Title: Fault diagnosis and prognosis in discrete event systems using statistical model and neural networks

Authors: M. Msaaf; F. Belmajdoub

Addresses: Laboratory of Industrial Technologies (LTI), Faculty of Sciences and Technologies, Sidi Mohamed Ben Abdellah University, Fez, 30000, Morocco ' Laboratory of Industrial Technologies (LTI), Faculty of Sciences and Technologies, Sidi Mohamed Ben Abdellah University, Fez, 30000, Morocco

Abstract: This paper deals with fault diagnosis and fault prognosis in discrete event systems described by sequences of events. We are interested in large industrial systems where the modelling with tools usually used for discrete event system (automata, Petri net…) is a complex task. The description of DES is made with a statistical model composed of events recorded from the considered DES and regrouped in the form of temporal windows. In the first phase, the theoretical framework is developed to perform diagnosis and prognosis using statistical model and temporal window concept. The second phase uses the result of the first phase to train radial basic function neural networks that preform online diagnosis and online prognosis. A case study and several examples serving to illuminate the developed approach are given.

Keywords: discrete event systems; fault diagnosis; fault prognosis; statistical model; neural networks; radial basic function neural network.

DOI: 10.1504/IJMA.2018.095517

International Journal of Mechatronics and Automation, 2018 Vol.6 No.4, pp.173 - 182

Received: 25 Apr 2018
Accepted: 10 May 2018
Published online: 08 Oct 2018 *

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