"Buzz-saw" noise: Prediction of the rotor-alone pressure field

Public expectations of lower environmental noise levels, and increasingly stringent legislative limits on aircraft noise, result in noise being a critical technical issue in the development of jet engines. Noise at take-off, when the engines are at high-power operating conditions, is a key reference level for engine noise certification. "Buzz-saw" noise is the dominant fan tone noise from modern high-bypass-ratio turbofan aircraft engines during take-off. Rotor-alone tones are the key component of buzz-saw noise. The rotor-alone pressure field is cut-off at subsonic fan tip speeds; buzz-saw noise is associated with supersonic fan tip speeds, or equivalently, high power engine operating conditions. A recent series of papers has described new work concerning the prediction of buzz-saw noise. The prediction method is based on modelling the nonlinear propagation of one-dimensional sawtooth waveforms. A sawtooth waveform is a simplified representation of the rotor-alone pressure field. Previous validation of the prediction method focussed entirely on reproducing the spectral characteristics of buzz-saw noise; this was dictated at that time by the availability of spectral data only for comparison between measurement and prediction. In this paper, full validation of the method by comparing measurement and prediction of the rotor-alone pressure field is published for the first time. It is shown that results from the modelling based on a one-dimensional sawtooth waveform capture the essential features of the rotor-alone pressure field as it propagates upstream inside a hard-walled inlet duct. This verifies that predictions of the buzz-saw noise spectrum, which are in good agreement with the measured data, are based on a model which reproduces the key physics of the noise generation process. Validation results for the rotor-alone pressure field in an acoustically lined inlet duct are also shown. Comparisons of the measured and predicted rotor-alone pressure field are more difficult to interpret because the acoustic lining significantly modifies the sawtooth waveform, but there remains good agreement with the measured spectral data. The buzz-saw noise prediction code used to generate the simulations in this paper has been used by the Rolls-Royce Noise Department since 2004. (c) 2012 Elsevier Ltd. All rights reserved.