Deep Physical Informed Neural Networks for Metamaterial Design
In this paper, we propose a physical informed neural network approach for designing the electromagnetic metamaterial. The approach can be used to deal with various practical problems such as cloaking, rotators, concentrators, etc. The advantage of this approach is the flexibility that we can deal wi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8946546/ |
| id |
doaj-7f393458fa884a96bc4286902bdd68f1 |
|---|---|
| record_format |
Article |
| spelling |
doaj-7f393458fa884a96bc4286902bdd68f12021-03-30T02:22:29ZengIEEEIEEE Access2169-35362020-01-018245062451310.1109/ACCESS.2019.29633758946546Deep Physical Informed Neural Networks for Metamaterial DesignZhiwei Fang0https://orcid.org/0000-0001-5540-1010Justin Zhan1https://orcid.org/0000-0001-8991-5669Department of Mathematical Sciences, University of Nevada, Las Vegas, NV, USADepartment of Computer Science and Computer Engineering, University of Arkansas, Fayetteville, AR, USAIn this paper, we propose a physical informed neural network approach for designing the electromagnetic metamaterial. The approach can be used to deal with various practical problems such as cloaking, rotators, concentrators, etc. The advantage of this approach is the flexibility that we can deal with not only the continuous parameters but also the piecewise constants. As our best knowledge, there is no other faster and much efficient method to deal with these problems. As a byproduct, we propose a method to solve high frequency Helmholtz equation, which is widely used in physics and engineering. Some benchmark problems have been solved in numerical tests to verify our method.https://ieeexplore.ieee.org/document/8946546/PINNactivation functionmetamaterial designelectromagnetic cloakingMaxwell’s equation |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Zhiwei Fang Justin Zhan |
| spellingShingle |
Zhiwei Fang Justin Zhan Deep Physical Informed Neural Networks for Metamaterial Design IEEE Access PINN activation function metamaterial design electromagnetic cloaking Maxwell’s equation |
| author_facet |
Zhiwei Fang Justin Zhan |
| author_sort |
Zhiwei Fang |
| title |
Deep Physical Informed Neural Networks for Metamaterial Design |
| title_short |
Deep Physical Informed Neural Networks for Metamaterial Design |
| title_full |
Deep Physical Informed Neural Networks for Metamaterial Design |
| title_fullStr |
Deep Physical Informed Neural Networks for Metamaterial Design |
| title_full_unstemmed |
Deep Physical Informed Neural Networks for Metamaterial Design |
| title_sort |
deep physical informed neural networks for metamaterial design |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2020-01-01 |
| description |
In this paper, we propose a physical informed neural network approach for designing the electromagnetic metamaterial. The approach can be used to deal with various practical problems such as cloaking, rotators, concentrators, etc. The advantage of this approach is the flexibility that we can deal with not only the continuous parameters but also the piecewise constants. As our best knowledge, there is no other faster and much efficient method to deal with these problems. As a byproduct, we propose a method to solve high frequency Helmholtz equation, which is widely used in physics and engineering. Some benchmark problems have been solved in numerical tests to verify our method. |
| topic |
PINN activation function metamaterial design electromagnetic cloaking Maxwell’s equation |
| url |
https://ieeexplore.ieee.org/document/8946546/ |
| work_keys_str_mv |
AT zhiweifang deepphysicalinformedneuralnetworksformetamaterialdesign AT justinzhan deepphysicalinformedneuralnetworksformetamaterialdesign |
| _version_ |
1724185302578233344 |