Stable neural controller design for unknown nonlinear systems using backstepping

Youping Zhang, Pei Yaun Peng, Zhong-Ping Jiang

Research output: Contribution to journalArticle

Abstract

Despite the vast development of neural controllers in the literature, their stability properties are usually addressed inadequately. With most neural control schemes, the choices of neural-network structure, initial weights, and training speed are often nonsystematic, due to the lack of understanding of the stability behavior of the closed-loop system. In this paper, we propose, from an adaptive control perspective, a neural controller for a class of unknown, minimum phase, feedback linearizable nonlinear system with known relative degree. The control scheme is based on the backstepping design technique in conjunction with a linearly parameterized neural-network structure. The resulting controller, however, moves the complex mechanics involved in a typical backstepping design from offline to online. With appropriate choice of the network size and neural basis functions, the same controller can be trained online to control different nonlinear plants with the same relative degree, with semiglobal stability as shown by simple Lyapunov analysis. Meanwhile, the controller also preserves some of the performance properties of the standard backstepping controllers. Simulation results are shown to demonstrate these properties and to compare the neural controller with a standard backstepping controller.

Original languageEnglish (US)
Pages (from-to)1347-1360
Number of pages14
JournalIEEE Transactions on Neural Networks
Volume11
Issue number6
DOIs
StatePublished - 2000

Fingerprint

Backstepping
Controller Design
Nonlinear systems
Nonlinear Systems
Controller
Unknown
Controllers
Backstepping Design
Network Structure
Neural Networks
Neural networks
Neural Control
Feedback Systems
Closed loop systems
Adaptive Control
Lyapunov
Closed-loop System
Mechanics
Basis Functions
Linearly

Keywords

  • Backstepping
  • Nonlinear system
  • Stability

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture

Cite this

Stable neural controller design for unknown nonlinear systems using backstepping. / Zhang, Youping; Peng, Pei Yaun; Jiang, Zhong-Ping.

In: IEEE Transactions on Neural Networks, Vol. 11, No. 6, 2000, p. 1347-1360.

Research output: Contribution to journalArticle

@article{f86b47b07de845028d20d43b4a4c12b5,
title = "Stable neural controller design for unknown nonlinear systems using backstepping",
abstract = "Despite the vast development of neural controllers in the literature, their stability properties are usually addressed inadequately. With most neural control schemes, the choices of neural-network structure, initial weights, and training speed are often nonsystematic, due to the lack of understanding of the stability behavior of the closed-loop system. In this paper, we propose, from an adaptive control perspective, a neural controller for a class of unknown, minimum phase, feedback linearizable nonlinear system with known relative degree. The control scheme is based on the backstepping design technique in conjunction with a linearly parameterized neural-network structure. The resulting controller, however, moves the complex mechanics involved in a typical backstepping design from offline to online. With appropriate choice of the network size and neural basis functions, the same controller can be trained online to control different nonlinear plants with the same relative degree, with semiglobal stability as shown by simple Lyapunov analysis. Meanwhile, the controller also preserves some of the performance properties of the standard backstepping controllers. Simulation results are shown to demonstrate these properties and to compare the neural controller with a standard backstepping controller.",
keywords = "Backstepping, Nonlinear system, Stability",
author = "Youping Zhang and Peng, {Pei Yaun} and Zhong-Ping Jiang",
year = "2000",
doi = "10.1109/72.883443",
language = "English (US)",
volume = "11",
pages = "1347--1360",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "6",

}

TY - JOUR

T1 - Stable neural controller design for unknown nonlinear systems using backstepping

AU - Zhang, Youping

AU - Peng, Pei Yaun

AU - Jiang, Zhong-Ping

PY - 2000

Y1 - 2000

N2 - Despite the vast development of neural controllers in the literature, their stability properties are usually addressed inadequately. With most neural control schemes, the choices of neural-network structure, initial weights, and training speed are often nonsystematic, due to the lack of understanding of the stability behavior of the closed-loop system. In this paper, we propose, from an adaptive control perspective, a neural controller for a class of unknown, minimum phase, feedback linearizable nonlinear system with known relative degree. The control scheme is based on the backstepping design technique in conjunction with a linearly parameterized neural-network structure. The resulting controller, however, moves the complex mechanics involved in a typical backstepping design from offline to online. With appropriate choice of the network size and neural basis functions, the same controller can be trained online to control different nonlinear plants with the same relative degree, with semiglobal stability as shown by simple Lyapunov analysis. Meanwhile, the controller also preserves some of the performance properties of the standard backstepping controllers. Simulation results are shown to demonstrate these properties and to compare the neural controller with a standard backstepping controller.

AB - Despite the vast development of neural controllers in the literature, their stability properties are usually addressed inadequately. With most neural control schemes, the choices of neural-network structure, initial weights, and training speed are often nonsystematic, due to the lack of understanding of the stability behavior of the closed-loop system. In this paper, we propose, from an adaptive control perspective, a neural controller for a class of unknown, minimum phase, feedback linearizable nonlinear system with known relative degree. The control scheme is based on the backstepping design technique in conjunction with a linearly parameterized neural-network structure. The resulting controller, however, moves the complex mechanics involved in a typical backstepping design from offline to online. With appropriate choice of the network size and neural basis functions, the same controller can be trained online to control different nonlinear plants with the same relative degree, with semiglobal stability as shown by simple Lyapunov analysis. Meanwhile, the controller also preserves some of the performance properties of the standard backstepping controllers. Simulation results are shown to demonstrate these properties and to compare the neural controller with a standard backstepping controller.

KW - Backstepping

KW - Nonlinear system

KW - Stability

UR - http://www.scopus.com/inward/record.url?scp=0000922214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000922214&partnerID=8YFLogxK

U2 - 10.1109/72.883443

DO - 10.1109/72.883443

M3 - Article

VL - 11

SP - 1347

EP - 1360

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 6

ER -