Estimation of Li-ion battery SOH using Fletcher-Reeves based ANFIS

With the wide application of batteries, the battery state of health (SOH) is increasingly concerned by people. The battery SOH reflects its ability to store charge and plays a key role in electric power systems. This paper proposes an adaptive neural fuzzy inference system (ANFIS) based method to estimate the battery SOH. The main steps of the proposed method include model creating, model training and SOH estimation. The constant current charging time, the voltage drop at the beginning of discharge and the released energy within a certain depth of discharge are used as the inputs for the model training. Since the basic ANFIS algorithm has large estimation errors and the model trains slowly, A Fletcher-Reeves based method is proposed to improve the basic ANFIS. The trained model is then used for the estimation of the SOH. Experimental results show that the Fletcher-Reeves based ANFIS method is effective and efficient.