期刊
ENGINEERING OPTIMIZATION
卷 54, 期 6, 页码 973-988出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/0305215X.2021.1902998
关键词
Convolutional neural network; deep learning; generalization ability; machine learning; topology optimization
资金
- National Natural Science Foundation of China [52078365]
- Ministry of Transport of the People's Republic of China for developing the 'Specifications for Landscape Design of Highway Bridges' [JTG/T 3360-03-2018]
- Science and Technology Research and Development Project of China Communications Construction Company [2018-ZJKJ-02]
This article introduces a deep convolutional neural network for structural topology optimization with perceptible generalization ability. It significantly reduces computation cost while maintaining accuracy in design solutions. Furthermore, the model can achieve solutions with a certain accuracy even when boundary conditions are not included in the training dataset.
This article proposes a deep convolutional neural network with perceptible generalization ability for structural topology optimization. The architecture of the neural network is made up of encoding and decoding parts, which provide down- and up-sampling operations. The popular U-Net was adopted to improve the performance of the proposed neural network. To train the neural network, a large dataset is generated by Simplified Isotropic Material with Penalization (SIMP). The performance of the proposed method was evaluated by comparing its efficiency and accuracy with SIMP on a series of typical optimization problems. Results show that a significant reduction in computation cost was achieved with little sacrifice to the performance of design solutions. Furthermore, the generalization ability of the proposed method is discussed. This ability enables the model to obtain a solution to a problem when a boundary condition is not included in the training dataset with a certain accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据