A comparative study of ANN and Kalman Filtering-based observer for SOC estimation

International Conference on Renewable Energies and Energy Efficiency 2017

Sassi, H Ben^1 ; Errahimi, F.^1 ; Es-Sbai, N.^1 ; Alaoui, C.^2

Laboratory of Renewable Energies and Intelligent Systems (LERSI), Faculty of Sciences and Technology, Sidi Mohamed Ben Abdellah University Fez, Box 2202, Fez, Morocco^1

University EUROMED, Fez, Morocco^2

关键词: Comparative studies;    Electrical vehicle battery;    High energy densities;    Kalman-filtering;    Operational modes;    SOC estimations;    State-of-charge estimation;    Status monitoring;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/161/1/012022/pdf
DOI  :  10.1088/1755-1315/161/1/012022

来源: IOP

【 摘 要 】

Electrical Vehicle Batteries (EVB) study has gained a lot of interest in recent years, with the aim of better managing their use, due to the high changes in the electric vehicle dynamics and operational modes, which could cause severe damages to the battery if not properly managed. Recently lithium-ion (Li-ion) batteries have become the most suitable technology for electric vehicles, because of their interesting features such as a relatively long cycle life, lighter weight and high energy density. However, there is a lot of work that is still needed to be done in order to ensure safe operating lithium-ion batteries, starting with their internal status monitoring, cell balancing within a battery pack and thermal management. In this paper, a comparative study of two different methods for state of charge estimation techniques are presented: Kalman filtering observers and artificial neural network based observers. The respective results are compared in terms of accuracy, implementation requirement, and overall performances.