Connectivity and Flowrate Estimation of Discrete Fracture Network Using Artificial Neural Network

Hydraulic parameters of rock mass are the most effective factors that affect rock mass behavioral and mechanical analysis. Aforementioned parameters include intensity and density of fracture intersections, percolation frequency, conductance parameter and mean outflow flowrate which flowing perpendicular to the hydraulic gradient direction. In order to obtain hydraulic parameters, three-dimensional discrete fracture network generator, 3DFAM, was developed. But unfortunately, hydraulic parameters obtaining process using conventional discrete fracture network calculation is either time consuming and tedious. For this reason, in this paper using Artificial Neural Network, a tool is designed which precisely and accurately estimate hydraulic parameters of discrete fracture network. Performance of designed optimum artificial neural network is evaluated from mean Squared error, errors histogram, and correlation between artificial neural network predicted value and with discrete fracture network conventionally calculated value. Results indicate that there is acceptable value of mean squared error and also major part of estimated values deviation from actual value placed in acceptable error interval of (-1.17, 0.85). In the other hand, excellent correlation of 0.98 exist between predicted and actual value that prove reliability of designed artificial neural network.

[1]  Z. Jaeger,et al.  Fluid Flow Through a Crack Network in Rocks , 1983 .

[2]  P. C. Robinson.  Connectivity of fracture systems-a percolation theory approach , 1983 .

[3]  N. Rivier,et al.  A criterion for percolation threshold in a random array of plates , 1984 .

[4]  S. Redner,et al.  Introduction To Percolation Theory , 2018 .

[5]  A. Rouleau,et al.  Statistical characterization of the fracture system in the Stripa granite, Sweden , 1985 .

[6]  Paul A. Witherspoon,et al.  The relationship of the degree of interconnection to permeability in fracture networks , 1985 .

[7]  Björn Dverstorp,et al.  Conditional simulations of fluid flow in three-dimensional networks of discrete fractures , 1987 .

[8]  G. Marsily,et al.  Modeling fracture flow with a stochastic discrete fracture network: calibration and validation: 1. The flow model , 1990 .

[9]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[10]  Cheng-Haw Lee,et al.  Fluid flow and connectivity in fractured rock , 1993 .

[11]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[12]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[13]  Olivier Bour,et al.  Connectivity of random fault networks following a power law fault length distribution , 1997 .

[14]  Olivier Bour,et al.  On the connectivity of three‐dimensional fault networks , 1998 .

[15]  Rajat Gupta,et al.  Applied Hydrogeology of Fractured Rocks , 1999 .

[16]  S. W. Hong,et al.  Neural network based prediction of ground surface settlements due to tunnelling , 2001 .

[17]  C. Gokceoğlu,et al.  Predicting the deformation moduli of rock masses , 2003 .

[18]  J. Kemeny,et al.  Estimating three-dimensional rock discontinuity orientation from digital images of fracture traces , 2003 .

[19]  Olivier Bour,et al.  Connectivity properties of two‐dimensional fracture networks with stochastic fractal correlation , 2003 .

[20]  Dimitris Kaliampakos,et al.  Modelling TBM performance with artificial neural networks , 2004 .

[21]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[22]  Kanti V. Mardia,et al.  A Connectivity Index for Discrete Fracture Networks , 2007 .

[23]  Holger R. Maier,et al.  Bayesian model selection applied to artificial neural networks used for water resources modeling , 2008 .

[24]  A. Baghbanan.  Scale and Stress Effects on Hydro-Mechanical Properties of Fractured Rock Masses , 2008 .

[25]  K. P. Sudheer,et al.  Ultimate bearing capacity prediction of shallow foundations on cohesionless soils using neurofuzzy models , 2008 .

[26]  Wu Qiong,et al.  Mean particle size prediction in rock blast fragmentation using neural networks , 2010 .

[27]  Chaoshui Xu,et al.  A new computer code for discrete fracture network modelling , 2010, Comput. Geosci..

[28]  Sara Kvartsberg.  Hydrogeological characterisation of a fracture network: Case study of horizontal drifts at Äspö Hard Rock Laboratory , 2010 .

[29]  Masoud Monjezi,et al.  Prediction of Rock Fragmentation Due to Blasting in Sarcheshmeh Copper Mine Using Artificial Neural Networks , 2010 .

[30]  Patrick Jenny,et al.  MODELING OF FLOW AND TRANSPORT IN ENHANCED GEOTHERMAL SYSTEMS , 2011 .

[31]  Isam Shahrour,et al.  Back Analysis of Equivalent Permeability Tensor for Fractured Rock Masses from Packer Tests , 2011 .

[32]  Robert W. Zimmerman,et al.  Estimating the Hydraulic Conductivity of Two-Dimensional Fracture Networks Using Network Geometric Properties , 2010, Transport in Porous Media.

[33]  Chaoshui Xu,et al.  Connectivity analysis of the Habanero enhanced geothermal system , 2012 .

[34]  Thomas C. Badger,et al.  The use of discrete fracture network simulations in the design of horizontal hillslope drainage networks in fractured rock , 2013 .

[35]  Peter A. Dowd,et al.  A Spatial Clustering Approach for Stochastic Fracture Network Modelling , 2014, Rock Mechanics and Rock Engineering.

[36]  A. Ghazvinian,et al.  On the use of the RMR system for estimation of rock mass deformation modulus , 2014, Bulletin of Engineering Geology and the Environment.

[37]  Chaoshui Xu,et al.  CONNECTIVITY INDEX AND CONNECTIVITY FIELD TOWARDS FLUID FLOW IN FRACTURE-BASED GEOTHERMAL RESERVOIRS , 2013 .

[38]  Qihua Zhang,et al.  Solution of two key issues in arbitrary three-dimensional discrete fracture network flow models , 2014 .

[39]  Peter A. Dowd,et al.  Connectivity Field: a Measure for Characterising Fracture Networks , 2014, Mathematical Geosciences.

[40]  Jun Zheng,et al.  Validation of Monte Carlo simulation for discontinuity locations in space , 2015 .

[41]  Pengpeng Ni,et al.  Estimation of REV Size for Fractured Rock Mass Based on Damage Coefficient , 2017, Rock Mechanics and Rock Engineering.

[42]  Yanjun Shang,et al.  Connectivity of Three-Dimensional Fracture Networks: A Case Study from a Dam Site in Southwest China , 2016, Rock Mechanics and Rock Engineering.

[43]  Mohamed A. Shahin,et al.  State-of-the-art review of some artificial intelligence applications in pile foundations , 2016 .