TY - JOUR
T1 - More intelligent and robust estimation of battery state-of-charge with an improved regularized extreme learning machine
AU - Jiao, Meng
AU - Wang, Dongqing
AU - Yang, Yan
AU - Liu, Feng
N1 - Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/9
Y1 - 2021/9
N2 - State-of-charge (SOC) is the key parameter for battery management, and the accurate estimation of SOC is pretty important for the safe and stable operation of lithium batteries. This paper investigates a regularized extreme learning machine trained with the spectral Fletcher–Reeves algorithm and tuned with the beetle antennae search algorithm (BAS-SFR-RELM) for intelligent and robust SOC estimation. In the experiment section, the urban dynamometer driving schedule (UDDS) profile and the Los Angeles 92 (LA92) profile are performed on a battery test platform for data collection. In the simulation section, the root mean squared error (RMSE) and the mean absolute error (MAE) are adopted to evaluate the performance of the model. Compared with the linear regression (LR), the back propagation (BP) network, the multi-layer perceptron (MLP), and the long short-term memory (LSTM) network, the BAS-SFR-RELM method can efficiently obtain the optimal regularization coefficient to effectively prevent overfitting with faster convergence speed. Increasing the number of hidden neurons in the BAS-SFR-RELM appropriately can improve the SOC estimation precision.
AB - State-of-charge (SOC) is the key parameter for battery management, and the accurate estimation of SOC is pretty important for the safe and stable operation of lithium batteries. This paper investigates a regularized extreme learning machine trained with the spectral Fletcher–Reeves algorithm and tuned with the beetle antennae search algorithm (BAS-SFR-RELM) for intelligent and robust SOC estimation. In the experiment section, the urban dynamometer driving schedule (UDDS) profile and the Los Angeles 92 (LA92) profile are performed on a battery test platform for data collection. In the simulation section, the root mean squared error (RMSE) and the mean absolute error (MAE) are adopted to evaluate the performance of the model. Compared with the linear regression (LR), the back propagation (BP) network, the multi-layer perceptron (MLP), and the long short-term memory (LSTM) network, the BAS-SFR-RELM method can efficiently obtain the optimal regularization coefficient to effectively prevent overfitting with faster convergence speed. Increasing the number of hidden neurons in the BAS-SFR-RELM appropriately can improve the SOC estimation precision.
KW - Beetle antennae search
KW - Overfitting
KW - Regularized extreme learning machine
KW - Spectral Fletcher–Reeves
KW - State-of-charge
UR - http://www.scopus.com/inward/record.url?scp=85111539741&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85111539741&partnerID=8YFLogxK
U2 - 10.1016/j.engappai.2021.104407
DO - 10.1016/j.engappai.2021.104407
M3 - Article
AN - SCOPUS:85111539741
SN - 0952-1976
VL - 104
JO - Engineering Applications of Artificial Intelligence
JF - Engineering Applications of Artificial Intelligence
M1 - 104407
ER -