Modeling of Back-Propagation Neural Network Based State-of-Charge Estimation for Lithium-Ion Batteries with Consideration of Capacity Attenuation

Abstract

The state of charge of lithium-ion batteries reflects the power available in the battery. Precise SOC estimation is a challenging task for battery management system. In this paper, a novel hybrid method by fusion of back-propagation (BP) neural network and improved ampere-hour counting method is proposed for SOC estimation of lithium-ion battery, which considers the impact of battery capacity attenuation on SOC estimation during the process of charging and discharging. The predictive accuracy and effectiveness of model are validated by NASA lithium-ion battery dataset. Moreover, the adaptability and feasibility of this method are further demonstrated using dataset of accelerated life experiment. The validation results indicate that the proposed method can provide accurate SOC estimation in different capacity attenuation stage.

Keywords

• attenuation measurement
• backpropagation
• battery management systems
• lithium batteries
• neural networks