Title :
Memory neuron networks for identification and control of dynamical systems
Author :
Sastry, P.S. ; Santharam, G. ; Unnikrishnan, K.P.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Sci., Bangalore, India
fDate :
3/1/1994 12:00:00 AM
Abstract :
This paper discusses memory neuron networks as models for identification and adaptive control of nonlinear dynamical systems. These are a class of recurrent networks obtained by adding trainable temporal elements to feedforward networks that makes the output history-sensitive. By virtue of this capability, these networks can identify dynamical systems without having to be explicitly fed with past inputs and outputs. Thus, they can identify systems whose order is unknown or systems with unknown delay. It is argued that for satisfactory modeling of dynamical systems, neural networks should be endowed with such internal memory. The paper presents a preliminary analysis of the learning algorithm, providing theoretical justification for the identification method. Methods for adaptive control of nonlinear systems using these networks are presented. Through extensive simulations, these models are shown to be effective both for identification and model reference adaptive control of nonlinear systems
Keywords :
adaptive control; feedforward neural nets; identification; model reference adaptive control systems; nonlinear control systems; nonlinear dynamical systems; recurrent neural nets; adaptive control; feedforward networks; identification; memory neuron networks; model reference adaptive control; nonlinear dynamical systems; recurrent networks; trainable temporal elements; Adaptive control; Artificial neural networks; Control system synthesis; Control systems; Feedforward systems; Neural networks; Neurons; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems;
Journal_Title :
Neural Networks, IEEE Transactions on