Machine Learning Assisted Long-Range Wireless Power Transfer

TL;DR

This paper introduces a machine learning-optimized topological wireless power transfer system that significantly improves efficiency and robustness, leveraging gradient descent and non-Hermitian physics for near-field applications.

Contribution

It applies gradient descent optimization to a topological WPT system, integrating machine learning with physics to enhance performance and robustness.

Findings

Enhanced transfer efficiency demonstrated experimentally

Improved system robustness against environmental disturbances

Integration of non-Hermitian and topological physics with machine learning

Abstract

Near-field magnetic resonance wireless power transfer (WPT) technology has garnered significant attention due to its broad application prospects in medical implants, electric vehicles, and robotics. Addressing the challenges faced by traditional WPT systems in frequency optimization and sensitivity to environmental disturbances, this study innovatively applies the gradient descent optimization algorithm to enhance a system with topological characteristics. Experimental results demonstrate that the machine learning-optimized Su-Schrieffer-Heeger (SSH)-like chain exhibits exceptional performance in transfer efficiency and system robustness. This achievement integrates non-Hermitian physics, topological physics, and machine learning, opening up new avenues and showcasing immense potential for the development of high-performance near-field wave functional devices.