Remaining Useful Life (RUL) Estimation of Lead Acid Battery using Bayesian Approach

Abstract

This article deals with Remaining Useful Life (RUL) estimation of Lead Acid Battery using a probabilistic approach which is Bayesian inference of Linear Regression. RUL estimation of lead acid battery plays a very crucial role as it can prevent the catastrophic failure for the system in which it is used to serve as a power supply mainly in automobiles. Although there are various methods for age estimation of lead acid battery, machine learning algorithms always played a major role in the same. In this paper we have implemented one such algorithm for the RUL estimation. Bayesian approach is a probabilistic method which can be used for predicting the RUL of the battery. Firstly, we present a framework for feature extraction and then the RUL estimation model is trained on Bayesian inference of Linear Regression. The proposed approach is then applied to the collected dataset from five differently aged batteries which have undergone some charging/discharging and load cycle test. The experiment result shows that the proposed approach can improve the accuracy of RUL estimation than the regular methods.