Prediction of swelling pressures of expansive soils using artificial neural networks


İKİZLER S. B., AYTEKIN M., Vekli M., Kocabas F.

ADVANCES IN ENGINEERING SOFTWARE, cilt.41, sa.4, ss.647-655, 2010 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 41 Sayı: 4
  • Basım Tarihi: 2010
  • Doi Numarası: 10.1016/j.advengsoft.2009.12.005
  • Dergi Adı: ADVANCES IN ENGINEERING SOFTWARE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.647-655
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

Swelling behavior of expansive soil is a complicated phenomenon. In order to cope with the complications in describing the swelling behavior of expansive soil, researchers developed alternative approaches. In this paper, the prediction model of transmitted lateral swelling pressure, and vertical swelling pressures on a retaining structure was developed using artificial neural network (ANN) approach. in the first stage of this study, the lateral and vertical swelling pressures were measured with different thicknesses of expanded polystyrene (EPS) geofoam placed between one of the vertical walls of the steel testing box and the expansive soil. Then, artificial neural network was trained using these pressures for prediction transmitted lateral swelling pressure, and vertical swelling pressures on a retaining structure. Results obtained from this study showed that neural network-based prediction models could satisfactorily be used in obtaining the swelling pressures of the expansive soils. (C) 2009 Elsevier Ltd. All rights reserved.