Accurately predicting the remaining mileage of electric vehicles (EVs) can effectively alleviate user's mileage anxiety and develop refinement of energy management strategy. However, traditional prediction methods not only consume time and resources, but also accumulate errors and lack interpretability. In this paper, we proposed a model based on dimension expansion and model fusion strategy, which uses the extreme gradient boosting (XGBoost) algorithm to directly predict the remaining mileage of EVs. After pre‐processing the real running data of EVs, we constructed the field of remaining driving range and analyzed the relationship between features and remaining driving range, and then directly predicted the remaining driving mileage. Compared with other machine learning methods, XGBoost model has the highest accuracy. Then dimensional extended data set was obtained based on prior knowledge and symbol conversion, which improved the model performance. Finally, the model fusion strategy was adopted to further improve the generalization ability and stability of the model. The experimental results show that the Bootstrap aggregating (Bagging) fusion model has the highest predictive performance on the test set and outperformed other methods. The maximum RAE is not more than 3.5%, RMSE is less than 3km and MAE is about 2 km.
Fault prediction is an important part of the safe operation and maintenance of pure electric vehicles, and it is crucial to predict faults efficiently and accurately. To address the problems that the pure electric vehicle fault prediction model has less than ideal prediction effect and classification bias to most classes due to unbalanced data set categories and high dimensionality of features, this paper firstly obtains a low dimensional balanced dataset based on hybrid sampling and joint feature selection. Then the classification ability of the model is improved through ensemble learning. Finally, a new hybrid model STLRF‐Stack is proposed to realize efficient fault prediction of pure electric vehicles. This paper is validated on a real operating dataset of pure electric vehicles. The experimental results show that the prediction effect of the hybrid model proposed in this paper is better than that of the single model and related literature. In addition, this model can successfully predict the fault 5 min before the actual fault of electric vehicles occurs, which provides the drivers with the opportunity of accident prevention and early treatment. Therefore, the model has specific feasibility and practical application value.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.