Deep learning enabled invisibility cloak design

• Main Author: Yang, Chenbo
• Other Authors: Luo Yu
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering::Optics, optoelectronics, photonics
• Online Access: https://hdl.handle.net/10356/167756
• Institution: Nanyang Technological University

The invisibility cloak is a new type of artificial metamaterial device based on the theory of transformation optics, which allows electromagnetic waves to propagate around an object by reasonably planning the actual space and virtual space and changing the electromagnetic parameters of the material to achieve invisibility. Cylindrical invisibility cloak designs based on traditional methods often choose to use the discretized layer approximation due to material constraints in practice. The resulting simplification leads to increased scattering and disturbances, so it is important to assess the performance of a discretized multilayer cylindrical invisibility cloak. The project is based on Matlab simulations and the design of a multilayer cylindrical invisibility cloak by two methods. The cloak will be exposed to TE or TM waves and different frequency electromagnetic waves to analyze and compare the performance of the cloak under different conditions. The dataset is constructed by optimizing the parameters and then using deep learning for the purpose of trying to design a multilayer invisibility cloak with less scattering and for practical production and to investigate the performance variation of the multilayer invisibility cloak.