Learning from neural control of nonlinear systems in normal form

A deterministic learning theory was recently proposed which states that an appropriately designed adaptive neural controller can learn the system internal dynamics while attempting to control a class of simple nonlinear systems. In this paper, we investigate deterministic learning from adaptive neural control (ANC) of a class of nonlinear systems in normal form with unknown affine terms. The existence of the unknown affine terms makes it difficult to achieve learning by using previous methods. To overcome the difficulties, firstly, an extension of a recent result is presented on stability analysis of linear time-varying (LTV) systems. Then, with a state transformation, the closed-loop control system is transformed into a LTV form for which exponential stability can be guaranteed when a partial persistent excitation (PE) condition is satisfied. Accurate approximation of the closed-loop control system dynamics is achieved in a local region along a recurrent orbit of closed-loop signals. Consequently, learning of control system dynamics (i.e. closed-loop identification) from adaptive neural control of nonlinear systems with unknown affine terms is implemented.

[1]  L. Chua,et al.  Methods of Qualitative Theory in Nonlinear Dynamics (Part II) , 2001 .

[2]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[3]  Dimitry M. Gorinevsky,et al.  On the persistency of excitation in radial basis function network identification of nonlinear systems , 1995, IEEE Trans. Neural Networks.

[4]  Antonio Loría,et al.  Uniform exponential stability of linear time-varying systems: revisited , 2002, Syst. Control. Lett..

[5]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[6]  Miroslav Krstic,et al.  Nonlinear and adaptive control de-sign , 1995 .

[7]  Anuradha M. Annaswamy,et al.  Stable Adaptive Systems , 1989 .

[8]  Jay A. Farrell,et al.  Stability and approximator convergence in nonparametric nonlinear adaptive control , 1998, IEEE Trans. Neural Networks.

[9]  S. Sastry,et al.  Adaptive Control: Stability, Convergence and Robustness , 1989 .

[10]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[11]  Frank L. Lewis,et al.  Robust backstepping control of nonlinear systems using neural networks , 2000, IEEE Trans. Syst. Man Cybern. Part A.

[12]  Cong Wang,et al.  Learning from neural control in motor systems , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[13]  Shuzhi Sam Ge,et al.  Direct adaptive NN control of a class of nonlinear systems , 2002, IEEE Trans. Neural Networks.

[14]  M. Polycarpou,et al.  Stable adaptive tracking of uncertain systems using nonlinearly parametrized on-line approximators , 1998 .

[15]  Shuzhi Sam Ge,et al.  Adaptive neural control of uncertain MIMO nonlinear systems , 2004, IEEE Transactions on Neural Networks.

[16]  B. Anderson.  Exponential stability of linear equations arising in adaptive identification , 1977 .

[17]  Cong Wang,et al.  Learning from neural control , 2006, IEEE Transactions on Neural Networks.

[18]  F. J. Narcowich,et al.  Persistency of Excitation in Identification Using Radial Basis Function Approximants , 1995 .

[19]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[20]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[21]  Frank L. Lewis,et al.  Neural Network Control Of Robot Manipulators And Non-Linear Systems , 1998 .

[22]  David J. Hill,et al.  Deterministic Learning Theory , 2009 .

[23]  Marios M. Polycarpou,et al.  Modelling, Identification and Stable Adaptive Control of Continuous-Time Nonlinear Dynamical Systems Using Neural Networks , 1992, 1992 American Control Conference.

[24]  K. Narendra,et al.  On the Stability of Nonautonomous Differential Equations $\dot x = [A + B(t)]x$, with Skew Symmetric Matrix $B(t)$ , 1977 .