A two-phase maxi-min algorithm for forward-inverse experiment design

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In customer-driven design of systems or products, one has performance targets in mind and would like to identify system design parameters that yield the target performance vector. Since most simulation models predict performance given design parameter values, this identification must be done iteratively through an optimization search procedure. In some cases it would be preferable to find design parameter values directly via an explicit inverse model. Regression and other forms of approximation 'metamodels' provide estimates of simulation model outputs as a function of design parameters. It is possible to design fitting experiments (DOE's) that allow simultaneous fitting of both forward and inverse metamodels. This paper discusses the potential for this strategy and shows a simple two-phase DOE strategy using a maxi-min measure of DOE quality.

Original languageEnglish (US)
Title of host publicationProceedings of the 2006 Winter Simulation Conference, WSC
Pages376-381
Number of pages6
DOIs
StatePublished - Dec 1 2006
Event2006 Winter Simulation Conference, WSC - Monterey, CA, United States
Duration: Dec 3 2006Dec 6 2006

Publication series

NameProceedings - Winter Simulation Conference
ISSN (Print)0891-7736

Other

Other2006 Winter Simulation Conference, WSC
CountryUnited States
CityMonterey, CA
Period12/3/0612/6/06

Fingerprint

Parameter Design
Metamodel
Simulation Model
Experiment
Inverse Model
Target
Experiments
System Design
Customers
Regression
Predict
Optimization
Output
Approximation
Identification (control systems)
Estimate
Systems analysis
Design
Strategy

All Science Journal Classification (ASJC) codes

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Barton, R. R. (2006). A two-phase maxi-min algorithm for forward-inverse experiment design. In Proceedings of the 2006 Winter Simulation Conference, WSC (pp. 376-381). [4117629] (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2006.323105
Barton, Russell Richard. / A two-phase maxi-min algorithm for forward-inverse experiment design. Proceedings of the 2006 Winter Simulation Conference, WSC. 2006. pp. 376-381 (Proceedings - Winter Simulation Conference).
@inproceedings{b64f5a4a7fd145579eaeaaf00c5ac8ad,
title = "A two-phase maxi-min algorithm for forward-inverse experiment design",
abstract = "In customer-driven design of systems or products, one has performance targets in mind and would like to identify system design parameters that yield the target performance vector. Since most simulation models predict performance given design parameter values, this identification must be done iteratively through an optimization search procedure. In some cases it would be preferable to find design parameter values directly via an explicit inverse model. Regression and other forms of approximation 'metamodels' provide estimates of simulation model outputs as a function of design parameters. It is possible to design fitting experiments (DOE's) that allow simultaneous fitting of both forward and inverse metamodels. This paper discusses the potential for this strategy and shows a simple two-phase DOE strategy using a maxi-min measure of DOE quality.",
author = "Barton, {Russell Richard}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/WSC.2006.323105",
language = "English (US)",
isbn = "1424405017",
series = "Proceedings - Winter Simulation Conference",
pages = "376--381",
booktitle = "Proceedings of the 2006 Winter Simulation Conference, WSC",

}

Barton, RR 2006, A two-phase maxi-min algorithm for forward-inverse experiment design. in Proceedings of the 2006 Winter Simulation Conference, WSC., 4117629, Proceedings - Winter Simulation Conference, pp. 376-381, 2006 Winter Simulation Conference, WSC, Monterey, CA, United States, 12/3/06. https://doi.org/10.1109/WSC.2006.323105

A two-phase maxi-min algorithm for forward-inverse experiment design. / Barton, Russell Richard.

Proceedings of the 2006 Winter Simulation Conference, WSC. 2006. p. 376-381 4117629 (Proceedings - Winter Simulation Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A two-phase maxi-min algorithm for forward-inverse experiment design

AU - Barton, Russell Richard

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In customer-driven design of systems or products, one has performance targets in mind and would like to identify system design parameters that yield the target performance vector. Since most simulation models predict performance given design parameter values, this identification must be done iteratively through an optimization search procedure. In some cases it would be preferable to find design parameter values directly via an explicit inverse model. Regression and other forms of approximation 'metamodels' provide estimates of simulation model outputs as a function of design parameters. It is possible to design fitting experiments (DOE's) that allow simultaneous fitting of both forward and inverse metamodels. This paper discusses the potential for this strategy and shows a simple two-phase DOE strategy using a maxi-min measure of DOE quality.

AB - In customer-driven design of systems or products, one has performance targets in mind and would like to identify system design parameters that yield the target performance vector. Since most simulation models predict performance given design parameter values, this identification must be done iteratively through an optimization search procedure. In some cases it would be preferable to find design parameter values directly via an explicit inverse model. Regression and other forms of approximation 'metamodels' provide estimates of simulation model outputs as a function of design parameters. It is possible to design fitting experiments (DOE's) that allow simultaneous fitting of both forward and inverse metamodels. This paper discusses the potential for this strategy and shows a simple two-phase DOE strategy using a maxi-min measure of DOE quality.

UR - http://www.scopus.com/inward/record.url?scp=46149097925&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46149097925&partnerID=8YFLogxK

U2 - 10.1109/WSC.2006.323105

DO - 10.1109/WSC.2006.323105

M3 - Conference contribution

AN - SCOPUS:46149097925

SN - 1424405017

SN - 9781424405015

T3 - Proceedings - Winter Simulation Conference

SP - 376

EP - 381

BT - Proceedings of the 2006 Winter Simulation Conference, WSC

ER -

Barton RR. A two-phase maxi-min algorithm for forward-inverse experiment design. In Proceedings of the 2006 Winter Simulation Conference, WSC. 2006. p. 376-381. 4117629. (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2006.323105