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 ...
详细信息
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 bpneuralnetwork (bpNN)-basedvoltagepredictionmodels are developed, respectively, for the four kinds of driving conditions. based on the statistical analysis of prediction error and the comparison with other voltagepredictionmodels, 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 voltageprediction and fault diagnosis for EVs under various driving conditions during the entire operation process.
暂无评论