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

Stable adaptive neurocontrol for nonlinear discrete-time systems.

Quanmin Zhu1, Lingzhong Guo

  • 1Faculty of Computing, Engineering and Mathematical Science, University of the West of England, Bristol, BS16 1QY, UK. quan.zhu@uwe.ac.uk

IEEE Transactions on Neural Networks
|September 24, 2004
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

A generalisation study in deep learning-based segmentation of lower-limb muscles across different populations.

Scientific reports·2026
Same author

Assessing the reproducibility of a subject-specific finite element modelling pipeline for the human metastatic vertebrae.

Scientific reports·2026
Same author

Automatic Segmentation of Placenta from MR images Using a Novel BiGC U-Net.

IEEE journal of biomedical and health informatics·2026
Same author

Deep Learning-Based Surrogate Model of Subject-Specific Finite-Element Analysis for Vertebrae.

IEEE transactions on bio-medical engineering·2025
Same author

A novel mean shape based post-processing method for enhancing deep learning lower-limb muscle segmentation accuracy.

PloS one·2024
Same author

Automatic segmentation of lower limb muscles from MR images of post-menopausal women based on deep learning and data augmentation.

PloS one·2024

This study introduces neural network adaptive controllers for nonlinear systems, simplifying design and enhancing efficiency. Lyapunov stability analysis ensures closed-loop system stability, validated by simulations.

Area of Science:

  • Control Systems Engineering
  • Artificial Intelligence
  • Nonlinear Dynamics

Background:

  • Designing controllers for nonlinear discrete-time systems presents significant challenges due to complex dynamics.
  • Existing methods may lack efficiency or simplicity in handling such nonlinearities.
  • Generalized Minimum Variance (GMV) controllers offer a framework for linear systems, but adaptation to nonlinear systems is complex.

Purpose of the Study:

  • To propose a novel neural network-based adaptive controller design for nonlinear discrete-time systems.
  • To simplify the controller design procedure while maintaining efficiency in managing nonlinear dynamics.
  • To establish theoretical guarantees for system stability using Lyapunov analysis.

Main Methods:

  • A recurrent neural network is employed to compensate for system nonlinearities and simplify the controller design.

Related Experiment Videos

  • The network weight adaptation law is derived using Lyapunov stability analysis.
  • A theorem is presented to define the conditions for closed-loop system stability.

    • Main Results:

    • The proposed approach simplifies the design of adaptive controllers for nonlinear discrete-time systems.
    • The recurrent neural network effectively handles complex nonlinear dynamics.
    • Lyapunov stability analysis provides a rigorous foundation for the convergence of network weights and system stability.
    • Simulation examples demonstrate the effectiveness of the developed control strategy.

    Conclusions:

    • The novel neural network-based adaptive controller offers a promising solution for controlling nonlinear discrete-time systems.
    • The method combines the simplicity of linear controller design with the efficiency needed for complex nonlinear dynamics.
    • The established stability conditions and simulation results validate the approach's practical applicability.