Authors: Md. Shamsuzzaman; Mysore G. Satish; János D. Pintér
Addresses: Department of Civil and Resource Engineering, Dalhousie University, Halifax, Nova Scotia, B3H 4R2, Canada ' Department of Civil and Resource Engineering, Dalhousie University, Halifax, Nova Scotia, B3H 4R2, Canada ' Department of Civil and Resource Engineering, Dalhousie University, Halifax, Nova Scotia, B3H 4R2, Canada; PCS, Inc., Halifax, NS, B3M 3J7, Canada
Abstract: In many real-world applications of optimisation, the required model (function) evaluations are determined by expensive and time-consuming physical experiments or numerical procedures. Within this context, the objective of experimental design is to obtain meaningful information based on a strongly limited number of experiments or function evaluations. In order to generate informative designs, space-filling and orthogonality are widely considered to be essential. In this study, we review several existing design performance metrics that address these criteria, and the distance correlation-based metric is proposed for achieving improved experimental design. Three closely related randomised sampling schemes are proposed to generate nearly orthogonal designs with good space-filling properties in real time. The effectiveness of our approach is demonstrated by numerical examples and an illustrative borehole model case study.
Keywords: design of experiments; DOE; Latin hypercube design; LHD; space-filling designs; orthogonal designs; performance metrics; distance correlation; design initialisation and search algorithms; orthogonality; randomised sampling; borehole modelling.
International Journal of Experimental Design and Process Optimisation, 2015 Vol.4 No.3/4, pp.216 - 233
Received: 08 Aug 2014
Accepted: 07 Jun 2015
Published online: 03 Nov 2015 *