Identification of helicopter noise using a neural network

The use of an artificial neural network (ANN) to distinguish between the noise of two helicopters is discussed. Two simulated helicopter noises with fundamental rotor frequencies of 12 kilohertz but with different prototype spectras were generated using a Gaussian-based equation. The ANN was then tested on these helicopter noises. It was found that ANN is very sensitive to changes in spectral shape, allowing it to distinguish between the helicopters even in the absence of tail-rotor noise.