Neural modeling of dynamic systems with nonmeasurable state variables

Abstract

The paper studies the ability possessed by recurrent neural networks to model dynamic systems when some relevant state variables are not measurable. Neural architectures based on virtual states—which naturally arise from a space state representation—are introduced and compared with the more traditional neural output error ones. Despite the evident potential… (More)
DOI: 10.1109/19.816116

Topics

9 Figures and Tables

Cite this paper

@article{Alippi1999NeuralMO, title={Neural modeling of dynamic systems with nonmeasurable state variables}, author={Cesare Alippi and Vincenzo Piuri}, journal={IEEE Trans. Instrumentation and Measurement}, year={1999}, volume={48}, pages={1073-1080} }