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

Performance-oriented antiwindup for a class of linear control systems with augmented neural network controller.

Guido Herrmann1, Matthew C Turner, Ian Postlethwaite

  • 1Control and Instrumentation Research Group, University of Leicester, Leicester LE1 7RH, UK. gh17@le.ac.uk

IEEE Transactions on Neural Networks
|March 28, 2007
PubMed
Summary

This study introduces a neural network (NN) controller to enhance linear control systems facing amplitude limits. The NN controller compensates for nonlinear disturbances, improving system performance and stability.

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

From traditional robotic deployments towards assisted robotic deployments in nuclear decommissioning.

Frontiers in robotics and AI·2025
Same author

Using skeletal position to estimate human error rates in telemanipulator operators.

Frontiers in robotics and AI·2024
Same author

Assessing tele-manipulation systems using task performance for glovebox operations.

Frontiers in robotics and AI·2022
Same author

Distributed Neural Networks Training for Robotic Manipulation With Consensus Algorithm.

IEEE transactions on neural networks and learning systems·2022
Same author

Reduced-Order Neural Network Synthesis With Robustness Guarantees.

IEEE transactions on neural networks and learning systems·2022
Same author

Radiation Tolerance Testing Methodology of Robotic Manipulator Prior to Nuclear Waste Handling.

Frontiers in robotics and AI·2021

Area of Science:

  • Control Systems Engineering
  • Artificial Intelligence in Control
  • Nonlinear System Analysis

Background:

  • Linear control systems often struggle with unmodeled nonlinear disturbances and control signal saturation.
  • Neural network (NN) controllers offer potential for improved performance by estimating and compensating for these complex dynamics.
  • Anti-windup (AW) compensators are crucial for maintaining system stability and performance during actuator saturation.

Purpose of the Study:

  • To develop a robust conditioning scheme for linear control systems augmented with NN controllers under amplitude constraints.
  • To mitigate the effects of unmodeled nonlinear disturbances using an NN controller.
  • To design an effective anti-windup (AW) compensator for rapid saturation recovery.

Main Methods:

Related Experiment Videos

  • A neural network (NN) controller is integrated into a linear control system to estimate and compensate for nonlinear disturbances.
  • The NN controller's output is bounded to respect known disturbance limits.
  • A low-order anti-windup (AW) compensator is designed using convex linear matrix inequalities (LMIs) optimization.

Main Results:

  • The proposed NN-enhanced control scheme effectively compensates for unmodeled nonlinear disturbances.
  • The integrated AW compensator ensures performance close to the nominal controller and enables swift recovery from saturation.
  • The NN controller's bounded output prevents exceeding disturbance limits, enhancing system robustness.

Conclusions:

  • The presented conditioning scheme effectively integrates NN control with anti-windup strategies for linear systems with amplitude limits.
  • This approach enhances system performance and stability by addressing nonlinear disturbances and saturation.
  • The use of LMIs for AW compensator design provides a systematic and efficient method for robust control.