A 3D Structure Mapping-Based Efficient Topology Optimization FrameworkSource: Journal of Mechanical Design:;2023:;volume( 145 ):;issue: 008::page 81703-1DOI: 10.1115/1.4062352Publisher: The American Society of Mechanical Engineers (ASME)
Abstract: It is well known that the computational cost of classic topology optimization (TO) methods increases rapidly with the size of the design problem because of the high-dimensional numerical simulation required at each iteration. Recently, the technical route of replacing the TO process with artificial neural network (ANN) models has gained popularity. These ANN models, once trained, can rapidly produce an optimized design solution for a given design specification. However, the complex mapping relationship between design specifications and corresponding optimized structures presents challenges in the construction of neural networks with good generalizability. In this paper, we propose a new design framework that uses deep learning techniques to accelerate the TO process. Specifically, we present an efficient topology optimization (ETO) framework in which structure update at each iteration is conducted on a coarse scale and a structure mapping neural network (SMapNN) is constructed to map the updated coarse structure to its corresponding fine structure. As such, fine-scale numerical simulations are replaced by coarse-scale simulations, thereby greatly reducing the computational cost. In addition, fragmentation and padding strategies are used to improve the trainability and adaptability of SMapNN, leading to a better generalizability. The efficiency and accuracy of the proposed ETO framework are verified using both benchmark and complex design tasks. It has been shown that with the SMapNN, TO designs of millions of elements can be completed within a few minutes on a personal computer.
|
Collections
Show full item record
contributor author | Li, Kangjie | |
contributor author | Ye, Wenjing | |
contributor author | Gao, Yicong | |
date accessioned | 2023-11-29T19:30:32Z | |
date available | 2023-11-29T19:30:32Z | |
date copyright | 5/30/2023 12:00:00 AM | |
date issued | 5/30/2023 12:00:00 AM | |
date issued | 2023-05-30 | |
identifier issn | 1050-0472 | |
identifier other | md_145_8_081703.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl1/handle/yetl/4294823 | |
description abstract | It is well known that the computational cost of classic topology optimization (TO) methods increases rapidly with the size of the design problem because of the high-dimensional numerical simulation required at each iteration. Recently, the technical route of replacing the TO process with artificial neural network (ANN) models has gained popularity. These ANN models, once trained, can rapidly produce an optimized design solution for a given design specification. However, the complex mapping relationship between design specifications and corresponding optimized structures presents challenges in the construction of neural networks with good generalizability. In this paper, we propose a new design framework that uses deep learning techniques to accelerate the TO process. Specifically, we present an efficient topology optimization (ETO) framework in which structure update at each iteration is conducted on a coarse scale and a structure mapping neural network (SMapNN) is constructed to map the updated coarse structure to its corresponding fine structure. As such, fine-scale numerical simulations are replaced by coarse-scale simulations, thereby greatly reducing the computational cost. In addition, fragmentation and padding strategies are used to improve the trainability and adaptability of SMapNN, leading to a better generalizability. The efficiency and accuracy of the proposed ETO framework are verified using both benchmark and complex design tasks. It has been shown that with the SMapNN, TO designs of millions of elements can be completed within a few minutes on a personal computer. | |
publisher | The American Society of Mechanical Engineers (ASME) | |
title | A 3D Structure Mapping-Based Efficient Topology Optimization Framework | |
type | Journal Paper | |
journal volume | 145 | |
journal issue | 8 | |
journal title | Journal of Mechanical Design | |
identifier doi | 10.1115/1.4062352 | |
journal fristpage | 81703-1 | |
journal lastpage | 81703-16 | |
page | 16 | |
tree | Journal of Mechanical Design:;2023:;volume( 145 ):;issue: 008 | |
contenttype | Fulltext |