New Applications of a Supervised Computational Intelligence (CI) Approach: Case Study in Civil Engineering
In this study, artificial neural network (ANN) techniques are used in an attempt to predict the nonlinear hyperbolic soil stress–strain relationship parameters (k and Rf). Two ANN models are developed and trained to achieve the planned target, in an attempt at making the experimental test (unconsolidated undrained triaxial test) unnecessary. The first is logarithm of modulus number (log k), and the second is failure ratio (Rf). A database of laboratory measurements comprises a total of (83) case records for modulus number (k) and failure ratio (Rf). Four parameters are considered to have the most significant impact on the nonlinear soil stress–strain relationship parameters, which are used as an independent input variables (IIVs) to the developed the proposed ANNs models. These comprise of: Plasticity index (PI), Dry unit weight (γdry), Water content (ωo), and Confining stress (σ3), the output models are respectively, (log k), and (Rf). Multilayer perceptron trainings using back-propagation algorithm are used in this work. The effect of a number of issues in relation to ANN construction such as ANN geometry and internal parameters on the performance of ANN models is investigated. Information on the relative importance of the factors affecting the (log k), and (Rf) is presented, and practical equations for their prediction are proposed.
KeywordsArtificial neural network (ANN) Soil stress–strain parameters Unconsolidated undrained triaxial test Supervised computational intelligence
The authors would like to acknowledge the Iraqi Ministry of Higher Education and Scientific Research and Wasit University for the grant provided to carry out this research under the grant agreement number 162575, dated 28/05/2013, with the Liverpool John Moores University, university reference number (744221).
- 4.Millie, D. F., Weckman, G. R., Young II, W. A., Ivey, J. E., Carrick, H. J., & Fahnenstiel, G. L. (2012). Modeling microalgal abundance with artificial neural networks: Demonstration of a heuristic ‘grey-box’ to deconvolve and quantify environmental influences. Environmental Modelling and Software, 38, 27–39.CrossRefGoogle Scholar
- 9.Alizadeh, B., Najjari, S., & Kadkhodaie-Ilkhchi, A. (2012). Artificial neural network modeling and cluster analysis for organic facies and burial history estimation using well log data: A case study of the South Pars Gas Field, Persian Gulf, Iran. Computers and Geosciences, 45, 261–269.CrossRefGoogle Scholar
- 16.Kriesel, D. (2011). Brief introduction to neural networks [Online]. University of Bonn, Germany. Retrieved July 20, 2018, from http://www.dkriesel.com/_media/science/neuronalenetze-en-zeta2-2col-dkrieselcom.pdf.
- 19.Caudill, M. (1988). Neural networks primer. Part III. AI Expert, 3(6), 53–59.Google Scholar
- 21.Al-Janabi, K. R. (2006). Laboratory leaching process modeling in gypseous soils using Artificial Neural Networks (ANNs). PhD thesis, Building and Construction Engineering Department, University of Technology, Iraq.Google Scholar
- 22.Garson, G. D. (1991). Interpreting neural-network connection weights. AI Expert, 6, 46–51.Google Scholar
- 23.Wong, K. S., & Duncan, J. M. (1974). Hyperbolic stress–strain parameters for nonlinear finite element analyses of stresses and movements in soil masses. La Jolla, CA: College of Engineering, Office of Research Services, University of California.Google Scholar
- 24.Abdellatif, M. E. M. (2013). Modelling the impact of climate change on urban drainage system. PhD thesis, Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool, UK.Google Scholar