CAD for fault tree-based diagnosis of industrial processes

Citation
M. Kavcic et D. Juricic, CAD for fault tree-based diagnosis of industrial processes, ENG APP ART, 14(2), 2001, pp. 203-216
Citations number
27
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
ISSN journal
09521976 → ACNP
Volume
14
Issue
2
Year of publication
2001
Pages
203 - 216
Database
ISI
SICI code
0952-1976(200104)14:2<203:CFFTDO>2.0.ZU;2-9
Abstract
Despite extensive research in the area of model-based fault diagnosis, the number of applied solutions is still rather limited. The reason for this is to be partly sought in the relatively high costs related to the developmen t of a diagnostic system. Hopefully, the efficiency of the development cycl e can be substantially improved with the use of computer-aided design (CAD) tools. This fact served as a major motivation for the realisation of a CAD prototype which performs automatic synthesis of rule-based diagnostic syst ems for industrial processes. The tool relies on fault propagation models a nd an object-oriented modelling paradigm. A model of the whole process deri ves from the component models and information about the way the components are interconnected. As the library of component models is inherent to the t ool, the major input expected from the user is a process flowsheet. This ca n be simply provided through a graphic user-interface. The synthesis of pro pagation models, and synthesis of the rules thereof, is performed using an automatic synthesis procedure. An algorithm that transforms fault trees int o event trees and diagnostic rules is presented. Handling complex structure s, such as feedback loops, is also addressed. For on-line execution of the resulting diagnostic rules, the approximate reasoning scheme referred to as the transferable belief model (TBM) is suggested. The underlying CAD tool is suitable for performing several routine tasks that occur in the process of the development of a diagnostic system. This is illustrated on an exampl e of a laboratory test rig. (C) 2001 Elsevier Science Ltd. All rights reser ved.