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

Multiple neural-network-based adaptive controller using orthonormal activation function neural networks.

D Shukla1, D M Dawson, F W Paul

  • 1High Technology Corporation, Hampton, VA 23666, USA.

IEEE Transactions on Neural Networks
|February 7, 2008
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

[Minimally invasive arthrodesis of the talonavicular joint].

Operative Orthopadie und Traumatologie·2026
Same author

A core outcome set for cranioplasty following stroke or traumatic brain injury - The COAST study.

Brain & spine·2025
Same author

Corrigendum to: DOP01 Exclusive Enteral Nutrition for the Treatment of Adult Crohn's Disease.

Journal of Crohn's & colitis·2020
Same author

High temperature-mediated rocksalt to wurtzite phase transformation in cadmium oxide nanosheets and its theoretical evidence.

Nanoscale·2019
Same author

Redundant and regulatory roles for Toll-like receptors in Leishmania infection.

Clinical and experimental immunology·2017
Same author

Post-traumatic cervical spondyloptosis: A rare entity with multiple management options.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2016
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a novel direct adaptive control scheme using orthonormal activation function-based neural networks (OAFNNs) for nonlinear systems. Experimental results demonstrate superior learning and accurate modeling of complex dynamics.

Area of Science:

  • Control Engineering
  • Artificial Intelligence
  • Nonlinear Dynamics

Background:

  • Trajectory tracking in nonlinear systems presents significant control challenges.
  • Existing adaptive control methods often face limitations in handling complex dynamics and computational load.
  • Neural networks offer potential for adaptive control but require efficient architectures.

Purpose of the Study:

  • To develop a direct adaptive control scheme for nonlinear systems using orthonormal activation function-based neural networks (OAFNNs).
  • To investigate the effectiveness of multiple OAFNNs for feedforward compensation of unknown system dynamics.
  • To reduce computational requirements through optimized network size.

Main Methods:

  • A direct adaptive control scheme employing multiple OAFNNs was designed.

Related Experiment Videos

  • Network weights were tuned online in real-time.
  • Lyapunov analysis was used to guarantee system and neural network stability.
  • Experimental evaluations were conducted to validate the control scheme.

    • Main Results:

    • The developed OAFNN-based controllers demonstrated effective trajectory tracking for nonlinear systems.
    • Experimental results confirmed the theoretical analysis and superior learning capability of OAFNNs.
    • The controllers accurately modeled nonlinear system dynamics, including rolling-sliding contact and stiction.
    • Network parameter effects on system performance were experimentally assessed.

    Conclusions:

    • The proposed OAFNN-based direct adaptive control scheme is effective for trajectory tracking in nonlinear systems.
    • The use of multiple OAFNNs reduces computational load while maintaining control performance.
    • OAFNNs exhibit superior learning capabilities and accurate dynamic modeling for complex nonlinear systems.