A recurrent neural-network-based real-time learning control strategy applying to nonlinear systems with unknown dynamics

In this paper, the authors present a real-time learning control scheme for unknown nonlinear dynamical systems using recurrent neural networks (RNNs). Two RNNs, based on the same network architecture, are utilized in the learning control system. One is used to approximate the nonlinear system, and the other is used to mimic the desired system response output. The learning rule is achieved by combining the two RNNs to form the neural network control system. A generalized real-time iterative learning algorithm is developed and used to train the RNNs. The algorithm is derived by means of two-dimensional (2-D) system theory that is different from the conventional algorithms that employ the steepest optimization to minimize a cost function. This paper shows that an RNN using the real-time iterative learning algorithm can approximate any trajectory tracking to a very high degree of accuracy. The proposed learning control scheme is applied to numerical problems, and simulation results are included. The results are very promising, and this paper suggests that the 2-D system theory-based RNN learning algorithm provides a new dimension in real-time neural control systems.

[1]  Barak A. Pearlmutter.  Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

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

[3]  U. R. Prasad,et al.  Back propagation through adjoints for the identification of nonlinear dynamic systems using recurrent neural models , 1994, IEEE Trans. Neural Networks.

[4]  Sun-Yuan Kung,et al.  New results in 2-D systems theory, part I: 2-D polynomial matrices, factorization, and coprimeness , 1977, Proceedings of the IEEE.

[5]  Oluseyi Olurotimi,et al.  Recurrent neural network training with feedforward complexity , 1994, IEEE Trans. Neural Networks.

[6]  Kwang Y. Lee,et al.  Improved nuclear reactor temperature control using diagonal recurrent neural networks , 1992 .

[7]  A. Isidori.  Nonlinear Control Systems , 1985 .

[8]  Madan M. Gupta,et al.  Dynamic Recurrent Neural Networks for Control of Unknown Nonlinear Systems , 1994 .

[9]  Kwang Y. Lee,et al.  Diagonal recurrent neural networks for dynamic systems control , 1995, IEEE Trans. Neural Networks.

[10]  Jerzy Klamka,et al.  Minimum energy control of 2-D linear systems with variable coefficients , 1986 .

[11]  J. Kurek,et al.  Iterative learning control synthesis based on 2-D system theory , 1993, IEEE Trans. Autom. Control..

[12]  Thierry Catfolis,et al.  A method for improving the real-time recurrent learning algorithm , 1993, Neural Networks.

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

[14]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[15]  T. Kaczorek.  Two-Dimensional Linear Systems , 1985 .

[16]  Malur K. Sundareshan,et al.  Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators , 1993, IEEE Trans. Neural Networks.

[17]  Sun-Yuan Kung,et al.  Digital neural networks , 1993, Prentice Hall Information and System Sciences Series.

[18]  M. Gupta,et al.  Approximation of discrete-time state-space trajectories using dynamic recurrent neural networks , 1995, IEEE Trans. Autom. Control..

[19]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.