Parameter Optimization via CMA-ES for Implementation in the Active Control of Magnetic Pillar Arrays - Collections | Kyushu University Library

＜conference paper＞
Parameter Optimization via CMA-ES for Implementation in the Active Control of Magnetic Pillar Arrays

Creator	Creator Name Gaysornkaew, Suparat Affiliation Affiliation Name Dept. of Mechanical and Aerospace Engineering, Kyushu University 九州大学大学院工学府機械工学専攻
	Creator Name Vargas, Danilo Vasconcellos Affiliation Affiliation Name Dept. of Informatics, Kyushu University 九州大学大学院システム情報科学府電気電子工学専攻
	Author PID K003440 0000-0002-5512-2975 Creator Name Tsumori, Fujio 津守, 不二夫ツモリ, フジオ Affiliation Affiliation Name Dept. of Aeronautics and Astronautics, Kyushu University 九州大学大学院工学研究院航空宇宙工学部門
Language	English
Publisher	IEEE
Date	2021-06-28
Source Title	2021 5th IEEE International Conference on Cybernetics (CYBCONF)
Conference	Name 2021 IEEE International Conference on Cybernetics (CYBCONF) Sequence 5 Date 8-10, June 2021 Place Sendai Country Japan
Publication Type	Accepted Manuscript
Access Rights	open access
Date of Available	2023-06-28
Rights	© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related DOI	isVersionOf https://doi.org/10.1109/CYBCONF51991.2021.9464138
Related DOI
Abstract	Pillared surfaces are the products of a surface modification technique that allow the implementation of active control methods by an outer source such as magnetic fields. Pillar arrays with magnetic t...ips exhibit different characteristics depending on the initial positional arrangement of the pillars and/or the environmental magnetic field conditions. This study develops methods for simulation and parameter optimization by machine learning to aid the investigation of pillar behaviors in various combinations of initial positions and magnetic fields. Optimization is performed using the co-variance adaptation evolution strategy (CMA-ES). The algorithm is tested to obtain preliminary results: (1) the maximum size of the pillar pitch at a given magnetic field; (2) the initial pillar arrangement of a 3- pillar unit cell and three settings of applied magnetic field–each corresponds to a predefined contact state of a three-stage paring pattern.show more

Hide fulltext details.

File	FileType	Size	Views	Description
4752556	pdf	1.32 MB	33

Details

Record ID	4752556
Related ISBN	978-1-6654-0320-7
Subject Terms	magnetic pillar arrays
	simulation
	machine learning
	CMA-ES
Created Date	2022.01.31
Modified Date	2023.06.30