A Comparative Study of Fault Prognosis Approaches for Timed Stochastic Discrete Event Systems. Issue 1 (July 2017)

• Record Type: Journal Article
• Authors: Ammour, R.; Leclercq, E.; Sanlaville, E.; Lefebvre, D.
• Is Part Of: IFAC-PapersOnLine. Volume 50:Issue 1(2017)
• Page Start: 6807
• Page End: 6812
• Publication Date: 2017-07
• Subjects: Discrete-event systems -- Fault prognosis -- Stochastic Petri nets; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2017.08.1199
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: This paper studies the fault prognosis of timed stochastic discrete event systems. For that purpose, stochastic Petri nets are considered to model both the healthy and faulty behaviors of the system. Assuming that the possible current markings with their associated probabilities are known, the objective is to estimate the probability of faults occurrence within a future time interval. Two approaches, lmax -prognosis and ( Ƿ, δ )-prognosis, are presented and compared to deal with this problem. A case study describing a distribution system is proposed to show the applicability of the proposed methods.