Title :
A general structure for neurocontrol of dynamical systems
Author :
Tanomaru, Julio ; Takahashi, Yoshizo
Author_Institution :
Fac. of Eng., Tokushima Univ., Japan
Abstract :
A novel neurocontrol configuration consisting of three multilayer neural networks (MNNs) is proposed for nonlinear MIMO plants. Two MNNs, one with feedback inputs and the other without feedback, are used to perform plant identification based on a generalized state variable model for plant representation. The remaining MNN acts as a feedforward controller, by taking advantage of the state information generated as a by-product of the identification process. No hypothesis about the plant invertibility is assumed, overcoming the main drawback of most neurocontrol schemes suggested in the literature so far. The proposed configuration is very general, and only a few parameters must be user-specified. Training algorithms are provided in pseudocode and preliminary results attest the practicability and effectiveness of the proposed scheme
Keywords :
feedback; feedforward neural nets; identification; learning (artificial intelligence); multivariable systems; nonlinear systems; dynamical systems; feedback; feedforward controller; identification; learning algorithm; multilayer neural networks; neurocontrol; nonlinear MIMO plants; state variable model; Adaptive control; Artificial neural networks; Electronic mail; MIMO; Multi-layer neural network; Neural networks; Neurofeedback; Process control; Programmable control; State feedback;
Conference_Titel :
Industrial Electronics, Control, and Instrumentation, 1993. Proceedings of the IECON '93., International Conference on
Conference_Location :
Maui, HI
Print_ISBN :
0-7803-0891-3
DOI :
10.1109/IECON.1993.339062
