Flight flutter testing is a crucial part in the certification of a prototype aircraft. To aid the clearance process, a number of different methods have been proposed to determine the speed at which flutter occurs on the basis of data obtained during the flight envelope expansion. However, the most commonly used approach is simply to extrapolate the estimated damping ratios. In this paper, a method is proposed for the prediction of damping ratios during a flight test using a neural network trained on model data. The proposed method is compared with a simple statistical extrapolation approach, and the effects of noise are investigated. For noise-free data, the neural network method shows improved accuracy compared with the statistical method. With noisy data, the accuracy of the statistical method is unacceptably poor, but the accuracy of the neural network method remains good as long as the network is trained with noisy data.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Flight test flutter prediction using neural networks


    Contributors:


    Publication date :

    2001


    Size :

    11 Seiten, 26 Quellen




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English




    Flight test flutter prediction using neural networks

    Crowther, W.J. | Online Contents | 2001


    Flight test flutter prediction using neural networks

    Crowther, W J / Cooper, J E | SAGE Publications | 2001


    Flutter Speed Prediction during Flight Flutter Testing Using Neural Networks

    Cooper, J. E. / Crowther, W. J. / Confederation of European Aerospace Societies et al. | British Library Conference Proceedings | 1999


    Flutter Prediction from Flight Flutter Test Data

    G. Dimitriadis / J. E. Cooper | AIAA | 2001


    Comment on "Flutter Prediction from Flight Flutter Test Data"

    Dimitriadis, G. / Cooper, J. E. | AIAA | 2006