Probabilistic method for time-varying reliability analysis of structure via variational bayesian neural network
Article
Dang, H., Trestian, R., Bui-Tien, T. and Nguyen, H. 2021. Probabilistic method for time-varying reliability analysis of structure via variational bayesian neural network. Structures. 34, pp. 3703-3715. https://doi.org/10.1016/j.istruc.2021.09.069
Type | Article |
---|---|
Title | Probabilistic method for time-varying reliability analysis of structure via variational bayesian neural network |
Authors | Dang, H., Trestian, R., Bui-Tien, T. and Nguyen, H. |
Abstract | This study proposes a novel framework computing the dynamic reliability and associated uncertainty quantification of structures under time-varying excitation with significantly reduced time complexity. For this purpose, the deep neural network’s power and the Bayesian theory’s probabilistic ability are leveraged, forming a Bayesian neural network data-driven model (BNN). The BNN-based surrogate model can yield a probability distribution of outputs of interest, e.g., a limit state function and its derived statistics such as median value, confidence interval rather than only a deterministic quantity. The effectiveness and correctness of the proposed method are reaffirmed via three case studies involving examples from the literature and a 3D numerical model of a prestressed reinforced concrete bridge structure, showing a reduction in time complexity up to three orders of magnitude compared to the Monte Carlo method only using finite element models. As a result, an 11-year maintenance routine is recommended for a marine and chemically aggressive environment to ensure the high reliability of prestressed bridge structures when accounting for uncertainty estimation. |
Keywords | Structural engineering; Machine learning algorithms; Reliability; Stochastic processes; Numerical simulation |
Sustainable Development Goals | 9 Industry, innovation and infrastructure |
Middlesex University Theme | Sustainability |
Research Group | London Digital Twin Research Centre |
Publisher | Elsevier |
Journal | Structures |
ISSN | |
Electronic | 2352-0124 |
Publication dates | |
Online | 09 Oct 2021 |
Dec 2021 | |
Publication process dates | |
Submitted | 30 Dec 2020 |
Accepted | 22 Sep 2021 |
Deposited | 20 May 2024 |
Output status | Published |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.istruc.2021.09.069 |
Web of Science identifier | WOS:000712161700002 |
Language | English |
https://repository.mdx.ac.uk/item/1006v4
61
total views0
total downloads4
views this month0
downloads this month