arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04232cs.LGcs.CV
收藏

基于卷积神经网络的去均匀化

De-homogenization using Convolutional Neural Networks

Technical University of Denmark(丹麦技术大学)

Martin O. Elingaard, Niels Aage, J. Andreas Bærentzen, Ole Sigmund

摘要:

提出了一种基于深度学习的结构柔度最小化去均匀化方法。通过使用卷积神经网络来参数化从粗网格上的一组层压参数到细网格上的单尺度设计的映射,我们避免了与传统的去均匀化方法相关联的最小二乘问题,并且相应地节省了时间。为了训练神经网络,已经开发了两步自定义损失函数,其确保遵循局部层压取向的周期性输出场。所提出的方法的一个关键特征是,在不使用或参考底层结构优化问题的情况下进行训练,这使得所提出的方法具有鲁棒性和对wrt不敏感。域大小、边界条件和载荷。使用在输出场骨架上利用距离变换的后处理过程来将期望的层压宽度投影到输出场上,同时确保预定义的最小长度尺度和体积分数。为了证明深度学习方法具有出色的泛化性能,针对几种不同的负载和边界条件示出了数值示例。对于参数的适当选择,去均质化设计在基于均质化的解决方案的$7-25\%$内以计算成本的一小部分执行。该方案具有多个进一步改进的选项,可为未来的交互式高分辨率拓扑优化提供基础。

英文摘要:

This paper presents a deep learning-based de-homogenization method for structural compliance minimization. By using a convolutional neural network to parameterize the mapping from a set of lamination parameters on a coarse mesh to a one-scale design on a fine mesh, we avoid solving the least square problems associated with traditional de-homogenization approaches and save time correspondingly. To train the neural network, a two-step custom loss function has been developed which ensures a periodic output field that follows the local lamination orientations. A key feature of the proposed method is that the training is carried out without any use of or reference to the underlying structural optimization problem, which renders the proposed method robust and insensitive wrt. domain size, boundary conditions, and loading. A post-processing procedure utilizing a distance transform on the output field skeleton is used to project the desired lamination widths onto the output field while ensuring a predefined minimum length-scale and volume fraction. To demonstrate that the deep learning approach has excellent generalization properties, numerical examples are shown for several different load and boundary conditions. For an appropriate choice of parameters, the de-homogenized designs perform within $7-25\%$ of the homogenization-based solution at a fraction of the computational cost. With several options for further improvements, the scheme may provide the basis for future interactive high-resolution topology optimization.

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。

↑