Flow regime identification of co-current downward two-phase flow with neural network approach

Hiroshi Goda, Ye Mi, Joshua P. Finch, Seungjin Kim, Mamoru Ishii, Jennifer Uhle

    Research output: Contribution to conferencePaper

    6 Citations (Scopus)

    Abstract

    Flow regime identification for an adiabatic vertical cocurrent downward air-water two-phase flow in the 25.4 mm ID and the 50.8 mm ID round tubes was performed by employing an impedance void meter coupled with the neural network classification approach. This approach minimizes the subjective judgment in determining the flow regimes. The signals obtained by an impedance void meter were applied to train the self-organizing neural network to categorize these impedance signals into a certain number of groups. The characteristic parameters set into the neural network classification included the mean, standard deviation and skewness of impedance signals in the present experiment. The classification categories adopted in the present investigation were four widely accepted flow regimes, viz. bubbly, slug, churn-turbulent, and annular flows. These four flow regimes were recognized based upon the conventional flow visualization approach by a high-speed motion analyzer. The resulting flow regime maps classified by the neural network were compared with the results obtained through the flow visualization method, and consequently the efficiency of the neural network classification for flow regime identification was demonstrated.

    Original languageEnglish (US)
    Pages71-78
    Number of pages8
    DOIs
    StatePublished - Oct 19 2002
    Event10th International Conference on Nuclear Engineering (ICONE 10) - Arlington, VA, United States
    Duration: Apr 14 2002Apr 18 2002

    Other

    Other10th International Conference on Nuclear Engineering (ICONE 10)
    CountryUnited States
    CityArlington, VA
    Period4/14/024/18/02

    Fingerprint

    Two phase flow
    Neural networks
    Flow visualization
    Air
    Water
    Experiments

    All Science Journal Classification (ASJC) codes

    • Nuclear Energy and Engineering

    Cite this

    Goda, H., Mi, Y., Finch, J. P., Kim, S., Ishii, M., & Uhle, J. (2002). Flow regime identification of co-current downward two-phase flow with neural network approach. 71-78. Paper presented at 10th International Conference on Nuclear Engineering (ICONE 10), Arlington, VA, United States. https://doi.org/10.1115/ICONE10-22088
    Goda, Hiroshi ; Mi, Ye ; Finch, Joshua P. ; Kim, Seungjin ; Ishii, Mamoru ; Uhle, Jennifer. / Flow regime identification of co-current downward two-phase flow with neural network approach. Paper presented at 10th International Conference on Nuclear Engineering (ICONE 10), Arlington, VA, United States.8 p.
    @conference{d68727e92a2a422e8e92a4d42c73ee70,
    title = "Flow regime identification of co-current downward two-phase flow with neural network approach",
    abstract = "Flow regime identification for an adiabatic vertical cocurrent downward air-water two-phase flow in the 25.4 mm ID and the 50.8 mm ID round tubes was performed by employing an impedance void meter coupled with the neural network classification approach. This approach minimizes the subjective judgment in determining the flow regimes. The signals obtained by an impedance void meter were applied to train the self-organizing neural network to categorize these impedance signals into a certain number of groups. The characteristic parameters set into the neural network classification included the mean, standard deviation and skewness of impedance signals in the present experiment. The classification categories adopted in the present investigation were four widely accepted flow regimes, viz. bubbly, slug, churn-turbulent, and annular flows. These four flow regimes were recognized based upon the conventional flow visualization approach by a high-speed motion analyzer. The resulting flow regime maps classified by the neural network were compared with the results obtained through the flow visualization method, and consequently the efficiency of the neural network classification for flow regime identification was demonstrated.",
    author = "Hiroshi Goda and Ye Mi and Finch, {Joshua P.} and Seungjin Kim and Mamoru Ishii and Jennifer Uhle",
    year = "2002",
    month = "10",
    day = "19",
    doi = "10.1115/ICONE10-22088",
    language = "English (US)",
    pages = "71--78",
    note = "10th International Conference on Nuclear Engineering (ICONE 10) ; Conference date: 14-04-2002 Through 18-04-2002",

    }

    Goda, H, Mi, Y, Finch, JP, Kim, S, Ishii, M & Uhle, J 2002, 'Flow regime identification of co-current downward two-phase flow with neural network approach', Paper presented at 10th International Conference on Nuclear Engineering (ICONE 10), Arlington, VA, United States, 4/14/02 - 4/18/02 pp. 71-78. https://doi.org/10.1115/ICONE10-22088

    Flow regime identification of co-current downward two-phase flow with neural network approach. / Goda, Hiroshi; Mi, Ye; Finch, Joshua P.; Kim, Seungjin; Ishii, Mamoru; Uhle, Jennifer.

    2002. 71-78 Paper presented at 10th International Conference on Nuclear Engineering (ICONE 10), Arlington, VA, United States.

    Research output: Contribution to conferencePaper

    TY - CONF

    T1 - Flow regime identification of co-current downward two-phase flow with neural network approach

    AU - Goda, Hiroshi

    AU - Mi, Ye

    AU - Finch, Joshua P.

    AU - Kim, Seungjin

    AU - Ishii, Mamoru

    AU - Uhle, Jennifer

    PY - 2002/10/19

    Y1 - 2002/10/19

    N2 - Flow regime identification for an adiabatic vertical cocurrent downward air-water two-phase flow in the 25.4 mm ID and the 50.8 mm ID round tubes was performed by employing an impedance void meter coupled with the neural network classification approach. This approach minimizes the subjective judgment in determining the flow regimes. The signals obtained by an impedance void meter were applied to train the self-organizing neural network to categorize these impedance signals into a certain number of groups. The characteristic parameters set into the neural network classification included the mean, standard deviation and skewness of impedance signals in the present experiment. The classification categories adopted in the present investigation were four widely accepted flow regimes, viz. bubbly, slug, churn-turbulent, and annular flows. These four flow regimes were recognized based upon the conventional flow visualization approach by a high-speed motion analyzer. The resulting flow regime maps classified by the neural network were compared with the results obtained through the flow visualization method, and consequently the efficiency of the neural network classification for flow regime identification was demonstrated.

    AB - Flow regime identification for an adiabatic vertical cocurrent downward air-water two-phase flow in the 25.4 mm ID and the 50.8 mm ID round tubes was performed by employing an impedance void meter coupled with the neural network classification approach. This approach minimizes the subjective judgment in determining the flow regimes. The signals obtained by an impedance void meter were applied to train the self-organizing neural network to categorize these impedance signals into a certain number of groups. The characteristic parameters set into the neural network classification included the mean, standard deviation and skewness of impedance signals in the present experiment. The classification categories adopted in the present investigation were four widely accepted flow regimes, viz. bubbly, slug, churn-turbulent, and annular flows. These four flow regimes were recognized based upon the conventional flow visualization approach by a high-speed motion analyzer. The resulting flow regime maps classified by the neural network were compared with the results obtained through the flow visualization method, and consequently the efficiency of the neural network classification for flow regime identification was demonstrated.

    UR - http://www.scopus.com/inward/record.url?scp=0036387963&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0036387963&partnerID=8YFLogxK

    U2 - 10.1115/ICONE10-22088

    DO - 10.1115/ICONE10-22088

    M3 - Paper

    AN - SCOPUS:0036387963

    SP - 71

    EP - 78

    ER -

    Goda H, Mi Y, Finch JP, Kim S, Ishii M, Uhle J. Flow regime identification of co-current downward two-phase flow with neural network approach. 2002. Paper presented at 10th International Conference on Nuclear Engineering (ICONE 10), Arlington, VA, United States. https://doi.org/10.1115/ICONE10-22088