Decentralized Fault Prognosis of Discrete-Event Systems Using State-Estimate-Based Protocols.

Abstract

We investigate the problem of decentralized fault prognosis in the context of discrete-event systems. In this problem, the system is monitored by a set of local agents; each of them sends its local information to a coordinator in order to issue a fault alarm before the occurrence of fault. Two new decentralized protocols are proposed by exploiting the state-estimate of each local agent. For each protocol, a necessary and sufficient condition for its correctness is proposed; they are termed as positive state-estimate-prognosability and negative state-estimate prognosability. Verification algorithms for the necessary and sufficient conditions are also provided. We show that the proposed new protocols are incomparable with any of the existing protocols in the literature. Therefore, they provide new opportunities for correctly predicting the fault when all existing protocols fail.