Incorporating Judgment into an Optimization Model of a Wastewater Treatment System

by James J. Geselbracht, Univ of Illinois at, Urbana-Champaign, Urbana, IL, USA,
E. Downey Brill, Jr., (M.ASCE), Univ of Illinois at, Urbana-Champaign, Urbana, IL, USA,
John T. Pfeffer, (M.ASCE), Univ of Illinois at, Urbana-Champaign, Urbana, IL, USA,



Document Type: Proceeding Paper

Part of: Water Forum '86: World Water Issues in Evolution

Abstract:

The use of design variable constraints according to textbook and state design standards might cause potentially good designs to be missed and would not capture the fuzzy interaction of design conditions leading to bulking problems. A better approach might be to use a rule-based system. The rules used to model the judgement regarding bulking problems initially were obtained from the published research regarding the factors which various researchers had felt might be related to the development of bulking problems. Those rules were then arranged into a logic structure which simultaneously considers the truth of those rules and then determines the likelihood of such a design experiencing bulking problems. Once the model was calibrated, it was incorporated into the judgement model in a straight-forward manner; each rule became a constraint in the optimization model and the weighted sum of each rule's satisfaction determined the likelihood of that design experiencing bulking problems.



Subject Headings: Optimization models | Water treatment plants | Structural models | Mathematical models | Expert systems | Artificial intelligence (AI) | Wood structures

Services: Buy this book/Buy this article

 

Return to search