In this paper we present monitoring, diagnosis and optimization in the
Ash Control Model (AshMod), a knowledge-based operator guidance syste
m (OGS) in the coal washing domain. AshMod assists the operator in mon
itoring the plant, performing fault diagnosis, and in plant optimizati
on. It assists the operators in maximizing clean coal yield while keep
ing ash (impurity) content within acceptable limits. AshMod performs d
eep reasoning through the use of knowledge models that capture purpose
, function, structure, behaviour and heuristics. Knowledge validation
and maintenance is facilitated through the use of graphical object-ori
ented knowledge models. AshMod has been developed for the B&C coal was
hing plants operated by Broken Hill Proprietary Limited (BHP) at Port
Kembla, Australia (The Broken Hill Proprietary Company Limited, Home P
age, http://www.bhp.com.au/; BHP, 1995) Owing to our focus on generali
ty and reuse during the development of this OGS, we expect that much o
f AshMod can be reused in future OGS developments in BHP operated coal
washeries, sinter plants, blast furnaces, coke ovens etc. AshMod is c
urrently undergoing offline testing at the coal washing plants. (C) 19
97 Elsevier Science Ltd.