One Near Space Hypersonic Aircraft Neural Networks Dynamic Surface Backstepping Control Design

• Published in: Applied Mechanics and Materials Vol. 494-495; no. Current Development of Mechanical Engineering and Energy; pp. 1068 - 1071
• Main Authors: Chen, Jie, Lin, Yan, Pan, Chang Peng
• Format: Journal Article
• Language: English
• Published: Zurich Trans Tech Publications Ltd 06.02.2014
• Subjects: Computer simulation; Control surfaces; Design engineering; Dynamics; Hypersonic aircraft; Mathematical models; Multilayers; Neural networks; Hypersonic Aircraft; Backstepping; Dynamic Surface; Neural Network (NN)
• ISBN: 3038350036; 9783038350033
• ISSN: 1660-9336; 1662-7482; 1662-7482
• DOI: 10.4028/www.scientific.net/AMM.494-495.1068

By using multilayer neural networks and dynamic surface backstepping,one new robust adaptive control design method is proposed for one hypersonic aircraft (HSA) uncertain MIMO nonaffine block control system. We adopt dynamic surface control strategy to eliminate the explosion of terms by introducing a series of first order filters to obtain the differentiation of the virtual control inputs. multi-layers nerual network adjust function to compensate the influence from the uncertain, and design the robust terms to solve the problem from approach error. The stability analysis and simulations demonstrate the good performance of the controller. Nonlinear six-degree-of-freedom (6-DOF) numerical simulation results for a HSA model are presented to demonstrate the effectiveness of the proposed method.