Reliability based design of engineering systems with monotonic models

M. Rajabalinejad, C. Spitas

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

Abstract

A computationally efficient Bayesian Monte Carlo for Monotonic (BMCM) models for reliability based design of engineering systems is described in this paper. The model employs Gaussian distribution and monotonicity principles that have been implemented in the Dynamic Bounds (DB) method (Rajabalinejad 2009) integrated with a Bayesian Monte Carlo (BMC) technique. Signficant improvements in the computational speed of coupled DB and BMC methods are realized by incorporating a weighted logical dependence between neighboring points of the Limit-State Equation (LSE) as prior information and global uncertaintiy concept for quantifying variations of the controlling input variables. The outcomes of preceding simulations are factored in subsequent calculations to accelerate computing efficiency of the Monte Carlo method. The theory and numerical algorithms of the BMCM are described in this paper, and extension of the BMCM to multi-dimensional problems is provided.

Original languageEnglish
Title of host publicationAdvances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011
Pages112-115
Number of pages4
Publication statusPublished - 2012
Externally publishedYes
EventEuropean Safety and Reliability Conference: Advances in Safety, Reliability and Risk Management, ESREL 2011 - Troyes, France
Duration: Sep 18 2011Sep 22 2011

Other

OtherEuropean Safety and Reliability Conference: Advances in Safety, Reliability and Risk Management, ESREL 2011
CountryFrance
CityTroyes
Period9/18/119/22/11

Fingerprint

Systems engineering
Monte Carlo methods
Gaussian distribution

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality

Cite this

Rajabalinejad, M., & Spitas, C. (2012). Reliability based design of engineering systems with monotonic models. In Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011 (pp. 112-115)

Reliability based design of engineering systems with monotonic models. / Rajabalinejad, M.; Spitas, C.

Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011. 2012. p. 112-115.

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

Rajabalinejad, M & Spitas, C 2012, Reliability based design of engineering systems with monotonic models. in Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011. pp. 112-115, European Safety and Reliability Conference: Advances in Safety, Reliability and Risk Management, ESREL 2011, Troyes, France, 9/18/11.
Rajabalinejad M, Spitas C. Reliability based design of engineering systems with monotonic models. In Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011. 2012. p. 112-115
Rajabalinejad, M. ; Spitas, C. / Reliability based design of engineering systems with monotonic models. Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011. 2012. pp. 112-115
@inproceedings{e0efa938fca048f5a75b8ab25001100a,
title = "Reliability based design of engineering systems with monotonic models",
abstract = "A computationally efficient Bayesian Monte Carlo for Monotonic (BMCM) models for reliability based design of engineering systems is described in this paper. The model employs Gaussian distribution and monotonicity principles that have been implemented in the Dynamic Bounds (DB) method (Rajabalinejad 2009) integrated with a Bayesian Monte Carlo (BMC) technique. Signficant improvements in the computational speed of coupled DB and BMC methods are realized by incorporating a weighted logical dependence between neighboring points of the Limit-State Equation (LSE) as prior information and global uncertaintiy concept for quantifying variations of the controlling input variables. The outcomes of preceding simulations are factored in subsequent calculations to accelerate computing efficiency of the Monte Carlo method. The theory and numerical algorithms of the BMCM are described in this paper, and extension of the BMCM to multi-dimensional problems is provided.",
author = "M. Rajabalinejad and C. Spitas",
year = "2012",
language = "English",
isbn = "9780415683791",
pages = "112--115",
booktitle = "Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011",

}

TY - GEN

T1 - Reliability based design of engineering systems with monotonic models

AU - Rajabalinejad, M.

AU - Spitas, C.

PY - 2012

Y1 - 2012

N2 - A computationally efficient Bayesian Monte Carlo for Monotonic (BMCM) models for reliability based design of engineering systems is described in this paper. The model employs Gaussian distribution and monotonicity principles that have been implemented in the Dynamic Bounds (DB) method (Rajabalinejad 2009) integrated with a Bayesian Monte Carlo (BMC) technique. Signficant improvements in the computational speed of coupled DB and BMC methods are realized by incorporating a weighted logical dependence between neighboring points of the Limit-State Equation (LSE) as prior information and global uncertaintiy concept for quantifying variations of the controlling input variables. The outcomes of preceding simulations are factored in subsequent calculations to accelerate computing efficiency of the Monte Carlo method. The theory and numerical algorithms of the BMCM are described in this paper, and extension of the BMCM to multi-dimensional problems is provided.

AB - A computationally efficient Bayesian Monte Carlo for Monotonic (BMCM) models for reliability based design of engineering systems is described in this paper. The model employs Gaussian distribution and monotonicity principles that have been implemented in the Dynamic Bounds (DB) method (Rajabalinejad 2009) integrated with a Bayesian Monte Carlo (BMC) technique. Signficant improvements in the computational speed of coupled DB and BMC methods are realized by incorporating a weighted logical dependence between neighboring points of the Limit-State Equation (LSE) as prior information and global uncertaintiy concept for quantifying variations of the controlling input variables. The outcomes of preceding simulations are factored in subsequent calculations to accelerate computing efficiency of the Monte Carlo method. The theory and numerical algorithms of the BMCM are described in this paper, and extension of the BMCM to multi-dimensional problems is provided.

UR - http://www.scopus.com/inward/record.url?scp=84856763674&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856763674&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780415683791

SP - 112

EP - 115

BT - Advances in Safety, Reliability and Risk Management - Proceedings of the European Safety and Reliability Conference, ESREL 2011

ER -