In this research work, we demonstrate state-of-charge (SoC) estimation using support vector regression (SVR) approach for a high capacity Lithium Ferro Phosphate (LiFePO4) battery module. The proposed SoC estimator in this work is extracted from open circuit voltage (OCV)-SoC lookup table which is obtained from the battery module discharging and charging testing cycles, using voltage and current as independent variables. The SoC estimation based on SVR gives a perfectly linear curve fitting with its reference within the range of 37.5% to 90% while the rest hysteresis due to the discharging and charging process is compensated using OCV-SoC curve as the training data set. The SVR estimates the battery module SoC with RMSE of 2.3% over the whole test and the maximum positive and negative error is 4%, which means that it shows good accuracy.
State of charge (SoC) estimation of LiFePO4 battery module using support vector regression
2015-11-01
646908 byte
Conference paper
Electronic Resource
English
Estimation of battery state-of-charge using ν-support vector regression algorithm
Springer Verlag | 2008
|Estimation of battery state-of-charge using ν-support vector regression algorithm
Springer Verlag | 2008
|Estimation of battery state-of-charge using ν-support vector regression algorithm
British Library Online Contents | 2008
|Estimation of battery state-of-charge using ν-support vector regression algorithm
Online Contents | 2008
|