A feedforward neural network for modelling of average pressure frequency response
This work aims to reduce the computational burden for engineers and researchers who need to model sound pressure fields across various geometries and frequencies, offering a more efficient alternative to traditional numerical methods.
This paper addresses the computational cost of modeling sound pressure fields using the Helmholtz equation by proposing a feedforward neural network to predict the average sound pressure over a frequency range. The model's accuracy and data requirements for specific prediction accuracies are analyzed.
The Helmholtz equation has been used for modelling the sound pressure field under a harmonic load. Computing harmonic sound pressure fields by means of solving Helmholtz equation can quickly become unfeasible if one wants to study many different geometries for ranges of frequencies. We propose a machine learning approach, namely a feedforward dense neural network, for computing the average sound pressure over a frequency range. The data is generated with finite elements, by numerically computing the response of the average sound pressure, by an eigenmode decomposition of the pressure. We analyze the accuracy of the approximation and determine how much training data is needed in order to reach a certain accuracy in the predictions of the average pressure response.