Neural Prediction of Aircraft Noise Levels Along a Flight Trajectory - ENAC - École nationale de l'aviation civile Accéder directement au contenu
Article Dans Une Revue IEEE Latin America Transactions Année : 2015

Neural Prediction of Aircraft Noise Levels Along a Flight Trajectory

Résumé

Sustained increase in air transportation as well as urban encroachment have generated noise critical situations around airports. Then the prediction of the noise impact resulting from new departure/arrival procedures and new traffic patterns at airports gains more importance. Until recently this estimation has been performed on statistical grounds through the segmentation of nominal aircraft trajectories. This approach is in general not representative of the temporal dimension of the noise impacts over the airport surrounding population. To go beyond this limitation, a dynamical approach to noise impact estimation taking explicitly into consideration the operated 3D+T aircraft trajectory, is proposed in this communication. This is achieved by taking profit of the differential flatness property of the flight guidance dynamics of transportation aircraft, which allows through inversion to compute the corresponding thrust and aerodynamic conditions which are also responsible for aircraft noise generation. In numerical grounds this is achieved by building a neural network device which produces ground noise levels histories along the trajectories flown by aircraft. The proposed approach is partially validated using for comparison noise levels estimated from the Integrated Noise Model (INM). The proposed tool appears to be useful to analyze the noise impact of complex traffic scenarios including traffic dispersion phenomena.
Fichier non déposé

Dates et versions

hal-01339913 , version 1 (30-06-2016)

Identifiants

Citer

Téo Cerqueira Revoredo, Jules Ghislain Slama, Felix Mora-Camino. Neural Prediction of Aircraft Noise Levels Along a Flight Trajectory. IEEE Latin America Transactions, 2015, 13 (5), pp.1313-1320. ⟨10.1109/TLA.2015.7111984⟩. ⟨hal-01339913⟩
35 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More