Yonggyun Yu

Topology Optimization for a Knuckle Using Design Space Adjustment and Refinement

Design space optimization using design space adjustment and refinement is used to optimize a knuckle in the suspension system of an automobile. This approach is a new efficient method for large-scale topology optimization by virtue of two reasons. First, design space adjustment including design space expansion and reduction is suitable for large-scale problems. Second, the design space refinement can be done globally or locally where and when necessary and thus is very effective in obtaining a target resolution with much less number of elements. Compliance minimization for a knuckle is considered with a realistic working condition to show the effectiveness and superiority of the new approach.

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

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.