Novel Neural Control for a Class of Uncertain Pure-Feedback Systems

• Published in: IEEE transaction on neural networks and learning systems Vol. 25; no. 4; pp. 718 - 727
• Main Authors: Shen, Qikun, Shi, Peng, Zhang, Tianping, Lim, Cheng-Chew
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.04.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptative systems; Adaptive control; Adaptive control systems; Adaptive systems; Algorithms; Applied sciences; Approximation methods; Artificial neural networks; Backstepping; Computer science; control theory; systems; Computer Simulation; Control system analysis; Control system synthesis; Control systems; Control theory. Systems; Derivatives; Design engineering; Dynamical systems; Exact sciences and technology; Feedback; Learning; Models, Statistical; neural control; Neural networks; Neural Networks (Computer); Nonlinear Dynamics; Nonlinear systems; Pattern Recognition, Automated - methods; pure feedback; Silicon; Trajectory; Control program; Non linear control; Feedback regulation; Control synthesis; Tracking task; neural control; Neural network; Non linear system; Recursive algorithm; Adaptive control; Backstepping control; Robust control; Radial basis function; Neurocontrollers; Uncertain system; pure feedback; Optimal trajectory; Derivative; Tracking error; Implicit function theorem; Derivative control; Intelligent control; Lyapunov function
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2013.2280728

This paper is concerned with the problem of adaptive neural tracking control for a class of uncertain pure-feedback nonlinear systems. Using the implicit function theorem and backstepping technique, a practical robust adaptive neural control scheme is proposed to guarantee that the tracking error converges to an adjusted neighborhood of the origin by choosing appropriate design parameters. In contrast to conventional Lyapunov-based design techniques, an alternative Lyapunov function is constructed for the development of control law and learning algorithms. Differing from the existing results in the literature, the control scheme does not need to compute the derivatives of virtual control signals at each step in backstepping design procedures. Furthermore, the scheme requires the desired trajectory and its first derivative rather than its first n derivatives. In addition, the useful property of the basis function of the radial basis function, which will be used in control design, is explored. Simulation results illustrate the effectiveness of the proposed techniques.