Observer-based adaptive neural optimal control for discrete-time systems in nonstrict-feedback form

Shiyi Zhao, Hongjing Liang, Choon Ki Ahn, Peihao Du

Research output: Contribution to journalArticle

Abstract

This paper considers the problem of observer-based adaptive near-optimal control for a class of nonstrict-feedback discrete-time nonlinear systems with non-symmetric dead zone. In order to compensate the effect of dead-zone on the control performance, an adaptive auxiliary signal is constructed to estimate the unknown dead-zone parameters. For the unknown nonlinear functions, neural networks (NNs)are introduced to identify them and to estimate the unknown parameters. To resolve the difficulty resulting from the unavailable state variables, an NN-based observer is designed. Moreover, according to the framework of adaptive control, a novel reinforcement learning algorithm is developed to guarantee that the near-optimal control performance is achieved. Finally, some simulation results are provided to illustrate the effectiveness of the proposed control algorithm.

Original languageEnglish
JournalNeurocomputing
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Feedback
Learning
Neural networks
Reinforcement learning
Learning algorithms
Nonlinear systems
Reinforcement (Psychology)

Keywords

  • Adaptive near-optimal control
  • Backstepping control
  • Dead-zone input
  • Nonstrict-feedback nonlinear system

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

Observer-based adaptive neural optimal control for discrete-time systems in nonstrict-feedback form. / Zhao, Shiyi; Liang, Hongjing; Ahn, Choon Ki; Du, Peihao.

In: Neurocomputing, 01.01.2019.

Research output: Contribution to journalArticle

@article{a1288225002a4d979371be4d690b6690,
title = "Observer-based adaptive neural optimal control for discrete-time systems in nonstrict-feedback form",
abstract = "This paper considers the problem of observer-based adaptive near-optimal control for a class of nonstrict-feedback discrete-time nonlinear systems with non-symmetric dead zone. In order to compensate the effect of dead-zone on the control performance, an adaptive auxiliary signal is constructed to estimate the unknown dead-zone parameters. For the unknown nonlinear functions, neural networks (NNs)are introduced to identify them and to estimate the unknown parameters. To resolve the difficulty resulting from the unavailable state variables, an NN-based observer is designed. Moreover, according to the framework of adaptive control, a novel reinforcement learning algorithm is developed to guarantee that the near-optimal control performance is achieved. Finally, some simulation results are provided to illustrate the effectiveness of the proposed control algorithm.",
keywords = "Adaptive near-optimal control, Backstepping control, Dead-zone input, Nonstrict-feedback nonlinear system",
author = "Shiyi Zhao and Hongjing Liang and Ahn, {Choon Ki} and Peihao Du",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.neucom.2019.03.029",
language = "English",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - Observer-based adaptive neural optimal control for discrete-time systems in nonstrict-feedback form

AU - Zhao, Shiyi

AU - Liang, Hongjing

AU - Ahn, Choon Ki

AU - Du, Peihao

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper considers the problem of observer-based adaptive near-optimal control for a class of nonstrict-feedback discrete-time nonlinear systems with non-symmetric dead zone. In order to compensate the effect of dead-zone on the control performance, an adaptive auxiliary signal is constructed to estimate the unknown dead-zone parameters. For the unknown nonlinear functions, neural networks (NNs)are introduced to identify them and to estimate the unknown parameters. To resolve the difficulty resulting from the unavailable state variables, an NN-based observer is designed. Moreover, according to the framework of adaptive control, a novel reinforcement learning algorithm is developed to guarantee that the near-optimal control performance is achieved. Finally, some simulation results are provided to illustrate the effectiveness of the proposed control algorithm.

AB - This paper considers the problem of observer-based adaptive near-optimal control for a class of nonstrict-feedback discrete-time nonlinear systems with non-symmetric dead zone. In order to compensate the effect of dead-zone on the control performance, an adaptive auxiliary signal is constructed to estimate the unknown dead-zone parameters. For the unknown nonlinear functions, neural networks (NNs)are introduced to identify them and to estimate the unknown parameters. To resolve the difficulty resulting from the unavailable state variables, an NN-based observer is designed. Moreover, according to the framework of adaptive control, a novel reinforcement learning algorithm is developed to guarantee that the near-optimal control performance is achieved. Finally, some simulation results are provided to illustrate the effectiveness of the proposed control algorithm.

KW - Adaptive near-optimal control

KW - Backstepping control

KW - Dead-zone input

KW - Nonstrict-feedback nonlinear system

UR - http://www.scopus.com/inward/record.url?scp=85064656796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064656796&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2019.03.029

DO - 10.1016/j.neucom.2019.03.029

M3 - Article

AN - SCOPUS:85064656796

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -