报告题目：Random Vibration and Reliability Analysis with Radial Basis Function Neural Networks
报告人：Jian-Qiao Sun，Professor, Ph.D., P.E., ASME Fellow，University of California
报告时间：2022/05/26 10:00-11:00
腾讯会议：363-313-568  会议密码：0526
邀请人：孙亚辉、杨勇歌
主持人：孙亚辉

报告摘要：Mechanical systems and civil structures are often subject to random excitations. Excessive vibrations of the system can lead to fatigue damages.  The theory of random vibrations lays the foundation for the reliability assessment of these systems.  Because the reliability assessment needs the probabilistic information of the response in the state space and because analytical solutions of the response statistics are not readily available, studies of random vibration and reliability assessment are usually numerical and have been limited to the systems with low degrees of freedom.  This talk reports some recent studies using radial basis function neural networks that are promising for multi-degree-of-freedom dynamic systems.
We first present the method and discuss various applications of the method including the transient and steady-state solutions of Fokker-Planck-Kolmogorov (FPK) equation of nonlinear stochastic dynamic systems and the response moments.  We then focus on the solution of the first-passage time probability problem and discuss the solution of the reliability function.  Examples are presented to demonstrate the ability of the method.

报告人介绍：Dr. Jian-Qiao Sun earned a BS degree in Solid Mechanics from Huazhong University of Science and Technology in Wuhan, China in 1982, a MS and a PhD in Mechanical Engineering from University of California at Berkeley in 1984 and 1988.  He worked for Lord Corporation at their Corporate R&D Center in Cary, North Carolina.  In 1994, Dr. Sun joined the faculty in the department of Mechanical Engineering at the University of Delaware as an Assistant Professor, was promoted to Associate Professor in 1998 and to Professor in 2003. He joined University of California at Merced in 2007, and served as the chair of the Department of Mechanical Engineering in School of Engineering in 2017-2021.  Besides many other editorial experiences, he is the Editor-in-Chief of International Journal of Dynamics and Control published by Springer. His research interests include time-delayed dynamic systems, stochastic non-linear dynamics and control, cell mapping methods, multi-objective optimization, high-density piezoelectric energy harvesting from highway traffic, data-driven energy management of office building HVAC systems and machine learning applications to mechanical systems.