Predicting compressive strength using the texture coefficient with soft computing techniques for rocks

Yıl 2022, Cilt: 11 Sayı: 4, 1127 - 1137, 14.10.2022

Ramazan Çomaklı Ümit Atıcı

https://doi.org/10.28948/ngumuh.1158645

Öz

Rock strength plays one of the most dominant roles for mining, geology, and civil engineering in terms of planning, excavation, and safety. Compressive strength (fc), which is the most used strength type, requires time, cost, and standard size specimens are needed to find it in the laboratory. In this study, Regression Analysis (RA), Neural Networks (NNs), Gene-Expression Programming (GEP), and Adaptive Network-based Fuzzy Inference System (ANFIS) were used for predicting using both textural and mechanical properties which are detected with a dimensionless sample or directly in the field. For this purpose, a data set consists of 136 data value (46 magmatic, 77 sedimentary and 13 metamorphic rocks) was used, and three different feature sets were constructed. The comparison of the estimated results with each other was performed by training, testing, and checking of these models. The comparisons and results of the statistical analyses indicate that soft computing techniques represent significantly effective methods to calculate fc even in situations when input and output values are not related to each other, and it is possible to create statistically suitable and valid mathematical models by everyone using GEP.

Anahtar Kelimeler

Texture coefficient, Compression strength, Adaptive network-based fuzzy inference system, Neural networks, Gene-expression programming.

Kayalar için yapay zekâ hesaplama teknikleri ile doku katsayını kullanarak basınç dayanımını tahmin etme

Öz

Kaya dayanımı, planlama, kazı ve güvenlik açısından madencilik, jeoloji ve inşaat mühendisliği için en baskın rollerden birini oynar. En çok kullanılan dayanım türü olan basınç dayanımını (fc), laboratuvar şartlarında bulmak için zaman, maliyet ve standart boyutlu numunelere ihtiyaç vardır. Bu çalışmada, kayaların şekilsiz numuneler üzerinde veya araziden elde edilen hem doku katsayıları hem de basınç dayanım değerleri regresyon analizi (RA), Sinir Ağları (NN'ler), Gen- ekspresyonu Programlama (GEP) ve Uyarlanabilir Ağ Tabanlı Bulanık Mantık Sistemi (ANFIS) kullanılarak tahmin edilmiştir. Bu amaçla 136 veriden oluşan bir veri seti (46 magmatik, 77 tortul ve 13 metamorfik kayaç) kullanılmış ve üç farklı özellik seti oluşturulmuştur. Tahmin edilen sonuçların birbirleri ile karşılaştırılması bu modellerin eğitimi, test edilmesi ve kontrol edilmesi ile yapılmıştır. İstatistiksel analizlerin karşılaştırmaları ve sonuçları, yapay zekâ hesaplama tekniklerinin, girdi ve çıktı değerlerinin birbiriyle ilişkili olmadığı durumlarda bile fc'yi hesaplamak için önemli ölçüde etkili olduğunu ve istatistiksel olarak uygun ve geçerli matematiksel modeller oluşturmanın GEP kullanan herkes tarafından yapılmasının mümkün olduğunu göstermektedir.

Anahtar Kelimeler

Doku katsayısı, basınç dayanımı, Adaptif ağ tabanlı bulanık mantık sistemi, Sinir ağları, Gen ekspresyonu programlama.

Kaynakça

• ISRM, The Complete ISRM Suggested Methods for Rock Characterization, Testing and Monitoring: 1974–2006, In: R. Ulusay and J. A. Hudson (Eds.), Ankara, Turkey, 2007.
• ASTM, Standard test method for unconfined compressive strength of intact rock core specimens. Soil and Rock, Building Stones: Annual Book of ASTM Standards 4.08. Philadelphia, Pennsylvania, ASTM, 1984.
• A. Asadi, Application of Artificial Neural Networks in Prediction of Uniaxial Compressive Strength of Rocks using Well Logs and Drilling Data. In Procedia Engineering, 191, 279-286, 2017. https://doi.org/10.1016/j.proeng.2017.05.182
• C. Zang and H. Huang, Prediction of rock mechanical parameters and rock mass classification by percussive drilling surveying in a rock tunnel, ISRM SINOROCK, Shanghai, China, June 2013. http://doi.org/10.1201/b14917-28
• H. Fattahi, Applying soft computing methods to predict the uniaxial compressive strength of rocks from schmidt hammer rebound values. Computational Geosciences, 21, (4), 665–681, 2017. http://doi.org/10.1007/s10596-017-9642-3
• A. Özbek, M. Unsal, and A. Dikec, Estimating uniaxial compressive strength of rocks using genetic expression programming. Journal of Rock Mechanics and Geotechnical Engineering, 5(4), 325–329, 2013. https://doi.org/10.1016/j.jrmge.2013.05.006
• U. Åkesson, J. Lindqvist, M. Göransson, and J. Stigh, Relationship between texture and mechanical properties of granites, Central Sweden, by use of image-analysing techniques. Bulletin of Engineering Geology and the Environment, 60(4), 277–284, 2001. http://doi.org/10.1007/s100640100105
• K. Gunsallus and F. H. Kulhawy, A comparative evaluation of rock strength measures. International Journal of Rock Mechanics and Mining Sciences , 21(5), 233-248, 1984. https://doi.org/10.1016/0148-9062(84)92680-9
• R. Merriam, H. H. Rieke, and Y. C. Kim, Tensile strength related to mineralogy and texture of some granitic rocks. Engineering Geology, 4(2), 155–160, 1970. https://doi.org/10.1016/0013-7952(70)90010-4
• T. F. Onodera and H. M. Asoka Kumara, Relation between texture and mechanical properties of crystalline rocks. Bulletin of Association Engineering Geology, 22, 173-177, 1980. https://doi.org/10.1016/j.enggeo.2004.03.009
• R. Přikryl, Assessment of rock geomechanical quality by quantitative rock fabric coefficients: Limitations and possible source of misinterpretations. Engineering Geology, 87(3–4), 149–162, 2006. https://doi.org/10.1016/j.enggeo.2006.05.011
• A. Tuǧrul and I. H. Zarif, Correlation of mineralogical and textural characteristics with engineering properties of selected granitic rocks from Turkey. Engineering Geology, 51(4), 303–317, 1999. https://doi.org/10.1016/S0013-7952(98)00071-4
• R. Ulusay, K. Türeli and M. H. Ider, Prediction of engineering properties of a selected litharenite sandstone from its petrographic characteristics using correlation and multivariate statistical techniques. Engineering Geology, 38(1–2), 135–157, 1994. https://doi.org/10.1016/0013-7952(94)90029-9
• D. F. Howarth and J. C. Rowlands, Quantitative assessment of rock texture and correlation with drillability and strength properties. Rock Mechanics and Rock Engineering, 20(1), 57–85, 1987.
• A. Ersoy and M. D. Waller, Textural characterisation of rocks. Engineering Geology, 39(3–4), 123–136, 1995. https://doi.org/10.1016/0013-7952(95)00005-Z
• V. Gupta, and R. Sharma, Relationship between textural, petrophysical and mechanical properties of quartzites: A case study from northwestern Himalaya. Engineering Geology, 135–136, 1–9, 2012. https://doi.org/10.1016/j.enggeo.2012.02.006
• C. A. Ozturk, E. Nasuf and S. Kahraman, Estimation of rock strength from quantitative assessment of rock texture. Journal of the Southern African Institute of Mining and Metallurgy, 114(6), 471–480, 2014.
• Y. Ozcelik, F. Bayram and N. E. Yasitli, Prediction of engineering properties of rocks from microscopic data. Arabian Journal of Geosciences, 6(10), 3651–3668, 2013. https://doi.org/10.1007/s12517-012-0625-3
• U. Atici and R. Comakli, Evaluation of the physico-mechanical properties of plutonic rocks based on texture coefficient. Journal of the Southern African Institute of Mining and Metallurgy, 119(1), 63–69, 2019. https://doi.org/10.17159/2411-9717/2019/v119n1a8
• C. Gokceoglu, E. Yesilnacar, H. Sonmez and A. Kayabasi, A neuro-fuzzy model for modulus of deformation of jointed rock masses. Computers and Geotechnics, 31(5), 375–383, 2004. https://doi.org/10.1016/j.compgeo.2004.05.001
• R. Singh, A. Kainthola and T. N. Singh, Estimation of elastic constant of rocks using an ANFIS approach. Applied Soft Computing Journal, 12(1), 40–45, 2012. https://doi.org/10.1016/j.asoc.2011.09.010
• K. Aali, M. Parsinejad and B. Rahmani, Estimation of Saturation Percentage of Soil Using Multiple Regression, ANN, and ANFIS Techniques. Computer and Information Science, 2(3), 127–136, 2009. https://doi.org/10.5539/cis.v2n3p127
• B. Tiryaki and A. C. Dikmen, Effects of rock properties on specific cutting energy in linear cutting of sandstones by picks. Rock Mechanics and Rock Engineering, 2006. https://doi.org/10.1007/s00603-005-0062-7
• A. Azzoni, F. Bailo, E. Rondena and A. Zaninetti, Assessment of texture coefficient for different rock types and correlation with uniaxial compressive strength and rock weathering. Rock Mechanics and Rock Engineering, 29(1), 39–46, 1996.
• M. Alber and S. Kahraman, Predicting the uniaxial compressive strength and elastic modulus of a fault breccia from texture coefficient. Rock Mechanics and Rock Engineering, 42(1), 117–127, 2009. https://doi.org/10.1007/s00603-008-0167-x
• U. Atici, Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network. Expert Systems with Applications, 38(8), 9609-9618, 2011. https://doi.org/10.1016/j.eswa.2011.01.156
• M. Sarıdemir, İ.B. Topçu, F. Özcan, and M. H. Severcan, Prediction of long-term effects of GGBFS on compressive strength of concrete by artificial neural networks and fuzzy logic. Construction and Building Materials, 23(3), 1279–1286, 2009. https://doi.org/10.1016/j.conbuildmat.2008.07.021
• A. Öztaş, M. Pala, E. Özbay, E. Kanca, N. Çaglar and M. A. Bhatti, Predicting the compressive strength and slump of high strength concrete using neural network. Construction and Building Materials, 20(9), 769–775, 2006. https://doi.org/10.1016/j.conbuildmat.2005.01.054
• J. L. Rogers, Simulating Structural Analysis with Neural Network. Journal of Computing in Civil Engineering, 8(2), 252–265, 1994. https://doi.org/10.1061/ (ASCE)0887-3801(1994)8:2(252)
• K. Swingler, Applying neural networks a practical guide. London: Academic Press, New York, 1996.
• M. M. Alshihri, A. M. Azmy and M. S. El-Bisy, Neural networks for predicting compressive strength of structural light weight concrete. Construction and Building Materials, 23(6), 2214–2219, 2009. https://doi.org/10.1016/j.conbuildmat.2008.12.003
• J. S. R. Jang, ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man and Cybernetics, 23(3), 665–685, 1993. https://doi.org/10.1109/21.256541
• H. F. Ho, Y. K. Wong, A. B. Rad, and W. L. Lo, State observer based indirect adaptive fuzzy tracking control. Simulation Modelling Practice and Theory, 13(7),646–663, 2005. https://doi.org/10.1016/j.simpat.2005.02.003
• C. X. Wong and K. Worden, Generalised NARX shunting neural network modelling of friction. Mechanical Systems and Signal Processing, 21(1), 553–572, 2007. https://doi.org/10.1016/j.ymssp.2005. 08.029
• T. Takagi and M. Sugeno, Fuzzy identification of systems and its applications to modeling and control. Systems, Man and Cybernetics, IEEE Transactions On, SMC-15(1), 116–132, 1985. https://doi.org/10.1016/B978-1-4832-1450-4.50045-6
• C. Kayadelen, O. Günaydin, M. Fener, A. Demir, A. Özvan, Modeling of the angle of shearing resistance of soils using soft computing systems. Expert Systems with Applications, 36(9), 11814–11826, 2009. https://doi.org/10.1016/j.eswa.2009.04.008
• H. Demuth and M. Beale, Neural Network Toolbox For Use with MATLAB - User Guide. The MathWorks, 2002.
• S. Akkurt, G. Tayfur and S. Can, Fuzzy logic model for the prediction of cement compressive strength. Cement and Concrete Research, 34(8), 1429–1433, 2004. https://doi.org/10.1016/j.cemconres.2004.01.020
• İ. B. Topçu and M. Sarıdemir, Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic. Computational Materials Science, 41(3), 305–311, 2008. https://doi.org/10.1016/j.commatsci.2007.04.009
• A. Cevik, A new formulation for longitudinally stiffened webs subjected to patch loading. Journal of Constructional Steel Research, 63, 1328–1340, 2007. https://doi.org/10.1016/j.jcsr.2006.12.004
• C. Ferreira, Gene Expression Programming : A New Adaptive Algorithm for Solving Problems. Complex Systems, 13(2), 1–22, 2001. https://doi.org/10.48550/arXiv.cs/0102027
• D. G. Muñoz, Discovering unknown equations that describe large data sets using genetic programming techniques. Master Thesis, Linköpings Universitet, Linköping, Sweden, 2005.