Accelerated Search and Design of Stretchable Graphene Kirigami Using Machine Learning
Accelerated Search and Design of Stretchable Graphene Kirigami Using Machine Learning
复制标题
DOI：
10.1103/physrevlett.121.255304
复制
发表时间：
2018-12-20
影响因子：
8.6
通讯作者：
Park, Harold S.
中科院分区：
文献类型：
--
作者：
Hanakata, Paul Z.;Cubuk, Ekin D.;Park, Harold S.
将剪纸灵感切割成薄片已被证明是设计具有变质特性的可拉伸材料的有效方法，其中 2D 形状可以转变为复杂的 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数量随着系统尺寸呈指数增长。在这里，我们报告如何使用机器学习 (ML) 来近似目标属性，例如屈服应力和屈服应变，作为切削模式的函数。我们的方法能够快速发现剪纸设计，这些剪纸设计可产生经分子动力学 (MD) 模拟验证的极端拉伸性。我们发现，通常用于视觉任务分类的卷积神经网络可以应用于回归，以达到接近 MD 模拟精度的精度。然后，该方法可用于在类似于 4 x 10(6) 候选设计的大型设计空间中搜索仅使用 1000 个训练样本即可最大化弹性拉伸性的最佳设计。这个例子展示了机器学习在少量迭代中找到最佳剪纸设计的能力和潜力，这是纯 MD 或基于实验的方法所需要的，在这种情况下，控制物理的先验知识是已知的或不可用的。
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, 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 similar to 4 x 10(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.