Diagnose car engine exhaust system damage using bispectral analysis and radial basic function

DOI

10.2991/iccnce.2013.78How to use a DOI?

Keywords

diagnostic system, vibration, engine, artificial neural networks.

Abstract

Diagnostic systems used in new combustion engines are intended for identifying the location of a element or system which can no longer perform its function assigned by the manufacturer, ensuing to its damage or ordinary wear. Increasing requirements regarding reliability and durability of combustion engines, as well as unfavorable effect on the environment and cost minimization, make that necessary to acquire information on the condition of the engine during its working. In this article is presented an experiment specifying possibilities of leakage diagnosis in car engine exhaust system using artificial neural networks. In the experiment radial basis function (RBF) was used as a neural network classifier. Optimization of the neural classifier was based on the change of ? coefficients. The optimization criterion was the minimum testing error. The input data for the classifier was in a form of matrix composed of measures, obtained from vibroacoustic signals and bispectral analysis.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Piotr Czech
PY  - 2013/07
DA  - 2013/07
TI  - Diagnose car engine exhaust system damage using bispectral analysis and radial basic function
BT  - Proceedings of the International Conference on Computer, Networks and Communication Engineering (ICCNCE 2013)
PB  - Atlantis Press
SP  - 312
EP  - 315
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccnce.2013.78
DO  - 10.2991/iccnce.2013.78
ID  - Czech2013/07
ER  -