Lithium‐ion battery state of charge estimation based on square‐root unscented Kalman filter

Abstract

This study represents a method for estimating the state of charge (SOC) of lithium-ion batteries using radial basis function (RBF) networks and square-root unscented Kalman filter (KF). The RBF network is trained offline by sampled data from the battery in the charging process. This type of neural network finds the non-linear relation which is required in the state-space equations. The state variables include the battery terminal voltage and the SOC, at the previous sample and the present sample, respectively. The proposed method is tested experimentally on a lithium-ion battery with 1.2 Ah capacity to estimate the actual SOC of the battery. The experimental results of the proposed method show some advantages, which include: (i) it is not very sensitive to determine, precisely, the measurement and process noise covariance matrices such as Kalman filter and (ii). It contains lower noise on the output, in comparison with Adaptive extended Kalman filter (EKF).

Lithium Polymer Battery State-of-Charge Estimation Based on Adaptive Unscented Kalman Filter and Support Vector Machine

“…Although the main drawback is their computational burden, Kalman filter-based methods prove to be an efficient algorithm to improve SOC estimation accuracy [14]- [17] [19]- [21]. The Kalman filter is widely used in system state estimation and has achieved expected efficiency and performance in many applications, such as aerospace, military, and other areas.…”

“…The research in [18] indicates that UKF is more accurate and easier to implement than EKF. Thus, L UKF has a higher accuracy over EKF in SOC estimation [19]- [21]. AUKF, with all the advantages of UKF, adaptively adjusts process noise covariance and measurement noise covariance in the estimation process.…”

“…Hence, LSSVM [22] is applied in this research to build the nonlinear battery model with limited initial training samples, which is different from other AUKF-based SOC estimation methods in literature [19]- [21]. In this paper, a moving window method is proposed for collecting enough training samples.…”

Charge equalisation for series‐connected LiFePO 4 battery strings

“…Lithium-ion batteries are developed and applied to electric vehicles. The advantages of lithium-ion battery are high energy density, small size, low self-discharge rate and no memory effect [5][6][7][8]. Owing to these benefits, the lithium-ion batteries are often used in the applications of electric vehicle [9][10][11].…”

State-of-charge estimation of lithium-ion battery for a satellite power management system

“…In addition, it does not require refactorization on state covariance as in the regular unscented Kalman filter (UKF). The square root aspect of the filter improves the numerical stability by ensuring the state covariance is always semi-positive definite [94,164]. The spherical transform requires fewer sigma points than the traditional unscented transform leading to lower computational cost [165,166].…”