Radial-basis-functions neural network sliding mode control for underactuated mechanical systems

Sonia Mahjoub, Faisal Mnif, Nabil Derbel, Mustapha Hamerlain

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper presents an indirect adaptive neural network sliding mode Control (IANSMC) technique and a neural network sliding mode control (NNSMC) for underactuated robot manipulators. The adaptive neural network (NN) based on radial basis functions (RBF) is used to estimate the equivalent control and to compensate model uncertainties. In IANSMC, the adaptive learning algorithms are derived using Lyapunov stability analysis. Sliding mode control and indirect adaptive technique are combined to deal with modeling parameter uncertainties and bounded disturbances. The stability of the mixed controller is then proved. NN parameters are tuned on-line, without an off-line learning phase. For the NNSMC, the NN control is used to learn the equivalent control due to the unknown nonlinear system dynamics and the robust sliding mode control (SMC) is designed for a trajectory tracking control. Simulation results show that the NNSMC and IANSMC are better than the classical SMC to control underactuated manipulators. Although the proposed controllers can eliminate the chattering phenomena and estimate matching uncertainties. The IANSMC can also reject mismatched perturbations. Discussions and comparisons between proposed controllers are presented.

Original languageEnglish
Pages (from-to)533-541
Number of pages9
JournalInternational Journal of Dynamics and Control
Volume2
Issue number4
DOIs
Publication statusPublished - Dec 1 2014

Fingerprint

Underactuated Mechanical Systems
Radial Basis Function Neural Network
Sliding mode control
Sliding Mode Control
Neural networks
Neural Networks
Controller
Controllers
Manipulators
Neural Network Control
Adaptive Techniques
Chattering
Adaptive Learning
Robot Manipulator
Nonlinear Dynamic System
Trajectory Tracking
Lyapunov Stability
Model Uncertainty
Parameter Uncertainty
Tracking Control

Keywords

  • Indirect adaptive
  • Lyapunov stability
  • Neural networks
  • Sliding mode control
  • Underactuated manipulator

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Modelling and Simulation

Cite this

Radial-basis-functions neural network sliding mode control for underactuated mechanical systems. / Mahjoub, Sonia; Mnif, Faisal; Derbel, Nabil; Hamerlain, Mustapha.

In: International Journal of Dynamics and Control, Vol. 2, No. 4, 01.12.2014, p. 533-541.

Research output: Contribution to journalArticle

@article{fb7a31493d5f4aa5a7f4a1270c76bc6b,
title = "Radial-basis-functions neural network sliding mode control for underactuated mechanical systems",
abstract = "This paper presents an indirect adaptive neural network sliding mode Control (IANSMC) technique and a neural network sliding mode control (NNSMC) for underactuated robot manipulators. The adaptive neural network (NN) based on radial basis functions (RBF) is used to estimate the equivalent control and to compensate model uncertainties. In IANSMC, the adaptive learning algorithms are derived using Lyapunov stability analysis. Sliding mode control and indirect adaptive technique are combined to deal with modeling parameter uncertainties and bounded disturbances. The stability of the mixed controller is then proved. NN parameters are tuned on-line, without an off-line learning phase. For the NNSMC, the NN control is used to learn the equivalent control due to the unknown nonlinear system dynamics and the robust sliding mode control (SMC) is designed for a trajectory tracking control. Simulation results show that the NNSMC and IANSMC are better than the classical SMC to control underactuated manipulators. Although the proposed controllers can eliminate the chattering phenomena and estimate matching uncertainties. The IANSMC can also reject mismatched perturbations. Discussions and comparisons between proposed controllers are presented.",
keywords = "Indirect adaptive, Lyapunov stability, Neural networks, Sliding mode control, Underactuated manipulator",
author = "Sonia Mahjoub and Faisal Mnif and Nabil Derbel and Mustapha Hamerlain",
year = "2014",
month = "12",
day = "1",
doi = "10.1007/s40435-014-0070-0",
language = "English",
volume = "2",
pages = "533--541",
journal = "International Journal of Dynamics and Control",
issn = "2195-268X",
publisher = "Springer International Publishing AG",
number = "4",

}

TY - JOUR

T1 - Radial-basis-functions neural network sliding mode control for underactuated mechanical systems

AU - Mahjoub, Sonia

AU - Mnif, Faisal

AU - Derbel, Nabil

AU - Hamerlain, Mustapha

PY - 2014/12/1

Y1 - 2014/12/1

N2 - This paper presents an indirect adaptive neural network sliding mode Control (IANSMC) technique and a neural network sliding mode control (NNSMC) for underactuated robot manipulators. The adaptive neural network (NN) based on radial basis functions (RBF) is used to estimate the equivalent control and to compensate model uncertainties. In IANSMC, the adaptive learning algorithms are derived using Lyapunov stability analysis. Sliding mode control and indirect adaptive technique are combined to deal with modeling parameter uncertainties and bounded disturbances. The stability of the mixed controller is then proved. NN parameters are tuned on-line, without an off-line learning phase. For the NNSMC, the NN control is used to learn the equivalent control due to the unknown nonlinear system dynamics and the robust sliding mode control (SMC) is designed for a trajectory tracking control. Simulation results show that the NNSMC and IANSMC are better than the classical SMC to control underactuated manipulators. Although the proposed controllers can eliminate the chattering phenomena and estimate matching uncertainties. The IANSMC can also reject mismatched perturbations. Discussions and comparisons between proposed controllers are presented.

AB - This paper presents an indirect adaptive neural network sliding mode Control (IANSMC) technique and a neural network sliding mode control (NNSMC) for underactuated robot manipulators. The adaptive neural network (NN) based on radial basis functions (RBF) is used to estimate the equivalent control and to compensate model uncertainties. In IANSMC, the adaptive learning algorithms are derived using Lyapunov stability analysis. Sliding mode control and indirect adaptive technique are combined to deal with modeling parameter uncertainties and bounded disturbances. The stability of the mixed controller is then proved. NN parameters are tuned on-line, without an off-line learning phase. For the NNSMC, the NN control is used to learn the equivalent control due to the unknown nonlinear system dynamics and the robust sliding mode control (SMC) is designed for a trajectory tracking control. Simulation results show that the NNSMC and IANSMC are better than the classical SMC to control underactuated manipulators. Although the proposed controllers can eliminate the chattering phenomena and estimate matching uncertainties. The IANSMC can also reject mismatched perturbations. Discussions and comparisons between proposed controllers are presented.

KW - Indirect adaptive

KW - Lyapunov stability

KW - Neural networks

KW - Sliding mode control

KW - Underactuated manipulator

UR - http://www.scopus.com/inward/record.url?scp=84975263718&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975263718&partnerID=8YFLogxK

U2 - 10.1007/s40435-014-0070-0

DO - 10.1007/s40435-014-0070-0

M3 - Article

AN - SCOPUS:84975263718

VL - 2

SP - 533

EP - 541

JO - International Journal of Dynamics and Control

JF - International Journal of Dynamics and Control

SN - 2195-268X

IS - 4

ER -