Publication Date
2022
Document Type
Thesis
Committee Members
Chandriker Dass, Ph.D. (Committee Co-Chair); Amit Sharma, Ph.D. (Committee Co-Chair); Ivan Medvedev, Ph.D. (Committee Member)
Degree Name
Master of Science (MS)
Abstract
A phonon is a discrete unit of vibrational motion that occurs in a crystal lattice. Phonons and the frequency at which they propagate play a significant role in the thermal, optical, and electronic properties of a material. A phononic material/device is similar to a photonic material/device, except that it is fabricated to manipulate certain bands of acoustic waves instead of electromagnetic waves. Phononic materials and devices have been studied much less than their photonic analogues and as such current materials exhibit control over a smaller range of frequencies. This study aims to test the viability of machine learning, specifically neural networks in aiding in phononic crystal design. Multiple combinations of training datasets, neural network configuration, and data formatting methods are attempted with performance metrics recorded. A novel inverse design scheme is proposed that utilizes phonon density of states to perform prediction of phononic crystal parameters given a desired band gap and center frequency.
Page Count
132
Department or Program
Department of Physics
Year Degree Awarded
2022
Copyright
Copyright 2022, some rights reserved. My ETD may be copied and distributed only for non-commercial purposes and may not be modified. All use must give me credit as the original author.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.
