Neural network prediction and control of three-dimensional unsteady separated flowfields

Using artificial neural networks (ANN), one approach to the control of unsteady aerodynamics is to develop real-time models which, given the actuator control signals, anticipate the unsteady flowfield wing interactions. These models of flow-wing interactions can then be used as the foundation upon which to develop adaptive control systems. This article supports this concept using three-dimensional unsteady surface pressure topologies collected from a rectangular wing pitched through the static stall angle at seven nondimensional pitch rates. A neural network model of the unsteady surface pressures was developed by training an ANN on five of these seven data sets. Following training, the only inputs required for the model were instantaneous angle of attack and angular velocity. These network-predicted unsteady surface pressure time histories were compared directly to the experimental pressure data. Then, a neural network controller for the wing motion history was developed using the pressure model. The results indicated that the controller actuator signals reliably yielded motion histories that generated the measured lift to drag ratio (LID) time histories. Further, the results suggest that for any desired LID requirement optimized motion histories can be generated.

[1]  Robert F. Stengel,et al.  Identification of aerodynamic coefficients using computational neural networks , 1992 .

[2]  M. C. Robinson,et al.  Wind turbine blade aerodynamics: The combined experiment , 1994 .

[3]  William E. Faller,et al.  Dynamic Reattachment on a Downward Pitching Finite Wing , 1994 .

[4]  Peter Lorber,et al.  Tip vortex, stall vortex, and separation observations on pitching three-dimensional wings , 1993 .

[5]  J. H. Jacobs,et al.  Use of Artificial Neural Networks for Buffet Environments , 1994 .

[6]  M. Dorn,et al.  Aircraft agility - The science and the opportunities , 1989 .

[7]  James E. Steck,et al.  Use of neural networks in control of high alpha maneuvers , 1992 .

[8]  M. S. Chandrasekhara,et al.  Reattachment studies of an oscillating airfoil dynamic stall flowfield , 1991 .

[9]  Mohamed Gad-el-Hak,et al.  Three-dimensional effects on a pitching lifting surface , 1985 .

[10]  Peter F. Lorber,et al.  Dynamic stall experiments on a swept three-dimensional wing in compressible flow , 1991 .

[11]  Walter C. Merrill,et al.  Neural network application to aircraft control system design , 1991 .

[12]  William E. Faller,et al.  Neural network prediction of three-dimensional unsteady separated flowfields , 1993 .

[13]  W. J. McCroskey,et al.  A Review of Recent Advances in Computational and Experimental Analysis of Dynamic Stall , 1993 .

[14]  W. J. McCroskey,et al.  The 1976 Freeman Scholar Lecture: Some Current Research in Unsteady Fluid Dynamics , 1977 .

[15]  M. S. Chandrasekhara,et al.  Reattachment studies of an oscillating airfoil dynamic stall flowfield , 1994 .

[16]  William E. Faller,et al.  Quasi-linear neural networks: application to the prediction and control of unsteady aerodynamics , 1993, Defense, Security, and Sensing.

[17]  C. M. Ha,et al.  Neural networks approach to AIAA aircraft control design challenge , 1991 .

[18]  Chih-Ming Ho,et al.  Lift Force of Delta Wings , 1990 .

[19]  Michael Robinson,et al.  Unsteady surface pressure measurements on a pitching rectangular wing , 1988 .

[20]  Scott Schreck,et al.  Neural networks: Applications and opportunities in aeronautics , 1996 .

[21]  S. Huyer.  Examination of forced unsteady separated flow fields on a rotating wind turbine blade , 1993 .

[22]  Donald Rockwell,et al.  Three-dimensional flow structure on delta wings at high angle-of-attack - Experimental concepts and issues , 1993 .

[23]  S. Schreck,et al.  Unsteady vortex dynamics and surface pressure topologies on a finite pitching wing , 1994 .

[24]  William E. Faller,et al.  Real-time prediction of unsteady aerodynamics: Application for aircraft control and manoeuvrability enhancement , 1995, IEEE Trans. Neural Networks.

[25]  William E. Faller,et al.  Unsteady fluid mechanics applications of neural networks , 1995 .

[26]  L. Carr.  Progress in analysis and prediction of dynamic stall , 1988 .