TY - GEN
T1 - The State Estimation Strategy of Vehicular Batteries under a CPS Architecture
AU - Dou, Jingwei
AU - He, Hongwen
AU - Li, Jianwei
AU - Tang, Yingjuan
AU - Zhao, Xuyang
AU - Wang, Yunlong
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Battery state estimation is always a crucial issue on electric vehicles (EVs), where the state-of-health (SOH) estimation and the state-of-charge (SOC) estimation are especially important. Given that, a state estimation strategy is proposed for vehicular power batteries in this paper. The cloud platform is connected with the vehicle terminal under a Cyber-Physical System (CPS) architecture. On the cloud platform, the SOH estimation is implemented with the long short-term memory (LSTM) algorithm, extracting three features from discharging processes as the inputs of the LSTM model. On the vehicle terminal, the SOC estimation is accomplished with the Extended Kalman Filter (EKF) algorithm, utilizing the estimated battery capacity to update the EKF equation. To identify the performance of the battery state estimation strategy, power batteries are experimented vehicularly on urban roads. Results illustrate that the proposed approach acquires high SOH and SOC estimation accuracy.
AB - Battery state estimation is always a crucial issue on electric vehicles (EVs), where the state-of-health (SOH) estimation and the state-of-charge (SOC) estimation are especially important. Given that, a state estimation strategy is proposed for vehicular power batteries in this paper. The cloud platform is connected with the vehicle terminal under a Cyber-Physical System (CPS) architecture. On the cloud platform, the SOH estimation is implemented with the long short-term memory (LSTM) algorithm, extracting three features from discharging processes as the inputs of the LSTM model. On the vehicle terminal, the SOC estimation is accomplished with the Extended Kalman Filter (EKF) algorithm, utilizing the estimated battery capacity to update the EKF equation. To identify the performance of the battery state estimation strategy, power batteries are experimented vehicularly on urban roads. Results illustrate that the proposed approach acquires high SOH and SOC estimation accuracy.
KW - Cyber-Physical System
KW - Extended Kalman Filter
KW - Long Short-Term Memory
KW - State-of Charge
KW - State-of-Health
UR - http://www.scopus.com/inward/record.url?scp=85138936839&partnerID=8YFLogxK
U2 - 10.1109/ICECET55527.2022.9873001
DO - 10.1109/ICECET55527.2022.9873001
M3 - Conference contribution
AN - SCOPUS:85138936839
T3 - International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022
BT - International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022
Y2 - 20 July 2022 through 22 July 2022
ER -