Acoustic plane-wave decomposition by means of multilayer perceptron neural networks

KTH, Farkostteknik och Solidmekanik KTH, Linné Flow Center, FLOW KTH, Competence Center for Gas Exchange (CCGEx) Academic Press 2020

Acoustic mode decomposition is used for evaluating the damping of aircraft liners and, in general, to investigate acoustic scattering in flow ducts. Classical methods rely on analytical solutions of the wave properties and accept uncertainties due to simplified descriptions of the duct flow. In contrast, the current study provides a wave decomposition method that does not require explicit analytical knowledge of the wave properties and registers a wide range of flow-related acoustic phenomena. A multilayer perceptron artificial neural network is trained to learn acoustic wave decomposition for plane-wave-like duct modes. Training data are the numerical solutions of the Linearized Navier-Stokes Equations, from which the network not only learns the wave motion properties but also the dispersion of sound into the fluid flow. The network can account for flow-related effects, such as turbulent attenuation, refraction, convection, and thermo-viscous dissipation, which are only included in the classical models based on simplifications. The new method is validated for plane-waves against analytical data and experiments. It is demonstrated that the network can mimic the classical solutions accurately when trained under the same flow simplifications. In addition, it can cope with complex flow effects, such as turbulent attenuation, by including them in the training data. Therefore, the proposed wave decomposition complements the classical plane-wave decomposition when investigating in-duct sound with complex flow conditions. An important continuation of this work is to extend the new wave decomposition method to multi-modal sound fields. As the first step in this direction, it is demonstrated that the proposed training scheme also works for higher-order modes.
QC 20201221

Acoustic dispersion; Acoustic two-port; Duct acoustics; Flow acoustic; Machine learning; Modal decomposition; Neural network; Acoustic field measurement; Acoustic fields; Complex networks; Ducts; Elastic waves; Microphones; Multilayers; Navier Stokes equations; Training aircraft; Viscous flow; Wave propagation; Acoustic mode decomposition; Acoustic plane waves; Analytical knowledge; Classical solutions; Linearized navier-stokes equations; Multi-layer perceptron neural networks; Plane-wave decomposition; Viscous dissipation; Multilayer neural networks; Fluid Mechanics; Strömningsmekanik; Article in journal; info:eu-repo/semantics/article; text

10.1016.j.jsv.2020.115518

Open access content. Open access content
info:eu-repo/semantics/restrictedAccess

English

UPE oai:DiVA.org:kth-287939
0000-0002-9939-8113
0000-0001-7898-8643
doi:10.1016/j.jsv.2020.115518
ISI:000576700400010
Scopus 2-s2.0-85088926104
1235096857

UPPSALA UNIV LIBR
From OAIster®, provided by the OCLC Cooperative.

edsoai.on1235096857