Data-driven prediction and analysis of chaotic origami dynamics
Data-driven prediction and analysis of chaotic origami dynamics
复制标题
DOI：
10.1038/s42005-020-00431-0
复制
发表时间：
2020-02
影响因子：
5.5
通讯作者：
H. Yasuda;Koshiro Yamaguchi;Yasuhiro Miyazawa;R. Wiebe;J. Raney;Jinkyu Yang
中科院分区：
文献类型：
--
作者：
H. Yasuda;Koshiro Yamaguchi;Yasuhiro Miyazawa;R. Wiebe;J. Raney;Jinkyu Yang
机器学习的进步已经彻底改变了从自然语言处理到营销再到医疗保健的应用能力。最近，机器学习技术也被用于学习物理，但其中一个巨大的挑战是预测复杂的动力学，特别是混沌。在这里，我们证明了准递归神经网络在预测多稳态折纸结构中的极端混沌行为方面的功效。虽然机器学习通常被视为一个“黑匣子”，但我们进行隐藏层分析，以了解神经网络如何以准确的方式处理周期性数据和混沌数据。我们的方法表明，它的有效性，在不依赖于数学模型的折纸系统的振动噪声环境中的混沌动力学的特征和预测。因此，我们的方法是完全数据驱动的，并且有潜力用于复杂的场景，例如薄壁结构和生物膜系统的非线性动力学。
Advances in machine learning have revolutionized capabilities in applications ranging from natural language processing to marketing to health care. Recently, machine learning techniques have also been employed to learn physics, but one of the formidable challenges is to predict complex dynamics, particularly chaos. Here, we demonstrate the efficacy of quasi-recurrent neural networks in predicting extremely chaotic behavior in multistable origami structures. While machine learning is often viewed as a “black box”, we conduct hidden layer analysis to understand how the neural network can process not only periodic, but also chaotic data in an accurate manner. Our approach shows its effectiveness in characterizing and predicting chaotic dynamics in a noisy environment of vibrations without relying on a mathematical model of origami systems. Therefore, our method is fully data-driven and has the potential to be used for complex scenarios, such as the nonlinear dynamics of thin-walled structures and biological membrane systems.