An importance sampling based approach for reliability analysis

Fan Li; Teresa Wu

doi:10.1109/COASE.2007.4341815

An importance sampling based approach for reliability analysis

Fan Li, Teresa Wu

Industrial, Systems and Operations Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

In this paper, an importance sampling based approach for reliability analysis is proposed. The fundamental of this approach is to bias the realization of random variables around the most probable point (MPP) such that the number of simulations can be reduced significantly. Compared to the basic Monte Carlo simulation (MCS), the proposed approach requires less computational effort since it only evaluates the system performance functions at the reduced probability space. Two comparison experiments are conducted at the end of the paper. One is used to demonstrate the proposed method improves the efficiency comparing with basic MCS without losing accuracy. The second one is used to illustrate the proposed method generates more accurate results than that of FORM (first order reliability method).

Original language	English (US)
Title of host publication	Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007
Pages	956-961
Number of pages	6
DOIs	https://doi.org/10.1109/COASE.2007.4341815
State	Published - 2007
Event	3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007 - Scottsdale, AZ, United States Duration: Sep 22 2007 → Sep 25 2007

Publication series

Name	Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007

Other

Other	3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007
Country/Territory	United States
City	Scottsdale, AZ
Period	9/22/07 → 9/25/07

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/COASE.2007.4341815

Cite this

Li, F., & Wu, T. (2007). An importance sampling based approach for reliability analysis. In Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007 (pp. 956-961). [4341815] (Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007). https://doi.org/10.1109/COASE.2007.4341815

An importance sampling based approach for reliability analysis. / Li, Fan; Wu, Teresa.

Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007. 2007. p. 956-961 4341815 (Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Li, F & Wu, T 2007, An importance sampling based approach for reliability analysis. in Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007., 4341815, Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007, pp. 956-961, 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007, Scottsdale, AZ, United States, 9/22/07. https://doi.org/10.1109/COASE.2007.4341815

@inproceedings{e289d85e2c134aa7aa3a1ac5b527ca62,

title = "An importance sampling based approach for reliability analysis",

abstract = "In this paper, an importance sampling based approach for reliability analysis is proposed. The fundamental of this approach is to bias the realization of random variables around the most probable point (MPP) such that the number of simulations can be reduced significantly. Compared to the basic Monte Carlo simulation (MCS), the proposed approach requires less computational effort since it only evaluates the system performance functions at the reduced probability space. Two comparison experiments are conducted at the end of the paper. One is used to demonstrate the proposed method improves the efficiency comparing with basic MCS without losing accuracy. The second one is used to illustrate the proposed method generates more accurate results than that of FORM (first order reliability method).",

author = "Fan Li and Teresa Wu",

year = "2007",

doi = "10.1109/COASE.2007.4341815",

language = "English (US)",

isbn = "1424411548",

series = "Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007",

pages = "956--961",

booktitle = "Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007",

note = "3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007 ; Conference date: 22-09-2007 Through 25-09-2007",

}

TY - GEN

T1 - An importance sampling based approach for reliability analysis

AU - Li, Fan

AU - Wu, Teresa

PY - 2007

Y1 - 2007

N2 - In this paper, an importance sampling based approach for reliability analysis is proposed. The fundamental of this approach is to bias the realization of random variables around the most probable point (MPP) such that the number of simulations can be reduced significantly. Compared to the basic Monte Carlo simulation (MCS), the proposed approach requires less computational effort since it only evaluates the system performance functions at the reduced probability space. Two comparison experiments are conducted at the end of the paper. One is used to demonstrate the proposed method improves the efficiency comparing with basic MCS without losing accuracy. The second one is used to illustrate the proposed method generates more accurate results than that of FORM (first order reliability method).

AB - In this paper, an importance sampling based approach for reliability analysis is proposed. The fundamental of this approach is to bias the realization of random variables around the most probable point (MPP) such that the number of simulations can be reduced significantly. Compared to the basic Monte Carlo simulation (MCS), the proposed approach requires less computational effort since it only evaluates the system performance functions at the reduced probability space. Two comparison experiments are conducted at the end of the paper. One is used to demonstrate the proposed method improves the efficiency comparing with basic MCS without losing accuracy. The second one is used to illustrate the proposed method generates more accurate results than that of FORM (first order reliability method).

UR - http://www.scopus.com/inward/record.url?scp=44449146101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44449146101&partnerID=8YFLogxK

U2 - 10.1109/COASE.2007.4341815

DO - 10.1109/COASE.2007.4341815

M3 - Conference contribution

AN - SCOPUS:44449146101

SN - 1424411548

SN - 9781424411542

T3 - Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007

SP - 956

EP - 961

BT - Proceedings of the 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007

T2 - 3rd IEEE International Conference on Automation Science and Engineering, IEEE CASE 2007

Y2 - 22 September 2007 through 25 September 2007

ER -

An importance sampling based approach for reliability analysis

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this