Technical Brief

Dynamic Neural Network-Based Output Feedback Tracking Control for Uncertain Nonlinear Systems

[+] Author and Article Information
Huyen T. Dinh

Department of Mechanical Engineering,
University of Transport and Communications,
Hanoi, Vietnam
e-mail: huyentdinh@utc.edu.vn

S. Bhasin

Department of Electrical Engineering,
Indian Institute of Technology,
Delhi, India
e-mail: sbhasin@ee.iitd.ac.in

R. Kamalapurkar

School of Mechanical and Aerospace Engineering,
Oklahoma State University,
Stillwater, OK 74074
e-mail: rushikesh.kamalapurkar@okstate.edu

W. E. Dixon

Department of Mechanical and Aerospace Engineering,
University of Florida,
Gainesville, FL 32611
e-mail: wdixon@ufl.edu

1Corresponding author.

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received May 3, 2016; final manuscript received January 20, 2017; published online May 10, 2017. Assoc. Editor: Yongchun Fang.

J. Dyn. Sys., Meas., Control 139(7), 074502 (May 10, 2017) (7 pages) Paper No: DS-16-1228; doi: 10.1115/1.4035871 History: Received May 03, 2016; Revised January 20, 2017

A dynamic neural network (DNN) observer-based output feedback controller for uncertain nonlinear systems with bounded disturbances is developed. The DNN-based observer works in conjunction with a dynamic filter for state estimation using only output measurements during online operation. A sliding mode term is included in the DNN structure to robustly account for exogenous disturbances and reconstruction errors. Weight update laws for the DNN, based on estimation errors, tracking errors, and the filter output are developed, which guarantee asymptotic regulation of the state estimation error. A combination of a DNN feedforward term, along with the estimated state feedback and sliding mode terms yield an asymptotic tracking result. The developed output feedback (OFB) method yields asymptotic tracking and asymptotic estimation of unmeasurable states for a class of uncertain nonlinear systems with bounded disturbances. A two-link robot manipulator is used to investigate the performance of the proposed control approach.

Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Velocity estimation x˙(t) using (a) DNN-based observer and (b) numerical backwards difference: (a) velocity estimation by DNN observer and (b) velocity estimation by backwards difference

Grahic Jump Location
Fig. 2

The tracking errors e(t) of (a) link 1 and (b) link 2 using classical PID, robust discontinuous OFB controller [15], and proposed controller: (a) link 1 tracking error and (b) link 2 tracking error

Grahic Jump Location
Fig. 3

The control inputs for link 1 and link 2 using (a), (d) classical PID, (b), (e) robust discontinuous OFB controller [15], and (c), (f) proposed controller: (a) link 1 control input (PID controller), (b) link 1 control input (robust OFB controller), (c) link 1 control input (proposed), (d) link 2 control input (PID controller), (e) link 2 control input (robust OFB controller), and (f) link 2 control input (proposed)

Grahic Jump Location
Fig. 4

Frequency analysis of torques u(t) using (a) classical PID and (b) robust discontinuous OFB controller [15], and (c) proposed controller: (a) frequency analysis (PID controller), (b) frequency analysis (robust OFB controller), and (c) frequency analysis (proposed)




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