FCCU simulation based on first principle and artificial neural network models

Maria Miheţ, Vasile Mircea Cristea, Paul Şerban Agachi

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    A first principle model has been developed for the reactor-regenerator system based on construction and operating data from an industrial fluid catalytic cracking unit (FCCU). The first principle model takes into account the main FCCU subsystems: reactor riser, regenerator, stripper, catalyst circulation lines, air blower, wet gas compressor and main fractionator. A five-lump kinetic scheme has been considered for the reactions taking place in the reactor riser. Subsequently, an artificial neural network (ANN) model has been built for the complex FCCU system. The dynamic simulator, based on the previously developed first principle model, served as the source of reliable data for ANN design, training and testing. The ANN developed model was successfully trained and tested. Comparison between first principle and neural network based model leads to a very good match between the two models. Results show the substantial reduction of the computation time featured by the ANN model compared to the first principle model, demonstrating its potential use for real-time implementation in model-based control algorithms.

    Original languageEnglish
    Pages (from-to)878-884
    Number of pages7
    JournalAsia-Pacific Journal of Chemical Engineering
    Volume4
    Issue number6
    DOIs
    Publication statusPublished - Nov 2009

    Fingerprint

    Fluid catalytic cracking
    artificial neural network
    Neural networks
    fluid
    simulation
    Regenerators
    riser
    Gas compressors
    Blowers
    network design
    simulator
    Simulators
    catalyst

    All Science Journal Classification (ASJC) codes

    • Chemical Engineering(all)
    • Renewable Energy, Sustainability and the Environment
    • Waste Management and Disposal

    Cite this

    @article{d5666cfc392442a6a3bcfe55db2d270d,
    title = "FCCU simulation based on first principle and artificial neural network models",
    abstract = "A first principle model has been developed for the reactor-regenerator system based on construction and operating data from an industrial fluid catalytic cracking unit (FCCU). The first principle model takes into account the main FCCU subsystems: reactor riser, regenerator, stripper, catalyst circulation lines, air blower, wet gas compressor and main fractionator. A five-lump kinetic scheme has been considered for the reactions taking place in the reactor riser. Subsequently, an artificial neural network (ANN) model has been built for the complex FCCU system. The dynamic simulator, based on the previously developed first principle model, served as the source of reliable data for ANN design, training and testing. The ANN developed model was successfully trained and tested. Comparison between first principle and neural network based model leads to a very good match between the two models. Results show the substantial reduction of the computation time featured by the ANN model compared to the first principle model, demonstrating its potential use for real-time implementation in model-based control algorithms.",
    author = "Maria Miheţ and Cristea, {Vasile Mircea} and Agachi, {Paul Şerban}",
    year = "2009",
    month = "11",
    doi = "10.1002/apj.312",
    language = "English",
    volume = "4",
    pages = "878--884",
    journal = "Asia-Pacific Journal of Chemical Engineering",
    issn = "1932-2135",
    publisher = "John Wiley and Sons Ltd",
    number = "6",

    }

    FCCU simulation based on first principle and artificial neural network models. / Miheţ, Maria; Cristea, Vasile Mircea; Agachi, Paul Şerban.

    In: Asia-Pacific Journal of Chemical Engineering, Vol. 4, No. 6, 11.2009, p. 878-884.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - FCCU simulation based on first principle and artificial neural network models

    AU - Miheţ, Maria

    AU - Cristea, Vasile Mircea

    AU - Agachi, Paul Şerban

    PY - 2009/11

    Y1 - 2009/11

    N2 - A first principle model has been developed for the reactor-regenerator system based on construction and operating data from an industrial fluid catalytic cracking unit (FCCU). The first principle model takes into account the main FCCU subsystems: reactor riser, regenerator, stripper, catalyst circulation lines, air blower, wet gas compressor and main fractionator. A five-lump kinetic scheme has been considered for the reactions taking place in the reactor riser. Subsequently, an artificial neural network (ANN) model has been built for the complex FCCU system. The dynamic simulator, based on the previously developed first principle model, served as the source of reliable data for ANN design, training and testing. The ANN developed model was successfully trained and tested. Comparison between first principle and neural network based model leads to a very good match between the two models. Results show the substantial reduction of the computation time featured by the ANN model compared to the first principle model, demonstrating its potential use for real-time implementation in model-based control algorithms.

    AB - A first principle model has been developed for the reactor-regenerator system based on construction and operating data from an industrial fluid catalytic cracking unit (FCCU). The first principle model takes into account the main FCCU subsystems: reactor riser, regenerator, stripper, catalyst circulation lines, air blower, wet gas compressor and main fractionator. A five-lump kinetic scheme has been considered for the reactions taking place in the reactor riser. Subsequently, an artificial neural network (ANN) model has been built for the complex FCCU system. The dynamic simulator, based on the previously developed first principle model, served as the source of reliable data for ANN design, training and testing. The ANN developed model was successfully trained and tested. Comparison between first principle and neural network based model leads to a very good match between the two models. Results show the substantial reduction of the computation time featured by the ANN model compared to the first principle model, demonstrating its potential use for real-time implementation in model-based control algorithms.

    UR - http://www.scopus.com/inward/record.url?scp=73449105082&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=73449105082&partnerID=8YFLogxK

    U2 - 10.1002/apj.312

    DO - 10.1002/apj.312

    M3 - Article

    VL - 4

    SP - 878

    EP - 884

    JO - Asia-Pacific Journal of Chemical Engineering

    JF - Asia-Pacific Journal of Chemical Engineering

    SN - 1932-2135

    IS - 6

    ER -