Maximum relative entropy-based probabilistic inference in fatigue crack damage prognostics

Xuefei Guan, Adom Giffin, Ratneshwar Jha, Yongming Liu

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

A general probabilistic inference procedure is proposed in this paper based on the Maximum relative Entropy (MrE) approach which generalizes both Bayesian and Maximum Entropy (MaxEnt) inference methodologies. The construction of the conditional probability (likelihood function) for general model-based inference problems is discussed in detail to systematically manage uncertainties from mechanism modeling, model parameters, and measurements. Analytical and numerical examples are used to investigate the sequence effect in the probabilistic inference using point observations and moment constraints. The developed methodology is applied to the engineering fatigue crack growth problem with experimental data for demonstration and validation. Following this, a detailed comparison between the classical Bayesian inference and the MrE inference is given.

Original languageEnglish (US)
Pages (from-to)157-166
Number of pages10
JournalProbabilistic Engineering Mechanics
Volume29
DOIs
StatePublished - Jul 2012
Externally publishedYes

Fingerprint

inference
Entropy
cracks
entropy
damage
Fatigue crack propagation
Demonstrations
methodology
Fatigue cracks
engineering
moments

Keywords

  • Bayesian updating
  • Fatigue crack propagation
  • Maximum relative entropy
  • Probabilistic inference
  • Uncertainty

ASJC Scopus subject areas

  • Nuclear Energy and Engineering
  • Ocean Engineering
  • Aerospace Engineering
  • Civil and Structural Engineering
  • Mechanical Engineering
  • Statistical and Nonlinear Physics
  • Condensed Matter Physics

Cite this

Maximum relative entropy-based probabilistic inference in fatigue crack damage prognostics. / Guan, Xuefei; Giffin, Adom; Jha, Ratneshwar; Liu, Yongming.

In: Probabilistic Engineering Mechanics, Vol. 29, 07.2012, p. 157-166.

Research output: Contribution to journalArticle

@article{7f4365a72a864e8888797909c91acbe0,
title = "Maximum relative entropy-based probabilistic inference in fatigue crack damage prognostics",
abstract = "A general probabilistic inference procedure is proposed in this paper based on the Maximum relative Entropy (MrE) approach which generalizes both Bayesian and Maximum Entropy (MaxEnt) inference methodologies. The construction of the conditional probability (likelihood function) for general model-based inference problems is discussed in detail to systematically manage uncertainties from mechanism modeling, model parameters, and measurements. Analytical and numerical examples are used to investigate the sequence effect in the probabilistic inference using point observations and moment constraints. The developed methodology is applied to the engineering fatigue crack growth problem with experimental data for demonstration and validation. Following this, a detailed comparison between the classical Bayesian inference and the MrE inference is given.",
keywords = "Bayesian updating, Fatigue crack propagation, Maximum relative entropy, Probabilistic inference, Uncertainty",
author = "Xuefei Guan and Adom Giffin and Ratneshwar Jha and Yongming Liu",
year = "2012",
month = "7",
doi = "10.1016/j.probengmech.2011.11.006",
language = "English (US)",
volume = "29",
pages = "157--166",
journal = "Probabilistic Engineering Mechanics",
issn = "0266-8920",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Maximum relative entropy-based probabilistic inference in fatigue crack damage prognostics

AU - Guan, Xuefei

AU - Giffin, Adom

AU - Jha, Ratneshwar

AU - Liu, Yongming

PY - 2012/7

Y1 - 2012/7

N2 - A general probabilistic inference procedure is proposed in this paper based on the Maximum relative Entropy (MrE) approach which generalizes both Bayesian and Maximum Entropy (MaxEnt) inference methodologies. The construction of the conditional probability (likelihood function) for general model-based inference problems is discussed in detail to systematically manage uncertainties from mechanism modeling, model parameters, and measurements. Analytical and numerical examples are used to investigate the sequence effect in the probabilistic inference using point observations and moment constraints. The developed methodology is applied to the engineering fatigue crack growth problem with experimental data for demonstration and validation. Following this, a detailed comparison between the classical Bayesian inference and the MrE inference is given.

AB - A general probabilistic inference procedure is proposed in this paper based on the Maximum relative Entropy (MrE) approach which generalizes both Bayesian and Maximum Entropy (MaxEnt) inference methodologies. The construction of the conditional probability (likelihood function) for general model-based inference problems is discussed in detail to systematically manage uncertainties from mechanism modeling, model parameters, and measurements. Analytical and numerical examples are used to investigate the sequence effect in the probabilistic inference using point observations and moment constraints. The developed methodology is applied to the engineering fatigue crack growth problem with experimental data for demonstration and validation. Following this, a detailed comparison between the classical Bayesian inference and the MrE inference is given.

KW - Bayesian updating

KW - Fatigue crack propagation

KW - Maximum relative entropy

KW - Probabilistic inference

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=84858439143&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858439143&partnerID=8YFLogxK

U2 - 10.1016/j.probengmech.2011.11.006

DO - 10.1016/j.probengmech.2011.11.006

M3 - Article

VL - 29

SP - 157

EP - 166

JO - Probabilistic Engineering Mechanics

JF - Probabilistic Engineering Mechanics

SN - 0266-8920

ER -