A Neural Network Approach to Absolute State-of-Health Estimation in Electric Vehicles Battery Degradation Study Based on Fleet Data

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/255593
Download file(s):
File Description SizeFormat 
255593.pdfFulltext8.15 MBAdobe PDFView/Open
Type: Examensarbete för masterexamen
Master Thesis
Title: A Neural Network Approach to Absolute State-of-Health Estimation in Electric Vehicles Battery Degradation Study Based on Fleet Data
Authors: Johansson, Herman
Abstract: Electrification is a trend within the automotive industry. Many car manufacturers are launching electric vehicles, which are believed to be more sustainable and environmentally friendly. A major component in these cars is the battery, and its performance is crucial to the success of the electric vehicle. Therefor, the degradation of battery properties is interesting, especially the capacity decline. To understand and counter this degradation it must be measured with high precision in the cars, and be connected to car use. This project approaches this challenge by: using real fleet data, the aggregation of the data into events, and a neural network to estimate the state of the battery. The result is a proof of concept that gives an improved measure of the battery state and how different usage affects the capacity degradation. The result is, however, not validated at this point, shows unexplained properties, and should be further developed.
Keywords: Energi;Grundläggande vetenskaper;Hållbar utveckling;Innovation och entreprenörskap (nyttiggörande);Annan teknik;Energy;Basic Sciences;Sustainable Development;Innovation & Entrepreneurship;Other Engineering and Technologies
Issue Date: 2018
Publisher: Chalmers tekniska högskola / Institutionen för fysik (Chalmers)
Chalmers University of Technology / Department of Physics (Chalmers)
URI: https://hdl.handle.net/20.500.12380/255593
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.