Estimation of state of charge and state of health of batteries using hybrid method and recurrent neural network.

This paper uses the hybrid method to estimate state of charge (SOC) for lead acid battery and the recurrent neural network (RNN) technique in order to estimate the state of health of a li-ion battery. The hybrid method utilises (i) the Coulomb Counting Method, (ii) the Electrical Circuit Model, and (iii) a mathematical model based on the Peukert Law in order to estimate state of charge of battery. In this work, the method that is used to measure the internal resistance of the battery in order to determine the open-circuit voltage and approximate the State of Charge is provided. The LSTM (Long-Short Term Memory) algorithm is used which is based on the recurrent neural network are to determine the State of Health (SOH) of a li-ion battery. Estimation of the battery's state of health can be derived from the NASA Li-ion battery dataset. [ABSTRACT FROM AUTHOR]