Tracking of periodic oscillations in an underactuated system via adaptive neural networks

Sergio A. Puga-Guzmán, Carlos Aguilar-Avelar, Javier Moreno-Valenzuela, Víctor Santibáñez

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

© The Author(s) 2018. In this paper, the tracking control of periodic oscillations in an underactuated mechanical system is discussed. The proposed scheme is derived from the feedback linearization control technique and adaptive neural networks are used to estimate the unknown dynamics and to compensate uncertainties. The proposed neural network-based controller is applied to the Furuta pendulum, which is a nonlinear and nonminimum phase underactuated mechanical system with two degrees of freedom. The new neural network-based controller is experimentally compared with respect to its model-based version. Results indicated that the proposed neural algorithm performs better than the model-based controller, showing that the real-time adaptation of the neural network weights successfully estimates the unknown dynamics and compensates uncertainties in the experimental platform.
Original languageAmerican English
Pages (from-to)128-143
Number of pages113
JournalJournal of Low Frequency Noise Vibration and Active Control
DOIs
StatePublished - 1 Mar 2018

Fingerprint

oscillation
Neural networks
controllers
oscillations
Controllers
Feedback linearization
pendulums
linearization
estimates
Pendulums
platforms
degrees of freedom
Uncertainty
freedom

Cite this

@article{436fc549a550493b9583951c1b8c1fe5,
title = "Tracking of periodic oscillations in an underactuated system via adaptive neural networks",
abstract = "{\circledC} The Author(s) 2018. In this paper, the tracking control of periodic oscillations in an underactuated mechanical system is discussed. The proposed scheme is derived from the feedback linearization control technique and adaptive neural networks are used to estimate the unknown dynamics and to compensate uncertainties. The proposed neural network-based controller is applied to the Furuta pendulum, which is a nonlinear and nonminimum phase underactuated mechanical system with two degrees of freedom. The new neural network-based controller is experimentally compared with respect to its model-based version. Results indicated that the proposed neural algorithm performs better than the model-based controller, showing that the real-time adaptation of the neural network weights successfully estimates the unknown dynamics and compensates uncertainties in the experimental platform.",
author = "Puga-Guzm{\'a}n, {Sergio A.} and Carlos Aguilar-Avelar and Javier Moreno-Valenzuela and V{\'i}ctor Santib{\'a}{\~n}ez",
year = "2018",
month = "3",
day = "1",
doi = "10.1177/1461348417752988",
language = "American English",
pages = "128--143",
journal = "Journal of Low Frequency Noise Vibration and Active Control",
issn = "1461-3484",
publisher = "SAGE Publications Inc.",

}

Tracking of periodic oscillations in an underactuated system via adaptive neural networks. / Puga-Guzmán, Sergio A.; Aguilar-Avelar, Carlos; Moreno-Valenzuela, Javier; Santibáñez, Víctor.

In: Journal of Low Frequency Noise Vibration and Active Control, 01.03.2018, p. 128-143.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Tracking of periodic oscillations in an underactuated system via adaptive neural networks

AU - Puga-Guzmán, Sergio A.

AU - Aguilar-Avelar, Carlos

AU - Moreno-Valenzuela, Javier

AU - Santibáñez, Víctor

PY - 2018/3/1

Y1 - 2018/3/1

N2 - © The Author(s) 2018. In this paper, the tracking control of periodic oscillations in an underactuated mechanical system is discussed. The proposed scheme is derived from the feedback linearization control technique and adaptive neural networks are used to estimate the unknown dynamics and to compensate uncertainties. The proposed neural network-based controller is applied to the Furuta pendulum, which is a nonlinear and nonminimum phase underactuated mechanical system with two degrees of freedom. The new neural network-based controller is experimentally compared with respect to its model-based version. Results indicated that the proposed neural algorithm performs better than the model-based controller, showing that the real-time adaptation of the neural network weights successfully estimates the unknown dynamics and compensates uncertainties in the experimental platform.

AB - © The Author(s) 2018. In this paper, the tracking control of periodic oscillations in an underactuated mechanical system is discussed. The proposed scheme is derived from the feedback linearization control technique and adaptive neural networks are used to estimate the unknown dynamics and to compensate uncertainties. The proposed neural network-based controller is applied to the Furuta pendulum, which is a nonlinear and nonminimum phase underactuated mechanical system with two degrees of freedom. The new neural network-based controller is experimentally compared with respect to its model-based version. Results indicated that the proposed neural algorithm performs better than the model-based controller, showing that the real-time adaptation of the neural network weights successfully estimates the unknown dynamics and compensates uncertainties in the experimental platform.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85053607468&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85053607468&origin=inward

U2 - 10.1177/1461348417752988

DO - 10.1177/1461348417752988

M3 - Article

SP - 128

EP - 143

JO - Journal of Low Frequency Noise Vibration and Active Control

JF - Journal of Low Frequency Noise Vibration and Active Control

SN - 1461-3484

ER -