Expert Decision Support System for Aeroacoustic Classification from Deconvolved Beamforming Maps

Abstract

This paper is part of a special issue on Machine Learning in Acoustics. This paper presents an expert decision support system for time-invariant aeroacoustic source classification. The system comprises two steps: first, the calculation of acoustic properties based on spectral and spatial information; and second, the clustering of the sources based on these properties. Example data of two scaled airframe half-model wind tunnel measurements is evaluated based on deconvolved beamforming maps. A variety of aeroacoustic features are proposed that capture the characteristics and properties of the spectra. These features represent aeroacoustic properties that can be interpreted by both the machine and experts. The features are independent of absolute flow parameters such as the observed Mach numbers. This enables the proposed method to analyze data which is measured at different flow configurations. The aeroacoustic sources are clustered based on these features to determine similar or atypical behavior. For the given example data, the method results in source type clusters that correspond to human expert classification of the source types. Combined with a classification confidence and the mean feature values for each cluster, these clusters help aeroacoustic experts in classifying the identified sources and support them in analyzing their typical behavior and identifying spurious sources in-situ during measurement campaigns.

Expert decision support system for aeroacoustic source type identification using clustering

“…In comparison, the EDSS aims at automating most of these tasks. First, the ROI definition RðxÞ and spectra generation were shown to have the capacity to be automated using the SIND method (Goudarzi et al, 2021). The EDSS then defines a source S rae for each ROI R r , at each angle of attack a a , and at each Reynolds number Re e .…”

“…We use CLEAN-SC (Sijtsma, 2007) beamforming maps (Merino-Mart ınez et al, 2019) of the scaled air-frame models of a Dornier 728 (Do728) (Ahlefeldt, 2013) and an Airbus A320 (A320) (Ahlefeldt, 2017) as example data, featuring multiple aeroacoustic source types. We employ the Source Identification based on spatial Normal Distributions (SIND) (Goudarzi et al, 2021) approach to identify individual sources and obtain their spectra from the beamforming maps. We explain typical aeroacoustic properties and derive corresponding features, discuss their usefulness, and propose mathematical definitions.…”

“…The method reported in this paper was originally presented at the AIAA Aviation 2020 conference (Goudarzi et al, 2020) as work-in-progress. This paper presents more data (five different Reynolds numbers for the Do728, and four for the A320 versus one for both models in the conference paper).…”