Data-Driven Approach for the Floquet Propagator Inverse Problem Solution

Floquet theory is a classical tool for the analysis of periodic structures' acoustics. However, it may be challenging to analyze material properties for complex cases, whereas the composite material's integral characteristics are obtained relatively straightforward. The paper shows the dat...

Full description

Saved in:
Bibliographic Details
Main Author: Hvatov, Alexander
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Crystals
data-driven polynomial
Finite element analysis
Floquet propagator
Inverse problems
Machine learning
periodic structures
phononic crystal
Propagation constant
Signal processing
sparse regression
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Floquet theory is a classical tool for the analysis of periodic structures' acoustics. However, it may be challenging to analyze material properties for complex cases, whereas the composite material's integral characteristics are obtained relatively straightforward. The paper shows the data-driven approach to inverse displacement data to the theoretical propagation constant approximation and consequently the material parameters using machine learning methods, namely a datadriven symbolic regression. Such an approach may be used to determine the material acoustic parameters in complex cases. Another application is a wave finite element analysis speedup. Two waveguide models are considered: axial rod and circular membrane.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747567