Machine Learning Approach for Retrieval of Complex Permittivity in Cavity Resonators

Abstract

This work presents a novel microwave sensor that is specially designed for retrieval of complex permittivity. The operating frequency range of the sensor is C band (4.54 GHz) and a tapered feeding topology is implemented to achieve a higher quality factor and coupling. The sensor is equipped with multiple techniques such as Photonic Band Gap, Slow-Wave vias, which enhances the sensitivity significantly. These techniques increase the interaction between the material under test and the electric field. By utilizing slow-wave via, a miniaturization of 35% is achieved. Due to the reduction in size and increasing the sensitivity, these two methods introduce a new possibility and application for sensor design. The values of complex permittivities are extracted from S-parameters obtained from simulation of the structure in CST Microwave Studio (MWS) using a Machine Learning approaches.