A radial basic function (RBF) neural networks based sliding model control and dynamic inverse control approach to a missile was presented. The basic control law was designed by dynamic inversion, and neural networks based sliding model and dynamic inverse controller was designed for the slow loop to compensate the uncertainty of the whole control system. The RBF neural networks were used to approximate the uncertainty of slow states model of missile and the approximation errors of the neural networks were introduced to the design of adaptive adjust law to improve the quality of the systems. Sliding model controller was used to attenuate the uncertainty of model and the approximation errors of the neural networks. The controller could guarantee stability of overall system and attenuate effect of uncertainty of model and approximation errors of neural networks to a prescribed level. Finally, simulation results show the effectiveness of the control method.
Yang Zhifeng, Lei Humin, Li Qingliang, Li Jiong.Design of sliding model and dynamic inverse control law for a missile based on RBF neural-networks[J] JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2011,V37(2): 167-170
Zeng Xianfa,Zhang Lei,Shen Gongzhang.Design of control system for missiles based on dynamic inversion and decentralized control[J].Journal of Beijing University of Aeronautics and Astronautics,2007,33(11):1303-1307(in Chinese)