Loading [MathJax]/extensions/MathZoom.js
Robust Adaptive Sliding-Mode Observer Using RBF Neural Network for Lithium-Ion Battery State of Charge Estimation in Electric Vehicles | IEEE Journals & Magazine | IEEE Xplore

Robust Adaptive Sliding-Mode Observer Using RBF Neural Network for Lithium-Ion Battery State of Charge Estimation in Electric Vehicles


Abstract:

This paper presents a robust sliding-mode observer (RSMO) for state-of-charge (SOC) estimation of a lithium-polymer battery (LiPB) in electric vehicles (EVs). A radial ba...Show More

Abstract:

This paper presents a robust sliding-mode observer (RSMO) for state-of-charge (SOC) estimation of a lithium-polymer battery (LiPB) in electric vehicles (EVs). A radial basis function (RBF) neural network (NN) is employed to adaptively learn an upper bound of system uncertainty. The switching gain of the RSMO is adjusted based on the learned upper bound to achieve asymptotic error convergence of the SOC estimation. A battery equivalent circuit model (BECM) is constructed for battery modeling, and its BECM is identified in real time by using a forgetting-factor recursive least squares (FFRLS) algorithm. The experiments under the discharge current profiles based on EV driving cycles are conducted on the LiPB to validate the effectiveness and accuracy of the proposed framework for the SOC estimation.
Published in: IEEE Transactions on Vehicular Technology ( Volume: 65, Issue: 4, April 2016)
Page(s): 1936 - 1947
Date of Publication: 19 May 2015

ISSN Information:

Funding Agency:


I. Introduction

With the rapid innovation of battery technologies, lithium-ion (Li-ion) batteries have exhibited outstanding performance, in comparison with other types of batteries such as lead–acid and nickel–metal hydride batteries. Li-ion batteries offer high energy and power density, fast charge capability, no memory effect, longer cycle life, and low self-discharge rate. These outstanding features facilitate Li-ion batteries as the most promising power sources for the eco-friendly electric vehicles (EVs) [1]– [3]. Among existing EV technologies, a reliable battery management system (BMS) is a remaining design challenge, and the pivotal function of this BMS is the indication of battery state of charge (SOC). The SOC reflects the ratio of the utilizable capacity to its nominal capacity [4]. It is substantial for managing battery energy utilization efficiently, preventing the battery from being overcharged and overdischarged [5], [6]. Thus, a well-developed method is essential for accurate SOC estimation.

References

References is not available for this document.