Synthesis of a Distributed and Accurate Diagnoser



Published Oct 11, 2010
Priscilla Kan John Alban Grastien Yannick Pencole ́


The complex behaviour of large discrete event systems makes such systems difficult to diagnose. Using decentralised techniques helps limit combinatorial explosion but is not sufficient. Often, the complexity of the diagnosis is dependent on how components in the system are connected and the number of connections between them. We propose to augment a decentralized junction tree- based approach by ignoring some connections on the system. This helps reduce the complexity, and hence the cost, of the diagnostic reasoning required. However accuracy of the diagnosis is also reduced. We get around this problem by performing an off-line analysis to determine which connections can be safely ignored.

How to Cite

Kan John, P. ., Grastien, A. ., & Pencole ́ Y. . (2010). Synthesis of a Distributed and Accurate Diagnoser. Annual Conference of the PHM Society, 2(2).
Abstract 166 | PDF Downloads 115



fault diagnosis, model-based methods, accuracy

(Cassandras and Lafortune, 1999) C. Cassandras and S. Lafortune. Introduction to Discrete Event Systems. Kluwer Academic Publishers, 1999.
(Cordier and Grastien, 2007) M.-O. Cordier and A. Grastien. Exploiting independence in a decentralised and incremental approach of diagnosis. In M. Veloso, editor, Twentieth International Joint Conference on Artificial Intelligence (IJCAI-07), pages 292–297. AAAI press, 2007.
(Huang and Darwiche, 1996) C. Huang and A. Dar- wiche. Inference in belief networks: A procedural guide. International Journal of Approximate Reasoning, 15(3):225–263, 1996.
(Kan John and Grastien, 2008) P. Kan John and A. Grastien. Local consistency and junction tree for diagnosis of discrete-event systems. In European Conference on Artificial Intelligence (ECAI-08), 2008.
(Pencole ́ and Cordier, 2005) Y. Pencole ́ and M.-O. Cordier. A formal framework for the decentralised diagnosis of large scale discrete event systems and its application to telecommunication networks. Artificial Intelligence (AIJ), 164:121–170, 2005.

(Pencole ́ et al., 2006) Y. Pencole ́, D. Kamenetsky, and A. Schumann. Towards low-cost fault diagnosis in large component-based systems. In Sixth IFAC Symposium on Fault Detection, Supervision and Safety of Technical PRocess, 2006.

(Sachenbacher and Struss, 2005) M. Sachenbacher and P. Struss. Task-dependent qualitative domain abstraction. Artificial Intelligence (AIJ), 162(1–2):121–143, 2005.

(Schumann et al., 2004) A. Schumann, Y. Pencole ́, and S. Thie ́baux. Symbolic models for diagnosing discrete-event systems. In Sixteenth European Conference on Artificial Intelligence (ECAI’04), 2004.
Poster Presentations