Derivation and Comparison of Open-loop and Closed-loop Neural Network Battery State-of-Charge Estimators

This paper presents two artificial neural network (ANN) based algorithms for battery state-of-charge (SOC) estimation. The SOC is an important quantity that must be estimated in real-time in many applications. ANN is a mathematical model that consists of interconnected artificial neurons inspired by biological neural networks and is used to predict the output of a dynamic system based on some historical data of that system. The first algorithm presented in this paper has an open-loop structure and known as nonlinear input output (NIO) feed-forward algorithm, while the second is closed loop called nonlinear autoregressive with exogenous input (NARX) feed-back algorithm. A pulse-discharge test is performed on a commercial lithium-ion (Li-ion) battery cell in order to collect data to evaluate those methods. Results are presented and compared.