Research Papers

Neural Network Adaptive Output Feedback Control of Flexible Link Manipulators

[+] Author and Article Information
A. Farmanbordar

Department of Electrical Engineering,
Islamic Azad University,
Borujerd Branch, 6915136111, Iran
e-mail: a.farmanbordar@gmail.com

S. M. Hoseini

Department of Electrical Engineering,
Malek Ashtar University of Technology,
Esfahan, 115-83145, Iran
e-mail: sm_hoseini@iust.ac.ir

Contributed by the Dynamic Systems Division of ASME for publication in the Journal of Dynamic Systems, Measurement, and Control. Manuscript received October 15, 2011; final manuscript received August 18, 2012; published online November 7, 2012. Assoc. Editor: Warren E. Dixon.

J. Dyn. Sys., Meas., Control 135(2), 021009 (Nov 07, 2012) (9 pages) Paper No: DS-11-1319; doi: 10.1115/1.4007701 History: Received October 15, 2011; Revised August 18, 2012

This paper presents an adaptive output-feedback control method based on neural networks for flexible link manipulator which is a nonlinear nonminimum phase system. The proposed controller comprises a linear, a neuro-adaptive, and an adaptive robustifying parts. The neural network is designed to approximate the matched uncertainty of the system. The inputs of the neural network are the tapped delays of the system input–output signals. In addition, an appropriate reference signal is proposed to compensate the unmatched uncertainty inherent in the internal system dynamics. The adaptation laws for the neural network weights and adaptive gains are obtained using the Lyapunov’s direct method. These adaptation laws employ a linear observer of system dynamics that is realizable. The ultimate boundedness of the error signals are analytically shown using Lyapunov's method.

Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Flexible link manipulator

Grahic Jump Location
Fig. 2

Block diagram of the augmented plant

Grahic Jump Location
Fig. 3

Block diagram of the proposed controller

Grahic Jump Location
Fig. 4

Response of the FLM closed-loop system without parameters uncertainty. Dotted line: linear optimal controller, solid line: the proposed controller.

Grahic Jump Location
Fig. 5

Response of the FLM system with parameters uncertainty. Dashed line: linear optimal controller, solid line: the proposed controller.

Grahic Jump Location
Fig. 6

Response of the FLM system with parameter uncertainty. (a) Matched uncertainty cancellation, (b) validation of unmatched uncertainty bound, (c) errors of estimation ξ˜, and (d) normalized norm of adaptive weights.

Grahic Jump Location
Fig. 7

Response of the FLM system with parameters uncertainty. Solid line: the proposed controller, dotted line: proposed control without unmatched uncertainty cancellation (yd = 0).




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In