Using Machine Learning to predict Characteristics of Microstrip Line and Microstrip Patch Antenna

TL;DR

This paper investigates applying machine learning algorithms to predict key characteristics of microstrip lines and patch antennas, aiming to improve design accuracy using data-driven models.

Contribution

It introduces a methodology for training ML models on generated data to predict transmission line parameters, identifying the most effective algorithms for specific cases.

Findings

Best algorithms vary for different transmission line types

ML models achieved low prediction errors

Data-driven approach enhances transmission line design accuracy

Abstract

This study, conducted in 2017, explores the use of Machine learning algorithms to predict Characteristics of Transmission Lines such as Impedance or resonance frequency using design parameters of Transmission Lines. Using formulas and equations that define the characteristics of Transmission lines, training data was generated. We trained different models for this dataset. The extent of deviation of predicted output from the actual output was measured in terms of maximum error and average error. This helped determine how well an algorithm worked for a particular transmission line. Further, the best-suited algorithm for each transmission line under consideration was found based on the error