论文标题
SELTO：样品效率学习的拓扑优化
SELTO: Sample-Efficient Learned Topology Optimization
论文作者
论文摘要
深度学习（DL）的最新发展表明拓扑优化（TO）具有巨大的潜力。但是，尽管有一些有希望的尝试，但子领域仍然缺乏关于基本方法和数据集的坚定基础。我们旨在解决这两个要点。首先，我们探索基于物理学的预处理和均衡网络，以创建用于DL管道的样品效率组件。我们在大规模消融研究中使用端到端监督培训对其进行评估。结果表明，样本效率和预测的身体正确性有了巨大的提高。其次，为了提高可比性和未来的进步，我们首先将两者发布到包含问题和相应地面真相解决方案的数据集。
Recent developments in Deep Learning (DL) suggest a vast potential for Topology Optimization (TO). However, while there are some promising attempts, the subfield still lacks a firm footing regarding basic methods and datasets. We aim to address both points. First, we explore physics-based preprocessing and equivariant networks to create sample-efficient components for TO DL pipelines. We evaluate them in a large-scale ablation study using end-to-end supervised training. The results demonstrate a drastic improvement in sample efficiency and the predictions' physical correctness. Second, to improve comparability and future progress, we publish the two first TO datasets containing problems and corresponding ground truth solutions.
