Artificial neural networks for mechanical strength prediction of lightweight mortar

S. V. Razavi, M. Z. Jumaat, Ahmed H. Ei-Shafie, Pegah Mohammadi

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    In this paper, the practical results of 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% of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content have been used to generate artificial neural networks (ANNs). Totally, 52 feed-forward back-propagation neural networks (FFBNN) with different parameters have been investigated in the case of 80 data for training, 15 data for verifying, and 10 data for testing. The performance for producing networks was evaluated by root mean squared error (RMSE) and the correlation coefficient between data. The two selected networks, N1 (Net Architecture 2-10-2) and N2 (Net Architecture 2-10-5-2) had (0.020, 0.027) and (0.017, 0.018) as (Training, Testing) RMSE set and 0.997 and 0.982 as testing correlation coefficient.

    Original languageEnglish
    Pages (from-to)3406-3417
    Number of pages12
    JournalScientific Research and Essays
    Volume6
    Issue number16
    Publication statusPublished - 19 Aug 2011

    Fingerprint

    Mortar
    neural networks
    Strength of materials
    cement
    Neural networks
    prediction
    Water
    Cements
    Testing
    cements
    predictions
    correlation coefficients
    education
    testing
    Backpropagation
    Sand
    sand
    sands
    water

    Keywords

    • Artificial neural networks
    • Feed-forward back-propagation neural networks
    • Scoria

    ASJC Scopus subject areas

    • Agricultural and Biological Sciences(all)
    • Biochemistry, Genetics and Molecular Biology(all)
    • Medicine(all)
    • Engineering(all)
    • Physics and Astronomy(all)

    Cite this

    Razavi, S. V., Jumaat, M. Z., Ei-Shafie, A. H., & Mohammadi, P. (2011). Artificial neural networks for mechanical strength prediction of lightweight mortar. Scientific Research and Essays, 6(16), 3406-3417.

    Artificial neural networks for mechanical strength prediction of lightweight mortar. / Razavi, S. V.; Jumaat, M. Z.; Ei-Shafie, Ahmed H.; Mohammadi, Pegah.

    In: Scientific Research and Essays, Vol. 6, No. 16, 19.08.2011, p. 3406-3417.

    Research output: Contribution to journalArticle

    Razavi, SV, Jumaat, MZ, Ei-Shafie, AH & Mohammadi, P 2011, 'Artificial neural networks for mechanical strength prediction of lightweight mortar', Scientific Research and Essays, vol. 6, no. 16, pp. 3406-3417.
    Razavi SV, Jumaat MZ, Ei-Shafie AH, Mohammadi P. Artificial neural networks for mechanical strength prediction of lightweight mortar. Scientific Research and Essays. 2011 Aug 19;6(16):3406-3417.
    Razavi, S. V. ; Jumaat, M. Z. ; Ei-Shafie, Ahmed H. ; Mohammadi, Pegah. / Artificial neural networks for mechanical strength prediction of lightweight mortar. In: Scientific Research and Essays. 2011 ; Vol. 6, No. 16. pp. 3406-3417.
    @article{ca3bc04a3fc143c999f2278a4f440763,
    title = "Artificial neural networks for mechanical strength prediction of lightweight mortar",
    abstract = "In this paper, the practical results of 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{\%} of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content have been used to generate artificial neural networks (ANNs). Totally, 52 feed-forward back-propagation neural networks (FFBNN) with different parameters have been investigated in the case of 80 data for training, 15 data for verifying, and 10 data for testing. The performance for producing networks was evaluated by root mean squared error (RMSE) and the correlation coefficient between data. The two selected networks, N1 (Net Architecture 2-10-2) and N2 (Net Architecture 2-10-5-2) had (0.020, 0.027) and (0.017, 0.018) as (Training, Testing) RMSE set and 0.997 and 0.982 as testing correlation coefficient.",
    keywords = "Artificial neural networks, Feed-forward back-propagation neural networks, Scoria",
    author = "Razavi, {S. V.} and Jumaat, {M. Z.} and Ei-Shafie, {Ahmed H.} and Pegah Mohammadi",
    year = "2011",
    month = "8",
    day = "19",
    language = "English",
    volume = "6",
    pages = "3406--3417",
    journal = "Scientific Research and Essays",
    issn = "1992-2248",
    publisher = "Academic Journals",
    number = "16",

    }

    TY - JOUR

    T1 - Artificial neural networks for mechanical strength prediction of lightweight mortar

    AU - Razavi, S. V.

    AU - Jumaat, M. Z.

    AU - Ei-Shafie, Ahmed H.

    AU - Mohammadi, Pegah

    PY - 2011/8/19

    Y1 - 2011/8/19

    N2 - In this paper, the practical results of 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% of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content have been used to generate artificial neural networks (ANNs). Totally, 52 feed-forward back-propagation neural networks (FFBNN) with different parameters have been investigated in the case of 80 data for training, 15 data for verifying, and 10 data for testing. The performance for producing networks was evaluated by root mean squared error (RMSE) and the correlation coefficient between data. The two selected networks, N1 (Net Architecture 2-10-2) and N2 (Net Architecture 2-10-5-2) had (0.020, 0.027) and (0.017, 0.018) as (Training, Testing) RMSE set and 0.997 and 0.982 as testing correlation coefficient.

    AB - In this paper, the practical results of 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% of scoria instead of sand and 0.55 water-cement ratio and 350 kg/m3 cement content have been used to generate artificial neural networks (ANNs). Totally, 52 feed-forward back-propagation neural networks (FFBNN) with different parameters have been investigated in the case of 80 data for training, 15 data for verifying, and 10 data for testing. The performance for producing networks was evaluated by root mean squared error (RMSE) and the correlation coefficient between data. The two selected networks, N1 (Net Architecture 2-10-2) and N2 (Net Architecture 2-10-5-2) had (0.020, 0.027) and (0.017, 0.018) as (Training, Testing) RMSE set and 0.997 and 0.982 as testing correlation coefficient.

    KW - Artificial neural networks

    KW - Feed-forward back-propagation neural networks

    KW - Scoria

    UR - http://www.scopus.com/inward/record.url?scp=80052053386&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=80052053386&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:80052053386

    VL - 6

    SP - 3406

    EP - 3417

    JO - Scientific Research and Essays

    JF - Scientific Research and Essays

    SN - 1992-2248

    IS - 16

    ER -