Abstract

This paper proposes a method for predicting the workload experienced by a pilot when flying a helicopter in highly turbulent wakes where the spatial scales of the eddies are comparable with the size of the aircraft. In this method, the temporal and spatial wind variations over the helicopter are quantified using wavelet decomposition. The extracted wind variation parameters are then correlated with pilot workload using a neural network trained by appropriate turbulence-workload datasets. The proposed method has been used to predict pilot workload for helicopter deck landings in ship airwakes that were produced using unsteady CFD. The prediction performance was seen to be comparable to that of a previous method based on the standard deviations of 4-axis pilot control activities. The proposed method has also been shown to be capable of predicting pilot workload for a different type of ship airwake to the one used to train the neural network. Further improvements in the method are planned to reflect the different dynamic characteristics exhibited by different helicopter types, and the effects of these on pilot workload.Copyright © 2009 by the American Helicopter Society International, Inc. All rights reserved.