Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A stable neural network-based observer with application to flexible-joint manipulators.

Farzaneh Abdollahi1, H A Talebi, Rajnikant V Patel

  • 1Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada. f-abdoll@ece.concordia.ca

IEEE Transactions on Neural Networks
|March 11, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Quercetin as a therapeutic agent activate the Nrf2/Keap1 pathway to alleviate lung ischemia-reperfusion injury.

Scientific reports·2024
Same author

A passive isolation of sensor faults from un-stealthy attacks in uncertain nonlinear systems.

ISA transactions·2023
Same author

Dietary status with demographic and anthropometric variables and some health affecting risk factors in people of Southeastern Iran: A population-based study (KERCADRS).

Caspian journal of internal medicine·2021
Same author

Involvement of T-type calcium channels in the mechanism of low dose morphine-induced hyperalgesia in adult male rats.

Neuropeptides·2021
Same author

Resilient control of multi-microgrids against false data injection attack.

ISA transactions·2020
Same author

Machine Vision System for 3D Plant Phenotyping.

IEEE/ACM transactions on computational biology and bioinformatics·2018

This study introduces a novel nonlinear-in-parameters neural network (NLPNN) observer for complex nonlinear systems. The NLPNN observer ensures stability and robustness without strict assumptions, enhancing performance in applications like robotics.

Area of Science:

  • Control Systems Engineering
  • Artificial Intelligence
  • Nonlinear Dynamics

Background:

  • Traditional neural network (NN) observers often require specific system knowledge or strong assumptions.
  • Existing methods struggle with systems exhibiting high degrees of nonlinearity.
  • Robustness and stability guarantees are critical for practical observer applications.

Purpose of the Study:

  • To develop a stable neural network (NN)-based observer for general multivariable nonlinear systems.
  • To introduce a nonlinear-in-parameters neural network (NLPNN) for enhanced applicability.
  • To ensure observer robustness and stability without restrictive system assumptions.

Main Methods:

  • Utilized a nonlinear-in-parameters neural network (NLPNN) architecture.

Related Experiment Videos

  • Developed a novel learning rule based on a modified backpropagation (BP) algorithm with an e-modification term.
  • Employed Lyapunov's direct method to prove the stability of the recurrent NN observer.
  • Avoided imposing strictly positive real (SPR) or other strong assumptions on the system.

    • Main Results:

    • Demonstrated the successful application of the NLPNN observer to systems with higher nonlinearity.
    • The modified BP learning rule with an e-modification term guaranteed observer robustness.
    • Stability of the recurrent NN observer was rigorously proven using Lyapunov's direct method.
    • Simulation results for a flexible-joint manipulator showed enhanced performance compared to conventional methods.

    Conclusions:

    • The proposed NLPNN observer offers enhanced performance and robustness for general nonlinear systems.
    • The approach relaxes traditional constraints, making it applicable to a wider range of systems.
    • This work advances the field of NN-based observers for complex dynamic systems.