[论文解读] 3D Topology Optimization using Convolutional Neural Networks

Saurabh Banga, Harsh Gehani+3 more|arXiv (Cornell University)|Aug 22, 2018

Topology Optimization in Engineering参考文献 15被引用 53

一句话总结

本文提出了一种三维编码-解码 CNN 方法，通过从早期迭代数据预测最终优化结构来加速拓扑优化，实现约40%时间缩减，结构精度约为96%。

ABSTRACT

Topology optimization is computationally demanding that requires the assembly and solution to a finite element problem for each material distribution hypothesis. As a complementary alternative to the traditional physics-based topology optimization, we explore a data-driven approach that can quickly generate accurate solutions. To this end, we propose a deep learning approach based on a 3D encoder-decoder Convolutional Neural Network architecture for accelerating 3D topology optimization and to determine the optimal computational strategy for its deployment. Analysis of iteration-wise progress of the Solid Isotropic Material with Penalization process is used as a guideline to study how the earlier steps of the conventional topology optimization can be used as input for our approach to predict the final optimized output structure directly from this input. We conduct a comparative study between multiple strategies for training the neural network and assess the effect of using various input combinations for the CNN to finalize the strategy with the highest accuracy in predictions for practical deployment. For the best performing network, we achieved about 40% reduction in overall computation time while also attaining structural accuracies in the order of 96%.

研究动机与目标

• 为计算量密集的基于物理的三维拓扑优化提供数据驱动的替代方案。
• 开发一个三维编码-解码 CNN，以加速对优化材料分布的预测。
• 探索来自 Solid Isotropic Material with Penalization (SIMP) 的早期迭代数据如何作为输入。
• 比较训练策略和输入配置，以实现部署时的最高预测准确性。

提出的方法

• 使用三维编码-解码 CNN 架构，将早期 SIMP 迭代数据映射到最终优化结构。
• 研究不同输入组合如何影响 CNN 的性能。
• 分析 SIMP 过程的逐迭代进展，以指导网络的输入选择。
• 训练并评估多种训练策略，以确定表现最佳的配置。
• 量化 CNN 预测的计算时间缩减和结构精度。

实验结果

研究问题

• RQ1 CNN 是否能够直接从早期 SIMP 迭代预测最终的拓扑优化结果？
• RQ2 哪些输入配置和训练策略能够为三维拓扑优化带来最高精度和最快推断？
• RQ3 在时间和准确性方面，基于 CNN 的方法与传统的基于物理的拓扑优化相比如何？

主要发现

• 性能最佳的网络实现了约40%的总计算时间降低。
• CNN 预测的结构精度约为96%。