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

Dynamic output feedback stabilization for nonlinear systems based on standard neural network models.

Meiqin Liu1

  • 1Department of System Science and Engineering, School of Electrical Engineering, Zhejiang University, Hangzhou 310027, PR China. liumeiqin@cee.zju.edu.cn

International Journal of Neural Systems
|September 15, 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

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Symmetric Entropy-Constrained Video Coding for Machines.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Precision-engineered STING agonist nanoparticles enable coordinated mucosal-systemic immunity for durable pan-β-coronavirus protection.

Nature nanotechnology·2026
Same author

Gamma Knife consolidation therapy improves prognosis in patients with advanced epidermal growth factor receptor-mutant lung adenocarcinoma treated with first-generation epidermal growth factor receptor-tyrosine kinase inhibitors.

Oncology letters·2025
Same author

Morphological Study of First Instar Elephant Stomach Bot Fly Larvae (Oestridae: Gasterophilinae: <i>Cobboldia elephantis</i>).

Insects·2025
Same author

Cooperative Fuzzy Event-Based Tracking Control of Heterogeneous Multiple Marine Vehicles With a Nonautonomous Leader.

IEEE transactions on cybernetics·2025
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces a standard neural network model (SNNM) for controlling nonlinear systems. The novel approach uses linear matrix inequalities for stable control design, applicable to many neural network systems.

Area of Science:

  • Control Systems Engineering
  • Artificial Intelligence
  • Nonlinear Dynamics

Background:

  • Nonlinear systems pose significant challenges for traditional control design.
  • Neural networks offer powerful approximation capabilities but require specific conditions for control synthesis.
  • Existing methods may lack a unified approach for diverse neural network-based nonlinear systems.

Purpose of the Study:

  • To develop a novel neural network model for approximating nonlinear systems.
  • To design robust output feedback control laws for these neural network models.
  • To establish a unified framework for stabilizing a broad class of neural network-based nonlinear systems.

Main Methods:

  • Approximation of nonlinear systems using neural networks with sector-bounded activation functions.

Related Experiment Videos

  • Development of a Standard Neural Network Model (SNNM) for control design.
  • Design of full-order dynamic output feedback control laws based on Linear Matrix Inequalities (LMIs).

    • Main Results:

    • The proposed SNNM effectively describes approximating neural networks for control.
    • Control design is formulated as a set of solvable LMIs, enabling convex optimization.
    • A unified method is demonstrated for transforming various neural network-based nonlinear systems into SNNMs for stabilization.

    Conclusions:

    • The SNNM provides a systematic approach to designing controllers for nonlinear systems approximated by neural networks.
    • The LMI-based control design ensures stability and is computationally tractable.
    • This unified framework broadens the applicability of neural network-based control for complex nonlinear systems.