PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Predicting Tool for the Battery Cycle Life
Iryna Snihir, William Rey and Evgeny Verbitskiy
In: PRIP 2005, 18-20 May 2005, Minsk, Belarus.

Abstract

We propose an efficient and reliable method to predict cycle life of a rechargeable battery. We study the cycle life data obtained under laboratory conditions: battery cells have been submitted to repeated identical charge/discharge cycles. We propose a method for the modelling of the separate cycles and the forecasting the next cycles, when a few previous cycles have been observed. The success of the method confirms the assumption that a great deal of the information on ageing already is present in the voltage curves of a few first battery cycles. The method is based on the compact representation of voltage curves via Karhunen-Loeve (KL) coefficients and with help of a regression model.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:1966
Deposited By:Iryna Snihir
Deposited On:02 January 2006