This paper presents a neural network oriented approach for online estimation of the state of charge (SOC) for lithium-ion batteries. Unlike other estimation strategies, this proposed technique requires no knowledge of any battery parameter and no mathematical model of the battery rather it takes into consideration ambient temperature variations while estimating the SOC. Experimental results highlight the high SOC accuracy of the estimation despite the effects of aging and temperature on the battery.

Additional Metadata
Keywords Artificial Neural Network (ANN), Lithium Iron Phosphate (LiFePO4), Open Circuit Voltage (OCV ), State Of Charge (SOC), State of Health (SoH)
Persistent URL
Conference 25th IEEE International Symposium on Industrial Electronics, ISIE 2016
Chaoui, H, Ibe-Ekeocha, C.C. (Chinemerem Christopher), El Mejdoubi, A. (Asmae), Oukaour, A. (Amrane), Gualous, H. (Hamid), & Omar, N. (Noshin). (2016). State of charge estimation of LiFePO4 batteries with temperature variations using neural networks. In IEEE International Symposium on Industrial Electronics (pp. 286–291). doi:10.1109/ISIE.2016.7744904