Performance of an ensemble of ordinary, universal, non-stationary and limit kriging predictors


Toal, David J.J. and Keane, A.J. (2013) Performance of an ensemble of ordinary, universal, non-stationary and limit kriging predictors. Structural and Multidisciplinary Optimization, 47, (6)

Download

[img] PDF - Pre print
Restricted to Registered users only

Download (178Kb) | Request a copy

Description/Abstract

The selection of stationary or non-stationary
Kriging to create a surrogate model of a black box
function requires apriori knowledge of the nature of
response of the function as these techniques are bet-
ter at representing some types of responses than oth-
ers. While an adaptive technique has been previously
proposed to adjust the level of stationarity within the
surrogate model such a model can be prohibitively ex-
pensive to construct for high dimensional problems. An
alternative approach is to employ a surrogate model
constructed from an ensemble of stationary and non-
stationary Kriging models. The following paper assesses
the accuracy and optimization performance of such a
modelling strategy using a number of analytical func-
tions and engineering design problems.

Item Type: Article
ISSNs: 1615-147X (print)
1615-1488 (electronic)
Related URLs:
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Engineering and the Environment > Aeronautics, Astronautics and Computational Engineering > Computational Engineering & Design
ePrint ID: 345732
Date Deposited: 29 Nov 2012 15:13
Last Modified: 27 Mar 2014 20:27
URI: http://eprints.soton.ac.uk/id/eprint/345732

Actions (login required)

View Item View Item