Dielectric substrate prediction through transmission measurements and machine learning

Abbasi, Muhammad Inam and Francis, Moses and Dali Khan, Sher and Sulaiman, Noor Hafizah and Dahri, Muhammad Hashim and Mohd Ibrahim, Imran and Shamsan, Zaid Ahmed (2025) Dielectric substrate prediction through transmission measurements and machine learning. Journal of Engineering, 2025 (941881). pp. 1-7. ISSN 2314-4912

Text 02622041120251427502415.pdf Download (1MB)

Abstract

Dielectric properties of the substrates play an important role in the design and performance characterization of communication components such as antennas, filters, and sensors. Conventionally, dielectric probes are used to measure the properties of the substrate. However, the dielectric probes are very expensive and easily breakable instruments. In this work, a novel method of dielectric substrate prediction has been proposed using S12 measurements with two waveguides, along with the application of machine learning. Extensive data collection is done using multiple simulations of the proposed method in 3D electromagnetic software in the X-band frequency range (8–12 GHz). The measurements are then conducted by using two waveguides, and the data is compared with the simulation data set, where the decision is made based on the comparison of dielectric properties. For verification of the proposed method, dielectric substrates of FR4 and Rogers 5880 have been used, which demonstrated very close agreement between the measured properties and properties from the data sheet.

Item Type:	Article
Uncontrolled Keywords:	Dielectric properties, Machine learning, Substrate, Waveguide, X-band measurements
Divisions:	Faculty Of Electronics And Computer Technology And Engineering
Depositing User:	Norfaradilla Idayu Ab. Ghafar
Date Deposited:	30 Dec 2025 03:00
Last Modified:	30 Dec 2025 03:00
URI:	http://eprints.utem.edu.my/id/eprint/29305
Statistic Details:	View Download Statistic

Actions (login required)

View Item