Machine learning approach to transform scattering parameters to complex permittivities

Abstract

This study investigates the application of artificial neural networks to determine the complex dielectric material properties derived from experimental VNA scattering parameter measurements. The study utilizes a finite element approach to synthetically generate data to train the neural network. The neural network was trained using a supervised learning approach and validated using experimental measurement data. The frequency range of interest was between 0.1 and 13.5 GHz with the real part of the dielectric constants ranging from 1 − 100 and the imaginary part ranging from 0 − 0.2. This modelling approach decreases the uncertainty when compared to existing inverse approaches. This approach demonstrates a general framework that can be used for converting experimental or computational derived scattering parameters to complex permittivities.

Keywords:

• Dielectrics
• permittivity
• GHz
• machine learning
• convolutional neural networks

Acknowledgments

R.T and T.M. would like to acknowledge the support in part by an appointment to the Department of Energy at National Energy Technology Laboratory, administered by ORAU through the U.S. Department of Energy Oak Ridge Institute for Science and Education. T.M. would like to thank Candice Ellison and Mike Spencer for their technical discussion on experimental measurement of complex permittivities.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

T.M. would also like to acknowledge the partial support of award DE-FE0026825. T.M. would also like to acknowledge the partial support of NSF Award #1709568.

Notes on contributors

Robert Tempke

Robert Tempke is a material science Ph.D. candidate whose research is focused on the development of machine learning techniques for chemical processes.

Liam Thomas

Liam Thomas is an undergraduate researcher whose research has focused on the development of machine learning methods for aerospace applications.

Christina Wildfire

Dr. Christina Wildfire is a researcher at NETL that focuses on microwave catalysis.

Dushyant Shekhawat

Dr. Dushyant Shekhawat, P.E. is a Senior Researcher at NETL that focuses on microwave chemical conversion.

Terence Musho

Dr. Terence Musho, P.E. is an Associate Professor whose research is focused on computational material science and a fundamental understanding of microwave processes.