题 目:Randomized Neural Networks with Petrov-Galerkin Methods for Solving Linear Elasticity and Navier-Stokes Equations
内容简介:We develop the Randomized Neural Networks with Petrov-Galerkin Methods (RNN-PG methods) to solve linear elasticity and Navier-Stokes equations. RNN-PG methods use the Petrov-Galerkin variational framework, where the solution is approximated by randomized neural networks and the test functions are piecewise polynomials. Unlike conventional neural networks, the parameters of the hidden layers of the randomized neural networks are fixed randomly, while the parameters of the output layer are determined by the least squares method, which can effectively approximate the solution. We also develop mixed RNN-PG (M-RNN-PG) methods for linear elasticity problems, which ensure the symmetry of the stress tensor and avoid locking effects. For the Stokes problem, we present various M-RNN-PG methods that enforce the divergence-free constraint by different techniques. For the Navier-Stokes equations, we propose a space-time M-RNN-PG method that uses Picard or Newton iteration methods to deal with the nonlinear term. We compare RNN-PG methods with the finite element method, the mixed discontinuous Galerkin method, and the physics-informed neural network on several examples, and the numerical results demonstrate that RNN-PG methods achieve higher accuracy and efficiency.
报告人:王飞
报告人简介:西安交通大学数学与统计学院教授、博士生导师,Commun. Nonlinear Sci.Numer. Simul. 副主编。2010年获浙江大学数学博士学位。2010年—2012年,在华中科技大学任教;2012年-2013年,为美国爱荷华大学客座助理教授;2013年-2016年,为美国宾州州立大学Research Associate;2015年入选西安交通大学青年拔尖人才B类(副教授),2017年入选陕西省青年百人,2022年入选西安交通大学青年拔尖人才A类(教授)。研究领域为数值分析与科学计算,主要研究兴趣包括:有限元分析及其应用,变分不等式的数值方法,求解偏微分方程的神经网络方法等。主持国家自然科学基金面上项目2项、青年基金1项。已在国际 SCI 期刊发表论文五十篇,其中包括计算数学方向的顶级期刊:SIAM J Numer. Anal.,IMA J Numer. Anal.,Numer. Math.,Comput. Methods Appl. Mech. Eng. 等。
时 间:2024年6月1日(周六)下午14:30开始
地 点:腾讯会议:59157539380
热烈欢迎广大师生参加!
信息科学技术学院
2024年5月25日