期刊名称：Advances in Electrical and Computer Engineering
印刷版ISSN：1582-7445
电子版ISSN：1844-7600
出版年度：2019
卷号：19
期号：3
页码：3-10
DOI：10.4316/AECE.2019.03001
出版社：Universitatea "Stefan cel Mare" Suceava
摘要：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.
