A novel application of a neuro-fuzzy computational technique in modeling of thermal cracking of heavy feedstock to light olefin

Mehdi Sedighi, Mostafa Ghasemi, Majid Mohammadi, Sedky H A Hassan

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    In the present paper, the ability and accuracy of an Adaptive Neuro-Fuzzy Inference System (ANFIS) was investigated for the process evaluation of thermal cracking to light olefin. The main objective of this research is to predict product yields as a function of Coil Outlet Temperature (COT), steam ratio, and feed flow rate, at the reactor tube outlet. Temperature, flow rate and steam-to-hydrocarbon ratio were in the range of 1023-1173 K, 3-7 g g -1, and 0.5-1.4 g min-1, respectively. The Adaptive Network-Based Fuzzy Inference System (ANFIS) technique was trained using historical data to generate the membership functions and rules that best interpret the input/output relationships of the process. Four fuzzy inference systems were independently developed for four output parameters, each of which consisted of three inputs and 27 rules. In order to better understand the capability of the present technique, an extensive comparison test was applied to the ANFIS, kinetic modeling, and response surface methodology. The obtained results demonstrate that these three models are in good agreement with the experimental data. The NF model showed the best results of all.

    Original languageEnglish
    Pages (from-to)28390-28399
    Number of pages10
    JournalRSC Advances
    Volume4
    Issue number54
    DOIs
    Publication statusPublished - 2014

    Fingerprint

    Fuzzy inference
    Alkenes
    Feedstocks
    Olefins
    Steam
    Flow rate
    Membership functions
    Hydrocarbons
    Temperature
    Kinetics
    Hot Temperature

    ASJC Scopus subject areas

    • Chemical Engineering(all)
    • Chemistry(all)

    Cite this

    A novel application of a neuro-fuzzy computational technique in modeling of thermal cracking of heavy feedstock to light olefin. / Sedighi, Mehdi; Ghasemi, Mostafa; Mohammadi, Majid; Hassan, Sedky H A.

    In: RSC Advances, Vol. 4, No. 54, 2014, p. 28390-28399.

    Research output: Contribution to journalArticle

    Sedighi, Mehdi ; Ghasemi, Mostafa ; Mohammadi, Majid ; Hassan, Sedky H A. / A novel application of a neuro-fuzzy computational technique in modeling of thermal cracking of heavy feedstock to light olefin. In: RSC Advances. 2014 ; Vol. 4, No. 54. pp. 28390-28399.
    @article{2966ab184121472bb5ee9f791edb8433,
    title = "A novel application of a neuro-fuzzy computational technique in modeling of thermal cracking of heavy feedstock to light olefin",
    abstract = "In the present paper, the ability and accuracy of an Adaptive Neuro-Fuzzy Inference System (ANFIS) was investigated for the process evaluation of thermal cracking to light olefin. The main objective of this research is to predict product yields as a function of Coil Outlet Temperature (COT), steam ratio, and feed flow rate, at the reactor tube outlet. Temperature, flow rate and steam-to-hydrocarbon ratio were in the range of 1023-1173 K, 3-7 g g -1, and 0.5-1.4 g min-1, respectively. The Adaptive Network-Based Fuzzy Inference System (ANFIS) technique was trained using historical data to generate the membership functions and rules that best interpret the input/output relationships of the process. Four fuzzy inference systems were independently developed for four output parameters, each of which consisted of three inputs and 27 rules. In order to better understand the capability of the present technique, an extensive comparison test was applied to the ANFIS, kinetic modeling, and response surface methodology. The obtained results demonstrate that these three models are in good agreement with the experimental data. The NF model showed the best results of all.",
    author = "Mehdi Sedighi and Mostafa Ghasemi and Majid Mohammadi and Hassan, {Sedky H A}",
    year = "2014",
    doi = "10.1039/c4ra02392g",
    language = "English",
    volume = "4",
    pages = "28390--28399",
    journal = "RSC Advances",
    issn = "2046-2069",
    publisher = "Royal Society of Chemistry",
    number = "54",

    }

    TY - JOUR

    T1 - A novel application of a neuro-fuzzy computational technique in modeling of thermal cracking of heavy feedstock to light olefin

    AU - Sedighi, Mehdi

    AU - Ghasemi, Mostafa

    AU - Mohammadi, Majid

    AU - Hassan, Sedky H A

    PY - 2014

    Y1 - 2014

    N2 - In the present paper, the ability and accuracy of an Adaptive Neuro-Fuzzy Inference System (ANFIS) was investigated for the process evaluation of thermal cracking to light olefin. The main objective of this research is to predict product yields as a function of Coil Outlet Temperature (COT), steam ratio, and feed flow rate, at the reactor tube outlet. Temperature, flow rate and steam-to-hydrocarbon ratio were in the range of 1023-1173 K, 3-7 g g -1, and 0.5-1.4 g min-1, respectively. The Adaptive Network-Based Fuzzy Inference System (ANFIS) technique was trained using historical data to generate the membership functions and rules that best interpret the input/output relationships of the process. Four fuzzy inference systems were independently developed for four output parameters, each of which consisted of three inputs and 27 rules. In order to better understand the capability of the present technique, an extensive comparison test was applied to the ANFIS, kinetic modeling, and response surface methodology. The obtained results demonstrate that these three models are in good agreement with the experimental data. The NF model showed the best results of all.

    AB - In the present paper, the ability and accuracy of an Adaptive Neuro-Fuzzy Inference System (ANFIS) was investigated for the process evaluation of thermal cracking to light olefin. The main objective of this research is to predict product yields as a function of Coil Outlet Temperature (COT), steam ratio, and feed flow rate, at the reactor tube outlet. Temperature, flow rate and steam-to-hydrocarbon ratio were in the range of 1023-1173 K, 3-7 g g -1, and 0.5-1.4 g min-1, respectively. The Adaptive Network-Based Fuzzy Inference System (ANFIS) technique was trained using historical data to generate the membership functions and rules that best interpret the input/output relationships of the process. Four fuzzy inference systems were independently developed for four output parameters, each of which consisted of three inputs and 27 rules. In order to better understand the capability of the present technique, an extensive comparison test was applied to the ANFIS, kinetic modeling, and response surface methodology. The obtained results demonstrate that these three models are in good agreement with the experimental data. The NF model showed the best results of all.

    UR - http://www.scopus.com/inward/record.url?scp=84903977771&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84903977771&partnerID=8YFLogxK

    U2 - 10.1039/c4ra02392g

    DO - 10.1039/c4ra02392g

    M3 - Article

    AN - SCOPUS:84903977771

    VL - 4

    SP - 28390

    EP - 28399

    JO - RSC Advances

    JF - RSC Advances

    SN - 2046-2069

    IS - 54

    ER -