Title: Using neural networks to identify annoying noises in vehicles

Authors: Javier Mauricio Antelis, Jose Ignacio Huertas

Addresses: Automotive Engineering Research Centre, Department of Mechanical Engineering, Tecnologico de Monterrey, Toluca, Mexico. ' Automotive Engineering Research Centre, Department of Mechanical Engineering, Tecnologico de Monterrey, Toluca, Mexico

Abstract: Previous papers have developed a methodology to characterise squeaks and rattles. Thus, for each noise, its origin and the means for eliminating it, are known. This paper describes the work done towards the development of a tool, based on neural networks, that determines if a squeak or rattle corresponds to any of the noises already characterised. Different types of neural networks have been evaluated. Preliminarily, it was found that for this application the best topology is a net 100-50-4. Additionally, it was found that the best training method is the gradient descent back-propagation method with a learning rate of 0.05.

Keywords: parametric representation; bandwidth; index of similitude; neural networks; multilayer perceptron; MLP; training patterns; unexpected patterns; performance evaluation; vehicle noise; annoying noises; squeaks; rattles.

DOI: 10.1504/IJVNV.2006.011965

International Journal of Vehicle Noise and Vibration, 2006 Vol.2 No.3, pp.177 - 190

Published online: 06 Jan 2007 *

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