Title: Neural network learning control of automotive active suspension systems

Authors: Y. Watanabe, R.S. Sharp

Addresses: School of Mechanical Engineering, Cranfield University, Bedford MK43 OAL, UK. ' School of Mechanical Engineering, Cranfield University, Bedford MK43 OAL, UK

Abstract: The paper contains theoretical treatments of neural network controllers allied to various simplified automotive active suspensions. In each case considered, the controlled system has a defined objective, the minimisation of a cost function, and the neural network is set up in a learning structure such that it systematically improves the system performance via repeated trials and modifications of parameters. The learning process is shown to be effective and, in selected cases, to give system performance in agreement with prior results, for both linear and non-linear plants. The final objective of the work is effective neuro-control of a variable geometry active suspension system, the action of which is essentially non-linear. This problem is introduced. The learning structures established are important milestones on the journey to the final objective. Also, they are generic and are likely to be more widely applicable.

Keywords: automotive active suspension; neurocontrol; dynamics; learning; neural networks; optimisation; suspension control; automobile industry; vehicle suspension systems; system performance.

DOI: 10.1504/IJVD.1999.005572

International Journal of Vehicle Design, 1999 Vol.21 No.2/3, pp.124 - 147

Published online: 20 Oct 2004 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article