Beamforming is an imaging tool for the investigation of aeroacoustic phenomena and results in high dimensional data that is 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.
Acoustical Society of America Journal
- Pub Date:
- September 2021
- Computer Science - Sound;
- Computer Science - Machine Learning;
- Electrical Engineering and Systems Science - Audio and Speech Processing
- Preprint for JASA special issue on machine learning in acoustics, Revision 2