An adaptive observer design methodology for bounded nonlinear processes

Naira Hovakimyan, Anthony J. Calise, Venkatesh K. Madyastha

Research output: Contribution to journalConference article

Abstract

In this paper we address the problem of augmenting a linear observer with an adaptive element. The design of the adaptive element employs two nonlinearly parameterized neural networks, the input and output layer weights of which are adapted on line. The goal is to improve the performance of the linear observer when applied to a nonlinear system. The networks teaching signal is generated using a second linear observer of the nominal system's error dynamics. Boundedness of signals is shown through Lyapunov's direct method. The approach is robust to unmodeled dynamics and disturbances. Simulations illustrate the theoretical results.

Original languageEnglish (US)
Pages (from-to)4700-4705
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
Volume4
StatePublished - Dec 1 2002
Externally publishedYes
Event41st IEEE Conference on Decision and Control - Las Vegas, NV, United States
Duration: Dec 10 2002Dec 13 2002

Fingerprint

Adaptive Observer
Adaptive Design
Observer Design
Nonlinear Process
Design Methodology
Observer
Nonlinear systems
Lyapunov Direct Method
Unmodeled Dynamics
Teaching
Neural networks
Categorical or nominal
Boundedness
Nonlinear Systems
Disturbance
Neural Networks
Line
Output
Simulation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Cite this

An adaptive observer design methodology for bounded nonlinear processes. / Hovakimyan, Naira; Calise, Anthony J.; Madyastha, Venkatesh K.

In: Proceedings of the IEEE Conference on Decision and Control, Vol. 4, 01.12.2002, p. 4700-4705.

Research output: Contribution to journalConference article

@article{84a674da3167451385f94f9cc590c86c,
title = "An adaptive observer design methodology for bounded nonlinear processes",
abstract = "In this paper we address the problem of augmenting a linear observer with an adaptive element. The design of the adaptive element employs two nonlinearly parameterized neural networks, the input and output layer weights of which are adapted on line. The goal is to improve the performance of the linear observer when applied to a nonlinear system. The networks teaching signal is generated using a second linear observer of the nominal system's error dynamics. Boundedness of signals is shown through Lyapunov's direct method. The approach is robust to unmodeled dynamics and disturbances. Simulations illustrate the theoretical results.",
author = "Naira Hovakimyan and Calise, {Anthony J.} and Madyastha, {Venkatesh K.}",
year = "2002",
month = "12",
day = "1",
language = "English (US)",
volume = "4",
pages = "4700--4705",
journal = "Proceedings of the IEEE Conference on Decision and Control",
issn = "0191-2216",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - An adaptive observer design methodology for bounded nonlinear processes

AU - Hovakimyan, Naira

AU - Calise, Anthony J.

AU - Madyastha, Venkatesh K.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - In this paper we address the problem of augmenting a linear observer with an adaptive element. The design of the adaptive element employs two nonlinearly parameterized neural networks, the input and output layer weights of which are adapted on line. The goal is to improve the performance of the linear observer when applied to a nonlinear system. The networks teaching signal is generated using a second linear observer of the nominal system's error dynamics. Boundedness of signals is shown through Lyapunov's direct method. The approach is robust to unmodeled dynamics and disturbances. Simulations illustrate the theoretical results.

AB - In this paper we address the problem of augmenting a linear observer with an adaptive element. The design of the adaptive element employs two nonlinearly parameterized neural networks, the input and output layer weights of which are adapted on line. The goal is to improve the performance of the linear observer when applied to a nonlinear system. The networks teaching signal is generated using a second linear observer of the nominal system's error dynamics. Boundedness of signals is shown through Lyapunov's direct method. The approach is robust to unmodeled dynamics and disturbances. Simulations illustrate the theoretical results.

UR - http://www.scopus.com/inward/record.url?scp=0036991398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036991398&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0036991398

VL - 4

SP - 4700

EP - 4705

JO - Proceedings of the IEEE Conference on Decision and Control

JF - Proceedings of the IEEE Conference on Decision and Control

SN - 0191-2216

ER -