Skip to main navigation Skip to search Skip to main content

A novel model predictive control strategy in modified PLS framework

  • School of Astronautics, Harbin Institute of Technology

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

Abstract

A data-driven model predictive control (MPC) in modified partial least squares (PLS) framework is proposed in this paper after a brief summary of MPC strategy in PLS framework. A theoretical comparison between data-driven MPC strategy in these two framework is presented, which demonstrates that MPC in modified PLS framework benefits in both computation complexity and robustness. The feature of modeling rapidly makes it possible to update the correlation model online. The reliability of the model is guaranteed by the model update strategy to a certain degree. Performance of the proposed control strategy is verified through simulations of a numerical example. It can be illuminated from the simulation that the proposed method performances well.

Original languageEnglish
Title of host publication7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages105-110
Number of pages6
ISBN (Electronic)9781509021550
DOIs
StatePublished - 23 Mar 2017
Externally publishedYes
Event7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Siem Reap, Cambodia
Duration: 1 Dec 20164 Dec 2016

Publication series

Name7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings

Conference

Conference7th International Conference on Intelligent Control and Information Processing, ICICIP 2016
Country/TerritoryCambodia
CitySiem Reap
Period1/12/164/12/16

Keywords

  • Data-driven
  • Model predictive control (MPC)
  • Modified partial least squares(PLS)

Fingerprint

Dive into the research topics of 'A novel model predictive control strategy in modified PLS framework'. Together they form a unique fingerprint.

Cite this