Deep learning for determining a near-optimal topological design without any iteration

By Yonggyun Yu, Taeil Hur, Jaeho Jung, Inseon Jang. Structural And Multidisciplinary Optimization, 2018

338 citations recorded by the source corpus.

In this study, we propose a novel deep learning-based method to predict an optimized structure for a given boundary condition and optimization setting without using any iterative scheme. For this purpose, first, using open-source topology optimization code, datasets of the optimized structures paired with the corresponding information on boundary conditions and optimization settings are generated at low (32 × 32) and high (128 × 128) resolutions. To construct the artificial neural network for the proposed method, a convolutional neural network (CNN)-based encoder and decoder network is trained using the training dataset generated at low resolution. Then, as a two-stage refinement, the conditional generative adversarial network (cGAN) is trained with the optimized structures paired at both low and high resolutions and is connected to the trained CNN-based encoder and decoder network. The performance evaluation results of the integrated network demonstrate that the proposed method can determine a near-optimal structure in terms of pixel values and compliance with negligible computational time.

Subfields: Civil and Structural Engineering, Computational Theory and Mathematics, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/2cb43c686233e8fca415f234e91b662319b67247

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Computational Theory and Mathematics

In Industrial and Manufacturing Engineering

Citations in the corpus

Deep Generative Design: Integration of Topology Optimization and Generative Models (2019, methodology): “[4] propose the framework where a low-resolution structure is first generated using a convolutional neural network (CNN)-based encoder and decoder constructed on 2D topology optimal designs, and then, it is upscaled to a high-resolution structure through conditional GAN (cGAN) without any iterative ”
Deep Generative Models in Engineering Design: A Review (2021, background): “cGAN/infoGAN [71]i [72]i [73]i [74]i [75]p [76]p [77]p [78]ph”