Prof. Hajime Igarashi
Graduate School of Information Science and Technology, Hokkaido University, Japan
Topology Optimization Based on Deep Learning and toward Their Coevolution
I will talk about the topology optimization applied to the design of electromagnetic devices and machines. In the topology optimization, in contrast to the conventional parameter optimization, the boundary of an objective material is freely deformed with possible production and annihilation of holes. The topology optimization based on the genetic algorithm and Gaussian basis functions is shown to have excellent search ability and performance, while it needs large computational cost. It is shown that the computational cost is effectively reduced by using deep learning as a surrogate model. Moreover, it is shown that both techniques can coevolve; the deep neural network is trained by the results of the topology optimization, and the latter is accelerated by the former, and these processes is repeated to realize reciprocal improvement.
Hajime Igarashi received the B.E. and M.E. degrees in electrical engineering from Hokkaido University, Sapporo, Japan, in 1982 and 1984, respectively, and the Ph.D. degree in engineering from Hokkaido University in 1992. He has been a professor at the Graduate School of Information Science and Technology, Hokkaido University, since 2004. He was a guest researcher at Berlin Technical University, Germany, under support from the Humboldt Foundation from 1995 to 1997. His research area is computational electromagnetism, design optimization and energy harvesting. He is a member of JSST, IEEE, IEEJ, IEICE, Japan AEM society and International COMPUMAG society. He received culture, sports, science and technology minister’s award, IEEJ distinguished paper award etc.
Prof. Tetsuro Ogi
Graduate School of System Design and Management, Keio University, Japan
Construction of Virtual Reality Application based on System Design Approach
Due to the recent spread of VR technology, not only the number of developers and users have increased, but also several tools and frameworks have been provided as elemental technology, so that it has become possible that the VR technology can be used as a system design approach. This paper introduces recent trend of VR technology as well as several examples of developing VR applications such as immersive visual analytics environment and VR information search system from the viewpoint of system design.
Tetsuro Ogi received the B.E., M.E., and Dr. Eng. degrees from The University of Tokyo, in 1984, 1986 and 1994, respectively. After working at Mitsubishi Research Institute, he became an Associate Professor at The University of Tokyo in 1996, and Associate Professor at Tsukuba University in 2004, respectively. From 2008, he is a Professor in the Graduate School of System Design and Management, Keio University. His current research interests include virtual reality, human interface and systems engineering.
Prof. Amane Takei
Department of Electrical and Systems Engineering, Faculty of Engineering, University of Miyazaki, Japan
Microwave analysis based on parallel finite element analysis
In this lecture, a microwave analysis method based on an iterative domain decomposition method is explained. The simplified Berenger’s PML is introduced which these eight corners are given the average value of all PML’s layers. As for accuracy verification of the analysis solver, the absorbing performance of the PML is evaluated by using reflection coefficient based on the S parameter. In the accuracy verification, when the maximum side length of the tetrahedral element is set to 1/20 of the wavelength, the error rate of the numerical solution and the theoretical solution is about 1.70 [%] with the PML of 9 layers. So, we have found that proposed method can calculate with high accuracy.
Amane Takei received the B. E. and the M. E. degree from Hosei University in 1997 and 1999, respectively, and the Ph.D. of environmental study degree from The University of Tokyo in 2006. He has worked as Postdoctoral Fellow for The University of Tokyo from 2006 to 2010, and Associate professor for Tomakomai Collage from 2010 to 2014. He is working as Associate Professor for Department of Electrical and Systems Engineering, University of Miyazaki from 2014.