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 - 2024/4/23

Y1 - 2024/4/23

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 -