Details
| Original language | English |
|---|---|
| Article number | 109390 |
| Number of pages | 9 |
| Journal | Materials & Design |
| Volume | 199 |
| Early online date | 8 Dec 2020 |
| Publication status | Published - Feb 2021 |
Abstract
classic wave functions for potential broad applications. To obtain topological mechanical wave states with
good quality at desired frequency ranges, it needs repetitive trials of different geometric parameters with tradi-
tional forward designs. In this work, we develop an inverse design of topological edge states for flexural wave
using machine learning method which is promising for instantaneous design. Nonlinear mapping function
from input targets to output desired parameters are adopted in artificial neural networks where the data sets for training are generated by the plane wave expansion method. Topological edge states are then realized and compared for different bandgap width conditions with such inverse designs, proving that wide bandgap can pro- mote the confinement of the topological edge states. Finally, direction selective propagations with sharp turns are further demonstrated as anomalous wave behaviors. The machine learning inverse design of topological states for flexural wave provides an efficient way to design practical devices with targeted needs for potential applications such as signal processing, sensing and energy harvesting.
ASJC Scopus subject areas
- Materials Science(all)
- General Materials Science
- Engineering(all)
- Mechanics of Materials
- Engineering(all)
- Mechanical Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Materials & Design, Vol. 199, 109390, 02.2021.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Inverse design of topological metaplates for fl exural waves with machine learning
AU - He, Liangshu
AU - Wen, Zhihui
AU - Jin, Yabin
AU - Torrent, Daniel
AU - Zhuang, Xiaoying
AU - Rabczuk, Timon
N1 - Funding Information: This work is supported by the National Natural Science Foundation of China (11902223), the Shanghai Pujiang Program (19PJ1410100), the program for professor of special appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning, the Fundamental Research Funds for the Central Universities and Shanghai municipal peak discipline program (2019010106). Acknowledgment: The authors would like to thank Dr. Hongwei Guo for fruitful discussions.
PY - 2021/2
Y1 - 2021/2
N2 - The mechanical analog to the topological insulators brings anomalous elastic wave properties which diversifiesclassic wave functions for potential broad applications. To obtain topological mechanical wave states withgood quality at desired frequency ranges, it needs repetitive trials of different geometric parameters with tradi-tional forward designs. In this work, we develop an inverse design of topological edge states for flexural waveusing machine learning method which is promising for instantaneous design. Nonlinear mapping functionfrom input targets to output desired parameters are adopted in artificial neural networks where the data sets for training are generated by the plane wave expansion method. Topological edge states are then realized and compared for different bandgap width conditions with such inverse designs, proving that wide bandgap can pro- mote the confinement of the topological edge states. Finally, direction selective propagations with sharp turns are further demonstrated as anomalous wave behaviors. The machine learning inverse design of topological states for flexural wave provides an efficient way to design practical devices with targeted needs for potential applications such as signal processing, sensing and energy harvesting.
AB - The mechanical analog to the topological insulators brings anomalous elastic wave properties which diversifiesclassic wave functions for potential broad applications. To obtain topological mechanical wave states withgood quality at desired frequency ranges, it needs repetitive trials of different geometric parameters with tradi-tional forward designs. In this work, we develop an inverse design of topological edge states for flexural waveusing machine learning method which is promising for instantaneous design. Nonlinear mapping functionfrom input targets to output desired parameters are adopted in artificial neural networks where the data sets for training are generated by the plane wave expansion method. Topological edge states are then realized and compared for different bandgap width conditions with such inverse designs, proving that wide bandgap can pro- mote the confinement of the topological edge states. Finally, direction selective propagations with sharp turns are further demonstrated as anomalous wave behaviors. The machine learning inverse design of topological states for flexural wave provides an efficient way to design practical devices with targeted needs for potential applications such as signal processing, sensing and energy harvesting.
UR - http://www.scopus.com/inward/record.url?scp=85097720326&partnerID=8YFLogxK
U2 - 10.15488/14508
DO - 10.15488/14508
M3 - Article
AN - SCOPUS:85097720326
VL - 199
JO - Materials & Design
JF - Materials & Design
SN - 1873-4197
M1 - 109390
ER -