Prediction of acoustic field in 1-D uniform duct with varying mean flow and temperature using neural networks

TL;DR

This paper develops a neural network approach to predict acoustic fields in a 1-D duct with varying flow and temperature, validated against traditional methods and demonstrating the impact of temperature gradients.

Contribution

It introduces a physics-informed neural network framework for solving the acoustic propagation problem in heterogeneous ducts, incorporating transfer learning and automatic differentiation.

Findings

Neural network predictions match Runge-Kutta results.

Temperature gradients significantly affect acoustic fields.

Transfer learning enhances model efficiency.

Abstract

Neural networks constrained by the physical laws emerged as an alternate numerical tool. In this paper, the governing equation that represents the propagation of sound inside a one-dimensional duct carrying a heterogeneous medium is derived. The problem is converted into an unconstrained optimization problem and solved using neural networks. Both the acoustic state variables: acoustic pressure and particle velocity are predicted and validated with the traditional Runge-Kutta solver. The effect of the temperature gradient on the acoustic field is studied. Utilization of machine learning techniques such as transfer learning and automatic differentiation for acoustic applications is demonstrated.