Multifunctional controller for new energy automobile and new energy automobile

Abstract

The invention provides a multifunctional controller for a new energy automobile and the new energy automobile, and relates to the technical field of new energy automobile control. The multifunctional controller for the new energy automobile comprises a data collection module, a data processing module, a prediction module, a storage system, a communication system, a user interface, a software system, a battery management system, an auxiliary driving system, a safety system, an emotion recognition module, a power supply system and a continuous learning system. Through the prediction model and time sequence analysis, the charging and discharging strategy of the battery is optimized, the service life of the battery is prolonged, the energy efficiency is improved, a power system is optimized according to real-time data and a prediction result, the performance and efficiency of the vehicle are improved, and thermal management of the vehicle is optimized according to weather forecast and real-time traffic information. The optimal performance can be kept under different weather conditions, and the system can automatically adjust the internal environment, such as temperature and music playing, of the vehicle by analyzing the emotional state of the driver so as to adapt to the emotion of the driver.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicle control, and in particular to a multifunctional controller for a new energy vehicle and a new energy vehicle. Background Art

[0002] New energy vehicles refer to vehicles that use unconventional vehicle fuels as a power source, or use conventional vehicle fuels and new vehicle power devices, and integrate advanced technologies in vehicle power control and drive to form vehicles with advanced technical principles, new technologies, and new structures. New energy vehicles include pure electric vehicles, extended-range electric vehicles, hybrid vehicles, fuel cell electric vehicles, and hydrogen engine vehicles. The multifunctional controller of new energy vehicles is the core part of the vehicle's electronic control system. It is responsible for coordinating and managing multiple key systems of the vehicle, including the power system, battery management system, thermal management system, etc. This controller is usually called a vehicle controller.

[0003] At present, there are still some problems in the use of multi-function controllers for new energy vehicles. Traditional systems may not be able to effectively manage the discharge process of the battery, resulting in shortened battery life and performance degradation. They cannot optimize vehicle performance based on real-time data and prediction results, resulting in energy waste and inefficiency. They cannot provide sufficient personalized options, resulting in poor user experience. Therefore, technical personnel in this field provide a multi-function controller for new energy vehicles and new energy vehicles to solve the problems raised in the above background technology. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the deficiencies in the prior art, the present invention provides a multifunctional controller for new energy vehicles and a new energy vehicle, which solves the problems that traditional systems may not be able to effectively manage the discharge process of the battery, resulting in shortened battery life and performance degradation, and cannot optimize vehicle performance based on real-time data and prediction results, resulting in energy waste and inefficiency, and cannot provide sufficient personalized options, resulting in poor user experience.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a multifunctional controller for new energy vehicles, including a collection module, using a camera and a microphone to collect the driver's facial expression and voice data, the vehicle's real-time data speed, acceleration, battery status, the user's historical driving habits, real-time traffic information, weather forecast, and user schedule;

[0008] Data processing and storage systems for processing collected data, executing prediction models and optimization algorithms, and storing historical data and parameters of prediction models;

[0009] Communication system: The vehicle communication module is used to receive real-time traffic information, weather forecast, user schedule and other data, and the assisted driving system interface is used to exchange data with the assisted driving system;

[0010] User interface, instrument panel display for displaying real-time information and prediction results to the driver, mobile application or in-vehicle system for providing user interaction interface, allowing users to view and adjust battery management settings, and interact with users;

[0011] Software system: The prediction module is used to predict future driving behavior and route selection based on historical data and real-time data. The battery management algorithm is used to optimize the battery charging and discharging strategy based on the prediction results and the information provided by the assisted driving. The user behavior analysis module is used to analyze the user's historical driving habits and provide personalized suggestions.

[0012] Battery management system: battery status monitoring is used to monitor battery voltage, current, temperature and other parameters in real time; battery health monitoring is used to monitor battery health and predict battery life;

[0013] In the assisted driving system, the path planning module is used to plan the path based on real-time traffic information and weather forecasts, and the driving behavior prediction module is used to predict the driver's driving behavior;

[0014] Safety system: The safety monitoring module is used to monitor the battery status to ensure that the battery works safely and efficiently, and the fault diagnosis module is used to detect and handle battery faults in a timely manner;

[0015] Power system: The power management module is used to manage the battery charging and discharging process to ensure stable operation of the system;

[0016] A continuous learning system, where machine learning algorithms are used to continuously optimize prediction models and battery management strategies based on new data;

[0017] By collecting the vehicle's real-time data, speed, acceleration and battery status, the user's historical driving habits, real-time traffic information, weather forecast and user schedule, and combining the prediction module, historical habits and road conditions provided by assisted driving to optimize the battery discharge size, the detailed steps are as follows:

[0018] S1. Data collection: vehicle status data collects speed, acceleration and battery status data through vehicle sensors; user historical driving habits collect user historical driving habits data through the vehicle system; real-time traffic information receives real-time traffic information through the vehicle communication module; weather forecast receives weather forecast data through the vehicle communication module; user schedule obtains user schedule data through the vehicle system or mobile application;

[0019] S2. Data processing: Data cleaning removes noise and outliers, and data fusion combines data from different sources to form a unified data set;

[0020] S3. Prediction model, machine learning model uses historical data set to train machine learning model, uses random forest machine learning model, uses training data set to train model, and finds the best parameters;

[0021] S3.1. Data preparation, assuming that this function is used to load a dataset, return the feature set x and the target variable y, and divide the dataset into a training set (80%) and a test set (20%);

[0022] S3.2. Initialize, random forest model, create a random forest regressor instance;

[0023] S3.3. Set the parameter range and define a dictionary containing the parameters to be optimized and their possible values, including the number of trees, the maximum depth of the tree, and the minimum number of samples required for internal nodes;

[0024] S3.4. Validation, use grid search to find the best parameters, use grid search for cross validation, evaluate the performance of different parameter combinations, here use 5-fold cross validation, and use negative mean square error as the scoring criterion, and use the training set data to fit the grid search model;

[0025] S3.5. Output the best parameters and obtain the best parameter combination;

[0026] S3.6. Determine the model, train the final model using the optimal parameters, create a new random forest regressor instance using the optimal parameters, and train the model using the optimal parameters;

[0027] S3.7. Evaluate the model, use the test set data to predict the target variable, calculate the mean square error between the predicted value and the true value, and print the mean square error;

[0028] S4. Time series analysis, the autoregressive integrated moving average model is a statistical model used to analyze and predict time series data. It combines three parts: autoregression (AR), difference (I) and moving average (MA). The detailed steps are as follows:

[0029] S4.1. Data preparation: collect and clean time series data;

[0030] S4.2.Stationary test: Use ADF test to test the stationary nature of the time series.

[0031] S4.3. Difference: If the time series is not stationary, perform difference until the series becomes stationary.

[0032] S4.4. Model identification: determine the order of AR and MA based on the autocorrelation function and partial autocorrelation function graphs;

[0033] S4.5. Model fitting, fit the ARIMA model using the selected AR and MA orders;

[0034] S4.6. Model diagnosis, check whether the residual is white noise;

[0035] S4.7. Prediction, use the fitted model to make predictions;

[0036] Its ARIMA model can be expressed as:

[0037] ARIMA(p,d,q)=AR(p)+I(d)+MA(q)

[0038] Among them, p is the order of the autoregressive term, d is the difference order, and q is the order of the moving average term;

[0039] S5. Battery management algorithm, battery discharge optimization optimizes the battery charging and discharging strategy based on the prediction results and path planning results. Energy-saving driving suggestions provide energy-saving driving suggestions to the driver. The detailed steps are as follows:

[0040] S5.1. Control output, predict the user's future driving behavior and route selection based on the above prediction model, use time series analysis method to predict the battery usage pattern and energy demand, optimize the battery charging and discharging strategy based on the prediction results and path planning results, and adjust the battery charging rate and discharging rate based on the predicted battery demand and path planning results;

[0041] S5.2. Provide suggestions, energy-saving driving suggestions. Provide energy-saving driving suggestions to the driver based on the predicted battery demand and route planning results, such as suggesting to use economic driving mode or slow down in advance to save energy;

[0042] S5.3. User behavior analysis: analyzing the user's historical driving habits and providing personalized suggestions;

[0043] S5.4. Battery status monitoring, battery health monitoring, monitoring battery health status, and predicting battery life;

[0044] S5.5. Safety system, monitoring battery status to ensure safe and efficient operation of the battery;

[0045] S5.6. Power system, manages the battery charging and discharging process to ensure stable operation of the system;

[0046] S5.7. Continuous learning system to continuously optimize prediction models and battery management strategies based on new data.

[0047] Preferably, in the above step S3, ensure that the function loads the data set correctly, ensure that x and y contain the correct features and target variables, and if the data set is large, adjust the parameters of GridSearchCV and the number of CPU cores for parallel computing to speed up the grid search process.

[0048] Preferably, the emotion recognition module is used to integrate emotion recognition technology, analyze the driver's facial expressions and voice, adjust the internal environment of the vehicle to adapt to the driver's emotional state, provide a personalized driving experience according to the driver's preferences and habits, and adjust the seat position and driving mode. The detailed steps are as follows:

[0049] A. Emotion recognition: Use cameras and microphones to collect the driver's facial expression and voice data, pre-process the collected data, such as cropping and normalization of facial expression images, noise reduction of voice signals, etc., and extract features from the pre-processed data, such as feature points of facial expressions, pitch and rhythm of voice;

[0050] B. Emotion classification: Use machine learning models to classify the extracted features, identify the driver’s emotional state, and adjust the vehicle’s interior environment, temperature, and music playback based on the identified emotional state;

[0051] C. User preference learning: Collect historical user interaction data, seat position and driving mode selection, use machine learning algorithms to build a user preference model, provide drivers with personalized driving experience recommendations based on the user preference model, and dynamically adjust the recommended personalized settings based on real-time user feedback.

[0052] Preferably, according to the above step B, cluster analysis is performed, using the K-means algorithm to cluster user data to discover preference patterns of user groups, and using a collaborative filtering algorithm to recommend personalized settings based on the user's historical behavior and the behavior of similar users.

[0053] A device for a new energy vehicle comprises a vehicle body, a battery pack, a motor, a PTC heater, a compressor, a fast charging plug, a slow charging port, a battery and a controller, wherein the controller adopts the multifunctional controller mentioned above.

[0054] (III) Beneficial effects

[0055] The present invention provides a multifunctional controller for a new energy vehicle and a new energy vehicle, which has the following beneficial effects:

[0056] 1. In the present invention, the battery charging and discharging strategy is optimized through prediction model and time series analysis, the battery life is extended and the energy efficiency is improved. According to the real-time data and prediction results, the power system is optimized to improve the performance and efficiency of the vehicle. According to the weather forecast and real-time traffic information, the thermal management of the vehicle is optimized to ensure that the best performance can be maintained under different climatic conditions. According to the new data, the prediction model and battery management strategy are continuously optimized to improve the adaptability and efficiency of the system.

[0057] 2. In the present invention, by analyzing the driver's emotional state, the system can automatically adjust the vehicle's internal environment, such as temperature and music playback, to adapt to the driver's emotions, thereby providing a more comfortable and pleasant driving experience. The system can provide the driver with personalized driving experience suggestions based on the user's historical interaction data and preference model, such as adjustment of seat position and driving mode, so that the vehicle better meets the user's personal needs. When the driver's emotions fluctuate greatly, the system can provide safe driving suggestions or warnings to help the driver stay calm and reduce driving risks caused by emotional fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic diagram of the flow of the prediction model and time series analysis of the present invention;

[0059] Figure 2 Schematic diagram of the flow of the emotion recognition module of the present invention. DETAILED DESCRIPTION

[0060] 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.

[0061] Embodiment 1:

[0062] like Figure 1-2 As shown, an embodiment of the present invention provides a multifunctional controller for a new energy vehicle, including a collection module, which uses a camera and a microphone to collect the driver's facial expression and voice data, the vehicle's real-time data speed, acceleration, battery status, the user's historical driving habits, real-time traffic information, weather forecast, and user schedule;

[0063] Data processing and storage systems for processing collected data, executing prediction models and optimization algorithms, and storing historical data and parameters of prediction models;

[0064] Communication system: The vehicle communication module is used to receive real-time traffic information, weather forecast, user schedule and other data, and the assisted driving system interface is used to exchange data with the assisted driving system;

[0065] User interface, instrument panel display for displaying real-time information and prediction results to the driver, mobile application or in-vehicle system for providing user interaction interface, allowing users to view and adjust battery management settings, and interact with users;

[0066] Software system: The prediction module is used to predict future driving behavior and route selection based on historical data and real-time data. The battery management algorithm is used to optimize the battery charging and discharging strategy based on the prediction results and the information provided by the assisted driving. The user behavior analysis module is used to analyze the user's historical driving habits and provide personalized suggestions.

[0067] Battery management system: battery status monitoring is used to monitor battery voltage, current, temperature and other parameters in real time; battery health monitoring is used to monitor battery health and predict battery life;

[0068] In the assisted driving system, the path planning module is used to plan the path based on real-time traffic information and weather forecasts, and the driving behavior prediction module is used to predict the driver's driving behavior;

[0069] Safety system: The safety monitoring module is used to monitor the battery status to ensure that the battery works safely and efficiently, and the fault diagnosis module is used to detect and handle battery faults in a timely manner;

[0070] Power system: The power management module is used to manage the battery charging and discharging process to ensure stable operation of the system;

[0071] A continuous learning system, where machine learning algorithms are used to continuously optimize prediction models and battery management strategies based on new data;

[0072] By collecting the vehicle's real-time data, speed, acceleration and battery status, the user's historical driving habits, real-time traffic information, weather forecast and user schedule, and combining the prediction module, historical habits and road conditions provided by assisted driving to optimize the battery discharge size, the detailed steps are as follows:

[0073] S1. Data collection: vehicle status data collects speed, acceleration and battery status data through vehicle sensors; user historical driving habits collect user historical driving habits data through the vehicle system; real-time traffic information receives real-time traffic information through the vehicle communication module; weather forecast receives weather forecast data through the vehicle communication module; user schedule obtains user schedule data through the vehicle system or mobile application;

[0074] S2. Data processing: Data cleaning removes noise and outliers, and data fusion combines data from different sources to form a unified data set;

[0075] S3. Prediction model, machine learning model uses historical data set to train machine learning model, uses random forest machine learning model, uses training data set to train model, and finds the best parameters;

[0076] S3.1. Data preparation, assuming that this function is used to load a dataset, return the feature set x and the target variable y, and divide the dataset into a training set (80%) and a test set (20%);

[0077] S3.2. Initialize, random forest model, create a random forest regressor instance;

[0078] S3.3. Set the parameter range and define a dictionary containing the parameters to be optimized and their possible values, including the number of trees, the maximum depth of the tree, and the minimum number of samples required for internal nodes;

[0079] S3.4. Validation, use grid search to find the best parameters, use grid search for cross validation, evaluate the performance of different parameter combinations, here use 5-fold cross validation, and use negative mean square error as the scoring criterion, and use the training set data to fit the grid search model;

[0080] S3.5. Output the best parameters and obtain the best parameter combination;

[0081] S3.6. Determine the model, train the final model using the optimal parameters, create a new random forest regressor instance using the optimal parameters, and train the model using the optimal parameters;

[0082] S3.7. Evaluate the model, use the test set data to predict the target variable, calculate the mean square error between the predicted value and the true value, and print the mean square error;

[0083] S4. Time series analysis, the autoregressive integrated moving average model is a statistical model used to analyze and predict time series data. It combines three parts: autoregression (AR), difference (I) and moving average (MA). The detailed steps are as follows:

[0084] S4.1. Data preparation: collect and clean time series data;

[0085] S4.2.Stationary test: Use ADF test to test the stationary nature of the time series.

[0086] S4.3. Difference: If the time series is not stationary, perform difference until the series becomes stationary.

[0087] S4.4. Model identification: determine the order of AR and MA based on the autocorrelation function and partial autocorrelation function graphs;

[0088] S4.5. Model fitting, fit the ARIMA model using the selected AR and MA orders;

[0089] S4.6. Model diagnosis, check whether the residual is white noise;

[0090] S4.7. Prediction, use the fitted model to make predictions;

[0091] Its ARIMA model can be expressed as:

[0092] ARIMA(p,d,q)=AR(p)+I(d)+MA(q)

[0093] Among them, p is the order of the autoregressive term, d is the difference order, and q is the order of the moving average term;

[0094] S5. Battery management algorithm, battery discharge optimization optimizes the battery charging and discharging strategy based on the prediction results and path planning results. Energy-saving driving suggestions provide energy-saving driving suggestions to the driver. The detailed steps are as follows:

[0095] S5.1. Control output, predict the user's future driving behavior and route selection based on the above prediction model, use time series analysis method to predict the battery usage pattern and energy demand, optimize the battery charging and discharging strategy based on the prediction results and path planning results, and adjust the battery charging rate and discharging rate based on the predicted battery demand and path planning results;

[0096] S5.2. Provide suggestions, energy-saving driving suggestions. Provide energy-saving driving suggestions to the driver based on the predicted battery demand and route planning results, such as suggesting to use economic driving mode or slow down in advance to save energy;

[0097] S5.3. User behavior analysis: analyzing the user's historical driving habits and providing personalized suggestions;

[0098] S5.4. Battery status monitoring, battery health monitoring, monitoring battery health status, and predicting battery life;

[0099] S5.5. Safety system, monitoring battery status to ensure safe and efficient operation of the battery;

[0100] S5.6. Power system, manages the battery charging and discharging process to ensure stable operation of the system;

[0101] S5.7. Continuous learning system, continuously optimizes prediction models and battery management strategies based on new data, optimizes battery charging and discharging strategies through prediction models and time series analysis, extends battery life and improves energy efficiency, optimizes powertrain based on real-time data and prediction results, improves vehicle performance and efficiency, optimizes vehicle thermal management based on weather forecasts and real-time traffic information, ensures optimal performance under different climate conditions, continuously optimizes prediction models and battery management strategies based on new data, and improves system adaptability and efficiency.

[0102] In step S3 above, make sure that the function loads the dataset correctly and that x and y contain the correct features and target variables. If the dataset is large, you need to adjust the parameters of GridSearchCV and the number of CPU cores for parallel computing to speed up the grid search process and improve the accuracy of the calculation.

[0103] The emotion recognition module is used to integrate emotion recognition technology, analyze the driver's facial expressions and voice, adjust the vehicle's internal environment to adapt to the driver's emotional state, provide a personalized driving experience according to the driver's preferences and habits, and adjust the seat position and driving mode. The detailed steps are as follows:

[0104] A. Emotion recognition: Use cameras and microphones to collect the driver's facial expression and voice data, pre-process the collected data, such as cropping and normalization of facial expression images, noise reduction of voice signals, etc., and extract features from the pre-processed data, such as feature points of facial expressions, pitch and rhythm of voice;

[0105] B. Emotion classification: Use machine learning models to classify the extracted features, identify the driver’s emotional state, and adjust the vehicle’s interior environment, temperature, and music playback based on the identified emotional state;

[0106] C. User preference learning, collect users' historical interaction data, seat position and driving mode selection, use machine learning algorithms to build a user preference model, and provide drivers with personalized driving experience suggestions based on the user preference model. Dynamically adjust the recommended personalized settings based on the user's real-time feedback. By analyzing the driver's emotional state, the system can automatically adjust the vehicle's internal environment, such as temperature and music playback, to adapt to the driver's emotions, thereby providing a more comfortable and pleasant driving experience. Based on the user's historical interaction data and preference model, the system can provide drivers with personalized driving experience suggestions, such as adjustment of seat position and driving mode, so that the vehicle is more in line with the user's personal needs. When the driver's emotions fluctuate greatly, the system can provide safe driving suggestions or warnings to help the driver stay calm and reduce driving risks caused by emotional fluctuations.

[0107] Preferably, according to the above step B, cluster analysis is performed, and the K-means algorithm is used to cluster the user data to discover the preference patterns of the user group, so as to better understand the common needs and characteristics of the user group. The collaborative filtering algorithm is used to recommend personalized settings based on the user's historical behavior and the behavior of similar users, so as to provide more accurate personalized suggestions.

[0108] A device for a new energy vehicle comprises a vehicle body, a battery pack, a motor, a PTC heater, a compressor, a fast charging plug, a slow charging port, a battery and a controller, wherein the controller adopts the multifunctional controller mentioned above.

[0109] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multifunctional controller for new energy vehicles, characterized in that: Including data collection module, data processing, prediction module, storage system, communication system, user interface, software system, battery management system, assisted driving system, safety system, emotion recognition module, power system and continuous learning system; By collecting the vehicle's real-time data, speed, acceleration and battery status, the user's historical driving habits, real-time traffic information, weather forecast and user schedule, and combining the prediction module, historical habits and road conditions provided by assisted driving to optimize the battery discharge size, the detailed steps are as follows: S1. Data collection: vehicle status data collects speed, acceleration and battery status data through vehicle sensors; user historical driving habits collect user historical driving habits data through the vehicle system; real-time traffic information receives real-time traffic information through the vehicle communication module; weather forecast receives weather forecast data through the vehicle communication module; user schedule obtains user schedule data through the vehicle system or mobile application; S2. Data processing: Data cleaning removes noise and outliers, and data fusion combines data from different sources to form a unified data set; S3. Prediction model, machine learning model uses historical data set to train machine learning model, uses random forest machine learning model, uses training data set to train model, and finds the best parameters; S3.

1. Data preparation, assuming that this function is used to load a dataset, return the feature set x and the target variable y, and divide the dataset into a training set (80%) and a test set (20%); S3.

2. Initialize, random forest model, create a random forest regressor instance; S3.

3. Set the parameter range and define a dictionary containing the parameters to be optimized and their possible values, including the number of trees, the maximum depth of the tree, and the minimum number of samples required for internal nodes; S3.

4. Validation, use grid search to find the best parameters, use grid search for cross validation, evaluate the performance of different parameter combinations, here use 5-fold cross validation, and use negative mean square error as the scoring criterion, and use the training set data to fit the grid search model; S3.

5. Output the best parameters and obtain the best parameter combination; S3.

6. Determine the model, train the final model using the optimal parameters, create a new random forest regressor instance using the optimal parameters, and train the model using the optimal parameters; S3.

7. Evaluate the model, use the test set data to predict the target variable, calculate the mean square error between the predicted value and the true value, and print the mean square error; S4. Time series analysis, the autoregressive integrated moving average model is a statistical model used to analyze and predict time series data. It combines three parts: autoregression (AR), difference (I) and moving average (MA). The detailed steps are as follows: S4.

1. Data preparation: collect and clean time series data; S4.2.Stationary test: Use ADF test to test the stationary nature of the time series. S4.

3. Difference: If the time series is not stationary, perform difference until the series becomes stationary. S4.

4. Model identification: determine the order of AR and MA based on the autocorrelation function and partial autocorrelation function graphs; S4.

5. Model fitting, fit the ARIMA model using the selected AR and MA orders; S4.

6. Model diagnosis, check whether the residual is white noise; S4.

7. Prediction, use the fitted model to make predictions; Its ARIMA model can be expressed as: ARIMA(p,d,q)=AR(p)+I(d)+MA(q) Among them, p is the order of the autoregressive term, d is the difference order, and q is the order of the moving average term; S5. Battery management algorithm, battery discharge optimization optimizes the battery charging and discharging strategy based on the prediction results and path planning results. Energy-saving driving suggestions provide energy-saving driving suggestions to the driver. The detailed steps are as follows: S5.

1. Control output, predict the user's future driving behavior and route selection based on the above prediction model, use time series analysis method to predict the battery usage pattern and energy demand, optimize the battery charging and discharging strategy based on the prediction results and path planning results, and adjust the battery charging rate and discharging rate based on the predicted battery demand and path planning results; S5.

2. Provide suggestions, energy-saving driving suggestions. Provide energy-saving driving suggestions to the driver based on the predicted battery demand and route planning results, such as suggesting to use economic driving mode or slow down in advance to save energy; S5.

3. User behavior analysis: analyzing the user's historical driving habits and providing personalized suggestions; S5.

4. Battery status monitoring, battery health monitoring, monitoring battery health status, and predicting battery life; S5.

5. Safety system, monitoring battery status to ensure safe and efficient operation of the battery; S5.

6. Power system, manages the battery charging and discharging process to ensure stable operation of the system; S5.

7. Continuous learning system to continuously optimize prediction models and battery management strategies based on new data.

2. A multifunctional controller for new energy vehicles according to claim 1, characterized in that: In step S3 above, make sure the function loads the dataset correctly, make sure x and y contain the correct features and target variables, and if the dataset is large, adjust the parameters of GridSearchCV and the number of CPU cores for parallel computing to speed up the grid search process.

3. A multifunctional controller for new energy vehicles according to claim 1, characterized in that: The emotion recognition module is used to integrate emotion recognition technology, analyze the driver's facial expressions and voice, adjust the vehicle's internal environment to adapt to the driver's emotional state, provide a personalized driving experience according to the driver's preferences and habits, and adjust the seat position and driving mode. The detailed steps are as follows: A. Emotion recognition: Use cameras and microphones to collect the driver's facial expression and voice data, pre-process the collected data, such as cropping and normalization of facial expression images, noise reduction of voice signals, etc., and extract features from the pre-processed data, such as feature points of facial expressions, pitch and rhythm of voice; B. Emotion classification: Use machine learning models to classify the extracted features, identify the driver’s emotional state, and adjust the vehicle’s interior environment, temperature, and music playback based on the identified emotional state; C. User preference learning: Collect historical user interaction data, seat position and driving mode selection, use machine learning algorithms to build a user preference model, provide drivers with personalized driving experience recommendations based on the user preference model, and dynamically adjust the recommended personalized settings based on real-time user feedback.

4. A multifunctional controller for new energy vehicles according to claim 3, characterized in that: According to the cluster analysis in step B above, the K-means algorithm is used to cluster the user data to discover the preference patterns of the user group, and the collaborative filtering algorithm is used to recommend personalized settings based on the user's historical behavior and the behavior of similar users.

5. A device for new energy vehicles, comprising a vehicle body, a battery pack, a motor, a PTC heater, a compressor, a fast charging plug, a slow charging port, a battery and a controller, characterized in that: The controller adopts a multifunctional controller for new energy vehicles as described in any one of claims 1 to 4 above.

Images