Interval Predictability in Discrete Event Systems

TL;DR

This paper investigates interval predictability in partially observable discrete event systems, extending previous definitions to include time intervals and providing an efficient algorithm to determine predictability.

Contribution

It introduces a new interval-based predictability concept and offers a quadratic algorithm for deciding predictability in such systems.

Findings

Defined $(i,j)$-predictability for fault prediction timing

Developed a quadratic algorithm for predictability decision

Extended predictability analysis to partial observability scenarios

Abstract

In this paper we study the problem of predictability in partially observable discrete event systems, i.e., the question whether an observer can predict the occurrence of a fault. We extend the definition of predictability to consider the time interval where the fault will occur: the $(i,j)$-predictability does not only specify that the fault will be predicted before it occurs, but also that the predictor will be able to predict that its occurrence will occur in $i$ to $j$ observations from now. We also provide a quadratic algorithm that decides predictability of the system.