Please use this identifier to cite or link to this item:
|Title:||A graphical approach to the dual response robust design problems||Authors:||Lam, S.W.
Response surface optimization
|Issue Date:||2005||Citation:||Lam, S.W.,Tang, L.C. (2005). A graphical approach to the dual response robust design problems. Proceedings - Annual Reliability and Maintainability Symposium : 200-206. ScholarBank@NUS Repository.||Abstract:||In the past, approaches to the simultaneous optimization of mean and variance in robust design are usually a priori methods whereby the decision maker is assumed to have a well-defined objective. Some of the more well-known pre-defined objectives are the target-the-best, larger-the-better and smaller-the-better. The related optimization procedure is generally to optimize a primary response function, subject to some appropriate constraints on a secondary response, or some integrated objective function. Exploration of alternative designs near the optimal point may be difficult in such methods. A graphical approach is proposed here using compromise programming. This would generate a set of Pareto optimal solutions for the dual response problem. The decision maker can then have the flexibility of studying the trade-offs involved in selecting the optimal design point. The method is fully implemented using the Solver function in Excel, producing graphically the set of Pareto optimal design points that can aid decision making. In order to support effective consideration of the predictive capability, confidence and prediction intervals were also established for these Pareto optimal solutions. ©2005 IEEE.||Source Title:||Proceedings - Annual Reliability and Maintainability Symposium||URI:||http://scholarbank.nus.edu.sg/handle/10635/72238||ISSN:||0149144X|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.