Lévy-driven non-Gaussian Ornstein–Uhlenbeck processes for degradation-based reliability analysis

Yin Shu, Qianmei Feng, Edward P.C. Kao, Hao Liu

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

We use Lévy subordinators and non-Gaussian Ornstein–Uhlenbeck processes to model the evolution of degradation with random jumps. The superiority of our models stems from the flexibility of such processes in the modeling of stylized features of degradation data series such as jumps, linearity/nonlinearity, symmetry/asymmetry, and light/heavy tails. Based on corresponding Fokker–Planck equations, we derive explicit results for the reliability function and lifetime moments in terms of Laplace transforms, represented by Lévy measures. Numerical experiments are used to demonstrate that our general models perform well and are applicable for analyzing a large number of degradation phenomena. More important, they provide us with a new methodology to deal with multi-degradation processes under dynamicenvironments.

Original languageEnglish (US)
Pages (from-to)993-1003
Number of pages11
JournalIIE Transactions (Institute of Industrial Engineers)
Volume48
Issue number11
DOIs
StatePublished - Nov 1 2016
Externally publishedYes

Fingerprint

Reliability analysis
Degradation
Laplace transforms
Experiments

Keywords

  • degradation processes
  • Fokker–Planck equations
  • Laplace transform
  • lifetime moments
  • Lévy subordinators
  • non-Gaussian OU processes

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Lévy-driven non-Gaussian Ornstein–Uhlenbeck processes for degradation-based reliability analysis. / Shu, Yin; Feng, Qianmei; Kao, Edward P.C.; Liu, Hao.

In: IIE Transactions (Institute of Industrial Engineers), Vol. 48, No. 11, 01.11.2016, p. 993-1003.

Research output: Contribution to journalArticle

@article{ca6e930a4afb4d6481e3447d45094a51,
title = "L{\'e}vy-driven non-Gaussian Ornstein–Uhlenbeck processes for degradation-based reliability analysis",
abstract = "We use L{\'e}vy subordinators and non-Gaussian Ornstein–Uhlenbeck processes to model the evolution of degradation with random jumps. The superiority of our models stems from the flexibility of such processes in the modeling of stylized features of degradation data series such as jumps, linearity/nonlinearity, symmetry/asymmetry, and light/heavy tails. Based on corresponding Fokker–Planck equations, we derive explicit results for the reliability function and lifetime moments in terms of Laplace transforms, represented by L{\'e}vy measures. Numerical experiments are used to demonstrate that our general models perform well and are applicable for analyzing a large number of degradation phenomena. More important, they provide us with a new methodology to deal with multi-degradation processes under dynamicenvironments.",
keywords = "degradation processes, Fokker–Planck equations, Laplace transform, lifetime moments, L{\'e}vy subordinators, non-Gaussian OU processes",
author = "Yin Shu and Qianmei Feng and Kao, {Edward P.C.} and Hao Liu",
year = "2016",
month = "11",
day = "1",
doi = "10.1080/0740817X.2016.1172743",
language = "English (US)",
volume = "48",
pages = "993--1003",
journal = "IISE Transactions",
issn = "2472-5854",
publisher = "Taylor and Francis Ltd.",
number = "11",

}

TY - JOUR

T1 - Lévy-driven non-Gaussian Ornstein–Uhlenbeck processes for degradation-based reliability analysis

AU - Shu, Yin

AU - Feng, Qianmei

AU - Kao, Edward P.C.

AU - Liu, Hao

PY - 2016/11/1

Y1 - 2016/11/1

N2 - We use Lévy subordinators and non-Gaussian Ornstein–Uhlenbeck processes to model the evolution of degradation with random jumps. The superiority of our models stems from the flexibility of such processes in the modeling of stylized features of degradation data series such as jumps, linearity/nonlinearity, symmetry/asymmetry, and light/heavy tails. Based on corresponding Fokker–Planck equations, we derive explicit results for the reliability function and lifetime moments in terms of Laplace transforms, represented by Lévy measures. Numerical experiments are used to demonstrate that our general models perform well and are applicable for analyzing a large number of degradation phenomena. More important, they provide us with a new methodology to deal with multi-degradation processes under dynamicenvironments.

AB - We use Lévy subordinators and non-Gaussian Ornstein–Uhlenbeck processes to model the evolution of degradation with random jumps. The superiority of our models stems from the flexibility of such processes in the modeling of stylized features of degradation data series such as jumps, linearity/nonlinearity, symmetry/asymmetry, and light/heavy tails. Based on corresponding Fokker–Planck equations, we derive explicit results for the reliability function and lifetime moments in terms of Laplace transforms, represented by Lévy measures. Numerical experiments are used to demonstrate that our general models perform well and are applicable for analyzing a large number of degradation phenomena. More important, they provide us with a new methodology to deal with multi-degradation processes under dynamicenvironments.

KW - degradation processes

KW - Fokker–Planck equations

KW - Laplace transform

KW - lifetime moments

KW - Lévy subordinators

KW - non-Gaussian OU processes

UR - http://www.scopus.com/inward/record.url?scp=84978971741&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978971741&partnerID=8YFLogxK

U2 - 10.1080/0740817X.2016.1172743

DO - 10.1080/0740817X.2016.1172743

M3 - Article

VL - 48

SP - 993

EP - 1003

JO - IISE Transactions

JF - IISE Transactions

SN - 2472-5854

IS - 11

ER -