Real-time fault diagnostics with multiple aspect models

A real-time fault diagnostics system that is applicable for diagnosing large-scale plants is described. It uses a multiple aspect model of the plant including the hierarchical process model, the hierarchical component model, and the hierarchical fault model (HFM). HFM represents the spatial and temporal aspects of faulty behavior in the form of a hierarchical fault propagation digraph. The reasoning algorithm is based on the structural and temporal constraint enforcement, and is migrated to lower levels of HFM hierarchy. It is able to guarantee response times, perform nonmonotonic and temporal reasoning, operate continuously, accept asynchronous data, generate requests, perform time and diagnostic resolution tradeoffs, and diagnose single and most multiple fault cases.<<ETX>>

[1]  Gabor Karsai,et al.  Modeling, model interpretation and intelligent control , 1988, Proceedings IEEE International Symposium on Intelligent Control 1988.

[2]  B. Chandrasekaran,et al.  A Mechanism for Forming Composite Explanatory Hypotheses , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Hidekatsu Tokumaru,et al.  A KNOWLEDGE-REPRESENTATION FOR DIAGNOSIS OF DYNAMICAL SYSTEMS , 1986 .

[4]  Thomas J. Laffey,et al.  Real-Time Knowledge-Based Systems , 1988, AI Mag..

[5]  Mark S. Fox,et al.  Techniques for Sensor-Based Diagnosis , 1983, IJCAI.

[6]  N. Hari Narayanan,et al.  A Methodology for Knowledge Acquisition and Reasoning in Failure Analysis of Systems , 1987, IEEE Transactions on Systems, Man, and Cybernetics.