Electric vehicle charging time prediction method, device and system, and storage medium

Abstract

The invention discloses an electric vehicle charging time prediction method, device and system and a storage medium, and the method comprises the steps: building a scatter diagram of the power distribution of a vehicle, a power interval distribution diagram at an interval of 10kw, and a power interval distribution diagram at an interval of 1kw, and carrying out the analysis of the scatter diagram, the power interval distribution diagram, and obtaining a boundary between fast charging and slow charging, and a boundary between overcharging and fast charging of the vehicle; dividing the historical charging data of the vehicle into slow charging data, fast charging data and overcharging data according to the boundary of fast charging and slow charging and the boundary of overcharging and fast charging of the vehicle; s3, establishing a slow charging model, a fast charging model and an overcharging model according to the slow charging data, the fast charging data and the overcharging data; and predicting a possible charging mode when the vehicle arrives at any charging pile according to geographical location information, time information and driver driving model information of historical charging and current charging of the vehicle. By adopting the technical scheme of the invention, the charging time of the electric vehicle can be predicted more accurately.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of electric vehicles, and particularly relates to an electric vehicle charging time prediction method and device, system and storage medium. BACKGROUND

[0002] With the continuous development of the electric vehicle industry, fast charging and super charging technologies are continuously developed, the charging speed of electric vehicles is continuously improved, and the charging mode is diversified. At present, the electric vehicle charging time prediction method is mostly only for slow charging, and usually only a single factor such as an SOC threshold is used to establish a model. However, in actual application, the slow charging time is jointly affected by various factors such as battery temperature and SOC, and there are various slow charging models. It is difficult to accurately reflect the real charging process with a single model. SUMMARY

[0003] The technical problem to be solved by the application is to provide an electric vehicle charging time prediction method and device, system and storage medium, which can better adapt to the current development of electric vehicles by selecting charging time prediction models of vehicles into slow charging, fast charging and super charging models, and can more accurately predict the charging time of electric vehicles.

[0004] To achieve the above-mentioned purpose, the application adopts the following technical solution: An electric vehicle charging time prediction method comprises the following steps: Step S1, a scatter plot of power distribution of a vehicle, a power interval distribution plot with an interval of 10kw and a power interval distribution plot with an interval of 1kw are established, and a slow charging and fast charging demarcation line and a super charging and fast charging demarcation line of the vehicle are obtained by analyzing the scatter plot of power distribution of the vehicle, the power interval distribution plot with an interval of 10kw and the power interval distribution plot with an interval of 1kw; Step S2, according to the slow charging and fast charging demarcation line and the super charging and fast charging demarcation line of the vehicle, historical charging data of the vehicle is divided into slow charging charging data, fast charging charging data and super charging charging data; Step S3, according to the slow charging charging data, the fast charging charging data and the super charging charging data, a slow charging model, a fast charging model and a super charging model are established; Step S4, according to geographical position information, time information and driver driving model information of historical charging and current charging of the vehicle, a possible charging mode of the vehicle when reaching any charging pile is predicted.

[0005] The application also provides an electric vehicle charging time prediction device, comprising: A first processing module is configured to establish a scatter plot of power distribution of a vehicle, a power interval distribution plot with an interval of 10kw and a power interval distribution plot with an interval of 1kw, and obtain a slow charging and fast charging demarcation line and a super charging and fast charging demarcation line of the vehicle by analyzing the scatter plot of power distribution of the vehicle, the power interval distribution plot with an interval of 10kw and the power interval distribution plot with an interval of 1kw; The second processing module is used to divide the vehicle's historical charging data into slow charging data, fast charging data, and super charging data according to the vehicle's fast charging and slow charging boundary and the super charging and fast charging boundary; A third processing module is used to establish a slow charging model, a fast charging model and a super charging model based on the slow charging data, the fast charging data and the super charging data; The fourth processing module is used to predict the possible charging mode when the vehicle arrives at any charging pile based on the vehicle's historical charging and current charging geographic location information, time information, and driver driving model information.

[0006] The present invention also provides an electric vehicle charging time prediction system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes the electric vehicle charging time prediction method when executed by the processor.

[0007] The present invention also provides a storage medium, on which a computer program is stored, and the computer program executes the electric vehicle charging time prediction method when running.

[0008] The beneficial effects of the present invention are as follows: 1) Based on the various phenomena that occur during the slow charging process of electric vehicles, multiple slow charging models have been established to encompass a wider range of actual vehicle charging conditions. This makes the slow charging time prediction more applicable to different types of vehicles and in different driving environments, resulting in higher applicability.

[0009] 2) For the same vehicle, not only multiple slow charging models are established, but also a fast charging model and a super charging model are established based on the fast charging data and super charging data distinguished from the vehicle's historical charging data. The fast charging model and super charging model established by distinguishing the fast charging data and super charging data have higher prediction accuracy due to the data differentiation. Establishing multiple models more comprehensively includes various situations in the actual charging of the vehicle, which can more accurately predict the vehicle's charging time. 3) The pattern prediction model used combines the driver's historical charging location information, charging time information, and driver model selection tendency information to continuously learn user habits and gradually achieve higher prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a flow chart of a method for predicting charging time of an electric vehicle according to an embodiment of the present invention.

[0012] Figure 2 This is the flow chart of slow charging duration prediction model I; Figure 3 This is the flow chart of slow charging duration prediction model II; Figure 4 This is the flow chart of slow charging duration prediction model III; Figure 5 This is the flow chart of slow charging duration prediction model IV; Figure 6 This is the flow chart of slow charging duration prediction model V; Figure 7 This is the flow chart of slow charging duration prediction model VI; Figure 8 This is a flowchart of the fast charging duration prediction model; Figure 9 Flowchart of the fast charging current prediction model. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0014] 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.

[0015] Example 1: like Figure 1 As shown, an embodiment of the present invention provides a method for predicting charging time of an electric vehicle, comprising: Step S1: Create a scatter plot of the vehicle's power distribution, a power interval distribution plot with an interval of 10 kW, and a power interval distribution plot with an interval of 1 kW, and analyze them to obtain the vehicle's fast charging and slow charging boundaries, and the vehicle's supercharging and fast charging boundaries; Step S2: dividing the vehicle's historical charging data into slow charging data, fast charging data, and super charging data based on the vehicle's fast charging and slow charging boundaries and the super charging and fast charging boundaries; Step S3: establishing a slow charging model, a fast charging model, and a super charging model based on the slow charging data, the fast charging data, and the super charging data; Step S4: predict the possible charging mode when the vehicle arrives at any charging pile based on the vehicle's historical charging and current charging geographic location information, time information, and driver driving model information; increase the accuracy of the mode used when predicting the vehicle charging time, thereby improving the accuracy of the predicted time.

[0016] As an implementation method of an embodiment of the present invention, in step S3, multiple slow charging models are established based on the various phenomena existing in the slow charging process of electric vehicles, so that it can be applied to a wider range of actual charging conditions of vehicles. It is more widely applicable to the prediction of slow charging time of vehicles of different types and driving environments. The slow charging process of electric vehicles has the following phenomena: 1. Charging is always carried out with a constant current during the charging process. 2. At the beginning of charging, charging is first carried out with a lower current value. At this time, the battery temperature gradually rises. After the battery temperature rises to a certain temperature, it is converted to high current for charging, and then charged with high current until it is fully charged. 3. At the beginning of charging, charging is also carried out with a low current. After the battery temperature rises to a certain temperature, it is converted to high current for charging. During the high current charging stage, the temperature of the battery begins to gradually decrease. When the temperature drops to the falling temperature threshold, the vehicle switches to low current for charging. During this process, the battery temperature begins to rise again. When it rises to the rising temperature threshold, it switches to high current for charging. The above stages are repeated until the vehicle is fully charged. 4. When the vehicle starts charging, it is charged with a certain current. When the vehicle reaches a certain SOC value, such as 80 or 90, the charging current is converted to another constant current for charging until the vehicle is fully charged. Different vehicles have different slow charging modes due to different charging protocols, usage conditions, and other conditions. By analyzing the above four phenomena, the present invention has established a variety of slow charging models. For example, Model I with only Phenomenon 1: The vehicle is charged with a constant current. Charge until the car is fully charged. The specific flow chart is as follows: Figure 2 Only the model II of phenomenon 2: the vehicle starts with a low current When charging, the battery temperature begins to rise. Calculate the temperature at any time: , (where represents the temperature at any time, It represents the initial temperature at the beginning. It represents the time from the start to the target time). When the temperature rises to the rising temperature threshold When the vehicle is converted into a high current To charge, the vehicle uses current Charge until charging is complete, the specific flow chart is as follows Figure 3 Only the model III of phenomenon 3: the vehicle starts with low current When charging, the battery temperature begins to rise. Calculate the temperature at any time: , (where represents the temperature at any time, It represents the initial temperature at the beginning. It represents the time from the start to the target time). When the temperature rises to the rising temperature threshold When the vehicle is converted into a high current During the high current charging stage, the battery temperature will gradually decrease. , calculate any temperature , (where represents the temperature at any time, It represents the initial temperature when it starts to drop. It represents the time from the start of temperature drop to the target time). When the temperature drops to the falling temperature threshold , then the high current Charging switches to low current Charging is carried out, and then the temperature rises again, and the cycle continues until charging is completed. The specific flow chart is as follows Figure 4 Charging Model IV: The vehicle starts with current Charging is carried out, but when the SOC reaches the threshold When the charging current changes, the vehicle will Charge until the vehicle is fully charged. The specific flow chart is as follows: Figure 5 Charging mode V: The vehicle starts with a low current When charging, the battery temperature begins to rise. Calculate the temperature at any time: , (where represents the temperature at any time, It represents the initial temperature at the beginning. It represents the time from the start to the target time). When the temperature rises to the rising temperature threshold When the vehicle is converted into a high current Charge, when SOC reaches the threshold The current becomes a constant value when , charge with this charging current until the vehicle is fully charged. The specific flow chart is as follows Figure 6 Charging mode VI: The vehicle starts with a low current When charging, the battery temperature begins to rise. Calculate the temperature at any time: , (where represents the temperature at any time, It represents the initial temperature at the beginning. It represents the time from the start to the target time). When the temperature rises to the rising temperature threshold When the vehicle is converted into a high current During the high current charging stage, the battery temperature will gradually decrease. , calculate any temperature , (where represents the temperature at any time, It represents the initial temperature when it starts to drop. It represents the time from the start of temperature drop to the target time). When the temperature drops to the falling temperature threshold , then the high current Charging switches to low current Charging is carried out, and then the temperature rises again, and the cycle continues until the SOC reaches the threshold , at this time the current becomes a constant value , charge with this charging current until the vehicle is fully charged. The specific flow chart is as follows Figure 7 shown.

[0017] Example 2: An embodiment of the present invention further provides a method for predicting charging time of an electric vehicle, comprising: Step 1: The vehicle transmits its historical charging data to the target cloud. The cloud performs some preprocessing on the vehicle's historical charging data, such as deleting data with abnormal SOC values, filling missing data with adjacent values, using low-pass filtering to reduce high-frequency vibrations in the data, and using median filtering to reduce accidental data mutations.

[0018] Step 2: After preprocessing the data, draw a scatter plot of the vehicle's power distribution, a power interval distribution diagram with an interval of 10kw, and a power interval distribution diagram with an interval of 1kw. Analyze the above power distribution diagrams: Based on the aggregation of charging data, the power dividing line between slow charging and fast charging, and the power dividing line between fast charging and supercharging are obtained. The vehicle's historical charging data is thus divided into slow charging data, fast charging data, and supercharging data. After that, the vehicle's historical charging data is analyzed to obtain the vehicle's OCV curve (a curve showing the corresponding relationship between voltage and SOC), the vehicle's temperature rise coefficient, and the temperature drop coefficient.

[0019] Step 3: Build the vehicle's slow charging model, fast charging model, and super charging model Slow charging model of vehicle is established: the following phenomena exist in the slow charging process of electric vehicle: 1. Constant current charging is performed during the charging process, 2. Low current charging is performed at the beginning of the charging process, at this time the battery temperature gradually rises, and after the battery temperature rises to a certain temperature, high current charging is performed, and then high current charging is performed until the battery is fully charged. 3. Low current charging is also performed at the beginning of the charging process, and high current charging is performed after the battery temperature rises to a certain temperature. During the high current charging stage, the temperature of the battery begins to gradually decrease, and when the temperature decreases to a lower temperature threshold, the vehicle changes to low current charging again. The battery temperature begins to rise again, and when it rises to an upper temperature threshold, it changes to high current charging again. The above stages are repeated until the vehicle is fully charged. 4. When the vehicle starts charging, a certain current is used for charging, and when the vehicle charging reaches a certain SOC value, such as 80 or 90, the charging current changes to another constant current for charging until the vehicle is fully charged. Different vehicles have different slow charging modes due to different charging protocols, usage conditions and other conditions. Through the analysis of the above four phenomena, the present application establishes a variety of slow charging models. For example, only phenomenon 1 charging model I: the vehicle charges with constant current until the vehicle is fully charged, as shown in the specific flow chart Figure 2 . Only phenomenon 2 charging model II: the vehicle starts charging with low current , at this time the battery temperature begins to rise. The temperature at any time is calculated using the temperature rise coefficient : , (in the formula represents the temperature at any time, represents the initial temperature at the beginning, represents the time from the beginning to the target time). When the temperature rises to the upper temperature threshold , the vehicle changes to high current charging, and the vehicle charges with current until the charging is completed, as shown in the specific flow chart Figure 3 . Only phenomenon 3 charging model III: the vehicle starts charging with low current , at this time the battery temperature begins to rise. The temperature at any time is calculated using the temperature rise coefficient : , (in the formula represents the temperature at any time, represents the initial temperature at the beginning, represents the time from the beginning to the target time). When the temperature rises to the upper temperature threshold , the vehicle changes to high current charging. During the high current charging stage, the temperature of the battery gradually decreases, at this time the temperature drop coefficient , calculate the temperature at any time , (in which represents the temperature at any time, represents the initial temperature at the beginning of the decrease, represents the time from the beginning of the decrease to the target time), when the temperature decreases to the decrease temperature threshold , the vehicle will be switched from high current charging to low current charging, and then the temperature will rise again, and the cycle will continue until the charging is completed, as shown in the flow chart Figure 4 . Charging model IV: the vehicle starts charging at current , but when the SOC reaches the threshold , the charging current will change, and the vehicle will charge at the changed current until the vehicle is fully charged, as shown in the flow chart Figure 5 . Charging model V: the vehicle starts charging at low current , and at this time the battery temperature starts to rise. The temperature at any time is calculated using the temperature rise coefficient , (in which represents the temperature at any time, represents the initial temperature at the beginning, represents the time from the beginning to the target time). When the temperature rises to the rise temperature threshold , the vehicle is switched to high current charging, and when the SOC reaches the threshold , the current becomes a constant value , and the vehicle is charged at this charging current until it is fully charged, as shown in the flow chart Figure 6 . Charging model VI: the vehicle starts charging at low current , and at this time the battery temperature starts to rise. The temperature at any time is calculated using the temperature rise coefficient , (in which represents the temperature at any time, represents the initial temperature at the beginning, represents the time from the beginning to the target time). When the temperature rises to the rise temperature threshold , the vehicle is switched to high current charging. During the high current charging phase, the temperature of the battery will gradually decrease, and at this time the temperature at any time is calculated according to the temperature decrease coefficient , (in which represents the temperature at any time, represents the initial temperature at the beginning of the decrease, ​​​It represents the time from the start of temperature drop to the target time). When the temperature drops to the falling temperature threshold , then the high current Charging switches to low current Charging is carried out, and then the temperature rises again, and the cycle continues until the SOC reaches the threshold , at this time the current becomes a constant value , charge with this charging current until the vehicle is fully charged. The specific flow chart is as follows Figure 7 shown.

[0020] Establishment of the fast charging model of the vehicle: Through data analysis and theoretical analysis, it was found that the current of the vehicle during charging is related to factors such as voltage, SOC, and temperature. After analyzing the fast charging data of the vehicle, no obvious model features were found, so a machine learning method was used to predict the current of the vehicle during charging, and voltage, SOC, minimum temperature, and maximum temperature were selected as influencing factors to predict the current. Comparing the effects of machine learning such as adaboost regression, K-nearest neighbor (KNN) regression, XGboost regression, and CatBoost regression, it was found that most vehicles used K-nearest neighbor regression and adaboost regression for better prediction results. Therefore, the K-nearest neighbor regression and adaboost regression algorithms with better universality were selected to predict the charging current. The fast charging data previously distinguished from the historical charging data of the vehicle were used to train the fast charging model of the vehicle. The steps to obtain the charging time of the vehicle using the fast charging model are: first, the voltage, current, vehicle SOC, minimum temperature, maximum temperature, and vehicle battery capacity when the vehicle starts charging are collected. The step size is 1 second. Multiply the current by 1 second to get the amount of charge charged in this time period. ,in , (where represents the charging current during this period, and t represents the time). The amount of charge that will be charged Divide by the vehicle's capacity Add the vehicle's You can get the next moment vehicle The formula is . ( The vehicle at the previous moment , The next moment vehicle value, is the amount of charge charged during this period of time, is the capacity of the vehicle). According to The OCV curve of the vehicle can obtain the voltage value of the vehicle at the next time, and according to the temperature rise coefficient of the vehicle, the temperature drop coefficient can calculate the maximum temperature and the minimum temperature of the vehicle at the next time. At this moment, the voltage, SOC, minimum temperature and maximum temperature of the vehicle at the next time are known, and the established vehicle fast charging model is used to input the voltage, SOC, minimum temperature and maximum temperature of the vehicle at the next time at this moment, and the fast charging model outputs the current, which is the current at the next time. The flow chart of the specific fast charging current prediction is as shown in Figure 9 At this moment, the voltage, current, vehicle SOC, minimum temperature and maximum temperature at the next time are obtained. The above steps can obtain the vehicle data at the next next time. The above steps are repeatedly executed until the SOC of the vehicle reaches the target SOC, and the number of repetitions is the charging time, and the flow chart of the specific fast charging time prediction is as shown in Figure 8

[0021] The vehicle super charging model is established: the charging time prediction process of the vehicle super charging model is basically the same as the fast charging process. After comparing a plurality of methods, the K nearest neighbor regression and adaboost regression methods are still selected to predict the charging current. The steps of obtaining the charging time of the vehicle by using the super charging model are similar to the fast charging: first, the voltage, current, vehicle SOC, minimum temperature, maximum temperature and vehicle battery capacity at the beginning of the vehicle charging are collected . The step length is 1 second. The current multiplied by 1 second obtains the charge amount charged in this time period , wherein , (in the formula , t represents the time). The charge amount is divided by the capacity of the vehicle, and then the voltage of the vehicle at the last time is added to obtain the voltage of the vehicle at the next time. The formula is . (The voltage of the vehicle at the last time is , , the voltage at the next time is , the charge amount charged in this time period is , and the capacity of the vehicle is ​And the OCV curve of the vehicle can obtain the voltage value of the vehicle at the next moment, and according to the temperature rise coefficient of the vehicle, the temperature drop coefficient can calculate the highest temperature and the lowest temperature of the vehicle at the next moment. At this moment, the voltage, SOC, minimum temperature and maximum temperature of the vehicle at the next moment are known, and the established vehicle fast charging model is used to input the voltage, SOC, minimum temperature and maximum temperature of the vehicle at the next moment at this moment, and the fast charging model outputs the current, and the current is the current at the next moment. At this time, the voltage, current, vehicle SOC, minimum temperature and maximum temperature at the next moment have been obtained. The above steps can obtain the vehicle data at the next next moment. The above steps are repeatedly executed until the SOC of the vehicle reaches the target SOC, and the number of repetitions is counted That is, the charging time.

[0022] According to the established six slow charging models, the slow charging model parameters of the vehicle are found from the slow charging data of the vehicle, and the slow charging model of the vehicle is established. Then, the fast charging data and the super charging data of the vehicle are used to establish the fast charging model and the super charging model of the vehicle, respectively.

[0023] Step four, when the vehicle reaches any charging pile, upload the geographic information, time information, charging pile current information and the like of the vehicle. According to the uploaded vehicle geographic and time information, the charging mode of the vehicle at this time is found in the vehicle historical charging record, and then the charging data is adapted to the initial selected charging mode for degree judgment. If the subsequent charging data such as current, voltage, SOC and the like is close to the data predicted by the selected model, the selected model is continued to be used for charging time prediction. If the subsequent actual charging data is greatly deviated from the data predicted by the selected model, the model is replaced for deviation analysis, and a model with smaller deviation is selected for subsequent charging time prediction. After the charging is completed, the data of the charging process is uploaded to the cloud, and the newly added charging data is used to optimize the charging model of the vehicle, increase the accuracy of the initial selected model, and improve the accuracy of the charging time prediction.

[0024] Embodiment 3 The application also provides an electric vehicle charging time prediction device, which comprises: A first processing module is configured to establish a scatter plot of power distribution of the vehicle, a power interval distribution plot with an interval of 10kw, and a power interval distribution plot with an interval of 1kw, and analyze the scatter plot to obtain a fast charging and slow charging demarcation line and a super charging and fast charging demarcation line of the vehicle. A second processing module is configured to divide historical charging data of the vehicle into slow charging data, fast charging data and super charging data according to the fast charging and slow charging demarcation line and the super charging and fast charging demarcation line. A third processing module is configured to establish a slow charging model, a fast charging model and a super charging model according to the slow charging data, the fast charging data and the super charging data. The fourth processing module is configured to predict a possible charging mode of the vehicle when reaching any charging pile according to historical charging and current charging geographical position information, time information and driver driving model information of the vehicle.

[0025] Embodiment 4: The embodiment of the present application also provides an electric vehicle charging time prediction system, comprising a memory and a processor, the memory storing a computer program run by the processor, and the computer program performing the electric vehicle charging time prediction method when run by the processor.

[0026] Embodiment 5: The embodiment of the present application also provides a storage medium, the storage medium storing a computer program, and the computer program performing the electric vehicle charging time prediction method when run.

[0027] The above-described embodiments are only used to describe the preferred modes of the present application, and do not limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements of the technical solutions of the present application made by those skilled in the art shall fall within the protection scope determined by the claims of the present application.

Claims

1. A method for predicting charging time of an electric vehicle, characterized in that: include: Step S1: Create a scatter plot of the vehicle's power distribution, a power interval distribution plot with an interval of 10 kW, and a power interval distribution plot with an interval of 1 kW, and analyze them to obtain the vehicle's fast charging and slow charging boundaries, and the vehicle's supercharging and fast charging boundaries; Step S2: dividing the vehicle's historical charging data into slow charging data, fast charging data, and super charging data based on the vehicle's fast charging and slow charging boundaries and the super charging and fast charging boundaries; Step S3: establishing a slow charging model, a fast charging model, and a super charging model based on the slow charging data, the fast charging data, and the super charging data; Step S4: predict the possible charging mode of the vehicle when it arrives at any charging pile based on the vehicle's historical charging and current charging geographic location information, time information, and driver driving model information.

2. An electric vehicle charging time prediction device, characterized in that: include: The first processing module is used to create a scatter plot of the vehicle's power distribution, a power interval distribution plot with an interval of 10 kW, and a power interval distribution plot with an interval of 1 kW, and analyze them to obtain the vehicle's fast charging and slow charging boundaries, and the vehicle's supercharging and fast charging boundaries; The second processing module is used to divide the vehicle's historical charging data into slow charging data, fast charging data, and super charging data according to the vehicle's fast charging and slow charging boundary and the super charging and fast charging boundary; A third processing module is used to establish a slow charging model, a fast charging model and a super charging model based on the slow charging data, the fast charging data and the super charging data; The fourth processing module is used to predict the possible charging mode when the vehicle arrives at any charging pile based on the vehicle's historical charging and current charging geographic location information, time information, and driver driving model information.

3. An electric vehicle charging time prediction system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the electric vehicle charging time prediction method according to claim 1 is executed.

4. A storage medium, characterized in that The storage medium stores a computer program, which, when running, executes the electric vehicle charging time prediction method according to any one of claims 1 to 3.

Images