Decision-theoretic reliability sensitivity

Daniel Straub; Max Ehre; Iason Papaioannou

doi:10.1016/j.ress.2021.108215

Decision-theoretic reliability sensitivity

Daniel Straub, Max Ehre, Iason Papaioannou

Associate Professorship of Engineering Risk Analysis

Technical University of Munich

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

We propose and discuss sensitivity metrics for reliability analysis, which are based on the value of information. These metrics are easier to interpret than other existing sensitivity metrics in the context of a specific decision and they are applicable to any type of reliability assessment, including those with dependent inputs. We develop computational strategies that enable efficient evaluation of these metrics, in some scenarios without additional runs of the deterministic model. The metrics are investigated by application to numerical examples.

Original language	English
Article number	108215
Journal	Reliability Engineering and System Safety
Volume	221
DOIs	https://doi.org/10.1016/j.ress.2021.108215
State	Published - May 2022

Keywords

Reliability
Sensitivity analysis
Value of information

Access to Document

10.1016/j.ress.2021.108215

Cite this

@article{049a57ebe21d411e976107ff368d2f70,

title = "Decision-theoretic reliability sensitivity",

abstract = "We propose and discuss sensitivity metrics for reliability analysis, which are based on the value of information. These metrics are easier to interpret than other existing sensitivity metrics in the context of a specific decision and they are applicable to any type of reliability assessment, including those with dependent inputs. We develop computational strategies that enable efficient evaluation of these metrics, in some scenarios without additional runs of the deterministic model. The metrics are investigated by application to numerical examples.",

keywords = "Reliability, Sensitivity analysis, Value of information",

author = "Daniel Straub and Max Ehre and Iason Papaioannou",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier Ltd",

year = "2022",

month = may,

doi = "10.1016/j.ress.2021.108215",

language = "English",

volume = "221",

journal = "Reliability Engineering and System Safety",

issn = "0951-8320",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Decision-theoretic reliability sensitivity

AU - Straub, Daniel

AU - Ehre, Max

AU - Papaioannou, Iason

PY - 2022/5

Y1 - 2022/5

N2 - We propose and discuss sensitivity metrics for reliability analysis, which are based on the value of information. These metrics are easier to interpret than other existing sensitivity metrics in the context of a specific decision and they are applicable to any type of reliability assessment, including those with dependent inputs. We develop computational strategies that enable efficient evaluation of these metrics, in some scenarios without additional runs of the deterministic model. The metrics are investigated by application to numerical examples.

AB - We propose and discuss sensitivity metrics for reliability analysis, which are based on the value of information. These metrics are easier to interpret than other existing sensitivity metrics in the context of a specific decision and they are applicable to any type of reliability assessment, including those with dependent inputs. We develop computational strategies that enable efficient evaluation of these metrics, in some scenarios without additional runs of the deterministic model. The metrics are investigated by application to numerical examples.

KW - Reliability

KW - Sensitivity analysis

KW - Value of information

UR - http://www.scopus.com/inward/record.url?scp=85122799864&partnerID=8YFLogxK

U2 - 10.1016/j.ress.2021.108215

DO - 10.1016/j.ress.2021.108215

M3 - Article

AN - SCOPUS:85122799864

SN - 0951-8320

VL - 221

JO - Reliability Engineering and System Safety

JF - Reliability Engineering and System Safety

M1 - 108215

ER -

Decision-theoretic reliability sensitivity

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this