arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.06111physics.comp-phcond-mat.dis-nn
收藏

使用机器学习加速可拉伸石墨烯kirigami的搜索和设计

Accelerated search and design of stretchable graphene kirigami using machine learning

Paul Z. Hanakata, Ekin D. Cubuk, David K. Campbell, Harold S. Park

摘要:

将kirigami灵感切割成片材已被证明是设计具有变形特性的可拉伸材料的有效方法,其中2D形状可以转换为复杂的3D形状。然而,找到最佳解决方案并不简单,因为可能的切割模式的数量随着系统规模呈指数级增长。在这里,我们报告了如何使用机器学习(ML)来近似目标属性,如屈服应力和屈服应变,作为切割模式的函数。我们的方法能够快速发现kirigami设计,产生极端的拉伸性验证的分子动力学(MD)模拟。我们发现,卷积神经网络(CNN),通常用于视觉任务的分类,可以应用于回归,以实现接近MD模拟精度的准确性。然后,该方法可以用于在$\sim 4\times10^6$候选设计的大设计空间中搜索仅用1000个训练样本就能使弹性拉伸性最大化的最佳设计。这个例子展示了ML在一小部分迭代中找到最佳kirigami设计的能力和潜力,这是纯粹的MD或基于实验的方法所需要的,其中没有已知或可用的管理物理学的先验知识。

英文摘要:

Making kirigami-inspired cuts into a sheet has been shown to be an effective way of designing stretchable materials with metamorphic properties where the 2D shape can transform into complex 3D shapes. However, finding the optimal solutions is not straightforward as the number of possible cutting patterns grows exponentially with system size. Here, we report on how machine learning (ML) can be used to approximate the target properties, such as yield stress and yield strain, as a function of cutting pattern. Our approach enables the rapid discovery of kirigami designs that yield extreme stretchability as verified by molecular dynamics (MD) simulations. We find that convolutional neural networks (CNN), commonly used for classification in vision tasks, can be applied for regression to achieve an accuracy close to the precision of the MD simulations. This approach can then be used to search for optimal designs that maximize elastic stretchability with only 1000 training samples in a large design space of $\sim 4\times10^6$ candidate designs. This example demonstrates the power and potential of ML in finding optimal kirigami designs at a fraction of iterations that would be required of a purely MD or experiment-based approach, where no prior knowledge of the governing physics is known or available.

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。

↑