Title: Adaptive sequential experimentation technique for 3³ factorial designs based on revised simplex search

Authors: Mubashir Siddiqui, Kai Yang

Addresses: Department of Industrial and Manufacturing Engineering, NED University of Engineering and Technology, Karachi, Pakistan. ' Department of Industrial and Manufacturing Engineering, Wayne State University, Detroit, MI 48201, USA

Abstract: This paper is an extension to the work carried out in the field of sequential experimentation strategy by Siddiqui and Yang (2009). The methodology presented in this paper deals with expensive industrial experiments under the constraint of limited testing budget. This research focuses on involving three factors, each being at three levels. Another constraint appropriately assumed for these experiments is that of inadequate prior knowledge of the system, i.e., the behaviour of the system is not very well known to the experimenter. The aim of this research is to explore high quality parameter space in a minimum number of experimental runs in such situations. The explained experimentation strategy uses adaptive one factor at a time method, simplex downhill method, and response surface method.

Keywords: sequential experiments; adaptive experiments; simplex downhill method; design of experiments; DOE; one factor at a time; OFAT; 3³ designs; expensive industrial experiments; limited testing budgets; response surface methodology; RSM; experimental design.

DOI: 10.1504/IJEDPO.2010.034987

International Journal of Experimental Design and Process Optimisation, 2010 Vol.1 No.4, pp.296 - 314

Published online: 31 Aug 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article