A new neural state observer for non linear plants is proposed. Using a dynamical backpropagation learning algorithm, a non linear dynamical system, the neural observer, is built in order to reproduce the input/output behaviour of an unknown non linear plant and to give us an estimation by the output of the plant state. A straightforward example illustrates the proposed technique. Simulation results seem to be attractive.
Adaptive neural state observer for unknown nonlinear plants
BICCHI, ANTONIO;LANDI, ALBERTO;
1992-01-01
Abstract
A new neural state observer for non linear plants is proposed. Using a dynamical backpropagation learning algorithm, a non linear dynamical system, the neural observer, is built in order to reproduce the input/output behaviour of an unknown non linear plant and to give us an estimation by the output of the plant state. A straightforward example illustrates the proposed technique. Simulation results seem to be attractive.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
