JOURNAL OF ROCK MECHANICS

JOURNAL OF ROCK MECHANICS

Estimating the rock mass deformation modulus using the statistical and artificial intelligence models

Document Type : Original Article

Author
Mohammad Rezaei
Department of Mining Engineering, Faculty of Engineering, University of Kurdistan, Sanandaj, Iran
10.22034/IRSRM.2024.513320.1066
Abstract
Direct measurement of the rock mass deformation modulus using in-situ and laboratory tests is a costly and time-consuming process. Therefore, the use of indirect methods such as artificial intelligence algorithms to estimate this parameter can be a useful, fast, and cost-effective alternative. In this study, the modeling of the rock mass deformation modulus was performed using Gene Expression Programming (GEP), Fuzzy Inference System (FIS), and Multiple Linear Regression (MLR) models. The input data for estimating the rock mass deformation modulus included overburden height, rock quality designation, weathering, uniaxial compressive strength, bedding inclination angle, joint roughness coefficient, and joint filling, which were collected at the Bakhtiari dam site. After modeling, the results from the three models (GEP, FIS, and MLR) were compared with each other, with real data, and with similar previous models. The performance evaluation indices, including root mean square error, mean absolute error, calculated variance, efficiency coefficient, and coefficient of determination, were 1.27, 1.85, 0.9912, 0.9889, and 0.9869 for the GEP model, 1.51, 2.05, 0.9876, 0.9823, and 0.9778 for the FIS model, and 4.45, 4.97, 0.7641, 0.7569, and 0.7444 for the MLR model, respectively. The results indicate that the accuracy of the GEP and FIS models is higher, and their error is lower than the MLR model. Based on the evaluation of the model results and their comparison with real values and the results of previous similar models, the high capability of the two models (GEP and FIS) and their relative superiority over previous studies in predicting the deformation modulus was confirmed. However, the accuracy of GEP is slightly higher than FIS, and its results match relatively better with real values. Finally, the results of the variable importance analysis showed that the weathering and overburden height parameters have the most and least influence on the rock mass deformation modulus in this study, respectively.
Keywords
Rock Mass Deformation Modulus
Bakhtiari Dam
Gene Expression Programming
Fuzzy Inference System
Multiple Linear Regression
Subjects
[1]    Rezaei, M., Asadizadeh, M., Majdi, A., & Hossaini, M.F. (2015). Prediction of representative deformation modulus of longwall panel roof rock strata using Mamdani fuzzy system. International Journal of Mining Science and Technology, 25, 23–30. DOI:10.1016/j.ijmst.2014.11.007.
[2]    Aksoy, C .O., Geniş, M., Aldaş, G. U., Özacar, V., Özer, S. C., & Yılmaz, Ö. (2012). A comparative study of the determination of rock mass deformation modulus by using different empirical approaches. Engineering Geology, 131–132, 19–28. DOI:10.1016/j.enggeo.2012.01.009.
[3]    Shen, J., Karakus, M., & Xu, C. (2012). A comparative study for empirical equations in estimating deformation modulus of rock masses. Tunnelling and Underground Space Technology, 32, 245–250. DOI:10.1016/j.tust.2012.07.004.
[4]    Sridevi, J., & Sitharam, T. G. (2003). Characterization of strength and deformation of jointed Rock Mass based on statistical analysis. International Journal of Geomechanics, 3(1), 43–54. DOI:10.1061/(ASCE)1532-3641(2003)3:1(43).
[5]    Bieniawski, Z. T. (1973). Engineering classification of rock masses. Transaction of the South African Institution of Civil Engineers, 15(12), 335–44.
[6]    Barton, N., Lien, R., & Lunde, J. (1974). Engineering classification of rockmasses for the design of tunnel support. Rock Mechanics, 6(4), 189–236. DOI:10.1007/BF01239496
[7]    Palmstrom, A., & Singh, R. (2001). The deformation modulus of rock masses: comparisons between in situ tests and indirect estimates. Tunnelling and Underground Space Technology, 16, 115–31. DOI:10.1016/S0886-7798(01)00038-4.
[8]    Nejati, H. R., Ghazvinian, A., Moosavi, S. A., & Sarfarazi, V. (2014). On the use of the RMR system for estimation of rock mass deformation modulus. Bulletin of Engineering Geology and the Environment,  73, 531–540. https://doi.org/10.1007/s10064-013-0522-3.
[9]    Zhang, L., Einstein, & H. H. (2004). Using RQD to estimate the deformation modulus of rock masses. International Journal of Rock Mechanics and Mining Sciences, 41, 337–41. DOI:10.1016/S1365-1609(03)00100-X.
[10] Verman, M., Singh, Viladkar, B. M. N., & Jethwa, J. L. (2005). Effect of Tunnel Depth on Modulus of Deformation of Rock Mass. Rock Mechanics and Rock Engineering, 30(3), 121–127. DOI:10.1007/BF01047388.
[11] Beiki, M., Bashiri, A., & Majdi, A. (2010). Genetic programming approach for estimating the deformation modulus of rock mass using sensitivity analysis by neural network. International Journal of Rock Mechanics and Mining Sciences, 47(7), 1091–10103. DOI:10.1016/j.ijrmms.2010.07.007.
[12] Majdi, A., & Beiki, M. (2010). Evolving neural network using a genetic algorithm for predicting the deformation modulus of rock masses. International Journal of Rock Mechanics and Mining Science, 47(2), 246–253. DOI:10.1016/j.ijrmms.2009.09.011.
[13] کریم دوست، س.، مهرنهاد، ح.، نجاتی، ح. ر. (۱۳۹۶). ارائه مدل تجربی جدید برای تخمین مدول دگرشکل‌پذیری توده‌سنگ (مطالعه موردی: سد خرسان). مجله انجمن زمین‌شناسی مهندسی ایران ، جلد دهم، شماره ۳ و ۴، صفحه ۴۳ تا ۵۳.
[14] Majdi, A., & Rezaei, M. (2013). Application of artificial neural networks for predicting the height of destressed zone above the mined panel in longwall coal mining. 47th US rock mechanics/geomechanics symposium, ARMA-2013-605, San Francisco, California, USA. ISBN: 978-0-9894844-0-4.
[15] Rezaei, M., Hossaini, M. F., Majdi, A., & Najmoddini, I. (2017). Determination of the height of destressed zone above the mined panel: An ANN model. International Journal of Mining and Geo-Engineering, 51(1), 1–7. DOI:10.22059/ijmge.2017.62147.
[16] Rezaei, M. (2018). Indirect measurement of the elastic modulus of intact rocks using the Mamdani fuzzy inference system. Measurement, 129, 319–331. DOI:10.1016/j.measurement.2018.07.047.
[17] Rezaei, M. (2020). Feasibility of novel techniques to predict the elastic modulus of rocks based on the laboratory data. International Journal of Geotechnical Engineering, 14(1), 25–34. DOI:10.1080/19386362.2017.1397873.
[18] Rajabi, M., Rahmannejad, R., & Rezaei, M. (2021). Studying the deformation and stability of rock mass surrounding the power station caverns using NA and GEP models. Structural Engineering and Mechanics, 79(1), 35–50. DOI:10.12989/sem.2021.79.1.035.
[19] Wang, Y., Rezaei, M., Abdullah, R. A., & Hasanipanah, M. (2023). Developing Two Hybrid Algorithms for Predicting the Elastic Modulus of Intact Rocks. Sustainability, 15(5), 4230. DOI:10.3390/su15054230.
[20] Rezaei, M., Ahmadi, S. R., Hoang, N., & Jahed Armaghani, D. (2024). Improved determination of the S-wave velocity of rocks in dry and saturated conditions: Application of machine-learning algorithms. Transportation Geotechnics, 49, 101371. DOI:10.1016/j.trgeo.2024.101371.
[21] Ding, X., Hasanipanah, M., & Rezaei, M. (2025). Assessment of mechanical properties of rock using deep learning approaches. Measurement, 250, 117180. DOI:10.1016/j.measurement.2025.117180.
[22] Rezaei, M., & Rajabi, M. (2021). Assessment of plastic zones surrounding the power station cavern using numerical, fuzzy and statistical models. Engineering with Computers, 37(2), 1499–1518. DOI:10.1007/s00366-019-00900-3.
[23] Asadizadeh, M., & Rezaei, M. (2021). Surveying the mechanical response of non-persistent jointed slabs subjected to compressive axial loading utilising GEP approach. International Journal of Geotechnical Engineering, 15(10), 1312–1324. DOI:10.1080/19386362.2019.1596610.
[24] Kayabasi, A., Gokceoglu, C., & Ercanoglu, M. (2003). Estimating the deformation modulus of rock masses: a comparative study. International Journal of Rock Mechanics & Mining Sciences, 40(1) 55–63. https://doi.org/10.1016/S1365-1609(02)00112-0.
[25] Gokceoglu, C., Yesilnacar, E., Sonmez, H., & Kayabasi, A. (2004). A neuro-fuzzy model for modulus of deformation of jointed rock masses. Computers and Geotechnics, 31(5), 375–383. https://doi.org/10.1016/j.compgeo.2004.05.001.
[26] Beiki, M., Bashari, A., & Majdi, A. (2010). Genetic programming approach for estimating the deformation modulus of rock mass using sensitivity analysis by neural network. International Journal of Rock Mechanics & Mining Sciences, 47(7), 1091–1103. https://doi.org/10.1016/j.ijrmms.2010.07.007.
[27] Bashari, A., Beiki, M., & Talebinejad, A. (2011). Estimation of deformation modulus of rock masses by using fuzzy clustering-based modeling. International Journal of Rock Mechanics & Mining Sciences, 48(8), 1224–1234. https://doi.org/10.1016/j.ijrmms.2011.09.017.
[28]  کیانپور، م.، سیاری، م.، ارومیه‌ای، ا. (1391). برآورد مقاومت تراکمی تک‌محوری و مدول تغییر شکل‌پذیری شیل‌های سازند شمشک با استفاده از الگوریتم منطق فازی. فصلنامه علمی علوم زمین، دوره ۲۱، شماره ۸۳، صفحه ۱۰۳ تا ۱۱۰.
[29]  علی‌آبادیان، ز.، شریف‌زاده، م. (1391). تخمین مدول تغییرشکل‌پذیری سنگ آهک آسماری با استفاده از سیستم عصبی-ژنتیک. مجله انجمن زمین‌شناسی مهندسی ایران ، دوره ۵، شماره ۱ و ۲، صفحه ۹۳ تا ۱۰۰.
[30] قاسمی، س. م.، غلام‌نژاد، ج. (۱۳۹۲). ارائه یک مدل شبکه عصبی جهت تخمین مدول تغییرشکل‌پذیری توده‌سنگ. اولین کنفرانس ملی ژئوتکنیک ایران، دانشگاه محقق اردبیلی، اردبیل، ایران.
[31] Feng, X., & Jimenez, R. (2015). Estimation of deformation modulus of rock masses based on Bayesian model selection and Bayesian updating approach. Engineering Geology, 199, 19–27. https://doi.org/10.1016/j.enggeo.2015.10.002.
[32] Alemdag, S., Gurocak, Z., Cevik, A., Cabalar, A. F., Gokceoglu, C. (2016). Modeling deformation modulus of a stratified sedimentary rock mass using neural network, fuzzy inference and genetic programming. Engineering Geology, 203, 70–82. https://doi.org/10.1016/j.enggeo.2015.12.002.
[33] اصلان زاده، م.، حسینی، م. (۱۳۹۶). پیش‌بینی مدول تغییرشکل‌پذیری توده‌سنگ‌های جنوب غربی ایران با استفاده از رگرسیون خطی چند متغیره. نشریه‌ی علمی-پژوهشی مکانیک سنگ، دوره ۱، شماره ۱، صفحه ۸۹ تا ۹۶.
[34] Fattahi, H., Varmazyari, Z., Babanouri, N. (2019). Feasibility of Monte Carlo simulation for predicting deformation modulus of rock mass. Tunnelling and Underground Space Technology, 89, 151–156. https://doi.org/10.1016/j.tust.2019.03.024.
[35] Aladejare, A. E., & Idris, M. A. (2020). Performance analysis of empirical models for predicting rock mass deformation modulus using regression and Bayesian methods. Journal of Rock Mechanics and Geotechnical Engineering, 12, 1263e1271. https://doi.org/10.1016/j.jrmge.2020.03.007.
[36] Hussain, S., Muhammad Khan, N., Emad, M. Z., Naji, A. M., Cao, K., Gao, Q., Rehman, Z. U., Raza, S., Cui, R., Salman, M., & Alarifi, S. S. (2022).  An Appropriate Model for the Prediction of Rock Mass Deformation Modulus among Various Artificial Intelligence Models. Sustainability, 14, 15225. https://doi.org/10.3390/su142215225.
[37] فتاحی، ه.، جیریایی شراهی، ف. (1402). استفاده از روش‌های مختلف هوشمند در نرم‌افزار Orange برای تخمین مدول تغییر شکل‌پذیری توده‌سنگ. مجله انجمن زمین‌شناسی مهندسی ایران ، جلد شانزدهم، شماره ۲، صفحه ۴۷ تا ۶۰.
[38] Asadizadeh, M., & Hossaini, M. F. (2016). Predicting rock mass deformation modulus by artificial intelligence approach based on dilatometer tests. Arabian Journal of Geosciences. 9, 96. DOI:10.1007/s12517-015-2189-5.
[39] Bakhtyari Joint Venture consultant (2008). Geology report (Stage II studies). Tehran: Iran Water and Power Resources Development Co (IWPC) Authority.
[40] Rezaei, M., Monjezi, M., Matinpoor, F., Mohammadi Bolbanabad, S., & Habibi, H. (2023).
Simulation of induced flyrock due to open-pit blasting using the PCA-CART hybrid modelling. Simulation Modelling Practice and Theory, 129, 102844. DOI:10.1016/j.simpat.2023.102844.
[41] Ferreira, C. (2001). Gene Expression Programming: A New Adaptive Algorithm for Solving Problems. Complex Systems, 13(2), 87–129. DOI:10.48550/arXiv.cs/0102027.
[42] Lopes, H. S. & Weinert, W. R. (2004). Egipsys: An enhanced gene expression programming approach for symbolic regression problems. International Journal of Applied Mathematics and Computer Science, 14(3), 375–384.
JOURNAL OF ROCK MECHANICS
Volume 8, Issue 2
Summer 2024
Pages 35-62