A Neuro-Genetic Network for Predicting Uniaxial Compressive Strength of Rocks

Uniaxial Compressive Strength (UCS) is considered as one of the most important parameters in designing rock structures. Determination of this parameter requires preparation of rock samples which is costly and time consuming. Moreover discrepancy of laboratory test results is often observed. To overcome the drawbacks of traditional method of UCS measurement, in this paper, predictive models based on neuro-genetic approach and multivariable regression analysis have been developed for predicting compressive strength of different type of rocks. Coefficient of determinatoin (R2) and the Mean Square Error (MSE) were calculated for comparison of the models' efficiency. It was observed that accuracy of the neuro-genetic model is significantly better than regression model. For the neuro-genetic and regression models, R2 and MSE were equal to 95.89 % and 0.0045 and 77.4 % and 1.61, respec- tively. According to sensitivity analysis for neuro- genetic model, Schmidt rebound number is the most effective parameter in predicting UCS.

[1]  Stefan Bornholdt,et al.  General asymmetric neural networks and structure design by genetic algorithms: a learning rule for temporal patterns , 1992, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[2]  Adnan Aydin,et al.  The Schmidt hammer in rock material characterization , 2005 .

[3]  Marcel Hürlimann,et al.  A Comparison of Different Indirect Techniques to Evaluate Volcanic Intact Rock Strength , 2009 .

[4]  Khalil Rahman,et al.  Rock Strength from Core and Logs, Where We Stand and Ways to Go , 2009 .

[5]  Ebru Akcapinar Sezer,et al.  Modeling of the uniaxial compressive strength of some clay-bearing rocks using neural network , 2011, Appl. Soft Comput..

[6]  J. O'rourke.  Rock index properties for geoengineering in underground development , 1989 .

[7]  Hun Hee Cho,et al.  Neural network model incorporating a genetic algorithm in estimating construction costs , 2004 .

[8]  L. Dobereiner,et al.  GEOTECHNICAL PROPERTIES OF WEAK SANDSTONES , 1986 .

[9]  Robert L. Schaefer,et al.  An Introduction to Computational Statistics: Regression Analysis , 1996 .

[10]  Candan Gokceoglu,et al.  Draft ISRM suggested method for determining block punch strength index (BPI) , 2001 .

[11]  Adrian R. Russell,et al.  Point load tests and strength measurements for brittle spheres , 2009 .

[12]  V. Kelessidis.  Rock drillability prediction from in situ determined unconfined compressive strength of rock , 2011 .

[13]  O. Gunaydin,et al.  Predicting the Schmidt hammer values of in–situ intact rock from core sample values , 2002 .

[14]  Bhawani Singh,et al.  Schmidt hammer rebound data for estimation of large scale in situ coal strength , 1984 .

[15]  Z. Moradian,et al.  Predicting the Uniaxial Compressive Strength and Static Young's Modulus of Intact Sedimentary Rocks Using the Ultrasonic Test , 2009 .

[16]  J. A. Franklin,et al.  Suggested method for determining point load strength , 1985 .

[17]  S. Kahraman,et al.  A Comparative Evaluation of Indirect Methods to Estimate the Compressive Strength of Rocks , 2005 .

[18]  O. Onal,et al.  Predicting Uniaxial Compressive Strengths of Brecciated Rock Specimens using neural networks and different learning models , 2008, 2008 23rd International Symposium on Computer and Information Sciences.

[19]  Lianyang Zhang,et al.  Study of scale effect on intact rock strength using particle flow modeling , 2011 .

[20]  Yi Huang,et al.  Application of artificial neural networks to predictions of aggregate quality parameters , 1999 .

[21]  P. Pomonis,et al.  Microcracks in ultrabasic rocks under uniaxial compressive stress , 2011 .

[22]  E. Yaşar,et al.  Estimation of rock physicomechanical properties using hardness methods , 2004 .

[23]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[24]  Umit Atici,et al.  Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network , 2011, Expert Syst. Appl..

[25]  R. Altindag,et al.  Dynamic mechanical behavior of some carbonate rocks , 2010 .

[26]  Mohammed Seddik Meddah,et al.  Effect of content and particle size distribution of coarse aggregate on the compressive strength of concrete , 2010 .

[27]  Abdul Shakoor,et al.  A Laboratory Investigation of the Effects of Cyclic Heating and Cooling, Wetting and Drying, and Freezing and Thawing on the Compressive Strength of Selected Sandstones , 2003 .

[28]  Djebbar Tiab,et al.  Point-Load Strength Test , 2004 .

[29]  Oded Katz,et al.  Evaluation of mechanical rock properties using a Schmidt Hammer , 2000 .

[30]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[31]  Fred Bell,et al.  Rock properties and their assessment , 2005 .

[32]  Ş. Niculescu.  Artificial neural networks and genetic algorithms in QSAR , 2003 .

[33]  T. N. Singh,et al.  Prediction of strength properties of some schistose rocks from petrographic properties using artificial neural networks , 2001 .

[34]  Kamil Kayabali,et al.  Nail penetration test for determining the uniaxial compressive strength of rock , 2010 .

[35]  F. P. Hassani,et al.  The Application Of Strength And Deformation Index Testing To The Stability Assessment Of Coal Measures Excavations , 1983 .

[36]  Yi Huang,et al.  The introduction of neural network system and its applications in rock engineering , 1998 .

[37]  R. Ulusay,et al.  Prediction of engineering properties of a selected litharenite sandstone from its petrographic characteristics using correlation and multivariate statistical techniques , 1994 .

[38]  Arindam Basu,et al.  Point load test on schistose rocks and its applicability in predicting uniaxial compressive strength , 2010 .

[39]  Paulo B. Lourenço,et al.  Prediction of the mechanical properties of granites by ultrasonic pulse velocity and Schmidt hammer hardness , 2007 .

[40]  Edward J. Cording,et al.  Estimation of rock engineering properties using hardness tests , 2007 .

[41]  F. Bell.  The physical and mechanical properties of the fell sandstones, Northumberland, England , 1978 .

[42]  A. K. Dube,et al.  Effect of humidity on Tensile Strength of Sandstone , 1972 .

[43]  S. N. Sivanandam,et al.  Introduction to genetic algorithms , 2007 .

[44]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[45]  Işık Yilmaz,et al.  A new testing method for indirect determination of the unconfined compressive strength of rocks , 2009 .

[46]  Z. T. Bieniawski,et al.  The point-load test in geotechnical practice , 1975 .

[47]  D. B. Fogel,et al.  Evolving neural networks , 1990, Biological Cybernetics.

[48]  Z. Bieniawski.  Estimating the strength of rock materials , 1974 .

[49]  Seung-Chang Lee,et al.  Prediction of concrete strength using artificial neural networks , 2003 .

[50]  T. Singh,et al.  A correlation between P-wave velocity, impact strength index, slake durability index and uniaxial compressive strength , 2008 .

[51]  P. Lourenço,et al.  Ultrasonic evaluation of the physical and mechanical properties of granites. , 2008, Ultrasonics.

[52]  C. S. Vishnu,et al.  AMS, ultrasonic P-wave velocity and rock strength analysis in quartzites devoid of mesoscopic foliations – implications for rock mechanics studies , 2010 .

[53]  J H Garrett,et al.  WHERE AND WHY ARTIFICIAL NEURAL NETWORKS ARE APPLICABLE IN CIVIL ENGINEERING , 1994 .