Jove
Visualize
Contact Us

Related Experiment Videos

An NN-based approach for tuning servocontrollers.

Elder M. Hemerly1, Cairo L. Nascimento

  • 1Instituto Tecnológico de Aeronáutica, CTA-ITA-IEEE, 12228-900 São José dos Campos, São Paulo, Brazil

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
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 journal

Unified knowledge distillation: Integrating offline, online, and self-distillation paradigms for image classification.

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

A survey of modern neural network based methods for the graph coloring problem.

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

Convergence of stochastic gradient methods for wide two-layer physics-informed neural networks for the Poisson equation.

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

CANav: Cognition-aligned object-goal navigation based on a hierarchical scene graph with personalized knowledge-guided reasoning.

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

Predefined-time synchronization of memristor-based competitive neural networks with time-varying delays and application in image encryption.

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

UMind: A unified multitask network for zero-shot M/EEG visual decoding.

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

This study introduces a neural network (NN) approach to tune proportional-integral (PI) controllers for complex industrial plants. The method effectively determines PI gains for unknown, unstable systems, simplifying process control applications.

Area of Science:

  • Control Engineering
  • Artificial Intelligence
  • Process Automation

Background:

  • Tuning proportional-integral (PI) controllers for unknown or unstable industrial plants is challenging.
  • Traditional methods often require detailed plant models or extensive tuning procedures.
  • Neural networks offer a potential solution for adaptive and robust control system design.

Purpose of the Study:

  • To develop and validate a novel method for tuning PI controllers using neural networks (NN).
  • To enable the automatic computation of PI gains for nonlinear and open-loop unstable systems.
  • To provide a practical approach for integrating NN-based tuning into existing industrial process control software.

Main Methods:

  • Training a neural network controller using a simple algorithm based on plant output response direction and control error.

Related Experiment Videos

  • Approximating the input-output behavior of the trained NN controller with a PI controller structure.
  • Calculating proportional and integral gains from the approximated PI controller.

    • Main Results:

    • The proposed NN-based method successfully tunes PI controllers for unknown, nonlinear, and open-loop unstable plants.
    • Computer simulations demonstrated effectiveness on an unstable nonlinear plant.
    • Experimental results on a thermal plant validated the practical applicability and usefulness of the approach.

    Conclusions:

    • The developed neural network approach provides an effective and straightforward way to determine PI controller gains for challenging industrial processes.
    • The computed PI gains are directly usable in standard industrial process control software, facilitating adoption.
    • This method simplifies the tuning of PI controllers for unknown and unstable systems, enhancing process automation capabilities.