A sequential sampling strategy to improve reliability-based design optimization with implicit constraint functions

Xiaotian Zhuang, Rong Pan

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Reliability-based design optimization (RBDO) has a probabilistic constraint that is used for evaluating the reliability or safety of the system. In modern engineering design, this task is often performed by a computer simulation tool such as finite element method (FEM). This type of computer simulation or computer experiment can be treated a black box, as its analytical function is implicit. This paper presents an efficient sampling strategy on learning the probabilistic constraint function under the design optimization framework. The method is a sequential experimentation around the approximate most probable point (MPP) at each step of optimization process. Our method is compared with the methods of MPP-based sampling, lifted surrogate function, and nonsequential random sampling. We demonstrate it through examples.

Original languageEnglish (US)
Article number021002
JournalJournal of Mechanical Design, Transactions Of the ASME
Volume134
Issue number2
DOIs
StatePublished - 2012

Fingerprint

Sampling
Computer simulation
Finite element method
Design optimization
Experiments

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications

Cite this

@article{5b3643ecaca145fbb041f2eb943df601,
title = "A sequential sampling strategy to improve reliability-based design optimization with implicit constraint functions",
abstract = "Reliability-based design optimization (RBDO) has a probabilistic constraint that is used for evaluating the reliability or safety of the system. In modern engineering design, this task is often performed by a computer simulation tool such as finite element method (FEM). This type of computer simulation or computer experiment can be treated a black box, as its analytical function is implicit. This paper presents an efficient sampling strategy on learning the probabilistic constraint function under the design optimization framework. The method is a sequential experimentation around the approximate most probable point (MPP) at each step of optimization process. Our method is compared with the methods of MPP-based sampling, lifted surrogate function, and nonsequential random sampling. We demonstrate it through examples.",
author = "Xiaotian Zhuang and Rong Pan",
year = "2012",
doi = "10.1115/1.4005597",
language = "English (US)",
volume = "134",
journal = "Journal of Mechanical Design - Transactions of the ASME",
issn = "1050-0472",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "2",

}

TY - JOUR

T1 - A sequential sampling strategy to improve reliability-based design optimization with implicit constraint functions

AU - Zhuang, Xiaotian

AU - Pan, Rong

PY - 2012

Y1 - 2012

N2 - Reliability-based design optimization (RBDO) has a probabilistic constraint that is used for evaluating the reliability or safety of the system. In modern engineering design, this task is often performed by a computer simulation tool such as finite element method (FEM). This type of computer simulation or computer experiment can be treated a black box, as its analytical function is implicit. This paper presents an efficient sampling strategy on learning the probabilistic constraint function under the design optimization framework. The method is a sequential experimentation around the approximate most probable point (MPP) at each step of optimization process. Our method is compared with the methods of MPP-based sampling, lifted surrogate function, and nonsequential random sampling. We demonstrate it through examples.

AB - Reliability-based design optimization (RBDO) has a probabilistic constraint that is used for evaluating the reliability or safety of the system. In modern engineering design, this task is often performed by a computer simulation tool such as finite element method (FEM). This type of computer simulation or computer experiment can be treated a black box, as its analytical function is implicit. This paper presents an efficient sampling strategy on learning the probabilistic constraint function under the design optimization framework. The method is a sequential experimentation around the approximate most probable point (MPP) at each step of optimization process. Our method is compared with the methods of MPP-based sampling, lifted surrogate function, and nonsequential random sampling. We demonstrate it through examples.

UR - http://www.scopus.com/inward/record.url?scp=84856986135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856986135&partnerID=8YFLogxK

U2 - 10.1115/1.4005597

DO - 10.1115/1.4005597

M3 - Article

AN - SCOPUS:84856986135

VL - 134

JO - Journal of Mechanical Design - Transactions of the ASME

JF - Journal of Mechanical Design - Transactions of the ASME

SN - 1050-0472

IS - 2

M1 - 021002

ER -