Kayaç Özelliklerine Bağlı Olarak Kayaç Delinebilirliğinin Yapay Sinir Ağları (YSA) Metodu ile Tahmini

Bu çalışmanın amacı; kayaçların mekanik, indeks ve petrografik özelliklerinden yararlanarak pratik bir delinebilirlik indeks modeli (DRI) geliştirmektir. DRI’nın tahmin edilmesi için geliştirilen modellerde yapay sinir ağları (YSA) kullanılmıştır. Bu amaçla, laboratuvarda farklı kayaçlar üzerinde yapılan delinebilirlik deney verileri kullanılmıştır. Ayrıca kayaçların; mekanik (tek eksenli basınç ve Brezilian çekme dayanımı) ve indeks (Schmidt sertlik ve nokta yükü dayanımı) özelliklerinin yanı sıra petrografik analiz (ortalama tane boyu, eş değer kuvars içeriği (%), çimentolanma derecesi) sonuçları da YSA modellemesi için kullanılmıştır. DRI ve kayaç özellikleri arasındaki korelasyon incelenmiş ve yüksek korelasyona sahip değişkenler YSA’na girdi parametresi olarak seçilmiştir. Buna göre 14 veri ağın eğitimi için, 7 veri ise test için kullanılmış ve en anlamlı sonucu veren model belirlenmiştir. Testler sonucunda tahmin edilen DRI sonuçları ile deneylerden elde edilen DRI sonuçlarının karşılaştırması yapılmıştır. Sonuç olarak YSA ile modellenen DRI sonuçlarının deneysel verilerden elde edilen sonuçlara oldukça yakın olduğu görülmüştür.

Prediction of Drillability of Rocks Based on Rock Properties Using Artificial Neural Networks (ANN)

The objective of this paper is to develop a practical model for predicting the drilling rate index (DRI) based on mechanical, index and petrographic properties of rocks. Artificial neural network (ANN) is employed in the models developed for predicting the DRI. For this purpose, experimental data obtained from drillability test carried out on different rocks in the laboratory were used. Furthermore, in addition to the mechanical (i.e. uniaxial compressive and Brazilian tensile strengths) and index (i.e. Schmidt hardness and point load index) properties, the results of petrographic analyses (i.e. mean grain size, equivalent quartz content, degree of cementation) were also used for the ANN modelling. The correlations between the DRI and rock properties were evaluated, and the parameters having high correlations were selected as input parameters for the ANN model. Accordingly, 14 data were used for network training and 7 data were used for testing, and the most meaningful was determined. The estimated DRI values from the ANN models were compared with the experimental DRI data. In conclusion, the DRI values estimated by the ANN models were found to be close to those obtained from experiments.

___

  • Andrews, R., Harelve, G., Nygaard, R. 2007. Methods of using logs to quantify drillability. Paper No. SPE 106571, SPE, Denver, CO, April 16–18.
  • Ataei, M., Kakaie, R., Ghavidel, M., Saeidi, O. 2015. Drilling rate prediction of an open pit mine using the rock mass drillability index. Int. J. Rock Mech. Min. Sci. 73: 130-138.
  • Avunduk, E., Tumaç, D., Atalay, A.K. 2014. Prediction of roadheader performance by artificial neural network. Tunn. Undergr. Space Tec., 44:3-9.
  • Basarir, H., Tutluoglu, L., Karpuz, C. 2014. Penetration rate prediction for diamond bit drilling by adaptive neuro-fuzzy inference system and multiple regressions. Eng Geol 173:1–9.
  • Benardos, A.G., Kaliampos, D.C. 2004. Modelling TBM performance with artificial neural networks. Tunn. Undergr. Space Tech., 19 (6) : 597-605
  • Bruland, A. 1998. Hard rock tunnel boring , drillability test methods. Norwegian University of Science and Technology, Dept. of Civil and Transport Engineering Project report 13A98.15.
  • Ceryan, N., Okkan, U., Kesimal, A. 2013. Prediction of unconfined compressive strength of carbonate rocks using artificial neural networks. Environ. Earth Sci. 68:907-819.
  • Dahl, F. 2003. DRI Standards, NTNU, Angleggsdrift, Trondheim. 21 p.
  • Dahl, F., Bruland, A., Jakobsen, PD., Nilsen, B., Grov, E. 2012. Classifications of properties influencing the drillability of rocks based on the NTNU/SINTED test method. Tunn. Undergr. Space Tech., 28:150-158
  • Denghan, S., Sattari, G., Cherreh C.S., Aliabadi M.A. 2010.
  • Predicition of uniaxial compressive strength and modulus of elasticity for Travertine samples using regression and artificial neural networks. Min. Sci. Techol., 20(1):41-46
  • Güvenç, U. 2007. Anahtarlamalı relüktans motor manyetik akısının yapay sinir ağı tabanlı modellenmesi. Akademik Bilişim’07- IX. Akademik Bilişim Konferansı Bildirileri, Dumlupınar Üniversitesi, Kütahya.
  • Güvenç, U., Dursun, M., Çimen, H. 2011. Mermer kesme işleminde kesim süresinin yapay sinir ağı tabanlı modellenmesi. SDU Int. Tech. Sci. 3(2):9-16.
  • Hoseinie, SH., Aghababaei, H., Pourrahimian, Y. 2008. Development of a new classification system for assesing of rock mass drillability index (RDi). Int. J. Rock Mech. Min. Sci. 45:1-10.
  • Hoseinie, SH., Ataei, M., Osanloo, M. 2009. A new classification system evalating rock penetrability. Int. J. Rock Mech. Rock Eng.46: 1329 - 1340.
  • Howarth, DF., Adamson, WR., Berndt, JR. 1986. Correlation of model tunnel boring and drilling machine performances with rock proporties. Int J Rock Mech Min. Sci, 23: 57-85.
  • Howarth, DF., Rowland, JC. 1987. Quantitative assessment of rock texture and correlation with drillability and strength properties. Rock Mech. Rock Eng. 20: 57–85.
  • İnan, A. 1999. Yapay sinir ağlarının güç sistemlerinde kullanım alanları. Kaynak Elektrik, 119: 104-114
  • ISRM. 1978. Suggested method for determining tensile strength of rock materials. Int. J. Rock Mech. Min. Sci. Geomech. 15: 99- 103.
  • ISRM. 1979. Suggested method for determining the uniaxial compressive strength and deformability of rock. Int. J. Rock Mech. Min. Sci. Geomech. 16: 135-140.
  • ISRM. 1985. Suggested methods for determining point load strength. Int. J. Rock Mech. Min. Sci. Geomech. 22(2): 51–60.
  • Kahraman, S. 1999. Rotary and percussive drilling prediction using regression analysis. Int. J. Rock Mech. Min. Sci. 36: 981– 989.
  • Kahraman, S. 2016. Estimating the penetration rate in diamond drilling in laboratory Works using the regression and artificial neural networks. Neural Process Lett., 43:523-535
  • Kahraman, S., Bilgin, N., Feridunoğlu, C. 2003. Dominant rock proporties affecting penetration rate of percussive drills. Int. J Rock Mech. Min. Sci., pp. 711-723.
  • Kahraman, S., Alber, M., Fener, M, Günaydın, O. 2010. The usability of Cerchar abrasivity index for the prediction of UCS and E of Misis Fault Breccia: regression and artificial neural networks analysis, Exp. Sys. with App., 37:8750-8756
  • Karpuz, C., Paşamehmetoğlu, AC., Dinçer, T., Müftüoğlu, Y. 1990. Drillability studies on the rotary blast hole drilling on lignite overburden series. Int. J. Surfine Min. Reel., 4 : 89-93.
  • Khandelwal, M., Armaghani, DJ. 2016. Predicition of drillability of rocks with strength propertiess using a Hybrid GA-AAN technique. Geotech. Geo. Eng. 34 (5) : 605- 620.
  • Kramadibrata, S., Made, AR., Juanda, J., Simangunsong, GM., Priagung, N. 2001. The use of dimensional analysis to anlyse the relationship between penetration rate of Jack Hammer and rock properties and operational characteristics. Proc. Indonesian Mining Conf. and Exh., Jakarta, Indonesia
  • McFeat-Smith. I., Fowell, RJ. 1977. Correlation of rock properties and the cutting performance of tunneling machines, In Proc. of a Conf. on Rock Eng., pp. 581-602.
  • Mishra, D.A., Srigyan, M., Basu, A., Rokade, P.J. 2015. Soft computing methods for estimating the uniaxial compressive strength of intact rock from index test. Int. J Rock Mech. Min. Sci., 80:418-424
  • Moein, MJA., Shaabani, E., Rezaeian, M. 2014. Experimental evaluation of hardness models by drillability tests for carbonate rocks, J. Petroleum Sci. Eng. 113: 104 -108
  • Nilsen. B., Özdemir, L. 1993. Hard rock tunnel boring prediction and field performance., RETC Conf. Proc., Boston, MA, Chapter 52, 832-852.
  • Sakız, U. 2016. Spesifik enerjinin kayaçların delinebilirliğine ve aşındırıcılığına olan etkisinin incelenmesi, Doktora Tezi: 3. Tez İzleme Raporu, Zonguldak Bülent Ecevit Üniversitesi, 81 s.
  • Selmer-Olsen, R., Blindheim, OT. 1970. On the drillability of rock by percussive drilling. In: Pro. of the Sec. Cong. Int. Soc. on Rock Mech., pp.65-70.
  • Schormair, N., Thuro, K., Plinninger, R. 2006. The influence of anisotropy on hard rock drilling and cutting, The Geological Society, IAEG-491, 1-11.
  • Sönmez, H., Gokceoglu, C. 2008. Discussion on the paper by H. Gullu and E Ercelebi A neural network approach for attenuation relationship: an application using strong ground motion data from Turkey, Eng. Geol. 97:91-93
  • Su, O. 2016. Performance evaluation of button bits in coal measure rocks by using multiple regression analysis, Rock Mech. Rock Eng., 49 (2) : 541 - 553.
  • Tamrock. 1987. Handbook of Underground Drilling, Tamrock Drills SF-33310 Tampere, Finland, 327 p.
  • Tanaino, AS. 2005. Rock classification by drillability. Part I: analysis of the avaible classification. J. Min. Sci., 41 (6): 541 - 549
  • Thuro, K. 1997. Predictionof drillability in hardrock tunneling by drilling and blasting, In: Golse J. et. al, Hinkel and Schubert (edt.), Tunnels for people, pp.103-108.
  • Thuro, K., Spaun, G. 1996. Introducing the ‘detruction work’ as a to new rock property of toughness refering to drillability in conventional drill and blast tunnelling. ed. M. Barla, Eurock’96 Pre. and Per. in Rock Mech. Rock Eng., 2 : 707-13.
  • Tumaç, D. 2016. Artificial neural network application to predict the sawability performance of large diameter circular saws. Measurement, 80:12-20.
  • Wijk, G. 1989. The stamp test for rock drillability classification. Int. J. Rock Mech. Min. Sci. Geomech, 26:37–44
  • Yaralı, O., Kahraman, S. 2011. The drillability assessment of rocks using the different brittleness values. Tunn. Undergr. Space Techol. 26: 406 – 414.
  • Yaralı, O., Soyer, E. 2013. Assessment of relationships between drilling rate ındex and mechanical properties of rocks, Tunn. Undergr. Space Techol., 33:46-53.
  • Yılmaz, I., Yüksek, A.G. 2008. An example of artificial neural network (ANN) application for indirect estimation of rock parameters. Rock Mech. Rock Eng., 41(5): 781- 795
  • Yurdakul, M. 2009. Karbonat kökenli doğal taşların yapay sinir ağları ile kesilebilirlik tayini. Doktora Tezi, Eskişehir Osmangazi Üniversitesi, 261 s.
  • Zare, S., Bruland A. 2013. Applications of NTNU/SINTEF drillability indices in hard rock tunneling. Rock Mech. Rock Eng., 46:179 – 187.
  • Zhang, X., Zhai, YH., Xue, CJ., Jiang, TX. 2012. A study of the distribution of formation drillability, Pet. Sci Technol., 29 : 149 – 159.
  • Zhang K, Hou R, Zhang G, Zhang G ve Zhang H 2016. Rock drillability assessment and lithology classification based on the operating parameters of a drifter: case study in coal mine in China. Rock Mech. Rock Eng., 49 (3) : 329-334.
Karaelmas Fen ve Mühendislik Dergisi-Cover
  • ISSN: 2146-4987
  • Yayın Aralığı: Yılda 2 Sayı
  • Başlangıç: 2011
  • Yayıncı: ZONGULDAK BÜLENT ECEVİT ÜNİVERSİTESİ