澳大利亚国立大学秦庆华教授与肖易研究员学术报告
报告题目：NELDER-MEAD OPTIMIZATION OF ELASTIC METAMATERIALS VIA DEEP-LEARNING-AIDED SURROGATE MODELLING（通过深度学习辅助的替代模型对弹性超材料进行单纯形算法的优化）
报告人：秦庆华教授（澳大利亚国立大学）
报告时间：2019年11月21日星期四下午14:00-15:00
报告地点：南校区土木与交通工程学院C501
报告内容提要：
One of the fundamental challenges of structural optimization of elastic metamaterials (EMMs) with complex geometry lies within the high consumption of computational power associated with finite element analysis (FEA) simulations, which often renders the numerical solution an ineffective and costly attempt. Additionally, due to the inherent mesh dependence of the FEA method, minuscule geometry features, which often arise during optimization, demand very fine elements, resulting in enormously high time consumption, especially when repetitive solutions are needed for objective function validations. In this study, we developed a surrogate modelling algorithm to reduce computational time in structural optimization of EMMs. The surrogate model is constructed based on a multilayer feedforward artificial neural network (ANN) architecture, trained with deep learning techniques and optimized through a genetic algorithm (GA) program to improve its accuracy in predicting the location and width of the primary elastic band gap. With the trained and optimized ANN model at the core, a Nelder-Mead (NM) algorithm was established and its performance inspected in comparison to the traditional FEA method. The ANN-NM model shows remarkable accuracy in predicting the band gap width and impressive reduction in the time consumption.
对具有复杂几何形状的弹性超材料（EMM）进行结构优化的基本挑战之一在于有限元分析（FEA）需要花费大量计算的时间，这常常使得数值模拟的方法低率且昂贵。另外，由于有限元分析方法对固有的网格有依赖性，因此需要将构件划分成很小的单元格。在优化过程中，尤其是在需要重复求解以进行目标函数验证时，通常出现的极小几何形状特征会导致极大的时间消耗。在这项研究中，我们开发了一种替代建模的算法，以减少在进行弹性超材料结构优化中的计算时间。所述的替代模型是基于多层前馈人工神经网络系统结构构成，并进行深度学习技术的训练和遗传算法（GA）程序的优化，以提高其在预测主弹性带隙位置和宽度的精度。以训练和优化的人工神经网络模型为核心，建立了单纯形算法，并将其性能与传统的有限元分析方法进行相比较。人工神经网络-单纯形算法模型在预测带隙宽度方面展现出显著的准确性，并能够大幅度降低时间消耗。
报告人介绍：
Qing-Hua Qin received his Bachelor of Engineering degree in mechanical engineering from Chang An University and earning his Master of Science degree and PhD degree from Huazhong University of Science and Technology (HUST) in China. Both MS and PhD are in applied mechanics. He joined the Department of Mechanics as an associate lecturer at HUST in 1984. After spending ten years lecturing at HUST, he was awarded a DAAD/K.C. Wong research fellowship in 1994, which enabled him to work at the University of Stuttgart in Germany for nine months. In 1995 he left HUST to take up a postdoctoral research fellowship at Tsinghua University, China, where he worked until 1997. He was awarded a Queen Elizabeth II fellowship in 1997 and a Professorial fellowship in 2002 at University of Sydney and stayed there till December 2003, both by the Australian Research Council, and is currently working as a professor, associate dean of the college, and group leader of materials and manufacturing group in the Research School of Engineering at the Australian National University, Australia. He was appointed a guest professor at HUST in 2000. He was also awarded a Cheung Kong Professorship at Tianjin University in 2001 from the Ministry of Education of China. He has published more than 300 journal papers and 8 English monographs in the field of applied mechanics.
中文简历：秦庆华（Qing-Hua Qin）教授，于1984年和1990年获华中科技大学固体力学专业硕士和博士学位，1994年获DAAD—王宽诚基金赴德国Stuttgart大学访问研究。1995年-1997年到清华大学作博士后研究；1997和2002年分获澳大利亚研究理事会Queen Elizabeth II 研究员和Professorial Fellow位置，2004年至今在澳大利亚国立大学工学院担任教授、副院长 (2011-2013)、研究中心材料加工制造组的带头人等职位。2000年被聘为华中科技大学客座教授；2002年被天津大学聘为**学者特聘教授。在应用力学领域，已发表300多篇期刊论文，出版8部专著，获得澳大利亚科学院颁发的J. G. Russell奖。
报告题目：Seismic wave attenuation by elastic metamaterials（弹性超材料对地震波的衰减研究）
报告人：肖易研究员（澳大利亚国立大学）
报告时间：2019年11月21日星期四下午15:00-16:00
报告地点：南校区土木与交通工程学院C501
报告内容提要：
Recently, researchers found that there is a large attenuation of elastic waves as they pass through metamaterial structures. As an application of elastic metamaterials, cylindrical metamaterials were proposed for seismic wave attenuation. Most of the structures however only have the ability to attenuate waves at high frequency while seismic waves in real life have low frequencies with long wavelengths (0.001 Hz and up to a few tens of Hz. Thus, it is still an open question to develop such a device to attenuate low-frequency waves.
This study aims at seismic wave attenuation at low frequencies. For this purpose, two schemes of elastic metamaterials embedded near protected objects are proposed, and the effectiveness of the elastic metamaterial structures under different geometrical parameters are evaluated via numerical simulations of the frequency responses of the systems.
最近的研究发现当穿过超材料结构时，弹性波会大大衰减。作为弹性超材料的一种，圆柱超材料被提出应用于衰减地震波。然而，大多数结构仅具有衰减高频波的能力，而现实生活中的地震波具有低频长波的特点（0.001 赫兹至几十赫兹）。因此，开发衰减低频波的设备仍然是一个悬而未决的问题。
这项研究的目的是在衰减低频地震波。为此，提出了两种嵌入受保护物体附近的弹性超材料的方案，并通过系统频率响应的数值模拟，评估了在不同几何参数下的弹性超材料结构的有效性。
报告人介绍：
Yi Xiao received her PhD from the University of Sydney in 2004. After that, she worked as postdoctoral fellow or research assistant in a few university. She is currently working as a research fellow in the Australian National University.
中文简历：肖易（Xiao Yi）于2004年获悉尼大学博士学位，并且后续还在几所大学从事博士后研究员或研究助理。她目前在澳大利亚国立大学担任研究员。
欢迎全校感兴趣的师生参加！
广东省滨海土木工程耐久性重点实验室
2019年11月19日
