Adaptive neural network model based nonlinear predictive control of a fluid catalytic cracking unit

Z. Nagy, S. Agachi, L. Bodizs

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    Neural Networks are used for a wide variety of chemical applications because of their ability to learn system features. This paper presents the use of artificial neural networks (ANN) for dynamic modeling and nonlinear model predictive control of a fluid catalytic unit (FCCU). An off-line trained ANN model based predictive control structure (NNMPC) and on adaptive neural network model based predictive control (ANNMPC) scheme were tested. Both control structures give a superior control performance compared to the classical proportional-integral (PI) controllers. To improve the convergence of the optimization process in both the off-line or on-line training of the ANN model and in the on-line control problem the use of genetic algorithm (GA) in combination with the classical optimization algorithms was proposed.

    Original languageEnglish
    Pages (from-to)235-240
    Number of pages6
    JournalComputer Aided Chemical Engineering
    Volume8
    Issue numberC
    DOIs
    Publication statusPublished - 2000

    Fingerprint

    Fluid catalytic cracking
    Neural networks
    Model predictive control
    Genetic algorithms
    Controllers
    Fluids

    All Science Journal Classification (ASJC) codes

    • Chemical Engineering(all)
    • Computer Science Applications

    Cite this

    @article{d6f8d813d0674301be7b15ba1690d38f,
    title = "Adaptive neural network model based nonlinear predictive control of a fluid catalytic cracking unit",
    abstract = "Neural Networks are used for a wide variety of chemical applications because of their ability to learn system features. This paper presents the use of artificial neural networks (ANN) for dynamic modeling and nonlinear model predictive control of a fluid catalytic unit (FCCU). An off-line trained ANN model based predictive control structure (NNMPC) and on adaptive neural network model based predictive control (ANNMPC) scheme were tested. Both control structures give a superior control performance compared to the classical proportional-integral (PI) controllers. To improve the convergence of the optimization process in both the off-line or on-line training of the ANN model and in the on-line control problem the use of genetic algorithm (GA) in combination with the classical optimization algorithms was proposed.",
    author = "Z. Nagy and S. Agachi and L. Bodizs",
    year = "2000",
    doi = "10.1016/S1570-7946(00)80041-3",
    language = "English",
    volume = "8",
    pages = "235--240",
    journal = "Computer Aided Chemical Engineering",
    issn = "1570-7946",
    publisher = "Elsevier",
    number = "C",

    }

    Adaptive neural network model based nonlinear predictive control of a fluid catalytic cracking unit. / Nagy, Z.; Agachi, S.; Bodizs, L.

    In: Computer Aided Chemical Engineering, Vol. 8, No. C, 2000, p. 235-240.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Adaptive neural network model based nonlinear predictive control of a fluid catalytic cracking unit

    AU - Nagy, Z.

    AU - Agachi, S.

    AU - Bodizs, L.

    PY - 2000

    Y1 - 2000

    N2 - Neural Networks are used for a wide variety of chemical applications because of their ability to learn system features. This paper presents the use of artificial neural networks (ANN) for dynamic modeling and nonlinear model predictive control of a fluid catalytic unit (FCCU). An off-line trained ANN model based predictive control structure (NNMPC) and on adaptive neural network model based predictive control (ANNMPC) scheme were tested. Both control structures give a superior control performance compared to the classical proportional-integral (PI) controllers. To improve the convergence of the optimization process in both the off-line or on-line training of the ANN model and in the on-line control problem the use of genetic algorithm (GA) in combination with the classical optimization algorithms was proposed.

    AB - Neural Networks are used for a wide variety of chemical applications because of their ability to learn system features. This paper presents the use of artificial neural networks (ANN) for dynamic modeling and nonlinear model predictive control of a fluid catalytic unit (FCCU). An off-line trained ANN model based predictive control structure (NNMPC) and on adaptive neural network model based predictive control (ANNMPC) scheme were tested. Both control structures give a superior control performance compared to the classical proportional-integral (PI) controllers. To improve the convergence of the optimization process in both the off-line or on-line training of the ANN model and in the on-line control problem the use of genetic algorithm (GA) in combination with the classical optimization algorithms was proposed.

    UR - http://www.scopus.com/inward/record.url?scp=77957235994&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77957235994&partnerID=8YFLogxK

    U2 - 10.1016/S1570-7946(00)80041-3

    DO - 10.1016/S1570-7946(00)80041-3

    M3 - Article

    VL - 8

    SP - 235

    EP - 240

    JO - Computer Aided Chemical Engineering

    JF - Computer Aided Chemical Engineering

    SN - 1570-7946

    IS - C

    ER -