Artificial Neural Network and Gaussian Approach to Predict Rotor-Airframe Acoustic Waveforms

Abstract

An artificial neural network-based surrogate model and Gaussian process model were developed to predict the acoustic interaction for a fixed-pitch rotor in proximity to a downstream cylindrical airframe typical of small unmanned aerial system platforms. The models were trained to predict the acoustic waveform under representative hover conditions as a function of rotational speed, airframe proximity, and observer angle. Training data were acquired in an anechoic chamber on both isolated rotors and rotor–airframe configurations. The acoustic amplitude and phase of the revolution-averaged interaction were predicted, which required up to 25 harmonics to capture the impulse event caused by the blade’s approach and departure from the airframe. Prediction performance showed, on average, that the artificial neural network models could estimate the acoustic amplitude and phase over the relevant harmonics for unseen conditions with 86% and 75% accuracy, respectively. This enables a time-domain reconstruction of the waveform for the range of geometric and flow parameters tested. In contrast, the Gaussian process matched the amplitude but underpredicted the phase for unseen conditions at 86% and 45% accuracy, respectively.