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

Multi-step-ahead prediction using dynamic recurrent neural networks.

A G Parlos1, O T Rais, A F Atiya

  • 1Department of Mechanical Engineering, Texas A&M University, College Station 77843, USA. a-parlos@tamu.edu

Neural Networks : the Official Journal of the International Neural Network Society
|January 11, 2001
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

Three-dimensional video compression using subband/wavelet transform with lower buffering requirements.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

A comparison between neural-network forecasting techniques--case study: river flow forecasting.

IEEE transactions on neural networks·2008
Same author

New results on recurrent network training: unifying the algorithms and accelerating convergence.

IEEE transactions on neural networks·2008
Same author

Bankruptcy prediction for credit risk using neural networks: a survey and new results.

IEEE transactions on neural networks·2008
Same author

An algorithmic approach to adaptive state filtering using recurrent neural networks.

IEEE transactions on neural networks·2008
Same author

A new algorithm for learning in piecewise-linear neural networks.

Neural networks : the official journal of the International Neural Network Society·2000
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

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

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a new method using dynamic recurrent neural networks for accurate multi-step-ahead predictions in complex processes. The approach effectively models process dynamics and enhances fault diagnosis and control systems.

Area of Science:

  • * Process modeling and control engineering.
  • * Artificial intelligence and machine learning applications.

Background:

  • * Accurate prediction of complex process dynamics is crucial for effective control and fault diagnosis.
  • * Existing methods often struggle with multi-step-ahead predictions in unstable or nonlinear systems.

Purpose of the Study:

  • * To develop an empirical predictive modeling method for complex processes capable of accurate multi-step-ahead predictions.
  • * To utilize dynamic recurrent neural networks, specifically nonlinear infinite impulse response (IIR) filters, for this purpose.
  • * To present a novel learning algorithm based on dynamic gradient descent.

Main Methods:

  • * Development of dynamic recurrent neural networks structured as nonlinear infinite impulse response (IIR) filters.

Related Experiment Videos

  • * Implementation of a learning algorithm employing a dynamic gradient descent approach.
  • * Testing and validation on an artificial problem and a complex, open-loop unstable process.

    • Main Results:

    • * The proposed method achieves accurate multi-step-ahead (MS) predictions while maintaining single-step-ahead (SS) accuracy.
    • * Comparative analysis shows superior performance over polynomial Nonlinear AutoRegressive with eXogeneous (NARX) predictors and teacher-forced recurrent networks.
    • * Validation studies confirm excellent generalization capabilities across studied operational dynamics.

    Conclusions:

    • * The proposed network architecture and learning algorithm are highly effective for modeling complex process dynamics.
    • * The method demonstrates significant potential for accurate multi-step-ahead predictions in practical applications.
    • * This approach offers a robust solution for enhancing model predictive controllers and fault diagnosis systems.