Back to Search Start Over

Convolutional Dimension-Reduction With Knowledge Reasoning for Reliability Approximations of Structures Under High-Dimensional Spatial Uncertainties.

Authors :
Luojie Shi
Kai Zhou
Zequn Wang
Source :
Journal of Mechanical Design. Jul2024, Vol. 149 Issue 7, p1-12. 12p.
Publication Year :
2024

Abstract

Along with the rapid advancement of additive manufacturing technology, 3D-printed structures and materials have been successfully employed in various applications. Computer simulations of these structures and materials are often characterized by a vast number of spatial-varied parameters to predict the structural response of interest. Direct Monte Carlo methods are infeasible for uncertainty quantification and reliability assessment of such systems as they require a large number of forward model evaluations to obtain convergent statistics. To alleviate this difficulty, this paper presents a convolutional dimension-reduction method with knowledge reasoning-based loss regularization for surrogate modeling and uncertainty quantification of structures with high-dimensional spatial uncertainties. To manage the inherent high-dimensionality, a deep convolutional dimension-reduction network (ConvDR) is constructed to transform the spatial data into a low-dimensional latent space. In the latent space, knowledge reasoning is formulated as a form of loss regularization, and evolutionary algorithms are employed to train both the ConvDR network and a linear regression model as surrogate models for predicting the response of interest. 2D structures with spatial-variated material compositions are used to demonstrate the performance of the proposed approach. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
10500472
Volume :
149
Issue :
7
Database :
Academic Search Index
Journal :
Journal of Mechanical Design
Publication Type :
Academic Journal
Accession number :
178344765
Full Text :
https://doi.org/10.1115/1.4064159