Discrete event system identification with the aim of fault detection

Abstract

In this paper, we present a method for discrete event system identification with the aim of fault detection. The method is based on a new model called Deterministic Automaton with Outputs and Conditional Transitions (DAOCT), which is computed from observed fault-free paths, and represents the fault-free system behavior. In practice, a trade-off between size and accuracy of the identified automaton has to be found. In order to obtain compact models, loops are introduced in the model, which implies that sequences that are not observed can be generated by the model leading to an exceeding language. This exceeding language is associated with possible non-detectable faults, and must be reduced in order to use the model for fault detection. We show, in this paper, that the exceeding language generated by the DAOCT is smaller than the exceeding language generated by another model proposed in the literature, reducing, therefore, the number of possible non-detectable faults. We also show that if the identified DAOCT does not have cyclic paths, then the exceeding language is empty, and the model represents all and only all observed fault-free sequences generated by the system. In order to illustrate the results of the paper, a physical system is simulated by using a 3D simulation software controlled by a Programmable Logic Controller (PLC). The main idea is to use a virtual digital system to simulate the fault-free behavior of a physical system, captured by the sequences of input and output signals of the PLC, and then use the method proposed in the paper to obtain the DAOCT model of the plant.