Neural network modeling of unsteady aerodynamic characteristics at high angles of attack

Abstract A neural network approach for modeling of unsteady aerodynamic characteristics in a wide angle-of-attack range is considered in the paper. Special tests have been carried out in TsAGI wind tunnel to investigate dynamic properties of unsteady aerodynamic characteristics of a generic transonic cruiser, which is a canard configuration. The aerodynamic derivatives have been studied with forced small-amplitude oscillations. In addition, forced large-amplitude oscillation tests have been carried out for the detailed investigation of dynamic effects on the unsteady aerodynamics in the extended flight envelope. To describe the nonlinear dependences of aerodynamic coefficients, observed in the dynamic experiments, two neural network models, which use the feed-forward and recurrent architectures, are developed and compared. A special regularization for the neural networks training taking into account that data are obtained in different experiments with different noise level is proposed to improve a model performance. The unsteady aerodynamics modeling results obtained with neural networks are compared with a state-space model results.

[1]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[2]  Sergio Ricci,et al.  Validation of numerical prediction of dynamic derivatives: The DLR-F12 and the Transcruiser test cases , 2011 .

[3]  Hafid Smaili,et al.  Pushing Ahead - SUPRA Airplane Model for Upset Recovery , 2012 .

[4]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[5]  John V. Foster,et al.  Dynamics Modeling and Simulation of Large Transport Airplanes in Upset Conditions , 2005 .

[6]  L. Planckaert.  Model of Unsteady Aerodynamic Coefficients of a Delta Wing Aircraft at High Angles of Attack , 2003 .

[7]  William E. Faller,et al.  Real-time model of three-dimensional dynamic reattachment using neural networks , 1995 .

[8]  L. B. Schiff,et al.  On the formulation of the aerodynamic characteristics in aircraft dynamics , 1976 .

[9]  Nikolay Abramov,et al.  Two-step linear regression method for identification of high incidence unsteady aerodynamic model , 2001 .

[10]  Ken Badcock,et al.  Modelling of 3D Dynamic Stall Using CFD and Neural Networks , 2006 .

[11]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[12]  V. Lutskii,et al.  Stability and Controllability of Supersonic Aircraft , 1970 .

[13]  Dmitry I. Ignatyev,et al.  APPLICATION OF NEURAL NETWORKS IN THE SIMULATION OF DYNAMIC EFFECTS OF CANARD AIRCRAFT AERODYNAMICS , 2011 .

[14]  Bernard Etkin,et al.  Dynamics of Atmospheric Flight , 1972 .

[15]  A. Da Ronch,et al.  Evaluation of Dynamic Derivatives Using Computational Fluid Dynamics , 2012 .

[16]  Alexander Nikolaevich Khrabrov,et al.  MATHEMATICAL SIMULATION OF DYNAMIC EFFECTS OF UNSTEADY AERODYNAMICS DUE TO CANARD FLOW SEPARATION DELAY , 2011 .

[17]  Mikhail Goman,et al.  State-Space Representation of Aerodynamic Characteristics of an Aircraft at High Angles of Attack , 1994 .

[18]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[19]  Vladislav Klein,et al.  Modeling of aircraft unsteady aerodynamic characteristics. Part 1: Postulated models , 1994 .

[20]  Patrick Reisenthel,et al.  Development of a nonlinear indicial model using response functions generated by a neural network , 1997 .