An efficient strategy for information reuse in probability density evolution method considering large shift of distributions with multiple random variables

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Jia Shu Yang
  • Zhiqiang Wan
  • Hector Jensen

Organisationseinheiten

Externe Organisationen

  • Xi'an University of Architecture and Technology
  • Northwestern Polytechnical University
  • Universidad Tecnica Federico Santa Maria
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer103728
Seitenumfang16
FachzeitschriftProbabilistic Engineering Mechanics
Jahrgang79
Frühes Online-Datum31 Dez. 2024
PublikationsstatusVeröffentlicht - Jan. 2025

Abstract

The probability density evolution method (PDEM) is a versatile approach for analyzing stochastic dynamical systems. When combined with the change of probability measure (COM), it provides a tool to efficiently deal with the aleatory and epistemic uncertainties, where shifts of probability distributions are frequently encountered. However, when the shifts of distributions are too large, the PDEM-COM method can lead to increasing numerical errors. This paper aims to propose an extension of the PDEM-COM that can address the large shifts of distributions involving multiple random variables. In the proposed method, the concepts of the multi-dimensional augmented support and the augmented probability density function (PDF) are introduced based on the differences between the original and updated distributions. Then, an efficient numerical procedure is established for selecting a small set of additional representative points based on the augmented PDF. These additional representative points serve as a complement to the representative point set selected according to the original distributions. By incorporating the augmented representative point set and solving the generalized probability density evolution equation (GDEE), the stochastic response of the system considering the updated distributions can be evaluated. Numerical examples are presented to demonstrate the capability and effectiveness of the proposed approach. The results demonstrate that the proposed approach offers improved accuracy compared to the PDEM-COM method, particularly for large distribution shifts, while maintaining a relatively lower computational cost.

ASJC Scopus Sachgebiete

Zitieren

An efficient strategy for information reuse in probability density evolution method considering large shift of distributions with multiple random variables. / Yang, Jia Shu; Wan, Zhiqiang; Jensen, Hector.
in: Probabilistic Engineering Mechanics, Jahrgang 79, 103728, 01.2025.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Download
@article{39bc8d6d242349429771011df49c3659,
title = "An efficient strategy for information reuse in probability density evolution method considering large shift of distributions with multiple random variables",
abstract = "The probability density evolution method (PDEM) is a versatile approach for analyzing stochastic dynamical systems. When combined with the change of probability measure (COM), it provides a tool to efficiently deal with the aleatory and epistemic uncertainties, where shifts of probability distributions are frequently encountered. However, when the shifts of distributions are too large, the PDEM-COM method can lead to increasing numerical errors. This paper aims to propose an extension of the PDEM-COM that can address the large shifts of distributions involving multiple random variables. In the proposed method, the concepts of the multi-dimensional augmented support and the augmented probability density function (PDF) are introduced based on the differences between the original and updated distributions. Then, an efficient numerical procedure is established for selecting a small set of additional representative points based on the augmented PDF. These additional representative points serve as a complement to the representative point set selected according to the original distributions. By incorporating the augmented representative point set and solving the generalized probability density evolution equation (GDEE), the stochastic response of the system considering the updated distributions can be evaluated. Numerical examples are presented to demonstrate the capability and effectiveness of the proposed approach. The results demonstrate that the proposed approach offers improved accuracy compared to the PDEM-COM method, particularly for large distribution shifts, while maintaining a relatively lower computational cost.",
keywords = "Change of probability measure, Information reuse, Multiple random variables, Probability density evolution method, Shift of distribution",
author = "Yang, {Jia Shu} and Zhiqiang Wan and Hector Jensen",
note = "Publisher Copyright: {\textcopyright} 2024 Elsevier Ltd",
year = "2025",
month = jan,
doi = "10.1016/j.probengmech.2024.103728",
language = "English",
volume = "79",
journal = "Probabilistic Engineering Mechanics",
issn = "0266-8920",
publisher = "Elsevier Ltd.",

}

Download

TY - JOUR

T1 - An efficient strategy for information reuse in probability density evolution method considering large shift of distributions with multiple random variables

AU - Yang, Jia Shu

AU - Wan, Zhiqiang

AU - Jensen, Hector

N1 - Publisher Copyright: © 2024 Elsevier Ltd

PY - 2025/1

Y1 - 2025/1

N2 - The probability density evolution method (PDEM) is a versatile approach for analyzing stochastic dynamical systems. When combined with the change of probability measure (COM), it provides a tool to efficiently deal with the aleatory and epistemic uncertainties, where shifts of probability distributions are frequently encountered. However, when the shifts of distributions are too large, the PDEM-COM method can lead to increasing numerical errors. This paper aims to propose an extension of the PDEM-COM that can address the large shifts of distributions involving multiple random variables. In the proposed method, the concepts of the multi-dimensional augmented support and the augmented probability density function (PDF) are introduced based on the differences between the original and updated distributions. Then, an efficient numerical procedure is established for selecting a small set of additional representative points based on the augmented PDF. These additional representative points serve as a complement to the representative point set selected according to the original distributions. By incorporating the augmented representative point set and solving the generalized probability density evolution equation (GDEE), the stochastic response of the system considering the updated distributions can be evaluated. Numerical examples are presented to demonstrate the capability and effectiveness of the proposed approach. The results demonstrate that the proposed approach offers improved accuracy compared to the PDEM-COM method, particularly for large distribution shifts, while maintaining a relatively lower computational cost.

AB - The probability density evolution method (PDEM) is a versatile approach for analyzing stochastic dynamical systems. When combined with the change of probability measure (COM), it provides a tool to efficiently deal with the aleatory and epistemic uncertainties, where shifts of probability distributions are frequently encountered. However, when the shifts of distributions are too large, the PDEM-COM method can lead to increasing numerical errors. This paper aims to propose an extension of the PDEM-COM that can address the large shifts of distributions involving multiple random variables. In the proposed method, the concepts of the multi-dimensional augmented support and the augmented probability density function (PDF) are introduced based on the differences between the original and updated distributions. Then, an efficient numerical procedure is established for selecting a small set of additional representative points based on the augmented PDF. These additional representative points serve as a complement to the representative point set selected according to the original distributions. By incorporating the augmented representative point set and solving the generalized probability density evolution equation (GDEE), the stochastic response of the system considering the updated distributions can be evaluated. Numerical examples are presented to demonstrate the capability and effectiveness of the proposed approach. The results demonstrate that the proposed approach offers improved accuracy compared to the PDEM-COM method, particularly for large distribution shifts, while maintaining a relatively lower computational cost.

KW - Change of probability measure

KW - Information reuse

KW - Multiple random variables

KW - Probability density evolution method

KW - Shift of distribution

UR - http://www.scopus.com/inward/record.url?scp=85214233658&partnerID=8YFLogxK

U2 - 10.1016/j.probengmech.2024.103728

DO - 10.1016/j.probengmech.2024.103728

M3 - Article

AN - SCOPUS:85214233658

VL - 79

JO - Probabilistic Engineering Mechanics

JF - Probabilistic Engineering Mechanics

SN - 0266-8920

M1 - 103728

ER -