Research on the SOC Prediction of Lithium Ion Battery Based on the Improved Elman Neural Network Model

• Main Authors: Mengxiong Lu, Jingbin Song
• Format: Article
• Language: English
• Published: AIDIC Servizi S.r.l. 2017-12-01
• Series: Chemical Engineering Transactions
• Online Access: https://www.cetjournal.it/index.php/cet/article/view/804

Lithium ion battery has the characteristics of good thermal stability, high energy ratio, long cycle life and so on. As an energy supply component, lithium ion battery is the key electronic equipment and a component of complex systems. Lithium ion battery (Li-ion battery) plays a crucial role in the overall system. In the current global advocacy of low carbon and emission reduction, these characteristics of the Li-ion battery make it a new driving power for electric vehicles. The prediction of SOC (State of Charge) of Li-ion battery is one of the key technologies of battery management. The research of the SOC prediction of Li-ion battery is of great importance to the development of electric vehicle industry. In this paper, we propose an improved Elman neural network model to predict the SOC of Li-ion battery. At the end of the paper, we found that the improved prediction model can provide better SOC prediction services for Li-ion battery and the prediction results are more accurately.