Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Predicting rock brittleness indices from simple laboratory test results using some machine learning methods

  • Received : 2023.02.08
  • Accepted : 2023.08.23
  • Published : 2023.09.25
⟨ Previous Next ⟩

Abstract

Brittleness as an important property of rock plays a crucial role both in the failure process of intact rock and rock mass response to excavation in engineering geological and geotechnical projects. Generally, rock brittleness indices are calculated from the mechanical properties of rocks such as uniaxial compressive strength, tensile strength and modulus of elasticity. These properties are generally determined from complicated, expensive and time-consuming tests in laboratory. For this reason, in the present research, an attempt has been made to predict the rock brittleness indices from simple, inexpensive, and quick laboratory test results namely dry unit weight, porosity, slake-durability index, P-wave velocity, Schmidt rebound hardness, and point load strength index using multiple linear regression, exponential regression, support vector machine (SVM) with various kernels, generating fuzzy inference system, and regression tree ensemble (RTE) with boosting framework. So, this could be considered as an innovation for the present research. For this purpose, the number of 39 rock samples including five igneous, twenty-six sedimentary, and eight metamorphic were collected from different regions of Iran. Mineralogical, physical and mechanical properties as well as five well known rock brittleness indices (i.e., B1, B2, B3, B4, and B5) were measured for the selected rock samples before application of the above-mentioned machine learning techniques. The performance of the developed models was evaluated based on several statistical metrics such as mean square error, relative absolute error, root relative absolute error, determination coefficients, variance account for, mean absolute percentage error and standard deviation of the error. The comparison of the obtained results revealed that among the studied methods, SVM is the most suitable one for predicting B1, B2 and B5, while RTE predicts B3 and B4 better than other methods.

Keywords

Acknowledgement

The authors acknowledge the official supports of the Engineering Geology and Rock Mechanics Laboratory of Damghan University for performing all laboratory tests of the research.

References

  1. Altindag, R. (2000), "The role of rock brittleness on the analysis of percussive drilling performance (in Turkish)", Proceedings of the 5th Turkish National Rock Mechanics Symposium, Isparta, Turkey.
  2. Altindag, R. (2002), "The evaluation of rock brittleness concept on rotary blasthole drills", J. Southern African Inst. Min. Metallurgy, 102, 61-66. https://hdl.handle.net/10520/AJA0038223X_2763. 10520/AJA0038223X_2763
  3. Altindag, R. (2003), "Correlation of specific energy with rock brittleness concepts on rock cutting", J. Southern African Inst. Min. Metallurgy, 103, 163-171. https://hdl.handle.net/10520/AJA0038223X_2948. 10520/AJA0038223X_2948
  4. Altindag, R. (2010), "Assessment of some brittleness indexes in rock-drilling efficiency", Rock mechanics and rock engineering, 43(3), 361-370. https://doi.org/10.1007/s00603-009-0057-x.
  5. Andreev, G.E. (1995), "Brittle failure of rock materials: test results and constitutive models", Brookfield Press: Rotterdam The Netherlands, p. 446.
  6. ASTM, (1990), "Standard test method for slake durability of shales and similar weak rocks (D4644)", Annual Book of ASTM Standards, vol. 4.08. ASTM, Philadelphia. 863-865.
  7. ASTM, (1995), "Standard test method for unconfined compressive strength of intact rock core specimens", ASTM standards on disc 04.08, Designation D2938.
  8. ASTM (1996), "Standard test method for laboratory determination of pulse velocities and ultrasonic elastic constants of rock", Designation: D2845-95.
  9. ASTM (2001a), "Standard test method for determination of rock hardness by rebound hammer method", ASTM standards on disc 04.09, D5873-00.
  10. ASTM (2001b), "Standard method for determination of the point load strength index of rock", ASTM standards on disc 04.08, Designation, D5731.
  11. ASTM (2001c), "Standard test method for splitting tensile strength of intact rock core specimens", ASTM standards on disc 04.08, Designation, D3967.
  12. Aubertin, M. and Gill, D.E. (1988), "A methodology for assessing the potential for rock bursts in Abitibi mine", Proceedings of the Colloque sur le Controle de Terrain (AMMQ), Val d'Or, 47-77.
  13. Aubertin, M., Gill, D.E. and Simon, R. (1994), "On the use of the brittleness index modified (BIM) to estimate the post-peak behaviour of rocks, rock mechanics", In: Nelson and Laubach (Eds.) Balkema, 945-952.
  14. Baron, L.I. (1962), "Determination of properties of rocks (in Russian)", Gozgotekhizdat, Moscow.
  15. Bezdek, J.C. (2013), "Pattern recognition with fuzzy objective function algorithms", Springer Science & Business Media. 
  16. Cao, J., Gao, J., Nikafshan Rad, H., Mohammed, A.S., Hasanipanah, M. and Zhou, J. (2021), "A novel systematic and evolved approach based on XGBoost-firefly algorithm to predict Young's modulus and unconfined compressive strength of rock", Eng. with Comput., 1-17. https://doi.org/10.1007/s00366-020-01241-2.
  17. Chen, P.H., Fan, R.E. and Lin, C.J. (2006), "A study on SMO-type decomposition methods for support vector machines", IEEE T. Neural Netw., 17(4), 893-908. https://doi.org/10.1109/TNN.2006.875973
  18. Coates, D.F. and Parsons, R.C. (1966), "Experimental criteria for classification of rock substances", Int. J. Rock Mechanics and Min. Sci., 3(3), 181-189. https://doi.org/10.1016/0148-9062(66)90022-2.
  19. Evans, I. and Pomeroy, C.D. (1966), "The strength fracture and workability of coal", Pergamon Press, Oxford.
  20. Gamble, J.C. (1971), "Durability-Plasticity classification of shales and other argillaceous rocks", Ph.D. Thesis, University of Illinois, Urbana-Champaign, IL, 161.
  21. Ghadernejad, S., Nejati, H.R. and Yagiz, S. (2020), "A new rock brittleness index on the basis of punch penetration test data", Geomech. Eng., 21(4), 391-399. https://doi.org/10.12989/gae.2020.21.4.391.
  22. Ghobadi, M.H. and Naseri, F. (2016), "Rock brittleness prediction using geomechanical properties of Hamekasi limestone: regression and artificial neural networks analysis", Geopersia, 6(1), 19-33. https://doi.org/10.22059/JGEOPE.2016.57819.
  23. Goktan, R.M. (1991), "Brittleness and micro-scale rock cutting efficiency", Min. Sci. Tech., 13, 237-241. https://doi.org/10.1016/0167-9031(91)90339-E.
  24. Goodman, R.E. (1989), "Introduction to Rock Mechanics", John Wiley & Sons Inc, New York, p. 562.
  25. Gunaydin, O., Kahraman, S. and Fener, M. (2004), "Sawability prediction of carbonate rocks from brittleness indexes", Journal of the Southern African Institute of Mining and Metallurgy, 104(4), 239-243. https://hdl.handle.net/10520/AJA0038223X_2828. 10520/AJA0038223X_2828
  26. Hajiabdolmajid, V. and Kaiser, P. (2003), "Brittleness of rock and stability assessment in hard rock tunneling", Tunn. Undergr. Sp. Tech., 18, 35-48. https://doi.org/10.1016/S0886-7798(02)00100-1.
  27. Hasanipanah, M., Jamei, M., Mohammed, A.S., Amar, M.N., Hocine, O. and Khedher, K. M. (2022), "Intelligent prediction of rock mass deformation modulus through three optimized cascaded forward neural network models", Earth Sci. Inform., 15(3), 1659-1669. https://doi.org/10.1007/s12145-022-00823-6.
  28. Hetenyi, M. (1966), "Handbook of experimental stress analysis", Wiley, New York.
  29. Howell, J.V. (1960), "Glossary of geology and related sciences", American Geological Institute, Washington, DC.
  30. Hucka, V. and Das, B. (1974), "Brittleness determination of rocks by different methods", Int. J. Rock Mech. Min. Sci. Geomech. Abstracts, 17(10), 389-392. https://doi.org/10.1016/0148-9062(74)91109-7.
  31. Ishikawa, K. (1986), "Guide to Quality Control", No. TS156.13713 1994.
  32. ISRM, (2007), "The Blue Book: The complete ISRM suggested methods for rock characterization, testing and monitoring", 1974-2006, (Eds., Ulusay, R., and Hudson, J.A.), Compilation arranged by the ISRM Turkish National Group, Ankara, Turkey, Kazan Offset Press, Ankara.
  33. Jahandideh, A. and Jafarpour, B. (2016), "Optimization of hydraulic fracturing design under spatially variable shale fracability", J. Petroleum Sci. Eng., 138, 174-188. https://doi.org/10.1016/j.petrol.2015.11.032.
  34. Jahed Armaghani, D., Asteris, P.G., Askarian, B., Hasanipanah, M., Tarinejad, R. and Huynh, V.V. (2020), "Examining hybrid and single SVM models with different kernels to predict rock brittleness", Sustainability, 12(6), 2229.
  35. Jamei, M., Mohammed, A.S., Ahmadianfar, I., Sabri, M.M.S., Karbasi, M. and Hasanipanah, M. (2022), "Predicting rock brittleness using a robust evolutionary programming paradigm and regression-based feature selection model", Appl. Sci., 12(14), 7101. https://doi.org/10.3390/app12147101.
  36. Jang, J.S., Sun, C.T. and Mizutani, E. (1997), "Neuro-fuzzy and soft computing-a computational approach to learning and machine intelligence [Book Review]", IEEE T Automat. Control, 42(10), 1482-1484. https://doi.org/10.1109/TAC.1997.633847
  37. Kahraman, S. and Altindag, R. (2004), "A brittleness index to estimate fracture toughness", Int. J. Rock Mech. Min. Sci. Geomech. Abstracts, 41, 343-348. https://doi.org/10.1016/j.ijrmms.07.010.
  38. Kahraman, S., Bilgin, N. and Feridunoglu, C. (2003a), "Dominant rock properties affecting the penetration rate of percussive drills", Int. J. Rock Mech. Min. Sci. Geomech. Abstracts, 40, 711-723. https://doi.org/10.1016/S1365-1609(03)00063-7.
  39. Kahraman, S., Gunaydin, O., Fener, M. and Bilgin, N. (2003b), Correlation between Los Angeles abrasion loss and uniaxial compressive strength", Proceedings of International Symposium on Industrial Minerals and Building Stones, Istanbul, Turkey.
  40. Kahraman, S. (2002), "Correlation of TBM and drilling machine performances with rock brittleness", Eng. Geol., 65(4), 269-283. https://doi.org/10.1016/S0013-7952(01)00137-5.
  41. Karimi, Z. and Farzinfar, M. (2020), "Estimation of power in combined cycle power plant using adaptive neuro-fuzzy inference system (in Persian)", Proceedings of the 1st national conference of applied water and power industry.
  42. Koopialipoor, M., Noorbakhsh, A., Noroozi Ghaleini, E., Jahed Armaghani, D. and Yagiz, S. (2019), "A new approach for estimation of rock brittleness based on non-destructive tests", Nondestruct. Test. Eval., 34(4), 354-375. https://doi.org/10.1080/10589759.2019.1623214.
  43. Koopialipoor, M., Asteris, P.G., Mohammed, A.S., Alexakis, D.E., Mamou, A. and Armaghani, D.J. (2022), "Introducing stacking machine learning approaches for the prediction of rock deformation", Transport. Geotech., 34, 100756. https://doi.org/10.1016/j.trgeo.2022.100756.
  44. Li, T., Chen, Y. and Zhang, J. (2012), "Logistics service provider segmentation based on improved FCM clustering for mixed data", J. Comput., 7(11), 2629-2633. https://doi.org/10.4304/jcp.7.11.2629-2633.
  45. Loh, W.Y. (2011), "Classification and regression trees", Wiley interdisciplinary reviews: data mining and knowledge discovery, 1(1), 14-23. https://doi.org/10.1002/widm.8
  46. Mahmood, W., Mohammed, A. and HamaHussein, S. (2020), "Predicting mechanical properties and ultimate shear strength of gypsum, limestone and sandstone rocks using Vipulanandan models", Geomech. Geoeng., 15(2), 90-106. https://doi.org/10.1080/17486025.2019.1632494.
  47. Mamdani, E.H. and Assilian, S. (1975), "An experiment in linguistic synthesis with a fuzzy logic controller", Int. J. Man-Machine Studies, 7(1), 1-13. https://doi.org/10.1016/S0020-7373(75)80002-2.
  48. Meng, F., Wong, L.N. and Zhou, H. (2020), "Rock brittleness indices and their applications to different fields of rock engineering: A review", J. Rock Mech. Geotech. Eng., 13(1), 221-247. https://doi.org/10.1016/j.jrmge.2020.06.008.
  49. Mohammed, A.S. (2019), "Vipulanandan models to predict the mechanical properties, fracture toughness, pulse velocity and ultimate shear strength of shale rocks", Geotech. Geol. Eng., 37(2), 625-638. https://doi.org/10.1007/s10706-018-0633-5.
  50. Morley, A. (1944), "Strength of materials: with 260 diagrams and numerous examples", Longmans, Green and Company, New York.
  51. Nejati, H.R. and Moosavi, S.A. (2017), "A new brittleness index for estimation of rock fracture toughness", J. Min. Environ., 8(1), 83-91. https://doi.org/10.22044/jme.2016.579.
  52. Obert, L. and Duvall, W.I. (1967), "Rock mechanics and the design of structures in rock", New York: Wiley.
  53. Parsajoo, M., Mohammed, A.S., Yagiz, S., Armaghani, D.J. and Khandelwal, M. (2021), "An evolutionary adaptive neuro-fuzzy inference system for estimating field penetration index of tunnel boring machine in rock mass", J. Rock Mech. Geotech. Eng., 13(6), 1290-1299. https://doi.org/10.1016/j.jrmge.2021.05.010.
  54. Ramezan, C.A. Warner, T.A. and Maxwell, A.E. (2019), "Evaluation of sampling and cross-validation tuning strategies for regional-scale machine learning classification", Remote Sens., 11(2), 185. https://doi.org/10.3390/rs11020185.
  55. Ramezani, R., Maadi, M. and Khatami, S.M. (2018), "A novel hybrid intelligent system with missing value imputation for diabetes diagnosis", Alexandria Eng. J., 57(3), 1883-1891. https://doi.org/10.1016/j.aej.2017.03.043.
  56. Ramsay, J.G. (1967), "Folding and fracturing of rocks", McGraw-Hill Press: London, UK.
  57. Ribacchi, R. (2000), "Mechanical tests on pervasively jointed rock material: insight into rock mass behaviour", Rock Mech. Rock Eng., 33(4), 243-266. https://doi.org/10.1007/s006030070002.
  58. Shin, Y. (2015), "Application of boosting regression trees to preliminary cost estimation in building construction projects", Comput. Intel. Neurosci., https://doi.org/10.1155/2015/149702.
  59. Singh, S.P. (1986), "Brittleness and the mechanical winning of coal", J. Min. Sci. Tech., 3, 173-180. https://doi.org/10.1016/S0167-9031(86)90305-1.
  60. Singh, S.P. (1987), "Criterion for the assessment of the cuttability of coal", (Eds., Szwilski, A.B. and Richards, M.J.), Underground mining methods and technology. Amsterdam. https://doi.org/10.1016/B978-0-444-42845-5.50024-3.
  61. Smola, A. and Scholkopf, B. (2004), "A tutorial on support vector regression", Stat. Comput., 14, 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88.
  62. Sugeno, M. (1985), "An introductory survey of fuzzy control", Inform. Sci., 36(1-2), 59-83. https://doi.org/10.1016/0020-0255(85)90026-X.
  63. Sun, D., Lonbani, M., Askarian, B., Jahed Armaghani, D., Tarinejad, R., Thai Pham, B. and Huynh, V.V. (2020), "Investigating the applications of machine learning techniques to predict the rock brittleness index", Appl. Sci., 10(5), 1691.
  64. Tarasov, B. and Potvin, Y. (2013), "Universal criteria for rock brittleness estimation under triaxial compression", Int. J. Rock Mech Min. Sci., 59, 57-69. https://doi.org/10.1016/j.ijrmms.2012.12.011.
  65. Tiryaki, B. (2008), "Predicting intact rock strength for mechanical excavation using multivariate statistics, artificial neural networks, and regression trees", Eng. Geol., 99(1-2), 51-60. https://doi.org/10.1016/j.enggeo.2008.02.003.
  66. Vipulanandan, C. and Mohammed, A. (2018), "New Vipulanandan failure model and property correlations for sandstone, shale and limestone rocks", In IFCEE 2018, 365-376.
  67. Vipulanandan, C., Mohammed, A. and Mahmood, W. (2021), "Characterizing rock properties and verifying failure parameters using data analytics with vipulanandan failure and correlation models", Proceedings of the 55th US Rock Mechanics/Geomechanics Symposium, OnePetro.
  68. Wang, Y. and Chen, Y. (2014), "A comparison of Mamdani and Sugeno fuzzy inference systems for traffic flow prediction", J. Comput., 9(1), 12-21. https://doi.org/10.4304/jcp.9.1.12-21.
  69. Wood, D.A. (2020), "Brittleness index predictions from Lower Barnett Shale well-log data applying an optimized data matching algorithm at various sampling densities", Geosci. Front., 101087. https://doi.org/10.1016/j.gsf.2020.09.016.
  70. Yang, S.Q., Yin, P.F. and Ranjith, P.G. (2020), "Experimental study on mechanical behavior and brittleness characteristics of longmaxi formation shale in Changning, Sichuan basin, China", Rock Mech. Rock Eng., 11, 1-23. https://doi.org/10.1007/s00603-020-02057-8.
  71. Yagiz, S., Yazitova, A. and Karahan, H. (2020), "Application of differential evolution algorithm and comparing its performance with literature to predict rock brittleness for excavatability", Int. J. Min. Reclamat. Environ., 34(9), 672-685. https://doi.org/10.1080/17480930.2019.1709012
  72. Yarali, O. (2007), "Investigation of the relations between rock brittleness and drilling rate index", Proceedings of the 20th International Mining Congress of Turkey, (in Turkish), Ankara, Turkey.
  73. Yarali, O. and Soyer, E. (2011), The effect of mechanical rock properties and brittleness on drillability", Scientific Res. Essays, 6(5), 1077-1088. https://doi.org/10.5897/SRE10.1004.
  74. Ye, Y., Tang, S. and Xi, Z. (2020), "Brittleness evaluation in shale gas reservoirs and its influence on fracability", Energies, 13(2), 388. https://doi.org/10.3390/en13020388.
  75. Yilmaz, N.G., Karaca, Z., Goktan, R.M. and Akal, C. (2008), Relative brittleness characterization of some selected granitic building stones: influence of mineral grain size", Constr. Build. Mater., 23(1), 370-375. https://doi.org/10.1016/j.conbuildmat.11.014.
  76. Zhang, Y., Feng, X.T., Yang, C., Han, Q., Wang, Z. and Kong, R. (2021), "Evaluation method of rock brittleness under true triaxial stress states based on pre-peak deformation characteristic and post-peak energy evolution", Rock Mech. Rock Eng., 54(3), 1277-1291. https://doi.org/10.1007/s00603-020-02330-w.
  77. Zhou, Z.H. (2019), "Ensemble methods: foundations and algorithms", Chapman and Hall/CRC.