Optimal design of wireless power transfer coils for biomedical implants using machine learning and meta-heuristic algorithms

Abstract

The classical methods for optimizing wireless power transfer (WPT) systems using mathematical equations or finite element methods can be time-consuming and may only sometimes yield optimal designs. In order to overcome this challenge, this paper introduces a novel approach integrating machine learning techniques with meta-heuristic methods to design and optimize a miniaturized, high-efficiency WPT receiving coil for biomedical applications. The objective is to achieve dimensions below 20 mm, a depth of 30 mm within the tissue, and a frequency of 13.56 MHz. Our approach leverages a neural network (NN) model to predict efficiency based on geometric coil parameters, eliminating the need for complex equations. The NN was trained on a dataset generated via finite element method simulations. We employ two meta-heuristic algorithms, the genetic algorithm and the coyote optimization method, to find optimal parameters that maximize efficiency. Our NN model demonstrates exceptional accuracy, exceeding 97%. Furthermore, the proposed WPT coil design approach enhances transfer efficiency by up to 76%, significantly reducing computation time compared to classical methods. Finally, we validate our results using finite element simulation with Ansys Maxwell 3D.