand prediction and energy sharing data to calculate and generate the optimal charging and energy allocation strategy. Specifically, the collaborative optimization is performed by integrating the following factors: the available status of the charging station, the power level of each vehicle, the current driving path and the real-time energy demand. The collaborative optimization formula is:
[0092]
[0093] in, is the overall performance indicator, Choose a weight for the charging station, is the predicted value of charging demand, is the energy sharing weight, To share energy;
[0094] Based on the collaborative optimization calculation results, a specific charging and energy allocation strategy is generated and sent to each vehicle and charging station. According to the received strategy, the vehicle goes to the designated charging station for charging or shares energy with neighboring vehicles. According to the optimization strategy, the charging station gives priority to providing charging services to high-priority vehicles and adjusts the use and maintenance plan of the charging piles.
[0095] like Figure 3 As shown, the present invention also provides a vehicle endurance management device, the device comprising:
[0096] The data acquisition module is used to collect the vehicle's historical charging data, real-time power status and user behavior data. The historical charging data includes the vehicle's past charging times, the power of each charge, the charging time and charging location; the real-time power status includes the vehicle's current battery remaining power, battery health status and current energy consumption rate; the user behavior data includes driving habits, driving speed and braking frequency information. The data acquisition module obtains this data in real time through various sensors installed on the vehicle and the vehicle networking system, and transmits it to the central processing unit for further processing and analysis;
[0097] The prediction module communicates with the data acquisition module and uses machine learning algorithms to predict the charging demand of vehicles and generate predicted values of future charging demand. The prediction module analyzes historical charging data, real-time power status and user behavior data to build a long short-term memory network LSTM model, which can capture complex relationships and patterns in time series data, thereby accurately predicting future charging demand;
[0098] The scheduling module communicates with the prediction module and dynamically adjusts the charging schedule according to the prediction results to ensure the optimal allocation of charging resources. The scheduling module uses the charging demand prediction value provided by the prediction module and combines the current status information of the charging station to formulate the optimal charging scheduling plan. The scheduling module will give priority to allocating charging resources to vehicles with higher charging demand, and reasonably arrange the charging time and location to reduce the charging waiting time and improve the charging efficiency;
[0099] Energy storage and sharing module, used to achieve distributed energy storage between vehicles, store excess energy in neighboring vehicles through wireless energy transmission technology, and dynamically adjust energy allocation strategy according to real-time demand. When the battery power of some vehicles is high, the excess energy can be transmitted to vehicles with lower power through wireless energy transmission technology to achieve efficient use of energy. The energy storage and sharing module uses electromagnetic induction coupling technology to establish energy transmission channels between vehicles, and optimizes the propagation efficiency of electromagnetic waves through high-frequency modulation technology to ensure efficient and stable energy transmission;
[0100] The collaborative optimization module communicates with the energy storage and sharing module, comprehensively considers the charging station status, vehicle power, driving path and energy demand, calculates and generates the optimal charging and energy distribution strategy. The optimal charging and energy distribution strategy generated by the collaborative optimization module will be sent to each vehicle and charging station to guide the actual charging and energy sharing operations.
[0101] The machine learning algorithms used in the prediction module include the long short-term memory network (LSTM), which improves the accuracy of charging demand prediction by combining historical data with real-time data;
[0102] The wireless energy transmission technology in the energy storage and sharing module uses high-frequency modulation technology to optimize the propagation efficiency of electromagnetic waves, making energy transmission more efficient and with lower losses, and is suitable for short-distance energy sharing environments between vehicles.
[0103] The present invention also provides a storage medium for vehicle range management, wherein the storage medium stores a computer program. When the computer program is executed by one or more processors, a vehicle range management method is implemented, including:
[0104] Collect historical charging data, real-time power status and user behavior data of vehicles;
[0105] Use machine learning algorithms to predict vehicle charging needs and generate forecasts of future charging needs;
[0106] Dynamically adjust charging scheduling based on prediction results to ensure optimal allocation of charging resources;
[0107] Distributed energy storage is realized between vehicles, excess energy is stored in neighboring vehicles through wireless energy transmission technology, and the energy distribution strategy is dynamically adjusted according to real-time demand.
[0108] like Figure 2 As shown, the present invention also provides a vehicle endurance management system, the system comprising:
[0109] The sensors installed on each vehicle are used to collect various data of the vehicle in real time, including historical charging data such as the number of times the battery is charged, the amount of electricity each time, the charging time and the charging location; real-time power status such as the current remaining battery power, battery health status and current energy consumption rate; and user behavior data such as the user's driving habits, driving speed and braking frequency. These data are pre-processed by the vehicle system and transmitted to the central processing unit in real time for subsequent analysis and processing;
[0110] A processor, used to execute the vehicle range management method, the processor receives data transmitted from the vehicle, and predicts the charging demand of the vehicle by performing prediction, scheduling and collaborative optimization, formulates a charging scheduling plan, and generates an optimal charging and energy distribution strategy. The processor ensures that the system can efficiently manage the energy demand of the vehicle and optimize the range management through analysis and calculation;
[0111] Communicator, used for data communication between vehicles and between vehicles and charging stations. The communicator realizes the interconnection between vehicles and charging stations through the Internet of Vehicles technology, ensuring the real-time transmission and sharing of data;
[0112] Energy management module: Through electromagnetic induction coupling device, the energy management module establishes energy transmission channel between energy supply vehicle and energy demand vehicle to realize efficient energy transmission. High-frequency modulation technology is used to optimize the propagation efficiency of electromagnetic waves and reduce the loss in the energy transmission process. The energy management module also contains intelligent control algorithm, which can monitor the energy transmission status in real time and dynamically adjust the energy distribution strategy according to actual needs to ensure that each vehicle can obtain sufficient energy support during driving;
[0113] The optimization control module is used to dynamically adjust the charging and energy distribution strategies according to the prediction and scheduling results generated by the processor to achieve overall optimization of vehicle endurance management.
[0114] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0115] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A vehicle endurance management method, characterized in that: The management steps include: Step a: The vehicle's historical charging data, real-time power status, and user behavior data are collected through on-board sensors and the Internet of Vehicles system. The vehicle's charging demand is predicted using a machine learning algorithm to generate a predicted value for future charging demand. The charging schedule is dynamically adjusted based on the predicted results to ensure optimal allocation of charging resources. The predicted results are used for subsequent energy allocation and collaborative optimization. The prediction formula is: in, For the moment The predicted value of charging demand, For the charging needs of the last moment, Charging data for history, User behavior data; The historical charging data includes the vehicle's charging frequency, the amount of electricity charged each time, the charging time and the charging location; The real-time power status includes the remaining battery power, battery health status and current energy consumption rate; The user behavior data includes the user's driving habits, driving speed and braking frequency; Step b: Based on the charging demand predicted in step a, the excess energy is stored in neighboring vehicles, and energy sharing between vehicles is achieved through wireless energy transmission technology. The energy allocation strategy is dynamically optimized according to the real-time charging demand prediction result generated in step a to optimize energy utilization efficiency, where the energy sharing formula is: in, For the moment The shared energy is the energy distribution coefficient, For the The real-time power of the vehicle is used to achieve efficient use of energy, thereby increasing overall energy utilization and driving range; Step c: Integrate the data in step a and step b, use the collaborative optimization algorithm to integrate the charging station status, vehicle power, driving path and energy demand, use the real-time charging demand prediction and energy sharing data to calculate and generate the optimal charging and energy allocation strategy, and perform collaborative optimization by integrating the following factors: the available status of the charging station, the power level of each vehicle, the current driving path and the real-time energy demand. The collaborative optimization formula is: in, is the overall performance indicator, Choose a weight for the charging station, is the predicted value of charging demand, is the energy sharing weight, To share energy; It is used to achieve overall optimization of charging and energy storage, obtain the best energy management plan when the vehicle is driving, and increase the driving range and driving efficiency.
2. A vehicle endurance management method according to claim 1, characterized in that: The charging frequency is given by the formula Calculate, where For the moment The charging frequency, For the The data is used to predict the vehicle's future charging needs.
3. A vehicle endurance management method according to claim 1, characterized in that: The remaining battery capacity is measured by voltage and current sensors and is calculated using the formula Calculate, where The remaining battery power. is the battery voltage, is the current, For time.
4. A vehicle endurance management method according to claim 1, characterized in that: By classifying user driving habits, clustering algorithms are used to divide driving habits into conservative, normal, and aggressive types, and each type of user behavior is modeled to improve the accuracy of charging demand prediction; in, For the moment User behavior data, is the average speed, is the braking frequency, is the acceleration.
5. A vehicle endurance management method according to claim 1, characterized in that: The wireless energy transmission technology is an electromagnetic induction coupling technology, which is used to transmit energy between vehicles; By establishing electromagnetic induction coupling between vehicles, efficient energy transmission is achieved. The energy transmission efficiency is calculated by the formula Calculate, where is the energy transfer efficiency, is the output power, The electromagnetic induction coupling is used to establish an energy transmission path between vehicles to realize the effective sharing of excess energy between vehicles.
6. The vehicle range management device according to any one of claims 1 to 5, characterized in that: The device comprises: Data collection module, used to collect historical charging data, real-time power status and user behavior data of the vehicle; A prediction module, communicating with the data acquisition module, predicting the charging demand of the vehicle using a machine learning algorithm and generating a predicted value of future charging demand; A scheduling module, communicating with the prediction module, dynamically adjusting charging scheduling according to the prediction results to ensure optimal allocation of charging resources; Energy storage and sharing module, which is used to realize distributed energy storage between vehicles, store excess energy in neighboring vehicles through wireless energy transmission technology, and dynamically adjust energy distribution strategy according to real-time demand; The collaborative optimization module communicates with the energy storage and sharing module, comprehensively considers the charging station status, vehicle power, driving path and energy demand, and calculates and generates the optimal charging and energy distribution strategy.
7. The vehicle endurance management device according to claim 6, characterized in that: The machine learning algorithm used by the prediction module includes a long short-term memory network LSTM, which improves the accuracy of charging demand prediction by combining historical data and real-time data; The wireless energy transmission technology in the energy storage and sharing module adopts high-frequency modulation technology to optimize the propagation efficiency of electromagnetic waves, making energy transmission more efficient and with lower losses, and is suitable for short-distance energy sharing environments between vehicles.
8. A storage medium for vehicle endurance management, characterized in that: The storage medium stores a computer program. When the computer program is executed by one or more processors, the vehicle range management method according to any one of claims 1 to 5 is implemented, including: Collect historical charging data, real-time power status and user behavior data of vehicles; Use machine learning algorithms to predict vehicle charging needs and generate forecasts of future charging needs; Dynamically adjust charging scheduling based on prediction results to ensure optimal allocation of charging resources; Distributed energy storage is realized between vehicles, excess energy is stored in neighboring vehicles through wireless energy transmission technology, and the energy distribution strategy is dynamically adjusted according to real-time demand.
9. A vehicle endurance management system, characterized in that: The system comprises: At least one vehicle is equipped with sensors for collecting historical charging data, real-time power status and user behavior data of the vehicle; A processor, executing the vehicle range management method according to any one of claims 1 to 5; a communicator for communicating data between vehicles and between a vehicle and a charging station; An energy management module, including a device and an algorithm for realizing energy transmission and sharing between vehicles, the device including an electromagnetic induction coupling device and a high-frequency modulation technology; The optimization control module is used to dynamically adjust the charging and energy distribution strategies according to the prediction and scheduling results generated by the processor to achieve overall optimization of vehicle endurance management.
Citation Information
Cited By
Intelligent scheduling management system and method for new energy electric vehicle charging pile
CN121765271A
