Introducing a Model-free Adaptive Neural Network Auto-tuned Control Method for Nonlinear SISO Systems

Arash Mehrafrooz, Fangpo He

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

1 Citation (Scopus)

Abstract

In this study, a novel Adaptive Neural Networks Controller (ANNC) is proposed for controlling single-input single-output nonlinear systems. The proposed ANNC does not rely on an existing model of a system for its weights' training, and does make a full use of the history of the system input and output information for achieving a suitable control effect. The model of the system is used for checking the stability of the system after the calculation of the learning algorithm at each training step, and the controller weights are appropriately tuned to deliver a stable system during the entire training process. Using the accumulated gradient of the system error, the weights' adjustment convergence of the system can be observed and an optimal training number of the system can be selected. The effectiveness of the ANNC in controlling nonlinear industrial plants is demonstrated via simulation. The proposed control scheme provides a building block for the development of comparable schemes useful for more complicated systems involving multiple inputs and outputs.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Information and Automation, ICIA 2018
Place of PublicationNew Jersey, USA
PublisherInstitute of Electrical and Electronics Engineers
Pages1372-1378
Number of pages7
ISBN (Electronic)9781538680698
ISBN (Print)978-1-5386-8070-4
DOIs
Publication statusPublished - Aug 2018
EventInternational Conference on Information and Automation -
Duration: 11 Aug 2018 → …

Publication series

Name2018 IEEE International Conference on Information and Automation, ICIA 2018

Conference

ConferenceInternational Conference on Information and Automation
Period11/08/18 → …

Keywords

  • Accumulated gradient
  • Adaptive neural networks
  • Auto-tuning
  • Closed-loop stability
  • Error back-propagation
  • Model-free control
  • Nonlinear systems

Fingerprint

Dive into the research topics of 'Introducing a Model-free Adaptive Neural Network Auto-tuned Control Method for Nonlinear SISO Systems'. Together they form a unique fingerprint.

Cite this