CONTROL OF COMPLEX DUNAMIC SYSTEMS BY NEURAL NGWORKS 14

This paper considers the use of neural networks (NN's) in controlling a nonlinear, stochastic system with unknown process equations. The NN is used to model the resulting unknown control law. The approach here is based on using the output error of the system to train the NN controller without the need to construct a separate model (NN or other type) for the unknown process dynamics. To implement such a direct adaptive control approach, it is required that connection weights in the NN be estimated while the system is being controlled. As a result of the feedback of the unknown process dynamics, however, it is not possible to determine the gradient of the loss function for use in standard (back-propagation-type) weight estimation algorithms. Therefore, this paper considers the use of a new stochastic approximation algorithm for this weight estimation, which is based on a "simultaneous perturbation" gradient approximation that only requires the system output error. It is shown that this algorithm can greatly enhance the efficiency over more standard stochastic approximation algorithms based on finite-difference gradient approximations.

[1]  A. Benveniste,et al.  A measure of the tracking capability of recursive stochastic algorithms with constant gains , 1982 .

[2]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[3]  A. Isidori,et al.  Output regulation of nonlinear systems , 1990 .

[4]  Kurt Hornik,et al.  Convergence of learning algorithms with constant learning rates , 1991, IEEE Trans. Neural Networks.

[5]  E. Eweda,et al.  Second-order convergence analysis of stochastic adaptive linear filtering , 1983 .

[6]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[7]  Daniel Sbarbaro,et al.  Neural Networks for Nonlinear Internal Model Control , 1991 .

[8]  S. Evans,et al.  On the almost sure convergence of a general stochastic approximation procedure , 1986, Bulletin of the Australian Mathematical Society.

[9]  F.-C. Chen,et al.  Back-propagation neural networks for nonlinear self-tuning adaptive control , 1990, IEEE Control Systems Magazine.

[10]  Hideaki Sakai,et al.  A nonlinear regulator design in the presence of system uncertainties using multilayered neural network , 1991, IEEE Trans. Neural Networks.

[11]  George N. Saridis,et al.  Self-organizing control of stochastic systems , 1977 .

[12]  D. S. Bayard.  A forward method for optimal stochastic nonlinear and adaptive control , 1991 .

[13]  T. Soderstrom,et al.  Stationary performance of linear stochastic systems under single step optimal control , 1982 .

[14]  Alexander Linden.  Iterative inversion of neural networks and its applications , 1997 .

[15]  Kumpati S. Narendra,et al.  Gradient methods for the optimization of dynamical systems containing neural networks , 1991, IEEE Trans. Neural Networks.

[16]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[17]  D. C. Chin,et al.  A more efficient global optimization algorithm based on Styblinski and Tang , 1994, Neural Networks.

[18]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[19]  J. Spall.  A stochastic approximation algorithm for large-dimensional systems in the Kiefer-Wolfowitz setting , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[20]  Ivan Ganchev Ivanov.  Stochastic Modeling and Control , 2012 .

[21]  Yih-Fang Huang,et al.  Bounds on the number of hidden neurons in multilayer perceptrons , 1991, IEEE Trans. Neural Networks.

[22]  J. Spall,et al.  Nonlinear adaptive control using neural networks: estimation with a smoothed form of simultaneous perturbation gradient approximation , 1994, Proceedings of 1994 American Control Conference - ACC '94.