深圳大学四十周年校庆暨数学学科四十周年庆

荔园学者Colloquium第五十七期

讲座题目:Large plate bending with isometry constraints: FEM vs machine learning

主讲人：明平兵 教授(中国科学院数学与系统科学研究院)

讲座时间：2023年12月09日（周六）上午11:00-12:00

讲座地点：深圳大学粤海校区汇星楼一楼一号教室

内容概述：We propose a deep learning based method for simulating the large bending deformation of bilayer plates. Inspired by the greedy algorithm, we propose a pre-training method on a series of nested domains, which accelerate the convergence of training and find the absolute minimizer more effectively. The proposed method exhibits the capability to converge to an absolute minimizer, overcoming the limitation of gradient flow methods getting trapped in local minimizer basins. We showcase better performance for the relative energy errors and relative L2-errors of the minimizer through several numerical experiments. Furthermore, our method successfully maintains the L2-norm of the isometric constraint, leading to improved solution accuracy. This is a joint work with Xiang Li and Yulei Liao.

主讲人简介：明平兵，中国科学院数学与系统科学研究院研究员，目前担任科学与工程计算国家重点实验室副主任。主要从事固体多尺度建模、模拟及机器学习方面的研究，在Cauchy-Born法则的数学理论以及石墨烯理想强度的理论预测领域做出了突出工作；于2014年获得国家杰出青年基金、2023年获第十五届“冯康科学计算奖”；曾应邀在SCADE2009，The SIAM Mathematics Aspects of Materials Science 2016等会议上作大会报告。

欢迎师生参加！

邀请人：太阳集团官网

太阳集团官网

2023年12月06日