arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.12282cs.AImath.OC
收藏

用在线神经合成子加速计算形态发生

Speeding up Computational Morphogenesis with Online Neural Synthetic Gradients

Georgia Institute of Technology(佐治亚理工学院);Siemens Corporate Technology(西门子企业技术)

Yuyu Zhang, Heng Chi, Binghong Chen, Tsz Ling Elaine Tang, Lucia Mirabella, Le Song, Glaucio H. Paulino

摘要:

广泛的现代科学和工程应用制定为一个系统的偏微分方程(PDE)作为约束的优化问题。这些偏微分方程约束的优化问题通常在一个标准的离散化,然后优化的方法来解决。在许多需要高分辨率解决方案的行业应用中,离散化约束很容易包含数百万甚至数十亿个变量,这使得标准迭代优化器求解精确梯度非常缓慢。在这项工作中,我们提出了一个通用的框架,以加快PDE约束优化使用在线神经合成梯度(ONSG)与一种新的两尺度优化方案。我们成功地将我们的ONSG框架计算形态,一类具有代表性和挑战性的偏微分方程约束优化问题。大量的实验表明,我们的方法可以显着加快计算形态生成(也称为拓扑优化),同时保持最终解决方案的质量相比,标准的优化器。在具有约1,400,000个设计变量的大规模3D优化设计问题上,我们的方法实现了高达7.5倍的加速,同时产生具有可比目标的优化设计。

英文摘要:

A wide range of modern science and engineering applications are formulated as optimization problems with a system of partial differential equations (PDEs) as constraints. These PDE-constrained optimization problems are typically solved in a standard discretize-then-optimize approach. In many industry applications that require high-resolution solutions, the discretized constraints can easily have millions or even billions of variables, making it very slow for the standard iterative optimizer to solve the exact gradients. In this work, we propose a general framework to speed up PDE-constrained optimization using online neural synthetic gradients (ONSG) with a novel two-scale optimization scheme. We successfully apply our ONSG framework to computational morphogenesis, a representative and challenging class of PDE-constrained optimization problems. Extensive experiments have demonstrated that our method can significantly speed up computational morphogenesis (also known as topology optimization), and meanwhile maintain the quality of final solution compared to the standard optimizer. On a large-scale 3D optimal design problem with around 1,400,000 design variables, our method achieves up to 7.5x speedup while producing optimized designs with comparable objectives.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑