Ib. Ozyurt et al., SQFDiag: Semiquantitative model-based fault monitoring and diagnosis via episodic fuzzy rules, IEEE SYST A, 29(3), 1999, pp. 294-306
Citations number
28
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS
A method for chemical process fault diagnosis using semiquantitative model
generated behavior envelopes is described in this paper. The method generat
es a sequence of rules for each fault class, with any rule in a sequence va
lid within the bounds of its time interval. This can be viewed as a qualita
tive description of the trend of numerical sensor measurements. For each va
riable in each fault class two sequences of episodic fuzzy rules are automa
tically generated one for the lower and one for the upper numerical behavio
r envelope. The diagnostic system monitors a process via the measured senso
rs. The measurements are matched against the fuzzy rules for the current ti
me in the rule base. In case of an overlapping region defined by behavior e
nvelopes, the introduced distance and time based fault belief sealing allow
s ranking of fault candidates. A novel abnormal situation will not pass the
introduced system undetected due to a novel class detection mechanism. The
diagnostic performance of the system is shown in two case studies. The sys
tem detected the correct fault even in cases of nearly total overlapped fau
lt regions: bounded by behavior envelopes.