Automatic estimation of the sound emergence of wind turbines using non-negative matrix factorization: a preliminary study

Forum Acusticum, LYON, FRANCE, 07-/12/2020 - 11/12/2020; The acoustic impact of French wind farms is currently estimated by measuring their sound emergence. These measures require the implementation of on/off cycles of the wind farms in order to determine the ambient noise (wind turbines in operation) and the residual noise (stopped wind turbines). These procedures result in very significant losses of electricity production for operators, which induce drastic limitations of the duration of emergence measurement periods (1 or 2 weeks). This reduced duration, compared to a full year of weather conditions, is to the detriment of the representativeness of the estimation of sound emergence. In order to remedy this disadvantage, we propose to estimate the noise emergence of wind turbines in real time, continuously and without stopping the machines, using a sound source separation method based on a machine learning technique: non-negative matrix factorization. This technique is tested on a corpus of simulated sound scenes that allows a total control of their composition and especially the emergence of wind turbine noise. A numerical experiment is conducted to determine, among the various influential parameters of this method, the optimal form that achieves the best estimates of sound emergence over the entire sound corpus. Initial results indicate that this approach generates average estimation errors similar to current methods but which are dependent on the emergence of wind noise within the studied scenes. This method makes it possible, subject to additional validation through the study of more complex corpuses, to estimate the noise emergence of wind farms continuously without stopping energy production.