Designing experiments for robust-optimization problems: theVs-optimality criterion
- 1 July 2006
- journal article
- research article
- Published by Informa UK Limited in IIE Transactions
- Vol. 38 (6), 445-461
- https://doi.org/10.1080/07408170500440437
Abstract
We suggest an experimentation strategy for the robust design of empirically fitted models. The suggested approach is used to design experiments that minimize the variance of the optimal robust solution. The new design-of-experiment optimality criterion, termed V s-optimal, prioritizes the estimation of a model's coefficients, such that the variance of the optimal solution is minimized by the performed experiments. It is discussed how the proposed criterion is related to known optimality criteria. We present an analytical formulation of the suggested approach for linear models and a numerical procedure for higher-order or nonpolynomial models. In comparison with conventional robust-design methods, our approach provides more information on the robust solution by numerically generating its multidimensional distribution. Moreover, in a case study, the proposed approach results in a better robust solution in comparison with these standard methods.Keywords
This publication has 22 references indexed in Scilit:
- Robust Optimization of Experimentally Derived Objective FunctionsIIE Transactions, 2003
- An integrated joint optimization procedure for robust and tolerance designInternational Journal of Production Research, 2000
- First-order optimal designs for non-linear modelsJournal of Statistical Planning and Inference, 1998
- Analysis of dynamic robust design experimentsInternational Journal of Production Research, 1997
- Some Properties of Multiresponse D-Optimal DesignsJournal of Mathematical Analysis and Applications, 1994
- STRATEGIES FOR ROBUST MULTIRESPONSE QUALITY ENGINEERINGIIE Transactions, 1993
- Design and Analysis of Computer ExperimentsStatistical Science, 1989
- Bootstrap Methods: Another Look at the JackknifeThe Annals of Statistics, 1979