An intelligent event-oriented diagnosis methodology and diagnostic sys
tem architecture is proposed in this paper. The dynamic behaviour of t
he process system in different faulty modes is described by cause-cons
equence event sequences represented by coloured Petri nets (CPNs). The
dynamic model of the system is assumed to be partially unknown and it
is refined using the observed event sequences by a learning method. T
he real-time diagnosis operates on the CPN model of the system and on
the expected operating procedures comparing observed event sequences t
o the model-based prediction.The diagnostic system architecture consis
ts of an event archivator, a data structure generator, a real-time dia
gnostic monitor and a learning subsystem.