A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)

06/25/2021
by   Tianle Yue, et al.
3

In this paper, a mechanistic data-driven approach is proposed to accelerate structural topology optimization, employing an in-house developed finite element convolutional neural network (FE-CNN). Our approach can be divided into two stages: offline training, and online optimization. During offline training, a mapping function is built between high and low resolution representations of a given design domain. The mapping is expressed by a FE-CNN, which targets a common objective function value (e.g., structural compliance) across design domains of differing resolutions. During online optimization, an arbitrary design domain of high resolution is reduced to low resolution through the trained mapping function. The original high-resolution domain is thus designed by computations performed on only the low-resolution version, followed by an inverse mapping back to the high-resolution domain. Numerical examples demonstrate that this approach can accelerate optimization by up to an order of magnitude in computational time. Our proposed approach therefore shows great potential to overcome the curse-of-dimensionality incurred by density-based structural topology optimization. The limitation of our present approach is also discussed.

READ FULL TEXT

page 5

page 8

page 11

page 15

page 16

research
08/30/2018

Parametric Topology Optimization with Multi-Resolution Finite Element Models

We present a methodical procedure for topology optimization under uncert...
research
05/05/2018

An efficient Moving Morphable Component (MMC)-based approach for multi-resolution topology optimization

In the present work, a highly efficient Moving Morphable Component (MMC)...
research
12/09/2020

Physics-consistent deep learning for structural topology optimization

Topology optimization has emerged as a popular approach to refine a comp...
research
07/19/2022

A Streamline-guided De-Homogenization Approach for Structural Design

We present a novel de-homogenization approach for efficient design of hi...
research
02/07/2018

A Spatial Mapping Algorithm with Applications in Deep Learning-Based Structure Classification

Convolutional Neural Network (CNN)-based machine learning systems have m...
research
10/21/2020

Component-wise reduced order model lattice-type structure design

Lattice-type structures can provide a combination of stiffness with ligh...
research
11/24/2018

Design and analysis adaptivity in multi-resolution topology optimization

Multiresolution topology optimization (MTO) methods involve decoupling o...

Please sign up or login with your details

Forgot password? Click here to reset