New energy electric vehicle charging monitoring method and system based on artificial intelligence

Abstract

The invention relates to the technical field of new energy automobile energy control, in particular to a new energy electric vehicle charging monitoring method and system based on artificial intelligence. The method comprises the following steps: obtaining charging original data of the new energy electric vehicle, analyzing the charging original data through a pre-trained charging monitoring model, and generating charging prediction data of the new energy electric vehicle. Wherein the charging original data comprises environment temperature, battery data of the new energy electric vehicle and user preference data, and the charging monitoring model is obtained by taking historical battery data, historical driving data and regional charging pile data of the new energy electric vehicle as a training data set for training. Charging prediction is carried out based on the charging original data, the charging monitoring model is trained in advance, and the accuracy of providing charging prediction for the user is improved.

Description

Technical Field

[0001] The present application relates to the field of energy control technology for new energy vehicles, and in particular to a charging monitoring method and system for new energy electric vehicles based on artificial intelligence. Background Art

[0002] With the continuous development of new energy technology and the increasing awareness of environmental protection, the market share and popularity of new energy electric vehicles, as a representative of clean energy transportation, are increasing year by year. In order to ensure the normal operation of new energy electric vehicles and optimize the user's charging experience, it is particularly important to control the charging behavior of electric vehicles. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present application provides a new energy electric vehicle charging monitoring method and system based on artificial intelligence.

[0004] A new energy electric vehicle charging monitoring method based on artificial intelligence, the method comprising:

[0005] Acquiring original charging data of the new energy electric vehicle, wherein the original charging data includes ambient temperature, battery data of the new energy electric vehicle, and user preference data;

[0006] Input the raw charging data into a pre-trained charging monitoring model for analysis; wherein the charging monitoring model is trained based on historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as a training data set, and is used to monitor the charging behavior of new energy electric vehicles;

[0007] The charging prediction data of the new energy electric vehicle is generated according to the output result of the charging monitoring model.

[0008] In one embodiment of the present application, the charging monitoring model is a fusion model, and the charging monitoring model includes at least a battery monitoring module, a charging behavior suggestion module, and a charging time prediction module; the charging prediction data includes at least a battery health rating, a recommended charging strategy, and a charging prediction completion time;

[0009] The battery monitoring module is used to monitor the usage status of the battery of the new energy electric vehicle and output a battery health rating;

[0010] The charging behavior suggestion module is used to predict the future charging behavior of the new energy electric vehicle and output a recommended charging strategy;

[0011] The charging time prediction module is used to predict the single charging time of the new energy electric vehicle and output the predicted charging completion time.

[0012] In one embodiment of the present application, inputting the raw charging data into a pre-trained charging monitoring model for analysis includes:

[0013] After data preprocessing, the charging raw data is input into a pre-trained charging detection and monitoring model for analysis; wherein the data preprocessing includes but is not limited to vectorizing the charging raw data.

[0014] In one embodiment of the present application, the method further includes:

[0015] At least one of the battery health rating, the recommended charging strategy and the predicted charging completion time is displayed on the user interface according to the current operating status of the new energy electric vehicle.

[0016] In one embodiment of the present application, the method further includes:

[0017] The recommended charging strategy is sent to the control system of the new energy electric vehicle to automatically start the recommended charging strategy.

[0018] In one embodiment of the present application, the user preference data includes charging time period preference, charging cost sensitivity, and charging station type preference; the method further includes:

[0019] Collecting user preference data input by the user through the user interface or user terminal; and / or,

[0020] The user preference data is obtained by analyzing the user's historical charging behavior data.

[0021] In one embodiment of the present application, the method further includes:

[0022] The actual charging data of the new energy electric vehicle is monitored in real time, the actual charging data is compared with the charging prediction data, and the charging monitoring model is adjusted according to the comparison result.

[0023] A new energy electric vehicle charging monitoring system based on artificial intelligence, the system comprising:

[0024] A charging raw data acquisition module is used to obtain the charging raw data of the new energy electric vehicle, wherein the raw data includes the ambient temperature, the battery data of the new energy electric vehicle and the user preference data;

[0025] A charging data analysis module, used to input the raw charging data into a pre-trained charging monitoring model for analysis; wherein the charging monitoring model is trained based on historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as a training data set, and is used to monitor the charging behavior of new energy electric vehicles;

[0026] The charging prediction module is used to generate charging prediction data of the new energy electric vehicle according to the output result of the charging monitoring model.

[0027] In one embodiment of the present application, the system further includes: a display module for displaying at least one of the battery health rating, the recommended charging strategy and the predicted charging completion time according to the current operating status of the new energy electric vehicle.

[0028] In one embodiment of the present application, the charging raw data acquisition module is connected to the battery sensor, environmental sensor, and display module of the new energy electric vehicle to collect corresponding data.

[0029] This application obtains the original charging data of new energy electric vehicles, analyzes it through a pre-trained charging monitoring model, and generates charging prediction data for new energy electric vehicles. The original charging data includes ambient temperature, battery data of new energy electric vehicles, and user preference data. The charging monitoring model is trained based on the historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as training data sets. Charging prediction is performed based on the original charging data, and the charging monitoring model is trained in advance to improve the accuracy of charging predictions provided to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The present invention is a flowchart of a new energy electric vehicle charging monitoring method based on artificial intelligence provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clear, the exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited to the embodiments described here.

[0032] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0033] The battery of a new energy electric vehicle, as its core component, affects the battery life and driving experience. In the related art, the battery's design physical parameters are usually used as benchmark parameters, and the charging recommendations are determined based on the comparison between the real-time detected battery remaining capacity and the accurate parameters. The batteries of new energy electric vehicles are subject to attenuation and aging. As the usage time increases, there is an error between the benchmark parameters and the actual total capacity of the battery, which may lead to inaccurate charging recommendations. In addition, there are many factors that affect the charging of new energy electric vehicles, such as the user's frequency of use, the configuration of charging piles in the user's location, and the user's preferences. Based on this, the present application provides a new energy electric vehicle charging monitoring method and system based on artificial intelligence to improve the accuracy of charging predictions.

[0034] In one embodiment, Figure 1 As shown, a new energy electric vehicle charging monitoring method based on artificial intelligence is provided, and the method is applied to the control system of a new energy electric vehicle as an example for explanation, including the following steps:

[0035] S110, obtaining original charging data of the new energy electric vehicle.

[0036] Among them, the charging raw data includes ambient temperature, battery data of new energy electric vehicles and user preference data.

[0037] The ambient temperature has a significant impact on the battery performance of new energy electric vehicles. Changes in ambient temperature can directly affect the capacity of the battery. Generally speaking, the capacity of the battery will increase at higher temperatures and decrease at lower temperatures. The charging and discharging efficiency of the battery at different temperatures also varies. At lower temperatures, the charging and discharging efficiency of the battery is low, and the energy conversion efficiency is poor. At higher temperatures, the internal reaction rate of the battery is accelerated, the energy transmission is smoother, the charging and discharging efficiency of the battery will be improved, and the energy conversion efficiency will also increase accordingly. The control system can collect the ambient temperature through the temperature sensor.

[0038] The battery data of new energy electric vehicles may include battery temperature, voltage, current, charge and discharge cycle, real-time power, etc. The control system can collect battery data through battery sensors.

[0039] Different users have different charging behaviors and usage habits. Predictions based solely on the remaining battery level are less convenient, resulting in users being unable to charge at the right time and at the right electricity price while meeting their travel needs. Based on this, this application introduces user preference data to solve the user habit problem. User preference data may include user charging time period preferences, charging cost sensitivity, charging station type preferences, etc. The control system can collect user preference data input by the user through the user interface or user terminal, or obtain user preference data from the user's historical charging behavior data through statistical analysis, anomaly analysis, and other methods. Taking user preference data into consideration can provide charging suggestions that meet the individual needs of users while meeting their car needs.

[0040] S120, inputting the raw charging data into a pre-trained charging monitoring model for analysis.

[0041] Among them, the charging monitoring model is trained based on the historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as training data sets, and is used to monitor the charging behavior of new energy electric vehicles. The historical battery data and historical driving data are time series data, which are the actual driving data or test data of the battery of the same model. The historical driving data may include vehicle speed, driving distance, driving frequency, etc. The regional charging pile data may be a distribution map of charging piles in the region to facilitate charging path planning. The training data set of the charging monitoring model includes time series data, fixed design parameter data, image data, etc., and the data structure is relatively complex. In some cases, the charging monitoring model can be composed of multiple independent models, which are trained separately based on the analysis purpose and used for power prediction, charging pile path planning, anomaly detection, etc. The charging monitoring model can also be a fusion model, including multiple prediction modules, and the output results of each prediction module are further fused to output charging prediction data. The fusion model can be a model with strong prediction and decision-making capabilities trained based on a large model framework, using massive data, and through advanced algorithms and technologies.

[0042] In a specific implementation, the control system can input the raw charging data into a pre-trained charging monitoring model for analysis. In some cases, the control system can pre-process the raw charging data, such as data cleaning, normalization, time series processing, etc., to improve the standardization of the raw data.

[0043] S130, generating charging prediction data for the new energy electric vehicle according to the output result of the charging monitoring model.

[0044] Among them, the charging prediction data may include charging time interval, charging power, charging pile selection, estimated charging time, charging completion time prediction, etc., and may also include battery health status prediction. The charging prediction data may be real-time data, which is provided to users through the display module of the new energy electric vehicle or the user's mobile terminal, so that users can understand the power status in real time and arrange charging in time.

[0045] In the above-mentioned artificial intelligence-based new energy electric vehicle charging monitoring method, the charging raw data of the new energy electric vehicle is obtained and analyzed through a pre-trained charging monitoring model to generate charging prediction data for the new energy electric vehicle. The charging raw data includes ambient temperature, battery data of the new energy electric vehicle and user preference data, and the charging monitoring model is trained based on the historical battery data, historical driving data and regional charging pile data of the new energy electric vehicle as a training data set. Charging prediction is performed based on the charging raw data, and the charging monitoring model is trained in advance to improve the accuracy of charging prediction provided to users.

[0046] In one embodiment, the charging monitoring model may be a fusion model, which may be a large model including a plurality of sub-modules, each of which processes a corresponding analysis purpose, and the output results of each sub-module are further fused to obtain a prediction result.

[0047] In this embodiment, the charging raw data can be vectorized and then input into the battery module, charging behavior suggestion module, and charging time prediction module for processing, and the output results are further integrated to obtain charging prediction data. The charging prediction data includes at least the battery health rating, the recommended charging strategy, and the charging prediction completion time.

[0048] Specifically, the battery monitoring module can be used to monitor the battery usage status of the new energy electric vehicle and output the battery health rating; the charging behavior recommendation module can be used to predict the future charging behavior of the new energy electric vehicle and output the recommended charging strategy, where the recommended charging strategy can include charging time interval, charging pile selection and charging power selection. The charging time prediction module can be used to predict the single charging time of the new energy electric vehicle and output the predicted charging completion time.

[0049] The solution of the above-mentioned embodiment processes the raw charging data through a fusion model. On the one hand, it deeply mines data associations from multi-dimensional data to improve the accuracy of charging prediction. On the other hand, it realizes multi-dimensional predictions such as battery health, charging strategy, and charging time prediction through one model, thereby improving the comprehensiveness of charging prediction. It can also reduce repeated data processing and improve the efficiency of charging prediction.

[0050] In one embodiment, the method further includes: displaying at least one of a battery health rating, a recommended charging strategy, and a predicted charging completion time on a user interface according to a current operating status of the new energy electric vehicle.

[0051] In this embodiment, the power forecast is a comprehensive forecast. Through a one-time data input, the model input contains forecast data of different dimensions. In order to facilitate user viewing, the different dimensions of the forecast data can be associated with the current operating status of the new energy electric vehicle, so that the user can get the right information at the right time, thereby improving the effectiveness of user interaction.

[0052] For example, when the control system detects that a new energy electric vehicle is started, a battery health rating may be popped up on the user interface of the new energy vehicle. For another example, when the control system detects that the remaining power is lower than a threshold, a recommended charging strategy may be popped up on the user interface. For another example, when charging is detected, the control system may display the predicted completion time of charging on the user interface. The control system may configure the association between the current operating status of the electric vehicle and each data sub-item in the charging prediction data according to actual needs, which is not specifically limited here.

[0053] The solution of the above embodiment improves the effectiveness of interaction by associating the charging prediction data with the current operating status.

[0054] In one embodiment, the method of each of the above embodiments further includes: sending the recommended charging strategy to the control system of the new energy electric vehicle to automatically start the recommended charging strategy.

[0055] In this embodiment, the recommended charging strategy may include charging time interval, charging pile selection, charging power selection, etc. The control system may automatically start charging according to the recommended charging strategy, realize the automation of charging prediction and charging execution, and improve user convenience.

[0056] In one embodiment, the user preference data includes charging period preference, charging cost sensitivity, and charging station type preference; the methods of the above embodiments also include: collecting user preference data input by the user through a user interface or a user terminal; and / or, analyzing the user preference data from the user's historical charging behavior data.

[0057] In this embodiment, user preference data can be used as an exceptional input, so that the output result of the charging monitoring model is more in line with the needs of the user and the accuracy of the prediction is improved.

[0058] In one embodiment, the methods of the above embodiments further include: real-time monitoring of actual charging data of the new energy electric vehicle, comparing the actual charging data with the charging prediction data, and adjusting the charging monitoring model according to the comparison result.

[0059] In this embodiment, the actual charging data may include the charging strategy actually selected by the user, the actual charging time of the user, etc. The actual charging data of each new energy electric vehicle can be used as a new data set to continue training the charging monitoring model so that the charging monitoring model better meets the needs of the user.

[0060] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present invention.

[0061] In one embodiment, a new energy electric vehicle charging monitoring system based on artificial intelligence is provided, the system comprising:

[0062] A charging raw data acquisition module is used to obtain the charging raw data of the new energy electric vehicle, wherein the raw data includes the ambient temperature, the battery data of the new energy electric vehicle and the user preference data;

[0063] A charging data analysis module, used to input the raw charging data into a pre-trained charging monitoring model for analysis; wherein the charging monitoring model is trained based on historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as a training data set, and is used to monitor the charging behavior of new energy electric vehicles;

[0064] The charging prediction module is used to generate charging prediction data of the new energy electric vehicle according to the output result of the charging monitoring model.

[0065] In one embodiment, the system further includes: a display module for displaying at least one of the battery health rating, the recommended charging strategy and the predicted charging completion time according to the current operating status of the new energy electric vehicle.

[0066] In one embodiment, the charging raw data acquisition module is connected to the battery sensor, environmental sensor, and display module of the new energy electric vehicle to collect corresponding data.

[0067] For the specific definition of the new energy electric vehicle charging monitoring device based on artificial intelligence, please refer to the definition of the new energy electric vehicle charging monitoring method based on artificial intelligence in the above text, which will not be repeated here. Each module in the above-mentioned new energy electric vehicle charging monitoring system based on artificial intelligence can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0068] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0069] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A new energy electric vehicle charging monitoring method based on artificial intelligence, characterized in that: The method comprises: Acquiring original charging data of the new energy electric vehicle, wherein the original charging data includes ambient temperature, battery data of the new energy electric vehicle, and user preference data; Input the raw charging data into a pre-trained charging monitoring model for analysis; wherein the charging monitoring model is trained based on historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as a training data set, and is used to monitor the charging behavior of new energy electric vehicles; The charging prediction data of the new energy electric vehicle is generated according to the output result of the charging monitoring model.

2. The method according to claim 1, characterized in that: The charging monitoring model is a fusion model, and the charging monitoring model at least includes a battery monitoring module, a charging behavior suggestion module, and a charging time prediction module; the charging prediction data at least includes a battery health rating, a recommended charging strategy, and a charging prediction completion time; The battery monitoring module is used to monitor the usage status of the battery of the new energy electric vehicle and output a battery health rating; The charging behavior suggestion module is used to predict the future charging behavior of the new energy electric vehicle and output a recommended charging strategy; The charging time prediction module is used to predict the single charging time of the new energy electric vehicle and output the predicted charging completion time.

3. The method according to claim 2, characterized in that The inputting the raw charging data into a pre-trained charging monitoring model for analysis includes: After data preprocessing, the charging raw data is input into a pre-trained charging detection and monitoring model for analysis; wherein the data preprocessing includes but is not limited to vectorizing the charging raw data.

4. The method according to claim 2, characterized in that: The method further comprises: At least one of the battery health rating, the recommended charging strategy and the predicted charging completion time is displayed on the user interface according to the current operating status of the new energy electric vehicle.

5. The method according to claim 4, characterized in that The method further comprises: The recommended charging strategy is sent to the control system of the new energy electric vehicle to automatically start the recommended charging strategy.

6. The method according to any one of claims 1 to 5, characterized in that: The user preference data includes charging time period preference, charging cost sensitivity, and charging station type preference; the method further includes: Collecting user preference data input by the user through the user interface or user terminal; and / or, The user preference data is obtained by analyzing the user's historical charging behavior data.

7. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: The actual charging data of the new energy electric vehicle is monitored in real time, the actual charging data is compared with the charging prediction data, and the charging monitoring model is adjusted according to the comparison result.

8. A new energy electric vehicle charging monitoring system based on artificial intelligence, characterized in that: The system comprises: A charging raw data acquisition module is used to obtain the charging raw data of the new energy electric vehicle, wherein the raw data includes the ambient temperature, the battery data of the new energy electric vehicle and the user preference data; A charging data analysis module, used to input the raw charging data into a pre-trained charging monitoring model for analysis; wherein the charging monitoring model is trained based on historical battery data, historical driving data, and regional charging pile data of new energy electric vehicles as a training data set, and is used to monitor the charging behavior of new energy electric vehicles; The charging prediction module is used to generate charging prediction data of the new energy electric vehicle according to the output result of the charging monitoring model.

9. The system according to claim 8, characterized in that The system further comprises: The display module is used to display at least one of the battery health rating, the recommended charging strategy and the predicted charging completion time according to the current operating status of the new energy electric vehicle.

10. The system according to claim 9, characterized in that The charging raw data acquisition module is connected to the battery sensor, environmental sensor and display module of the new energy electric vehicle to collect corresponding data.

Images