论文信息 - COMPARISON OF STATIC AND DYNAMIC ARTIFICIAL NEURAL NETWORKS FOR LIMIT CYCLE OSCILLATION PREDICTION

COMPARISON OF STATIC AND DYNAMIC ARTIFICIAL NEURAL NETWORKS FOR LIMIT CYCLE OSCILLATION PREDICTION

A dynamic artificial neural network in the form of a multi-layer perceptron with a delayed recurrent feedback connection is investigated to determine its ability to predict linear and nonlinear flutter response characteristics. The predictive capabilities are compared to those of a static artificial neural network. The network is developed and trained using linear flutter analysis and flight test results from a fighter test. Eleven external store carriage configurations are used as training data and three configurations are used as test cases. The network was successful in predicting the aeroelastic oscillation frequency and amplitude responses over a range of Mach numbers for two of the test cases. Predictions for the third test case were not as good.

Charles M. Denegri | Michael R. Johnson

[1] Malcolm A. Cutchins,et al. EVALUATION OF CLASSICAL FLUTTER ANALYSES FOR THE PREDICTION OF LIMIT CYCLE OSCILLATIONS , 1997 .

[2] Jos Meijer,et al. A semi-empirical unsteady nonlinear aerodynamic model to predict transonic LCO characteristics of fighter aircraft , 1995 .

[3] W. Rodden,et al. A doublet-lattice method for calculating lift distributions on oscillating surfaces in subsonic flows. , 1969 .

[4] Robert W. Bunton,et al. Limit Cycle Oscillation Characteristics of Fighter Aircraft , 2000 .

[5] Charles M. Denegri,et al. Limit Cycle Oscillation Prediction Using Artificial Neural Networks , 2001 .

[6] Charles M. Denegri,et al. Limit Cycle Oscillation Flight Test Results of a Fighter with External Stores , 2000 .

[7] Simon Haykin,et al. Neural Networks: A Comprehensive Foundation , 1998 .

[8] P. Chen,et al. LIMIT-CYCLE-OSCILLATION STUDIES OF A FIGHTER WITH EXTERNAL STORES , 1998 .