Skip to main content
UOIT Home
Please use this identifier to cite or link to this item: http://hdl.handle.net/10155/1117

Issue Date: 1-Nov-2019
Title: Design and development of advanced machine learning algorithms for lithium-ion battery state-of-charge estimation
Authors: Sidhu, Manjot
Publisher : University of Ontario Institute of Technology
Degree : Master of Applied Science (MASc)
Department : Electrical and Computer Engineering
Supervisor : Williamson, Sheldon
Keywords: State of charge
Machine learning
Estimation
kNearest neighbor
Abstract: Batteries have been becoming more and more popular because of their long life and lightweight. Accurate estimation of the SOC help in making plans in an application to conserve and further enhance battery life. State of Charge (SOC) estimation is a difficult task made more challenging by changes in battery characteristics over time and their nonlinear behavior. In recent years, intelligent schemes for the estimation of the SOC have been proposed because of the absence of the formula for calculating SOC which is hard to deduce because of the effect of external factors like temperature. As the traditional methods only considered certain aspects which with the aging and degradation of the battery results in errors. To tackle this problem several methods were proposed which made use of now evolving artificial intelligence technologies. This paper presents a new SOC estimation algorithm based on kNearest neighbor and random forest regression and a comparison study is done using four algorithms Support Vector Regression, Neural Network Regression, Random Forest Regression and kNearest Neighbor. Their performance is evaluated using data from two drive cycles.
Appears in Collections:Electronic Theses and Dissertations (Public)
Faculty of Engineering and Applied Science - Master Theses

Files in This Item:

File Description SizeFormat
Sidhu_Manjot_Singh.pdf4.3 MBAdobe PDFView/Open

Items in e-scholar@UOIT are protected by copyright, with all rights reserved, unless otherwise indicated.