Hybrid recurrent neural network for nonlinear hybrid dynamical systems identification

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

This paper is devoted to the development of a Neural Network Hybrid Identification Framework for unknown Nonlinear Hybrid Dynamical Systems. The proposal is based in the well known Recurrent Trainable Neural Networks Identifiers. In a first instance, the unknown hybrid system is considered like a black-box where by using only hybrid input-output data an approximated model is found. In a second instance, by considering that the hybrid output of the unknown hybrid system is triggered by a defined set of hypersurfaces we extent the approach identification by introducing a Hybrid Recurrent Trainable Neural Network Identifier. The effectiveness of the proposed approach is shown using a commutable pendulum example.

Original languageEnglish
Title of host publicationCCE 2011 - 2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, Program and Abstract Book
DOIs
StatePublished - 2011
Event2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2011 - Merida, Yucatan, Mexico
Duration: 26 Oct 201128 Oct 2011

Publication series

NameCCE 2011 - 2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, Program and Abstract Book

Conference

Conference2011 8th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2011
Country/TerritoryMexico
CityMerida, Yucatan
Period26/10/1128/10/11

Fingerprint

Dive into the research topics of 'Hybrid recurrent neural network for nonlinear hybrid dynamical systems identification'. Together they form a unique fingerprint.

Cite this