Simulation and model predictive control of the fluid catalytic cracking unit using artificial neural networks

Vasile Mircea Cristea, Letijia Toma, Paul Serban Agachi

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    An Artificial Neural Network (ANN) model has been developed for an industrial Fluid Catalytic Cracking Unit (FCCU). ANN design and training are presented. Successful training procedure is proved when the prediction capability of the network is investigated on the testing set of data. The trained ANN model has been subsequently used to implement FCCU control using the Model Predictive Control (MPC) algorithm. Main process variables have been controlled in the presence of typical disturbances. Setpoint tracking and disturbance rejection show good control performance and, associated to important decrease of computation time, reveal incentives of the ANN based MPC approach for industrial implementation.

    Original languageEnglish
    Pages (from-to)1157-1166
    Number of pages10
    JournalRevue Roumaine de Chimie
    Volume52
    Issue number12
    Publication statusPublished - Dec 2007

    Fingerprint

    Fluid catalytic cracking
    Model predictive control
    Neural networks
    Disturbance rejection
    Testing

    All Science Journal Classification (ASJC) codes

    • Chemistry(all)

    Cite this

    @article{6bd4768aa846493a86c32f56751f6680,
    title = "Simulation and model predictive control of the fluid catalytic cracking unit using artificial neural networks",
    abstract = "An Artificial Neural Network (ANN) model has been developed for an industrial Fluid Catalytic Cracking Unit (FCCU). ANN design and training are presented. Successful training procedure is proved when the prediction capability of the network is investigated on the testing set of data. The trained ANN model has been subsequently used to implement FCCU control using the Model Predictive Control (MPC) algorithm. Main process variables have been controlled in the presence of typical disturbances. Setpoint tracking and disturbance rejection show good control performance and, associated to important decrease of computation time, reveal incentives of the ANN based MPC approach for industrial implementation.",
    author = "Cristea, {Vasile Mircea} and Letijia Toma and Agachi, {Paul Serban}",
    year = "2007",
    month = "12",
    language = "English",
    volume = "52",
    pages = "1157--1166",
    journal = "Revue Roumaine de Chimie",
    issn = "0035-3930",
    publisher = "Editions de l'Academie Republique Populaire",
    number = "12",

    }

    Simulation and model predictive control of the fluid catalytic cracking unit using artificial neural networks. / Cristea, Vasile Mircea; Toma, Letijia; Agachi, Paul Serban.

    In: Revue Roumaine de Chimie, Vol. 52, No. 12, 12.2007, p. 1157-1166.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Simulation and model predictive control of the fluid catalytic cracking unit using artificial neural networks

    AU - Cristea, Vasile Mircea

    AU - Toma, Letijia

    AU - Agachi, Paul Serban

    PY - 2007/12

    Y1 - 2007/12

    N2 - An Artificial Neural Network (ANN) model has been developed for an industrial Fluid Catalytic Cracking Unit (FCCU). ANN design and training are presented. Successful training procedure is proved when the prediction capability of the network is investigated on the testing set of data. The trained ANN model has been subsequently used to implement FCCU control using the Model Predictive Control (MPC) algorithm. Main process variables have been controlled in the presence of typical disturbances. Setpoint tracking and disturbance rejection show good control performance and, associated to important decrease of computation time, reveal incentives of the ANN based MPC approach for industrial implementation.

    AB - An Artificial Neural Network (ANN) model has been developed for an industrial Fluid Catalytic Cracking Unit (FCCU). ANN design and training are presented. Successful training procedure is proved when the prediction capability of the network is investigated on the testing set of data. The trained ANN model has been subsequently used to implement FCCU control using the Model Predictive Control (MPC) algorithm. Main process variables have been controlled in the presence of typical disturbances. Setpoint tracking and disturbance rejection show good control performance and, associated to important decrease of computation time, reveal incentives of the ANN based MPC approach for industrial implementation.

    UR - http://www.scopus.com/inward/record.url?scp=51849152347&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=51849152347&partnerID=8YFLogxK

    M3 - Article

    VL - 52

    SP - 1157

    EP - 1166

    JO - Revue Roumaine de Chimie

    JF - Revue Roumaine de Chimie

    SN - 0035-3930

    IS - 12

    ER -