Mansouri, M. (MSc, Mining Department, Tarbiat Modares University) | Torabi, S.R. (Mining Department, Tarbiat Modares University) | Forough, O. (PhD Student, Mining Faculty, Shahrood University of Technology) | Goshtasbi, K. (Assoc. Prof., Mining Department, Tarbiat Modares University)
Ayatollahi, M.R. (Fatigue and fracture laboratory, Department of mechanical engineering, Iran university of science and technology (IUST), Narmak) | Aliha, M.R.M. (Fatigue and fracture laboratory, Department of mechanical engineering, Iran university of science and technology (IUST), Narmak)
Nadimi, S. (Faculty of Mining & Metallurgical Engineering, Amirkabir University of Technology) | Javani, D. (Faculty of Engineering & Technology, Mining & Petroleum Engineering Department) | Shahriar, K. (Associate Professor, Faculty of Mining & Metallurgical Engineering, Amirkabir University of Technology)
In the design of dam structure, one of the most important issues is detection of permeability variation in different levels of the dam site. Several different methods for assessing permeability variations in rock masses can be found in the literatures. In this paper potential of both artificial neural network (AANs) and geostatistics has been used to predict permeability whit regards to Lugeon test results at Ag-chaie dam site on northwestern of Iran. ANNs are computer systems composed of processing elements that are interconnected in particular topology which is the problem dependent (complexity of problem). In other hand, geostatistics is type of statistics that consider spatial dependence of values, hence regional variables of that case is used. we use Kriging as a geostatical method for prediction. The focus of this paper is on the Back Propagation (BP) network to predict permeability. Finally, the results of the both approaches are compared with each other. The comparison shows that the geostatistics has better prediction results.
Proper evaluation of in-situ rock masses, in particular, for dam foundations and the corresponding abutments are the most significant part of rock characterization in dam engineering. Sufficient knowledge of foundation rock’s permeability is essential if water seepage control grouting is required. Permeability data is helpful in other forms of grouting as well. It is obvious that an accurate estimation of ground water flow path based on a limited data obtained from field measurements is cumbersome. Hence, ANNs and geostatistical estimation of spatial distribution of permeable zones in a complex rock formations based on scattered in-situ permeability data is an advantageous. Therefore, effort is made to investigate in-situ permeability of the rock mass in order to estimate spatial distribution of permeable zones. For this purpose, we applied BP network as a ANNs method and the Kriging approach which is one of the most reliable method for geostatistical estimation in the Hydro science to predict the permeability [1, 2]. The dam site area is located in northwestern of Iran and the dam has been planned to be constructed. Single-hole permeability measurement (Lugeon water- pressure test) was carried out for 47 boreholes to a depth of about 75-100 meters below the foundation level in base-rock. 2. Data set Water pressure tests (WPT) were carried out for determination of the dam site permeability. WPT is an effective and widely used method for determination of rock mass permeability. In practice, the Lugeon test is used before and after grouting to quantitative determination the volume of water take per unit of time, then we can calculate lugeon number. The lugeon number may go above 100; however, the scale has no upper limit. Above 100 lugeon it is meaningless to distinguish further . Since, in practice, the maximum meaningful lugeon is considered as 100. In-situ permeability test results as a general assessment of the 47 boreholes at the dam site are show in Table 1.
Farokhnia, M. (Department of mining & metallurgical engineering, Amirkabir University of Technology) | Shahriar, K. (Department of mining & metallurgical engineering, Amirkabir University of Technology) | Sharifzadeh, M. (Department of mining & metallurgical engineering, Amirkabir University of Technology) | Tavakoli, H.R. (Sahel engineering consultant company, Resalat highway) | Shamsi, G.H. (Sahel engineering consultant company, Resalat highway)
Ghazvinian, A.H. (Academic Member, Rock Mechanics Division)) | Setayeshi, S. (Faculty of Nuc. Eng. & Phys., Amir Kabir University of technology) | Sarfarazi, V. (esearch Scholar, Rock Mechanics Division, Tarbiat Modares University) | Moosavi, S.A. (M.Sc. Student, Rock Mechanics Division, Tarbiat Modares University)
Zhu, D.P. (Faculty of Engineering,China University of Geosciences) | Deng, Q.L. (Faculty of Engineering,China University of Geosciences) | Yan, E.C. (Faculty of Engineering,China University of Geosciences)