A Neural Network Parallel Adaptive Controller for Fighter Aircraft Pitch-Rate Tracking
作者： S. Kamalasadan , Adel A. Ghandakly
关键词: Control engineering 、 Adaptive system 、 Motion control 、 Elevator 、 Nonlinear system 、 Pitch rate 、 Reference model 、 Artificial neural network 、 Engineering 、 Deflection (engineering) 、 Control theory
摘要: A fighter aircraft pitch-rate command-tracking controller based on a neural network parallel is proposed. The scheme consists of an online radial basis function (RBFNN) in with model reference adaptive (MRAC) and uses growing dynamic RBFNN to augment MRAC. Updating the width, center weight characteristics are performed such that error reduction improved tracking accuracy accomplished. architecture adapts its centers radii tunes relevant parameters, dynamically addressing issues related initial dimensional growth inherent static design. total control signal used change elevator deflection, keeping other surface deflections at random values, even when operates different maneuvers. Moreover, suitable structure for all operating modes, system then fully tuned by controller. strength proposed ability effectively perform, plant mode swings functional changes occur. Theoretical results validated conducting simulation studies nonlinear F16 modes created randomly changing parameter set.
sci-hub.se 参考文章(17)
Adel A. Ghandakly, Khalid S. Al-Olimat, Sukumar Kamalasadan, A Fuzzy Logic Based Multiple Reference Model Adaptive Control. computer applications in industry and engineering. pp. 58- 61 ,(2003)
C. Pereira, J. Henriques, A. Dourado, Adaptive RBFNN versus self-tuning controller: An experimental comparative study european control conference. pp. 3351- 3356 ,(1997) , 10.23919/ECC.1997.7082630
M.B. McFarland, A.J. Calise, Robust adaptive control of uncertain nonlinear systems using neural networks american control conference. ,vol. 3, pp. 1996- 2000 ,(1997) , 10.1109/ACC.1997.611038
Y. Li, N. Sundararajan, P. Saratchandran, Neuro-controller design for nonlinear fighter aircraft maneuver using fully tuned RBF networks Automatica. ,vol. 37, pp. 1293- 1301 ,(2001) , 10.1016/S0005-1098(01)00090-5
PO-CHIANG YEH, PETAR V. KOKOTOVIĆ, Adaptive control of a class of nonlinear discrete-time systems International Journal of Control. ,vol. 62, pp. 303- 324 ,(1995) , 10.1080/00207179508921545
Jorge I. Arciniegas, Adel H. Eltimsahy, Krzysztof J. Cios, Neural-networks-based adaptive control of flexible robotic arms Neurocomputing. ,vol. 17, pp. 141- 157 ,(1997) , 10.1016/S0925-2312(97)00037-4
Lu Yingwei, N. Sundararajan, P. Saratchandran, Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm IEEE Transactions on Neural Networks. ,vol. 9, pp. 308- 318 ,(1998) , 10.1109/72.661125
J.T. Lo, D. Bassu, Adaptive multilayer perceptrons with long- and short-term memories IEEE Transactions on Neural Networks. ,vol. 13, pp. 22- 33 ,(2002) , 10.1109/72.977262
S. Karnalasadan, A.A. Ghandakly, A neural network based intelligent model reference adaptive controller international conference on computational intelligence for measurement systems and applications. pp. 174- 179 ,(2004) , 10.1109/CIMSA.2004.1397257
Sukumar Kamalasadan, Adel A. Ghandakly, A Neural Network Parallel Adaptive Controller for Dynamic System Control IEEE Transactions on Instrumentation and Measurement. ,vol. 56, pp. 1786- 1796 ,(2007) , 10.1109/TIM.2007.895674