Battery voltage fault diagnosis for electric vehicles considering driving condition variation

Abstract

To ensure the real‐time operation safety of electric vehicles (EVs), it is essential to diagnose the fault in a battery pack timely and accurately. In this paper, with considering driving condition, a battery voltage fault diagnosis method is proposed based on the real‐world operation data of EVs with a high sampling frequency. Firstly, based on driving behaviour, the driving condition of EVs is classified into four categories, and accordingly, the operation process is divided into four segments. The influencing mechanism of driving condition on battery voltage is revealed by detailed analysis on extracted operation segments. Secondly, four BP neural network (BPNN)‐based voltage prediction models are developed, respectively, for the four kinds of driving conditions. Based on the statistical analysis of prediction error and the comparison with other voltage prediction models, the superiority and stability of the four well‐trained BPNN models are verified. Thirdly, the voltage abnormity levels and thresholds for fault diagnosis are set considering driving condition differences. The effectiveness of the proposed method is verified using the actual operational data. The verification results show that the proposed method can achieve good voltage prediction and fault diagnosis for EVs under various driving conditions during the entire operation process.

Guest Editorial: Electro‐mobility for urban traffic and transportation

“…He has participated in several international and national research projects and other activities. Dalin Zhang 1 Sabah Mohammed 2 Alessandro Calvi 3…”

“…Zhang et al. [2] proposed a battery voltage fault diagnosis method. The voltage prediction models based on BP neural network (BPNN) were established, respectively, for four driving conditions of electric vehicles, and the superiority and stability of the four well‐trained BPNN models were verified.…”

Online Prediction of Electric Vehicle Battery Failure Using LSTM Network

“…With the growing sales, the safety of electric vehicles has become a topic of concern, and the number of reported electric vehicle fires has increased every year. According to incomplete statistics on the Internet, the number of spontaneous combustions reached 70 cases from January to November 2022, and it was found, using analysis, that 90% of the accidents were caused by power batteries [2]. Therefore, it is significant to study how to accurately predict and warn about failures in advance using historical vehicle data.…”