Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar

S. V. Razavi, M. Z. Jumaat, El Shafie Ahmed, P. Mohammadi

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    In this paper, the mechanical strength of different lightweight mortars made with 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95 and 100 percentage of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content is investigated. The experimental result showed 7.9%, 16.7% and 49% decrease in compressive strength, tensile strength and mortar density, respectively, by using 100% scoria instead of sand in the mortar. The normalized compressive and tensile strength data are applied for artificial neural network (ANN) generation using generalized regression neural network (GRNN). Totally, 90 experimental data were selected randomly and applied to find the best network with minimum mean square error (MSE) and maximum correlation of determination. The created GRNN with 2 input layers, 2 output layers and a network spread of 0.1 had minimum MSE close to 0 and maximum correlation of determination close to 1.

    Original languageEnglish
    Pages (from-to)379-390
    Number of pages12
    JournalComputers and Concrete
    Volume10
    Issue number4
    Publication statusPublished - Oct 2012

    Fingerprint

    Mortar
    Strength of materials
    Neural networks
    Mean square error
    Compressive strength
    Cements
    Tensile strength
    Sand
    Water

    Keywords

    • ANN
    • GRNN
    • Mechanical strength
    • MSE
    • Scoria

    ASJC Scopus subject areas

    • Computational Mechanics

    Cite this

    Razavi, S. V., Jumaat, M. Z., Ahmed, E. S., & Mohammadi, P. (2012). Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar. Computers and Concrete, 10(4), 379-390.

    Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar. / Razavi, S. V.; Jumaat, M. Z.; Ahmed, El Shafie; Mohammadi, P.

    In: Computers and Concrete, Vol. 10, No. 4, 10.2012, p. 379-390.

    Research output: Contribution to journalArticle

    Razavi, SV, Jumaat, MZ, Ahmed, ES & Mohammadi, P 2012, 'Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar', Computers and Concrete, vol. 10, no. 4, pp. 379-390.
    Razavi, S. V. ; Jumaat, M. Z. ; Ahmed, El Shafie ; Mohammadi, P. / Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar. In: Computers and Concrete. 2012 ; Vol. 10, No. 4. pp. 379-390.
    @article{88ffeb51c28f4a0a96c49c09188eee81,
    title = "Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar",
    abstract = "In this paper, the mechanical strength of different lightweight mortars made with 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95 and 100 percentage of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content is investigated. The experimental result showed 7.9{\%}, 16.7{\%} and 49{\%} decrease in compressive strength, tensile strength and mortar density, respectively, by using 100{\%} scoria instead of sand in the mortar. The normalized compressive and tensile strength data are applied for artificial neural network (ANN) generation using generalized regression neural network (GRNN). Totally, 90 experimental data were selected randomly and applied to find the best network with minimum mean square error (MSE) and maximum correlation of determination. The created GRNN with 2 input layers, 2 output layers and a network spread of 0.1 had minimum MSE close to 0 and maximum correlation of determination close to 1.",
    keywords = "ANN, GRNN, Mechanical strength, MSE, Scoria",
    author = "Razavi, {S. V.} and Jumaat, {M. Z.} and Ahmed, {El Shafie} and P. Mohammadi",
    year = "2012",
    month = "10",
    language = "English",
    volume = "10",
    pages = "379--390",
    journal = "Computers and Concrete",
    issn = "1598-8198",
    publisher = "Techno Press",
    number = "4",

    }

    TY - JOUR

    T1 - Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar

    AU - Razavi, S. V.

    AU - Jumaat, M. Z.

    AU - Ahmed, El Shafie

    AU - Mohammadi, P.

    PY - 2012/10

    Y1 - 2012/10

    N2 - In this paper, the mechanical strength of different lightweight mortars made with 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95 and 100 percentage of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content is investigated. The experimental result showed 7.9%, 16.7% and 49% decrease in compressive strength, tensile strength and mortar density, respectively, by using 100% scoria instead of sand in the mortar. The normalized compressive and tensile strength data are applied for artificial neural network (ANN) generation using generalized regression neural network (GRNN). Totally, 90 experimental data were selected randomly and applied to find the best network with minimum mean square error (MSE) and maximum correlation of determination. The created GRNN with 2 input layers, 2 output layers and a network spread of 0.1 had minimum MSE close to 0 and maximum correlation of determination close to 1.

    AB - In this paper, the mechanical strength of different lightweight mortars made with 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95 and 100 percentage of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content is investigated. The experimental result showed 7.9%, 16.7% and 49% decrease in compressive strength, tensile strength and mortar density, respectively, by using 100% scoria instead of sand in the mortar. The normalized compressive and tensile strength data are applied for artificial neural network (ANN) generation using generalized regression neural network (GRNN). Totally, 90 experimental data were selected randomly and applied to find the best network with minimum mean square error (MSE) and maximum correlation of determination. The created GRNN with 2 input layers, 2 output layers and a network spread of 0.1 had minimum MSE close to 0 and maximum correlation of determination close to 1.

    KW - ANN

    KW - GRNN

    KW - Mechanical strength

    KW - MSE

    KW - Scoria

    UR - http://www.scopus.com/inward/record.url?scp=84869817201&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84869817201&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:84869817201

    VL - 10

    SP - 379

    EP - 390

    JO - Computers and Concrete

    JF - Computers and Concrete

    SN - 1598-8198

    IS - 4

    ER -