Fault Diagnosis in Discrete-Event Systems: Incomplete Models and Learning

Abstract

Most model-based approaches to fault diagnosis of discrete-event systems (DESs) require a complete and accurate model of the system to be diagnosed. However, the discrete-event model may have arisen from abstraction and simplification of a continuous time system or through model building from input-output data. As such, it may not capture the dynamic behavior of the system completely. In this paper, we address the problem of diagnosing faults, given an incomplete model of the discrete-event system. When the model is incomplete, discrepancies will arise between the actual output and the output predicted by the model. We introduce learning into the diagnoser construction by forming hypotheses that explain these discrepancies. We view the process of generating and evaluating hypotheses about the model of the system as an instance of the set-cover problem, which we formalize using parsimonious covering theory. We describe in detail the construction of the learning diagnoser, which not only performs fault diagnosis but also attempts to learn the missing model information. If the model is complete, the learning diagnoser reduces to the standard state-based diagnoser. Examples are provided to illustrate how learning and diagnosis can be simultaneously achieved through the learning diagnoser.

Robust prognosability for a set of partially observed discrete event systems

“…Model uncertainty is one of the important issues in modelbased approaches to DESs (Kwong & Yonge-Mallo, 2011;Lin, 1993;Young & Garg, 1995). Young and Garg (1995) considered a case where a set of possible models, which includes the exact model of a system, is given, and developed an algorithm to determine the exact model from the set of possible models.…”

Fault Diagnosis in Discrete-Event Systems with Incomplete Models: Learnability and Diagnosability

“…In addition, considerable efforts have been devoted to bridging the methodologies of the two communities [3]- [5]. As with our earlier paper [6], we focus here on systems described by a discrete-event model [7], [8]. For this class of systems, results have been obtained for a wide variety of problems and system structure.…”

“…In our earlier paper [6], we describe a fault diagnosis framework for DESs which may be used to diagnose faults even when a complete model of the system is unavailable. The DES model is assumed to be incomplete in the sense that some transitions in the true system are missing from the model description.…”

“…The DES model is assumed to be incomplete in the sense that some transitions in the true system are missing from the model description. When an inconsistency arises, the incomplete model is extended in accordance with the principle of parsimony [6]. We show how a learning procedure can be combined with fault diagnosis, resulting in a diagnosis algorithm called the learning diagnoser.…”

Solving the modules interaction problem in MES platform based on production process event model

“…Bryce (Bryce et al, 2011) study on Event-Driven Software and evolve the model. Kwong and Yonge-Mallo (Kwong and Yonge-Mallo, 2011) give an incomplete model of the discrete-event system and address the problems of diagnosing fault. An intelligence model in man-machine systems is proposed by Riad (Riad et al, 2012).…”