This paper presents an Expert Decision Support System for the identification of time-invariant, aeroacoustic source types. The system comprises two steps: first, acoustic properties are calculated based on spectral and spatial information. Second, clustering is performed based on these properties. The clustering aims at helping and guiding an expert for quick identification of different source types, providing an understanding of how sources differ. This supports the expert in determining similar or atypical behavior. A variety of features are proposed for capturing the characteristics of the sources. These features represent aeroacoustic properties that can be interpreted by both the machine and by experts. The features are independent of the absolute Mach number, which enables the proposed method to cluster data measured at different flow configurations. The method is evaluated on deconvolved beamforming data from two scaled airframe half-model measurements. For this exemplary data, the proposed support system method results in clusters that mostly correspond to the source types identified by the authors. The clustering also provides the mean feature values and the cluster hierarchy for each cluster, and for each cluster member, a clustering confidence. This additional information makes the results transparent and allows the expert to understand the clustering choices.

Beamforming is an imaging tool for the investigation of aeroacoustic phenomena and results in high-dimensional data that are broken down to spectra by integrating spatial regions of interest. This paper presents two methods that enable the automated identification of aeroacoustic sources in sparse beamforming maps and the extraction of their corresponding spectra to overcome the manual definition of regions of interest. The methods are evaluated on two scaled airframe half-model wind tunnel measurements and on a generic monopole source. The first relies on the spatial normal distribution of aeroacoustic broadband sources in sparse beamforming maps. The second uses hierarchical clustering methods. Both methods are robust to statistical noise and predict the existence, location, and spatial probability estimation for sources based on which regions of interest are automatically determined.

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.

No abstract