当前位置: X-MOL 学术arXiv.cs.CE › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
arXiv - CS - Computational Engineering, Finance, and Science Pub Date : 2020-09-15 , DOI: arxiv-2009.07110
Wei Chen and Faez Ahmed

Multi-objective optimization is key to solving many Engineering Design problems, where design parameters are optimized for several performance indicators. However, optimization results are highly dependent on how the designs are parameterized. Researchers have shown that deep generative models can learn compact design representations, providing a new way of parameterizing designs to achieve faster convergence and improved optimization performance. Despite their success in capturing complex distributions, existing generative models face three challenges when used for design problems: 1) generated designs have limited design space coverage, 2) the generator ignores design performance, and 3) the new parameterization is unable to represent designs beyond training data. To address these challenges, we propose MO-PaDGAN, which adds a Determinantal Point Processes based loss function to the generative adversarial network to simultaneously model diversity and (multi-variate) performance. MO-PaDGAN can thus improve the performances and coverage of generated designs, and even generate designs with performances exceeding those from training data. When using MO-PaDGAN as a new parameterization in multi-objective optimization, we can discover much better Pareto fronts even though the training data do not cover those Pareto fronts. In a real-world multi-objective airfoil design example, we demonstrate that MO-PaDGAN achieves, on average, a 186% improvement in the hypervolume indicator when compared to the vanilla GAN or other state-of-the-art parameterization methods.

中文翻译:

MO-PaDGAN:为增强多目标优化重新参数化工程设计

多目标优化是解决许多工程设计问题的关键,其中设计参数针对多个性能指标进行优化。然而,优化结果高度依赖于设计的参数化方式。研究人员已经表明,深度生成模型可以学习紧凑的设计表示,提供了一种参数化设计的新方法,以实现更快的收敛和改进的优化性能。尽管在捕获复杂分布方面取得了成功,但现有的生成模型在用于设计问题时面临三个挑战:1) 生成的设计具有有限的设计空间覆盖范围,2) 生成器忽略了设计性能,以及 3) 新的参数化无法表示超出范围的设计训练数据。为了应对这些挑战,我们提出了 MO-PaDGAN,它向生成对抗网络添加了基于行列式点过程的损失函数,以同时对多样性和(多变量)性能进行建模。MO-PaDGAN 因此可以提高生成设计的性能和覆盖率,甚至可以生成性能超过训练数据的设计。当在多目标优化中使用 MO-PaDGAN 作为新的参数化时,我们可以发现更好的帕累托前沿,即使训练数据没有覆盖那些帕累托前沿。在真实世界的多目标翼型设计示例中,我们证明,与普通 GAN 或其他最先进的参数化方法相比,MO-PaDGAN 的超体积指标平均提高了 186%。甚至生成性能超过训练数据的设计。当在多目标优化中使用 MO-PaDGAN 作为新的参数化时,我们可以发现更好的帕累托前沿,即使训练数据没有覆盖那些帕累托前沿。在真实世界的多目标翼型设计示例中,我们证明,与普通 GAN 或其他最先进的参数化方法相比,MO-PaDGAN 的超体积指标平均提高了 186%。甚至生成性能超过训练数据的设计。当在多目标优化中使用 MO-PaDGAN 作为新的参数化时,我们可以发现更好的帕累托前沿,即使训练数据没有覆盖那些帕累托前沿。在真实世界的多目标翼型设计示例中,我们证明,与普通 GAN 或其他最先进的参数化方法相比,MO-PaDGAN 的超体积指标平均提高了 186%。
更新日期:2020-09-16
down
wechat
bug