rLSTM-AE for dimension reduction and its application to active learning-based dynamic reliability analysis

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Hong Kong Polytechnic University
  • University of Liverpool
  • Tsinghua University
View graph of relations

Details

Original languageEnglish
Article number111426
Number of pages21
JournalMechanical Systems and Signal Processing
Volume215
Early online date23 Apr 2024
Publication statusPublished - 1 Jun 2024

Abstract

A novel method termed rLSTM-AE is developed for the low-dimensional latent space identification of the stochastic dynamic systems with more than 1000 input random variables and the active learning-based dynamic reliability analysis. First, the long short-term memory network considers both the time-variant stochastic excitation and the time-invariant random variables is developed (rLSTM), which adopts the time-series excitation as the pertinent input feature and makes it available for the metamodeling of the high-dimensional stochastic dynamic systems. To circumvent the insufficient accuracy of deep neural networks for reliability analysis results from the limited observations, autoencoder (AE) is incorporated with the rLSTM (rLSTM-AE) and utilized to decompose the approximate extreme value space found by rLSTM onto a low-dimensional latent space. The dimension of the latent space is adaptively determined by a Gaussian process regression reconstruction error, which enables the Gaussian process regression with the similar accuracy as rLSTM regarding the extreme responses prediction. The proposed rLSTM-AE conducts the low-dimensional features extraction from the perspective of the output space decomposition and considers the time-dependent property of the dynamic systems. Finally, the detected latent variables can be combined with the active learning-based Gaussian process regression for the high-dimensional dynamic reliability analysis. One single-degree-of-freedom system and a reinforced concrete frame structure subjected to the stochastic excitation are investigated to validate the performance of the proposed method.

Keywords

    High dimension, Latent space, Metamodel, Reliability analysis, Stochastic dynamic system

ASJC Scopus subject areas

Cite this

rLSTM-AE for dimension reduction and its application to active learning-based dynamic reliability analysis. / Zhang, Yu; Dong, You; Beer, Michael.
In: Mechanical Systems and Signal Processing, Vol. 215, 111426, 01.06.2024.

Research output: Contribution to journalArticleResearchpeer review

Download
@article{8008b0e22ce840a7949bd418e308ee04,
title = "rLSTM-AE for dimension reduction and its application to active learning-based dynamic reliability analysis",
abstract = "A novel method termed rLSTM-AE is developed for the low-dimensional latent space identification of the stochastic dynamic systems with more than 1000 input random variables and the active learning-based dynamic reliability analysis. First, the long short-term memory network considers both the time-variant stochastic excitation and the time-invariant random variables is developed (rLSTM), which adopts the time-series excitation as the pertinent input feature and makes it available for the metamodeling of the high-dimensional stochastic dynamic systems. To circumvent the insufficient accuracy of deep neural networks for reliability analysis results from the limited observations, autoencoder (AE) is incorporated with the rLSTM (rLSTM-AE) and utilized to decompose the approximate extreme value space found by rLSTM onto a low-dimensional latent space. The dimension of the latent space is adaptively determined by a Gaussian process regression reconstruction error, which enables the Gaussian process regression with the similar accuracy as rLSTM regarding the extreme responses prediction. The proposed rLSTM-AE conducts the low-dimensional features extraction from the perspective of the output space decomposition and considers the time-dependent property of the dynamic systems. Finally, the detected latent variables can be combined with the active learning-based Gaussian process regression for the high-dimensional dynamic reliability analysis. One single-degree-of-freedom system and a reinforced concrete frame structure subjected to the stochastic excitation are investigated to validate the performance of the proposed method.",
keywords = "High dimension, Latent space, Metamodel, Reliability analysis, Stochastic dynamic system",
author = "Yu Zhang and You Dong and Michael Beer",
note = "Funding Information: This study has been supported by the National Natural Science Foundation of China (Grant No. 52078448 ), the Research Grants Council of the Hong Kong Special Administrative Region , China (No. PolyU 15221521 and PolyU 15225722 ), and the Environment and Conservation Fund of the Hong Kong Special Administrative Region , China (No. ECF 42/2022 ). ",
year = "2024",
month = jun,
day = "1",
doi = "10.1016/j.ymssp.2024.111426",
language = "English",
volume = "215",
journal = "Mechanical Systems and Signal Processing",
issn = "0888-3270",
publisher = "Academic Press Inc.",

}

Download

TY - JOUR

T1 - rLSTM-AE for dimension reduction and its application to active learning-based dynamic reliability analysis

AU - Zhang, Yu

AU - Dong, You

AU - Beer, Michael

N1 - Funding Information: This study has been supported by the National Natural Science Foundation of China (Grant No. 52078448 ), the Research Grants Council of the Hong Kong Special Administrative Region , China (No. PolyU 15221521 and PolyU 15225722 ), and the Environment and Conservation Fund of the Hong Kong Special Administrative Region , China (No. ECF 42/2022 ).

PY - 2024/6/1

Y1 - 2024/6/1

N2 - A novel method termed rLSTM-AE is developed for the low-dimensional latent space identification of the stochastic dynamic systems with more than 1000 input random variables and the active learning-based dynamic reliability analysis. First, the long short-term memory network considers both the time-variant stochastic excitation and the time-invariant random variables is developed (rLSTM), which adopts the time-series excitation as the pertinent input feature and makes it available for the metamodeling of the high-dimensional stochastic dynamic systems. To circumvent the insufficient accuracy of deep neural networks for reliability analysis results from the limited observations, autoencoder (AE) is incorporated with the rLSTM (rLSTM-AE) and utilized to decompose the approximate extreme value space found by rLSTM onto a low-dimensional latent space. The dimension of the latent space is adaptively determined by a Gaussian process regression reconstruction error, which enables the Gaussian process regression with the similar accuracy as rLSTM regarding the extreme responses prediction. The proposed rLSTM-AE conducts the low-dimensional features extraction from the perspective of the output space decomposition and considers the time-dependent property of the dynamic systems. Finally, the detected latent variables can be combined with the active learning-based Gaussian process regression for the high-dimensional dynamic reliability analysis. One single-degree-of-freedom system and a reinforced concrete frame structure subjected to the stochastic excitation are investigated to validate the performance of the proposed method.

AB - A novel method termed rLSTM-AE is developed for the low-dimensional latent space identification of the stochastic dynamic systems with more than 1000 input random variables and the active learning-based dynamic reliability analysis. First, the long short-term memory network considers both the time-variant stochastic excitation and the time-invariant random variables is developed (rLSTM), which adopts the time-series excitation as the pertinent input feature and makes it available for the metamodeling of the high-dimensional stochastic dynamic systems. To circumvent the insufficient accuracy of deep neural networks for reliability analysis results from the limited observations, autoencoder (AE) is incorporated with the rLSTM (rLSTM-AE) and utilized to decompose the approximate extreme value space found by rLSTM onto a low-dimensional latent space. The dimension of the latent space is adaptively determined by a Gaussian process regression reconstruction error, which enables the Gaussian process regression with the similar accuracy as rLSTM regarding the extreme responses prediction. The proposed rLSTM-AE conducts the low-dimensional features extraction from the perspective of the output space decomposition and considers the time-dependent property of the dynamic systems. Finally, the detected latent variables can be combined with the active learning-based Gaussian process regression for the high-dimensional dynamic reliability analysis. One single-degree-of-freedom system and a reinforced concrete frame structure subjected to the stochastic excitation are investigated to validate the performance of the proposed method.

KW - High dimension

KW - Latent space

KW - Metamodel

KW - Reliability analysis

KW - Stochastic dynamic system

UR - http://www.scopus.com/inward/record.url?scp=85190772525&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2024.111426

DO - 10.1016/j.ymssp.2024.111426

M3 - Article

AN - SCOPUS:85190772525

VL - 215

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

M1 - 111426

ER -

By the same author(s)