Real Time Diagnosis & Fault Detection for the Reliability Improvement of the Embedded Systems

Authors:
O. Bennouna;J. P. Roux
Affiliations:
IRSEEM (Institut de Recherche en Systèmes Electroniques EMbarqués), EA 4353, Technopôle du Madrillet, Saint Etienne du Rouvray, France 76801;CEVAA (Centre d'Etudes Vibro-Acoustiques pour l'Automobile), Saint Etienne du Rouvray, France 76800
Venue:
Journal of Signal Processing Systems
Year:
2013

Citing 2
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A general regression neural network

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents the design of a diagnosis procedure in order to improve the reliability of embedded systems subjected to vibration. This procedure is based on the use of wavelet transform of the vibration signals. The transformation provides the wavelet coefficients needed to calculate indicators such as energy and entropy. Artificial neural networks provide a rapid detection of the presence of structural defects. Results have been implemented and verified in real time on a dSPACE platform.