Application of neural network to rock slope stability assessments

It is known that rock masses are inhomogeneous, discontinuous media composed of rock material and naturally occurring discontinuities such as joints, fractures and bedding planes. These features make any analysis very difficult using simple theoretical solutions. Generally speaking, back analysis technique can be used to capture some implicit parameters for geotechnical problems. In order to perform back analyses, the procedure of trial and error is generally required. However, it would be time-consuming. This study aims at applying a neural network to do the back analysis for rock slope failures. The neural network tool will be trained by using the solutions of finite element upper and lower bound limit analysis methods. Therefore, the uncertain parameter can be obtained, particularly for rock mass disturbance.

[1]  Ying Wang,et al.  Parametric Monte Carlo studies of rock slopes based on the Hoek–Brown failure criterion , 2012 .

[2]  Andrei V. Lyamin,et al.  Effect of rock mass disturbance on the stability of rock slopes using the Hoek–Brown failure criterion , 2011 .

[3]  Ralph B. Peck,et al.  Advantages and Limitations of the Observational Method in Applied Soil Mechanics , 1969 .

[4]  Xinghuo Yu,et al.  A fuzzy neural network approximator with fast terminal sliding mode and its applications , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[5]  P. R. Sheorey.  Empirical Rock Failure Criteria , 1997 .

[6]  Zhihong Man,et al.  Finite-time stabilization of stochastic nonlinear systems in strict-feedback form , 2013, Autom..

[7]  Andrei V. Lyamin,et al.  Stability charts for rock slopes based on the Hoek-Brown failure criterion , 2008 .

[8]  W. Fu,et al.  Non-linear shear strength reduction technique in slope stability calculation , 2010 .

[9]  Evert Hoek,et al.  HOEK-BROWN FAILURE CRITERION - 2002 EDITION , 2002 .

[10]  Scott W. Sloan,et al.  Upper bound limit analysis using finite elements and linear programming , 1989 .

[11]  A. Li,et al.  Two and three dimensional stability analyses for soil and rock slopes , 2009 .

[12]  R. S. Merifielda,et al.  Limit analysis solutions for the bearing capacity of rock masses using the generalised Hoek–Brown criterion , 2006 .

[13]  Scott W. Sloan,et al.  A new discontinuous upper bound limit analysis formulation , 2005 .

[14]  Zhihong Man,et al.  Robust Single-Hidden Layer Feedforward Network-Based Pattern Classifier , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Andrei V. Lyamin,et al.  Seismic rock slope stability charts based on limit analysis methods , 2009 .

[16]  Scott W. Sloan,et al.  Lower bound limit analysis using non‐linear programming , 2002 .

[17]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Zhihong Man,et al.  Finite-time stability and instability of stochastic nonlinear systems , 2011, Autom..

[19]  J. Burland.  Ninth Laurits Bjerrum Memorial Lecture: "Small is beautiful"—the stiffness of soils at small strains , 1989 .

[20]  Evert Hoek,et al.  Strength of jointed rock masses , 1983 .

[21]  Scott W. Sloan,et al.  Limit analysis solutions for the bearing capacity of rock masses using the generalised Hoek–Brown criterion , 2006 .

[22]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.