Neural Network Research on Validating Experimental Tilt-Rotor Performance

Abstract

Results from a neural network validation study with full-scale XV-15 tilt-rotor experimental hover and forward flight data are presented. Two test data bases, acquired during separate tests conducted at NASA Ames, were used. These two isolated XV-15 rotor test data bases were: the 80by 120-Foot Wind Tunnel hover and forward flight test data base, and secondly, an outdoor hover test data base. For this neural-network-based data validation study, the objective associated with the wind tunnel test data was: obtain neural network representations, conduct data quality checks, and demonstrate sensitivity to test conditions. Neural networks were successfully used to represent and assess the quality of full-scale tilt-rotor hover and forward flight performance test data. The neural networks accurately captured tilt-rotor performance at steady operating conditions and it was shown that the wind tunnel forward flight performance test data were generally of very high quality. The second objective, using outdoor hover test data, was to formulate and implement a neural-network-based wind correction procedure. Compared to existing, momentum-theorymethod based wiad corrections to outdoor hover performance, the present neural-network-procedure-based corrections were better. The present wind corrections procedure, based on a well-trained neural network, captured physical trends present in the outdoor hover test data that had been missed by the existing, momentum-theory-based method. Copyright © 1998 by the American Institute of Aeronautics and Astronautics, Inc. No copyright is asserted in the United States under Title 17, U.S. Code. The U.S. Government has a royalty-free license to exercise all rights under the copyright claimed herein for Governmental Purposes. All other rights are reserved by the copyright owner. A a