Multilayer discrete-time neural-net controller with guaranteed performance
- 1 January 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (1) , 107-130
- https://doi.org/10.1109/72.478396
Abstract
A family of novel multilayer discrete-time neural-net (NN) controllers is presented for the control of a class of multi-input multi-output (MIMO) dynamical systems. The neural net controller includes modified delta rule weight tuning and exhibits a learning while-functioning-features. The structure of the NN controller is derived using a filtered error/passivity approach. Linearity in the parameters is not required and certainty equivalence is not used. This overcomes several limitations of standard adaptive control. The notion of persistency of excitation (PE) for multilayer NN is defined and explored. New online improved tuning algorithms for discrete-time systems are derived, which are similar to /spl sigma/ or /spl epsiv/-modification for the case of continuous-time systems, that include a modification to the learning rate parameter plus a correction term. These algorithms guarantee tracking as well as bounded NN weights in nonideal situations so that PE is not needed. An extension of these novel weight tuning updates to NN with an arbitrary number of hidden layers is discussed. The notions of discrete-time passive NN, dissipative NN, and robust NN are introduced. The NN makes the closed-loop system passive.Keywords
This publication has 18 references indexed in Scilit:
- Discrete-time neural net controller with guaranteed performancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Stable adaptive control and recursive identification using radial Gaussian networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Evolution of Adaptive ControlJournal of Dynamic Systems, Measurement, and Control, 1993
- A perceptron network for functional identification and control of nonlinear systemsIEEE Transactions on Neural Networks, 1993
- Convergence and divergence in neural networks: Processing of chaos and biological analogyNeural Networks, 1992
- Universal Approximation Using Radial-Basis-Function NetworksNeural Computation, 1991
- The adaptation of perceptrons with applications to inverse dynamics identification of unknown dynamic systemsIEEE Transactions on Systems, Man, and Cybernetics, 1991
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- A new adaptive law for robust adaptation without persistent excitationIEEE Transactions on Automatic Control, 1987
- Robustness of discrete-time direct adaptive controllersIEEE Transactions on Automatic Control, 1985