Knowledge-based systems are normally designed to perform a single task
(e.g. diagnosis) for which they are competent, but their knowledge ba
se is rarely used for other tasks, even when they are very similar and
in the same application domain. An alternative approach is to build a
knowledge core that has the basic knowledge for a certain domain, on
top of which different tasks could be built. In this paper, a multifun
ctional knowledge-based system for engineering domains, called MF-KBS,
is described. MF-KBS has (i) a library of engineering components, suc
h as pumps, valves, tanks, etc. associated with mathematical models at
different abstraction levels, (ii) several reasoning mechanisms for t
hese models, and (iii) knowledge operators capable of performing diffe
rent tasks with the reasoning mechanisms, such as diagnosis, problem s
olving, tutoring, etc. Particular applications are built by joining co
mponents, producing a global model via composition, and selecting one
or more of the knowledge operators. Experiments in a subsystem of an e
lectric power plant with different knowledge operators are described.
(C) 1998 Elsevier Science Ltd. All rights reserved.