C. Chan et P. Lau, AN EXPERT-SYSTEM ARCHITECTURAL FRAMEWORK FOR ENGINEERING SELECTION, Engineering applications of artificial intelligence, 10(4), 1997, pp. 357-367
A generic architectural framework for constructing flexible expert sys
tems for engineering selection is proposed in this paper A two-tiered
framework is suggested to mirror the two steps of elimination and refi
nement in selection tasks. The top layer consists of reverse rules for
implementing the elimination of inapplicable alternatives, and the bo
ttom layer consists of multiple-criteria decision-making (MCDM) models
for explicitly modeling the decision-making processes in selection. S
ome MCDM models which involve user preferences or weights are incorpor
ated in the framework because the selection task involves user prefere
nces or weights assigned to decision parameters. The framework has bee
n applied to the domain of solvent selection for carbon dioxide remova
l processes, and a prototype advisory system based on the framework ha
s been developed. The proposed framework contributes to the field of e
ngineering selection because it enables the explicit representation of
selection knowledge, and the formal modeling of user preferences. (C)
1997 Elsevier Science Ltd. All rights reserved.