About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
ISGT 2014
Conference paper
A smart remaining battery life prediction based on MARS
Abstract
Prognosis of the remaining battery life is an important and practical research area of rechargeable battery and smart grid. It has promising application prospect in such area as grid energy storage systems, electrical vehicles etc. In this paper, by analysing the lithium-ion battery information, the most influencing factors of lifetime are collected. Based on this, a novel system is proposed to predict the battery capacity loss using a model based on multivariate adaptive regression splines (MARS) method by an iterative technique. Unlike static models the proposed system is designed to overcome the problem of data sparseness at the beginning in application. It implements a reliable forecast of the battery life by using newly gained data iteratively, which increases the prediction accuracy noticeably. Experiments prove that the solution can predict battery life with high precision, and the prediction results meet the accuracy and stability requirements of practical application. © 2014 IEEE.