Application of neural networks to tyre modelling for vehicle simulation
by L. Palkovics, M. El-Gindy, H.B. Pacejka
International Journal of Heavy Vehicle Systems (IJHVS), Vol. 3, No. 1/2/3/4, 1996

Abstract: A considerable amount of work has been done in the area of tyre modelling, using wide variety of different approaches that range from pure theoretical modelling to fully empirical formulae fitted to measured points. In this paper a new approach is examined using Artificial Neural Networks (ANN) to create a non-linear mapping between the steady-state input and output characteristics of a tyre. The quality and speed of computation by ANN are compared to those of Pacejka's Magic Formula for tyres, which has been developed for the characterisation of a tyre cornering properties. In the paper, the applicability of the ANN to the pure cornering characteristic of a tyre is investigated, and both steady-state models are implemented in a simple vehicle model. The vehicle behaviour is investigated during a severe evasive path-follow manoeuvre and a steady-state cornering assuming quasi-static load transfer between the two side tyres. The steady-state tyre characteristics are useful in various applications where the road excitation can be neglected. However, there is a need for combining a tyre's in-plane and out-of-plane dynamics. In the second part of the paper, the cornering characteristic of a tyre running on an uneven road surface is analysed. The resulted lateral forces are compared to those given by the extended version of the Pacejka's Magic Formula. The behaviour of this ''Neuro-Tyre'' is also investigated by implementing it in a realistic computer simulation model of a single vehicle, which is subjected to steering manoeuvre on variety of road surfaces.

Online publication date: Tue, 18-Jun-2013

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Heavy Vehicle Systems (IJHVS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com