Graphene-based phononic crystal lenses: Machine learning-assisted analysis and design

Area of Science:

• Materials Science
• Acoustics
• Artificial Intelligence

Background:

• Conventional acoustic lens design faces challenges with high computational costs and achieving precise refractive indices.
• Graphene-based composites and artificial intelligence offer new possibilities for advanced acoustic lens design.
• Phononic crystals provide a tunable platform for manipulating elastic waves.

Purpose of the Study:

• To develop an efficient and accurate design methodology for graphene-based gradient-index phononic crystal (GGPC) lenses.
• To leverage machine learning for predicting effective refractive indices in GGPC structures.
• To demonstrate the application of the proposed method in designing acoustic lenses for energy focusing.

Main Methods:

• Utilizing the plane wave expansion method to calculate dispersion relations and effective refractive indices.
• Establishing a comprehensive database of effective refractive indices based on structural parameters.
• Employing genetic programming, a machine learning algorithm, to generate predictive mathematical models.

Main Results:

• The study successfully generated explicit mathematical expressions for predicting effective refractive indices using genetic programming.
• A machine learning-assisted design methodology for GGPC lenses was established, demonstrating high efficiency and accuracy.
• The method enables inverse design capabilities for GGPC lenses.

Conclusions:

• The proposed design methodology significantly enhances the efficiency and accuracy of GGPC lens development.
• This approach facilitates novel phononic crystal lens designs and precise acoustic energy focusing.
• The integration of theoretical formulations and machine learning paves the way for advanced acoustic device engineering.