University of Tasmania
whole_CunninghamHelenJean2002_thesis.pdf (19.82 MB)

Prediction of parameters to avoid vehicle roll over using neural networks

Download (19.82 MB)
posted on 2023-05-26, 22:46 authored by Cunningham, Helen Jean
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, ‚àÜvºr. This prediction is seen as a step towards identifying online warning systems for roll over detection and subsequent control systems to avoid roll over.


Publication status

  • Unpublished

Rights statement

Copyright 2002 the Author - The University is continuing to endeavour to trace the copyright owner(s) and in the meantime this item has been reproduced here in good faith. We would be pleased to hear from the copyright owner(s). No access until 19 June 2007. Thesis (M.Eng.Sc.)--University of Tasmania, 2002. Includes bibliographical references

Repository Status

  • Open

Usage metrics

    Thesis collection


    No categories selected


    Ref. manager