Inverse design of topological metaplates for flexural waves with machine learning
The mechanical analog to the topological insulators brings anomalous elastic wave properties which diversifies 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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-02-01
|
| Series: | Materials & Design |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127520309266 |
| _version_ | 1818392521561079808 |
|---|---|
| author | Liangshu He Zhihui Wen Yabin Jin Daniel Torrent Xiaoying Zhuang Timon Rabczuk |
| author_facet | Liangshu He Zhihui Wen Yabin Jin Daniel Torrent Xiaoying Zhuang Timon Rabczuk |
| author_sort | Liangshu He |
| collection | DOAJ |
| description | The mechanical analog to the topological insulators brings anomalous elastic wave properties which diversifies 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 traditional 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 promote 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. |
| first_indexed | 2024-12-14T05:30:44Z |
| format | Article |
| id | doaj.art-a70d19d1081444419978c829cee68e74 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-12-14T05:30:44Z |
| publishDate | 2021-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-a70d19d1081444419978c829cee68e742022-12-21T23:15:21ZengElsevierMaterials & Design0264-12752021-02-01199109390Inverse design of topological metaplates for flexural waves with machine learningLiangshu He0Zhihui Wen1Yabin Jin2Daniel Torrent3Xiaoying Zhuang4Timon Rabczuk5School of Aerospace Engineering and Applied Mechanics, Tongji University, 200092 Shanghai, ChinaSchool of Aerospace Engineering and Applied Mechanics, Tongji University, 200092 Shanghai, ChinaSchool of Aerospace Engineering and Applied Mechanics, Tongji University, 200092 Shanghai, China; Corresponding author.GROC-UJI, Institut de Noves Tecnologies de la Imatge, Universitat Jaume I, 12080 Castello, SpainDepartment of Geotechnical Engineering, College of Civil Engineering, Tongji University, 200092 Shanghai, China; Institute of Photonics, Department of Mathematics and Physics, Leibniz University Hannover, GermanyInstitute of Structural Mechanics, Bauhaus-Universität Weimar, Weimar D-99423, GermanyThe mechanical analog to the topological insulators brings anomalous elastic wave properties which diversifies 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 traditional 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 promote 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.http://www.sciencedirect.com/science/article/pii/S0264127520309266 |
| spellingShingle | Liangshu He Zhihui Wen Yabin Jin Daniel Torrent Xiaoying Zhuang Timon Rabczuk Inverse design of topological metaplates for flexural waves with machine learning Materials & Design |
| title | Inverse design of topological metaplates for flexural waves with machine learning |
| title_full | Inverse design of topological metaplates for flexural waves with machine learning |
| title_fullStr | Inverse design of topological metaplates for flexural waves with machine learning |
| title_full_unstemmed | Inverse design of topological metaplates for flexural waves with machine learning |
| title_short | Inverse design of topological metaplates for flexural waves with machine learning |
| title_sort | inverse design of topological metaplates for flexural waves with machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S0264127520309266 |
| work_keys_str_mv | AT liangshuhe inversedesignoftopologicalmetaplatesforflexuralwaveswithmachinelearning AT zhihuiwen inversedesignoftopologicalmetaplatesforflexuralwaveswithmachinelearning AT yabinjin inversedesignoftopologicalmetaplatesforflexuralwaveswithmachinelearning AT danieltorrent inversedesignoftopologicalmetaplatesforflexuralwaveswithmachinelearning AT xiaoyingzhuang inversedesignoftopologicalmetaplatesforflexuralwaveswithmachinelearning AT timonrabczuk inversedesignoftopologicalmetaplatesforflexuralwaveswithmachinelearning |