A Neuro-Fuzzy based framework for online nonlinear system identification

Paulo Gil, Tiago Oliveira, Luís Palma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper a new general recurrent state-space Neuro-Fuzzy model structure based on the combination of a modified Jordan network and an Adaptive Neuro-Fuzzy Inference System is proposed. The Neural-Fuzzy System's online training is carried out based on a Constrained Unscented Kalman Filter, where weights, membership functions and consequents are recursively updated. Results from a benchmark MIMO system demonstrate the applicability and effectiveness of the proposed framework.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
Pages248-253
Number of pages6
DOIs
Publication statusPublished - 18 Feb 2017
Event9th International Conference on Computer and Automation Engineering, ICCAE 2017 - Sydney, Australia
Duration: 18 Feb 201721 Feb 2017

Conference

Conference9th International Conference on Computer and Automation Engineering, ICCAE 2017
CountryAustralia
CitySydney
Period18/02/1721/02/17

Keywords

  • Kalman filter
  • Neuro-Fuzzy systems
  • Nonlinear system identification
  • Time-varying dynamics
  • Unscented transform

Fingerprint Dive into the research topics of 'A Neuro-Fuzzy based framework for online nonlinear system identification'. Together they form a unique fingerprint.

  • Cite this

    Gil, P., Oliveira, T., & Palma, L. (2017). A Neuro-Fuzzy based framework for online nonlinear system identification. In ACM International Conference Proceeding Series (pp. 248-253) https://doi.org/10.1145/3057039.3057068