Li-ion Battery Aging Estimation Using Particle Swarm Optimization Based Feedforward Neural Network

Abstract

Battery Management System (BMS) is a critical component in modern electrical technology. The exact knowledge of the state of health and capacity impact is useful for the estimation and control strategy of battery. Therefore, this paper proposed the particle swarm optimization-based Feedforward Neural Network (PSO-FNN) for Battery Aging Estimate (BAE). This PSO is used to optimize the weights and biases of the FNN. For validating the proposed method, conventional FNN was simulated with battery data sets provided by NASA Prognostics Center of Excellence (PCoE) and compared to the proposed method. The simulation results show the performance of PSO-FNN is noticeably better in relatively volatile systems.