Citation

Zhu Y, Gao C. Design Eng. 2021; 2021(7): 96-112.

Copyright

(Copyright © 2021, Editorial Office of Design Engineering)

DOI

unavailable

PMID

unavailable

Abstract

The traditional electric vehicle operation and maintenance system is not timely and comprehensive to provide users with safety information, and the prediction accuracy of lithium-ion battery residual life is low. Based on this, an electric vehicle operation and maintenance system based on Internet of vehicles is designed. The system consists of three parts: slave computer, mobile app and cloud server. The slave computer can effectively collect and detect the data of electric vehicles in real time, and the cloud server can process and store the information. The mobile app can display the diagnosis of electric vehicles in all aspects, and can timely inform the user of the cause and treatment of the fault. In order to solve the problem that the prediction accuracy of residual life of lithium-ion battery is insufficient, a deep learning network model combining convolution neural network with long-term and short-term memory recurrent neural network is used for online prediction. The test results show that the system can realize the functions of safety diagnosis, fault prompt and safety warning of electric vehicles, and the root mean square error of residual life prediction of lithium battery is less than 4%, which can promote the improvement of operation and maintenance management system of electric vehicles to a certain extent.

Language: en