Abstract
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.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.