최대방전전류와 BiLTSM을 이용한 전력상태 예측 연구

Abstract

An accurate SoC(state-of-charge) to estimate SoP(state-of-power) is the most remarkable technique for electric vehicles (EV). Hence, the estimation of battery state-of-charge prior to estimation of battery state-of-power requires more computation cost and time. This paper makes two contributions: (1) a data-driven SoP estimation method has been proposed to accurately capture the characteristics of the battery through the bidirectional long-short term memory algorithm, (2) the estimation of maximum discharge current based on voltage and SoC constraints using BiLSTM. The robustness of the proposed method has been verified by comparing the method with co-estimation and conventional method. The results show higher accuracy (approximately 24%) compared to the conventional state-of-power estimation method with 15.54 root-mean-square-error and faster computing time (approximately 66%) compared to co-estimation method with 2015 seconds calculation time, which made the proposed SoP estimation more efficient and reliable for the electric vehicles application.