Initial Assumptions for the System of Automatic Detection and Classification of Aircraft Noise Events

The present study undertakes the development and implementation of an algorithm for an automatic separation of acoustic events related to aircraft flights. The data are provided by noise monitoring stations operating as part of multi-point continuous noise measurement systems around small and medium-sized airports and helicopter landing sites in Poland. The article presents initial assumptions of the developed method based on the conclusions of the research. For this purpose, two different methods of airborne noise signal detection will be discussed. The first method is based on the analysis of the value of the changing rate of the signal being the difference between the value of the analysed sample and the value of the h-th previous sample of the recorded sound level time history. The second method uses a convolutional neural network operating on values recorded in 1/3-octave bands. The objective of the study is to examine the effectiveness and limitations of the selected methods on the collected representative input data.