Design and performance analysis of deterministic learning of sampled-data nonlinear systems

In this paper, we extend the deterministic learning theory to sampled-data nonlinear systems. Based on the Euler approximate model, the adaptive neural network identifier with a normalized learning algorithm is proposed. It is proven that by properly setting the sampling period, the overall system can be guaranteed to be stable and partial neural network weights can exponentially converge to their optimal values under the satisfaction of the partial persistent excitation (PE) condition. Consequently, locally accurate learning of the nonlinear dynamics can be achieved, and the knowledge can be represented by using constant-weight neural networks. Furthermore, we present a performance analysis for the learning algorithm by developing explicit bounds on the learning rate and accuracy. Several factors that influence learning, including the PE level, the learning gain, and the sampling period, are investigated. Simulation studies are included to demonstrate the effectiveness of the approach.

[1]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

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

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

[4]  K. Narendra,et al.  An identification procedure for discrete multivariable systems , 1974 .

[5]  Cong Wang,et al.  Persistency of excitation and performance of deterministic learning , 2011, Proceedings of the 30th Chinese Control Conference.

[6]  Jagannathan Sarangapani,et al.  Neural Network Control of Nonlinear Discrete-Time Systems , 2018 .

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

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

[9]  Gang Tao,et al.  Persistency of excitation and overparameterization in model reference adaptive control , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[10]  R..  Lyapunov Techniques for the Exponential Stability of Linear Difference Equations with Random Coefficients , 2022 .

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

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

[13]  Cong Wang,et al.  DETERMINISTIC LEARNING AND RAPID DYNAMICAL PATTERN RECOGNITION , 2005 .

[14]  O. Rössler.  An equation for continuous chaos , 1976 .

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

[16]  Cong Wang,et al.  Deterministic Learning and Rapid Dynamical Pattern Recognition , 2007, IEEE Transactions on Neural Networks.

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

[18]  Frank L. Lewis,et al.  Identification of nonlinear dynamical systems using multilayered neural networks , 1996, Autom..

[19]  Cong Wang,et al.  Deterministic learning and robot manipulator control , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[20]  Cong Wang,et al.  Rapid detection of oscillation faults via deterministic learning , 2010, IEEE ICCA 2010.

[21]  Alex Simpkins,et al.  System Identification: Theory for the User, 2nd Edition (Ljung, L.; 1999) [On the Shelf] , 2012, IEEE Robotics & Automation Magazine.

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

[23]  C. Richard Johnson,et al.  Exponential convergence of adaptive identification and control algorithms , 1981, Autom..

[24]  Cong Wang,et al.  Deterministic Learning and Data-based Modeling and Control: Deterministic Learning and Data-based Modeling and Control , 2009 .

[25]  M. Gevers,et al.  A personal view of the development of system identification: A 30-year journey through an exciting field , 2006, IEEE Control Systems.

[26]  James Ting-Ho Lo,et al.  Finite-dimensional sensor orbits and optimal nonlinear filtering , 1972, IEEE Trans. Inf. Theory.

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

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

[29]  Alan Weiss,et al.  Digital adaptive filters: Conditions for convergence, rates of convergence, effects of noise and errors arising from the implementation , 1979, IEEE Trans. Inf. Theory.

[30]  Weifeng Liu,et al.  Adaptive and Learning Systems for Signal Processing, Communication, and Control , 2010 .

[31]  Cong Wang,et al.  Deterministic Learning and Rapid Dynamical Pattern Recognition of Discrete-Time Systems , 2008, 2008 IEEE International Symposium on Intelligent Control.

[32]  E. Bai,et al.  Persistency of excitation, sufficient richness and parameter convergence in discrete time adaptive control☆ , 1985 .

[33]  Chen Tian,et al.  Deterministic Learning and Data-based Modeling and Control , 2009 .

[34]  Songwu Lu,et al.  Robust nonlinear system identification using neural-network models , 1998, IEEE Trans. Neural Networks.

[35]  B. Anderson,et al.  Exponential convergence of adaptive identification and control algorithms , 1981, Autom..

[36]  Anuradha M. Annaswamy,et al.  Robust Adaptive Control , 1984, 1984 American Control Conference.

[37]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[38]  Petros A. Ioannou,et al.  Robust Adaptive Control , 2012 .

[39]  Brian D. O. Anderson,et al.  Stability of adaptive systems: passivity and averaging analysis , 1986 .

[40]  M. Sondhi,et al.  New results on the performance of a well-known class of adaptive filters , 1976, Proceedings of the IEEE.

[41]  Manolis A. Christodoulou,et al.  Dynamical Neural Networks that Ensure Exponential Identification Error Convergence , 1997, Neural Networks.