Abstract
Wireless power transfer (WPT), a convenient method for powering multiple devices, enables a truly wireless connection, eliminating the need for periodic charging and replacing a battery. To further enhance WPT, the unique characteristics of metamaterial, such as its field focusing and evanescent wave amplification, have been successfully utilized. With subwavelength characteristics, computational challenges arise when the number of metamaterial unit cells is increased. In this work, we investigate a deep neural network (DNN)-based design of the tunable metamaterial for WPT. Using structures specifically designed for different tasks, the DNN predicts the frequency spectra and synthesizes the unit cell's design parameters. When trained using a set of ~23000 randomly selected designs, we achieve an accumulated mean square error (MSE) of less than 1.5× 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-3</sup> for 97.3% of the 1929 test set. For synthesizing the unit cell's design parameters, the MSE is less than 2.5 × 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-3</sup> for 95.7% of the test set. The data-driven method is further extended to a generative adversarial network (GAN) to create the WPT paths and predict the frequency spectra of them. To achieve high efficiency, we propose a cost function focusing on the spectra's transmission peak. After training using 80 000 measured data, the GAN can create WPT paths that efficiently connect the transmitter and the receiver on the metasurface. The results show that the DNN provides an alternative and efficient design method for the metamaterial, replacing traditional EM-simulation-based approaches.
Highlights
Wave propagation control has played a fundamental role in generating, transferring, and utilizing energy [1]
When we accumulate the mean square error (MSE) of the 1929 test data, 95.7% of them have MSE < 2.5 × 10−3. These results show that the deep neural network (DNN) can be efficiently used for synthesizing the dimension of the metamaterial unit cell
The accumulated MSE is less than 2.5 × 10−3 for 95.7% of the test set for synthesizing the unit cell’s design parameters
Summary
Wave propagation control has played a fundamental role in generating, transferring, and utilizing energy [1]. Photonic bandgap (PBG) has been utilized to confine and guide electromagnetic waves (light) using waveguides, cavity resonance, and emission control [2]. The introduction of metamaterial marks another significant step up in progress for wave control. Metamaterials are artificial composites that exhibit unusual physical properties such as negative permittivity and permeability [3], which are not found in natural materials. The metamaterial is usually constructed using locally resonant unit cells in the deep subwavelength scale [4]. Unlike PBG materials based on Bragg interferences of periodic unit cells, the physical characteristics of metamaterial originate from overall averaged material properties.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
