Open Access Repository
Prediction of parameters to avoid vehicle roll over using neural networks
Downloads
Downloads per month over past year
|
PDF
(Whole thesis)
whole_Cunningha...pdf | Download (20MB) Available under University of Tasmania Standard License. | Preview |
Abstract
There is a need for reliable automotive performance. While automotive engineers are
highly trained mechanical engineers, there is a requirement to keep abreast of the
emerging technologies such as neural networks or fast-converging algorithms. Any
significant or radical change comes about through multi-disciplinary interaction.
Emerging technologies such as evolutionary algorithms, neural networks and fuzzy
logic are constantly applied to more diverse technological applications.
From automotive industry point of view, continual attempts are made to build models
to avoid vehicle roll over. While highly advanced automotive manufacturers are
carrying out such research, very little or no results are available in the public domain.
In this thesis, critical parameters responsible for vehicle roll over will be identified
and predicted. As part of the model verification, a hardware comprising of a Formula
SAE race-car, sensory technology and instrumentation will be developed. This thesis
highlights successful application of roll-over parameters namely longitudinal velocity,
v, and vehicle roll angle, Ɵr. This prediction is seen as a step towards identifying online
warning systems for roll over detection and subsequent control systems to avoid
roll over.
Item Type: | Thesis - Research Master |
---|---|
Authors/Creators: | Cunningham, Helen Jean |
Keywords: | Automobiles, Neural networks (Computer science), Automobiles, Driver assistance systems |
Copyright Holders: | The Author |
Copyright Information: | Copyright 2002 the Author - The University is continuing to endeavour to trace the copyright |
Additional Information: | No access until 19 June 2007. Thesis (M.Eng.Sc.)--University of Tasmania, 2002. Includes bibliographical references |
Item Statistics: | View statistics for this item |
Actions (login required)
![]() |
Item Control Page |