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

Adaptive neural network control for a class of low-triangular-structured nonlinear systems.

Hongbin Du, Huihe Shao, Pingjing Yao

    IEEE Transactions on Neural Networks
    |March 29, 2006
    PubMed
    Summary

    This study introduces adaptive neural network control to stabilize complex nonlinear systems with unknown disturbances. The novel approach ensures system stability and signal boundedness, overcoming previous limitations.

    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

    Mapping the BCSC-1 interactome in breast cancer.

    Scientific reports·2025
    Same author

    <i>In situ</i> one-pot synthesis of organic-functionalized crystalline silicon nanoparticles.

    Chemical communications (Cambridge, England)·2025
    Same author

    Pomegranate-Like Nano-Confined Silicon Inside Conductive Carbon Black as Anode Materials for Lithium-Ion Batteries.

    Chemistry (Weinheim an der Bergstrasse, Germany)·2025
    Same author

    Structure-directing synthesis of two germanate cages featuring odd-member ring windows.

    Dalton transactions (Cambridge, England : 2003)·2025
    Same author

    Synthesis of a high-silica intersecting-large-pore zeolite using hydrogen-bond-assisted structure-directing agents.

    Dalton transactions (Cambridge, England : 2003)·2025
    Same author

    Measurement and evolution of government attention to the health industry in China based on the BERTopic model.

    PloS one·2025

    Area of Science:

    • Control Theory
    • Nonlinear Systems
    • Artificial Intelligence

    Background:

    • Stabilizing unknown perturbed nonlinear systems with nonaffine functions and disturbances is challenging.
    • Existing methods are insufficient for systems with low triangular structures, including strict-feedback and pure-feedback systems.
    • Control direction and singularity issues hinder effective control design.

    Purpose of the Study:

    • To develop a theoretical framework for stabilizing a class of unknown perturbed nonlinear systems.
    • To address the limitations of existing control methods for complex system structures.
    • To overcome challenges related to control directions and singularity in nonlinear control.

    Main Methods:

    • Adaptive neural network control is employed for system stabilization.

    Related Experiment Videos

  • New conclusions regarding Nussbaum-Gain functions (NGF) are integrated.
  • Backstepping techniques are utilized in conjunction with NGF.
  • Semiglobal, uniform, and ultimate boundedness of closed-loop signals are proven.

    • Main Results:

    • The proposed adaptive neural network control scheme successfully stabilizes the target class of nonlinear systems.
    • The method effectively handles systems with disturbances and nonaffine unknown functions.
    • Control direction and singularity problems are resolved.
    • The theoretical findings are validated through simulations.

    Conclusions:

    • The developed adaptive neural network control strategy provides a robust solution for stabilizing complex nonlinear systems.
    • The approach generalizes and improves upon existing methods for uncertain systems.
    • The study demonstrates the effectiveness of combining Nussbaum-Gain functions and backstepping for challenging control problems.