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

Real-time flow control using neural networks

Chan1, Rad

  • 1Hong Kong Polytechnic University, Department of Electrical Engineering, Hung Hom, Kowloon, Hong Kong.

ISA Transactions
|May 29, 2000
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

Highly selective catalytic intermolecular reductive coupling of alkynes and aldehydes

Organic letters·2001
Same author

Comment on "Algebraic perturbation theory for polar fluids: A model for the dielectric constant"

Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics·2001
Same author

Combined intraoperative alcohol celiac ablation and lateral pancreaticojejunostomy for chronic pancreatitis.

Current surgery·2000
Same author

Erratum to: differential expression of S100B(1) and S100A6(1) in the human fetal and aged cerebral cortex.

Brain research. Developmental brain research·2000
Same author

Case of the month

The American journal of medicine·2000
Same author

Cardiac Neoplasms.

Current treatment options in cardiovascular medicine·2000
Same journal

Hybrid vehicle state estimation using closed-form liquid neural networks and nonlinear Kalman filtering.

ISA transactions·2026
Same journal

Cross-coupled synchronization control strategy for rebar binding robots based on impedance control.

ISA transactions·2026
Same journal

Gas flow tracking for electronic pressure control system in gas chromatography under state constraints and hysteresis：An innovative fuzzy adaptive control approach.

ISA transactions·2026
Same journal

Stackelberg differential game-based fuzzy adaptive hierarchical optimal control for a nonlinear system with unknown dynamics.

ISA transactions·2026
Same journal

Composite fault-tolerant predictive control strategy for PMSM demagnetization faults.

ISA transactions·2026
Same journal

Bias-compensated Q-learning for optimal tracking control under denial-of-service attacks.

ISA transactions·2026
See all related articles

An on-line trained neural network controller effectively manages process rig flow rates, outperforming traditional PID controllers in handling system noise and non-linearity for improved control.

Area of Science:

  • Process Control Engineering
  • Artificial Intelligence in Automation
  • Non-linear System Dynamics

Background:

  • Conventional controllers like PID struggle with complex process dynamics.
  • Non-linearity and noise significantly degrade control system performance.
  • Advanced control strategies are needed for robust process automation.

Purpose of the Study:

  • To evaluate an on-line trained neural network controller for process flow rate control.
  • To compare its performance against a Proportional-Integral-Derivative (PID) controller.
  • To assess robustness under noisy and non-linear conditions.

Main Methods:

  • Implemented an on-line trained neural network controller in the forward path of a process control rig.
  • Replaced a conventional controller with the neural network controller.

Related Experiment Videos

  • Tested system performance with and without added non-linearity and noise, comparing with a PID controller.

    • Main Results:

    • The neural network controller demonstrated robust performance across various conditions.
    • The Proportional-Integral-Derivative controller failed to track set-point changes effectively when non-linearity was introduced.
    • The neural controller successfully adapted and maintained control despite system disturbances.

    Conclusions:

    • On-line trained neural network controllers offer superior performance in challenging process control environments.
    • Neural controllers provide a viable alternative to PID controllers for systems with non-linearity and noise.
    • This approach enhances process stability and set-point tracking accuracy.