Modeling the slake durability index using regression analysis, artificial neural networks and adaptive neuro-fuzzy methods

KOLAY E., KAYABALI K., TAŞDEMİR Y.

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, cilt.69, sa.2, ss.275-286, 2010 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 69 Sayı: 2
  • Basım Tarihi: 2010
  • Doi Numarası: 10.1007/s10064-009-0259-1
  • Dergi Adı: BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.275-286
  • Anahtar Kelimeler: Slake durability index, Regression analysis, Artificial neural networks, Adaptive neuro-fuzzy inference systems, FEEDFORWARD NETWORKS, PREDICTION, ROCK
  • Yozgat Bozok Üniversitesi Adresli: Evet

Özet

Clay bearing, weathered and other weak rocks cause major problems in engineering practice due to their interactions with water. The slake durability index (I (d2)) is an important tool used to assess the resistance of these rocks to erosion and degradation, but sample preparation for this test is tedious. The paper reports an attempt to define I (d2) through statistical models using other parameters that are simpler to obtain. The main objective of this study was to define the best empirical relationship between the I (d2) and the point load strength index (I (s(50))), dry unit weight (gamma (d)) and fractal dimension (D) parameters of eight rock types by applying general multiple linear regression (GLM), artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS). The models obtained were evaluated using the R (2), MSE, MARE and d parameters. The results indicate that the relationships between I (d2) and gamma (d), I (s(50)) and D were best obtained using ANN, followed by GLM and ANFIS. It is concluded that ANN modelling is a fast and practical method of establishing I (d2).