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

Clay bearing, weathered and other weak rocks cause major problems in engineering practice due to their interactions with water. The slake durability index (Id2) 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 Id2 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 Id2 and the point load strength index (Is(50)), dry unit weight (γd) 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 R2, MSE, MARE and d parameters. The results indicate that the relationships between Id2 and γd, Is(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 Id2.RésuméLes roches argileuses, altérées et d’autres roches tendres causent des problèmes importants dans la pratique du fait de leurs interactions avec l’eau. L’indice de durabilité-humidification (Id2) est un outil important utilisé pour évaluer la résistance de ces roches à l’érosion et à la dégradation, mais la préparation des échantillons pour ce test est fastidieuse. L’article présente une tentative pour définir l’indice Id2 à partir de modèles statistiques utilisant d’autres paramètres plus simples à obtenir. L’objectif principal de cette étude était de définir la meilleure relation empirique entre l’indice de durabilité-humidification (Id2) et l’indice de résistance à la compression entre pointes (Is(50)), le poids spécifique sec (γd) et le paramètre de dimension fractale (D) pour huit types de roche, faisant appel à la régression linéaire multiple générale (GLM), aux réseaux de neurones artificiels (ANN) et au systèmes d’inférence de logique floue (ANFIS). Les modèles obtenus ont été évalués en utilisant les paramètres R2, MSE, MARE et d. Les résultats indiquent que les relations entre Id2 et γd, Is(50) et D ont été plus facilement obtenues en utilisant ANN, suivit de GLM et ANFIS. Il est conclu que la modélisation ANN est une méthode rapide et pratique pour établir Id2.

[1]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[2]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[3]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[4]  C. Willmott.  ON THE VALIDATION OF MODELS , 1981 .

[5]  Işık Yilmaz,et al.  Slaking durability and its effect on the doline formation in the gypsum , 2005 .

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  Daniel W Smith,et al.  A neural network model to predict the wastewater inflow incorporating rainfall events. , 2002, Water research.

[8]  Candan Gokceoglu,et al.  Factors affecting the durability of selected weak and clay-bearing rocks from Turkey, with particular emphasis on the influence of the number of drying and wetting cycles , 2000 .

[9]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[10]  Candan Gokceoglu,et al.  A fuzzy model to predict the uniaxial compressive strength and the modulus of elasticity of a problematic rock , 2004, Eng. Appl. Artif. Intell..

[11]  B. Mandelbrot.  How Long Is the Coast of Britain? Statistical Self-Similarity and Fractional Dimension , 1967, Science.

[12]  Peter K. Robertson,et al.  Collapse of dry sand , 1994 .

[13]  Ozgur Kisi,et al.  Flow prediction by three back propagation techniques using k-fold partitioning of neural network training data , 2005 .

[14]  J. Franklin,et al.  The slake-durability test , 1972 .

[15]  Paul M. Santi,et al.  Predicting the unconfined compressive strength of the Breathitt shale using slake durability, Shore hardness and rock structural properties , 1999 .

[16]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[17]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[18]  Ozgur Kisi,et al.  Daily pan evaporation modelling using a neuro-fuzzy computing technique , 2006 .

[19]  Maged M. Hamed,et al.  Prediction of wastewater treatment plant performance using artificial neural networks , 2004, Environ. Model. Softw..

[20]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[21]  Mustafa Laman,et al.  Settlement and slaking problems in the world's fourth largest rock-fill dam, the Ataturk Dam in Turkey , 2000 .

[22]  Cort J. Willmott,et al.  On the Evaluation of Model Performance in Physical Geography , 1984 .

[23]  M. Rezaee,et al.  Prediction of shear wave velocity from petrophysical data utilizing intelligent systems: An example from a sandstone reservoir of Carnarvon Basin, Australia , 2007 .

[24]  Abdul Shakoor,et al.  A geological approach toward developing a mudrock-durability classification system , 1994 .

[25]  Yong Lu,et al.  Underground blast induced ground shock and its modelling using artificial neural network , 2005 .

[26]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[27]  Kamil Kayabali,et al.  Investigation of the effect of aggregate shape and surface roughness on the slake durability index using the fractal dimension approach , 2006 .

[28]  Ozgur Kisi,et al.  Suspended sediment estimation using neuro-fuzzy and neural network approaches/Estimation des matières en suspension par des approches neurofloues et à base de réseau de neurones , 2005 .

[29]  Katsuhiko Kaneko,et al.  Slake durability and mineralogical properties of some pyroclastic and sedimentary rocks , 2002 .

[30]  Luis E. Vallejo,et al.  Fractal analysis of the slake durability test , 1994 .

[31]  Cort J. Willmott,et al.  Spatial statistics and models , 1984 .

[32]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[33]  T. N. Singh,et al.  Prediction of thermal conductivity of rock through physico-mechanical properties , 2007 .

[34]  J S Weaver,et al.  Creep and strength tests on warm dry spray ice , 1997 .

[35]  H. Riedwyl.  Goodness of Fit , 1967 .