Jove
Visualize
Contact Us

Related Experiment Videos

Multivariable alarming using neural networks.

W T Shaw

    ISA Transactions
    |January 1, 1990
    PubMed
    Summary
    This summary is machine-generated.

    Traditional process monitoring treats parameters independently. This study uses neural networks to model complex multivariable relationships, improving process safety and alarming by learning from live data.

    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

    Capitalizing interest: the FASB's answer.

    Hospital financial management·1980
    Same author

    Letter: Full and empty fat cells.

    Lancet (London, England)·1973
    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
    Same journal

    Motion prediction for leader manipulator of teleoperation system with large time delay based on inverse optimal control.

    ISA transactions·2026
    Same journal

    Neural network parameter identification-based prescribed-time adaptive control for morphing glide aircraft.

    ISA transactions·2026
    Same journal

    Nonlinear system-guided continuous-time generalization for cross-aircraft engine state monitoring.

    ISA transactions·2026
    See all related articles
    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

    Area of Science:

    • Process Engineering
    • Artificial Intelligence
    • Chemical Engineering

    Background:

    • Current process monitoring often analyzes parameters in isolation, limiting the detection of complex interdependencies.
    • Accurate mathematical modeling of multivariable processes requires pre-existing knowledge of intricate chemical, physical, and thermodynamic relationships.

    Purpose of the Study:

    • To introduce a novel approach for multivariable process monitoring and alarming.
    • To leverage neural networks for creating experience-based models of complex process dynamics.

    Main Methods:

    • Utilizing neural networks to map "N"-dimensional space relationships among "N" process variables.
    • Training neural networks on live process data to learn safe and unsafe operational states.

    Related Experiment Videos

    Main Results:

    • Demonstrated the capability of neural networks to model multivariable process relationships without prior knowledge of the underlying equations.
    • Enabled the identification of complex, interdependent process states previously undetectable by traditional methods.

    Conclusions:

    • Neural networks offer a powerful, data-driven alternative for advanced process monitoring and alarming.
    • This experience-based modeling approach enhances process safety by capturing intricate variable interactions.