Design of Tunable Metasurface Using Deep Neural Networks for Field Localized Wireless Power Transfer

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 1.5×10-3 for 97.3% of the 1929 test set. For synthesizing the unit cell's design parameters, the MSE is less than 2.5×10-3 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 80000 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. INDEX TERMS wireless power transfer, tunable metamaterial, metasurface, field localization, deep neural network, generative adversarial network.

Controlled Synthesis of Space–Time Modulated Metamaterial for Enhanced Nonreciprocity by Machine Learning

“…In this experiment, we place two ends of the waveguide in opposite corners of the metasurface so that there are eight metacells. [ 46 ] Each metasurface is measured over 6 MHz bandwidth (from 9 to 15 MHz) by a pair of 250‐point transmission coefficients. The three rows show the results for different V S , f S , and V B , respectively.…”

“…In this experiment, we place two ends of the waveguide in opposite corners of the metasurface so that there are eight metacells. [46]…”

“…The phase difference between harmonics is asymmetric, resulting in a different incremental wavenumber for forwardΔβ þ ¼ ðβ þ n À β þ nÀ1 Þ and backward propagation Δβ À ¼ ðβ À n À β À nÀ1 Þ, where n is the harmonic number in β AE n ¼ AEðβ 0 þ nβ S Þ. Nonreciprocal transmission is indicated by the relation of (Δβ þ 6 ¼ Δβ À ).To investigate the nonreciprocal transmission, we perform the parametric study using three STM parameters (V S , f S , and V B ), and the results are shown in Figure3. In this experiment, we place two ends of the waveguide in opposite corners of the metasurface so that there are eight metacells [46]. Each metasurface is measured over 6 MHz bandwidth (from 9 to 15 MHz) by a pair of 250-point transmission coefficients.…”

Enhanced WPT structures via EC-SRR-based metasurfaces

“…Moreover, extra efficiency and operational distance improvement may be further obtained via resonant-type metamaterials and metasurfaces, which can confine magnetic fields into the region between transmitting and the receiving part of the WPT system (Wang et al , 2020; Lu et al , 2021; Shi et al , 2021; Aboualalaa et al , 2022; Shan et al , 2022; Xue et al , 2022; Zhou et al , 2022; Zheng et al , 2022). Since the initial concept, several configurations using metamaterials have been presented (Ranaweera et al , 2019; Zhang et al , 2019; Bui et al , 2020; Rong et al , 2021; Lan et al , 2022), while instructive WPT realisations have, also, encompassed other emerging scientific domains (Li et al , 2018; Das et al , 2019; Gong et al , 2022; Tian et al , 2022; Wang et al , 2022). To this aim, the split-ring resonators (SRRs) are deemed the most commonly used elements, which conduct field amplification by modifying the electric and magnetic field distribution, because of their negative constitutive parameters (Gámez Rodríguez et al , 2016; Corrêa et al , 2019; Leumüller et al , 2022; Majumder et al , 2022).…”

Surface Routing for Wireless Power Transfer Using 2-D Relay Resonator Arrays

“…Furthermore, it is difficult to vary the dimensions of such arrays. Some approaches attempt to control these wave devices by making the components tunable [38], [39]; however, these approaches still require an exhaustive search for finding an optimal operating condition. At the system level, peripheral technologies for 2-D WPT systems based on resonator arrays have also been explored.…”