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

Robust and adaptive backstepping control for nonlinear systems using RBF neural networks.

Yahui Li1, Sheng Qiang, Xianyi Zhuang

  • 1Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China. lyahui2002@yahoo.com.cn

IEEE Transactions on Neural Networks
|September 24, 2004
PubMed
Summary

This study presents two novel neural network (NN) control methods for nonlinear systems. These approaches effectively avoid controller singularity and ensure system stability and accurate trajectory tracking.

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

Variation and fitness of hybrid F<sub>4</sub> between glyphosate-tolerant soybeans and three wild soybean populations from Northern China.

Pest management science·2026
Same author

TrCLIP-VAD : Weak supervised video anomaly detection by improving CLIP training with text rewriting.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

A cylindrical projection lithography-fabricated flexible on-catheter in situ integrated sensor for continuous in-artery blood pressure monitoring.

Microsystems & nanoengineering·2026
Same author

Cracking Mechanism and Life-Cycle Performance Evaluation of Early-Age Concrete Based on Environment-Damage Coupling.

Materials (Basel, Switzerland)·2026
Same author

An ultrathin and geometrically customizable plasmonic Janus silk fibroin membrane for simultaneous sweat enrichment and multiplex biomarker detection.

Biosensors & bioelectronics·2026
Same author

A Systematic Comparison of Two Host-Sourced Populations Suggests Tomato to be an Opportunistic Host for <i>Orobanche cumana</i>.

Plant disease·2026

Area of Science:

  • Control Theory
  • Artificial Intelligence
  • Nonlinear Systems

Background:

  • Affine nonlinear systems in strict-feedback form often present challenges due to unknown nonlinearities.
  • Controller singularity is a common issue in control design for such systems.
  • Ensuring stability and accurate tracking for nonlinear systems requires advanced control strategies.

Purpose of the Study:

  • To develop two distinct backstepping neural network (NN) control strategies.
  • To address and overcome the controller singularity problem in nonlinear system control.
  • To guarantee semiglobal uniform ultimate boundedness of closed-loop signals and precise trajectory tracking.

Main Methods:

  • Utilizing a backstepping design methodology combined with neural network approximators.

Related Experiment Videos

  • Implementing a specialized design scheme to circumvent controller singularity.
  • Employing Lyapunov stability theory to analyze system boundedness and convergence.

    • Main Results:

    • Both proposed NN control approaches successfully avoid controller singularity.
    • Closed-loop signals are guaranteed to be semiglobally uniformly ultimately bounded.
    • System outputs converge to a small neighborhood of the desired trajectory, with performance shaped by design parameters.

    Conclusions:

    • The presented backstepping NN control methods are effective for affine nonlinear systems with unknown nonlinearities.
    • The proposed techniques offer robust control, ensuring stability and accurate tracking.
    • Further analysis briefly explores differences between the two controller inputs, highlighting practical implementation considerations.