DIAGNOSIS OF DYNAMIC-SYSTEMS BASED ON EXPLICIT AND IMPLICIT BEHAVIORAL-MODELS - AN APPLICATION TO GAS-TURBINES IN ESPRIT PROJECT TIGER

Citation
L. Travemassuyes et R. Milne, DIAGNOSIS OF DYNAMIC-SYSTEMS BASED ON EXPLICIT AND IMPLICIT BEHAVIORAL-MODELS - AN APPLICATION TO GAS-TURBINES IN ESPRIT PROJECT TIGER, Applied artificial intelligence, 10(3), 1996, pp. 257-277
Citations number
24
Categorie Soggetti
System Science","Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic
ISSN journal
08839514
Volume
10
Issue
3
Year of publication
1996
Pages
257 - 277
Database
ISI
SICI code
0883-9514(1996)10:3<257:DODBOE>2.0.ZU;2-#
Abstract
We are interested in the monitoring and diagnosis of dynamic systems. We combine explicit temporal models of the behavior of a dynamic syste m with implicit behavioral models supporting model-based approaches. T his work is driven by the needs of and is applied to two gas turbines of very different size and power. We describe the problems of building systems for these domains and illustrate how we have developed a syst em where these two approaches complement each other to provide a compr ehensive fault detection and diagnosis system. We also explore the str engths and weaknesses of each approach. The work described here is cur rently working continuously on-line to a gas turbine in a major chemic al plant.