Abstract
Shear constitutive models of rock discontinuities have been viewed as an effective stability evaluation tool in the rock mass engineering application area. This paper proposes a new interpretable shear strength criterion for rock joints based on multivariate adaptive regression splines (MARS) algorithm. Sensitivity analyses are then performed on the developed shear strength criterion. As the second purpose of this research, the potential competence of five surrogate soft computing (SC) methods including Gaussian process (GP), alternating model tree (AMT), Cubist, radial basis function (RBF) networks, and elastic net (EN) paradigms for fast predicting the shear strength of rock discontinuities is also comparatively evaluated along with the MARS model. These approaches formulate nonlinear relations between input and output variables. The proposed methodologies consider eight input factors: sampling interval \((l)\), maximum contact area ratio \({(A}_{0})\), distribution parameter \((C)\), maximum apparent dip angle \(({\theta }_{\max}^{*})\), basic friction angle \(({\varphi }_{\text{b}})\), tensile strength (\({\sigma }_{\text{t}}\)), uniaxial compressive strength \({(\sigma }_{\text{c}})\), and normal stress \(({\sigma }_{\text{n}})\) to assess peak shear strength \(({\tau }_{\text{p}})\) of rock joints. A dataset collected from the literature conducted on the direct shear test is used for training and evaluating proposed methods. Ten-fold cross-validation is utilized to enhance the robustness and generalization of the developed SC-based shear strength surrogate models. Statistical indices and comparative analyses with conventional criteria indicate that the proposed SC regressors can deliver good agreements with the measured data in terms of performance accuracy and outperform or achieve comparable performances to the conventional models. However, GP, AMT, and RBF models have a good prediction performance than MARS and EN models.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11440-021-01442-z/MediaObjects/11440_2021_1442_Fig10_HTML.png)
Similar content being viewed by others
Abbreviations
- AMT:
-
Alternating model tree
- BF:
-
Basis function
- EN:
-
Elastic net
- GCV:
-
Generalized cross-validation
- GP:
-
Gaussian process
- JRC:
-
Joint roughness coefficient
- MAE:
-
Mean absolute error
- MARS:
-
Multivariate adaptive regression splines
- PUK:
-
Pearson VII kernel function
- RBF:
-
Radial basis function
- RMSE:
-
Root mean square error
- RSS:
-
Residual sums of squares
- SC:
-
Soft computing
- TSS:
-
Total sum of squares
- E:
-
Young’s modulus
- \({\tau }_{\text{p}}\) :
-
Peak shear strength (MPa)
- \({\sigma }_{\text{t}}\) :
-
Tensile strength (MPa)
- \({\sigma }_{\text{c}}\) :
-
Uniaxial compressive strength of the joint surface (MPa)
- \({\varphi }_{\text{b}}\) :
-
Basic friction angle (°)
- \({\sigma }_{\text{n}}\) :
-
Normal stress (MPa)
- \({A}_{0}\) :
-
Maximum potential contact area ratio
- \({\theta }_{\max}^{*}\) :
-
Maximum apparent dip angle (°)
- \(C\) :
-
Roughness parameter defined by Grasselli [15]
- \({C}^{\prime}\) :
-
Morphological parameter defined by Tian et al. [41]
- \(l\) :
-
Sampling interval
- \({R}^{2}\), RSq:
-
Coefficient of determination
- \(\beta_{0} ,\beta_{m}\) :
-
BF parameters
- \(B_{m} \left( X \right)\) :
-
mTh BF
- \(\max\left( , \right)\) :
-
Partitions data
- \(\left\| {x - x_{i} } \right\|\) :
-
Euclidean distance between points \(x\) and \(x_{i}\)
- M:
-
Number of terms
- \({\text{y}}\) :
-
Dependent variable or response
- \(x\) :
-
Independent variable or feature
- \(X\) :
-
Matrix of input variables
- \(f\left( x \right)\) :
-
Predicted value by a function \(f\) at \(x\)
- \(d\) :
-
Penalty factor
- \(\Sigma\) :
-
Sum
- \(N\) :
-
Number of observations
- \(k\left( {x,x^{\prime } } \right)\) :
-
Kernel function or covariance function
- \(m\left( x \right)\) :
-
Mean function
- \(\sim\) :
-
Distributed as
- \(E\left[ {f\left( x \right)} \right]\) :
-
Expectation of \(f\left( x \right)\)
- \(N\left( {0,\sigma_{\text{n}}^{2} } \right)\) :
-
The Gaussian distribution with mean 0 and variance \(\sigma_{\text{n}}^{2}\)
- \(\varepsilon\) :
-
Gaussian noise
- \(\overline{f}_{*}\) :
-
Predictive mean value
- \(\mathrm{var}\left( {y*} \right)\) :
-
Predictive variance
- \(I\) :
-
Identity matrix
- \(p\left( {\left. {y*} \right|X,y,X*} \right)\) :
-
Probability \(f*\) given \(X,y,X*\)
- \(\gamma ,\delta ,\omega\) :
-
Kernels hyper-parameters
- \(f_{s} \left( {x_{i} } \right)\) :
-
Standardizer function
- \(\mu_{i}\) :
-
Mean of the input variable \({ }i\)
- \(\sigma_{i}\) :
-
Standard deviation of the input variable \(i\)
- \(\omega_{mi}\) :
-
Synaptic weight between the \(i\) th node of hidden layer and the \(m\) th node of output layer
- \(O_{i} \left( x \right)\) :
-
Activation function
- \(c_{i}\) :
-
Center of the RBF for hidden node \(i\)
- \(\lambda\) :
-
Regularization positive constant value
- \(\alpha\) :
-
Regularization parameter between 0 and 1
- \(\left\| \beta \right\|\) :
-
Norm of \(\beta\)
- \(\beta\) :
-
Weight (coefficient variable) vector
References
Babanouri N, Fattahi H (2018) Constitutive modeling of rock fractures by improved support vector regression. Environ Earth Sci 77(6):1–13. https://doi.org/10.1007/s12665-018-7421-7
Babanouri N, Fattahi H (2020) An ANFIS–TLBO criterion for shear failure of rock joints. Soft Comput 24(7):4759–4773. https://doi.org/10.1007/s00500-019-04230-w
Babanouri N, Asadizadeh M, Hasan-Alizade Z (2020) Modeling shear behavior of rock joints: a focus on interaction of influencing parameters. Int J Rock Mech Min Sci 134:104449. https://doi.org/10.1016/j.ijrmms.2020.104449
Barton N (1973) Review of a new shear-strength criterion for rock joints. Eng Geol 7(4):287–332. https://doi.org/10.1016/0013-7952(73)90013-6
Barton N, Choubey V (1977) The shear strength of rock joints in theory and practice. Rock Mech 10(1):1–54. https://doi.org/10.1007/BF01261801
Buhmann MD (2003) Radial basis functions: theory and implementations. Cambridge University Press, Cambridge
Fathipour Azar H, Torabi SR (2014) Estimating fracture toughness of rock (KIC) using artificial neural networks (ANNS) and linear multivariable regression (LMR) models. In: 5th Iranian rock mechanics conference
Fathipour-Azar H (2021) Machine learning assisted distinct element models calibration: ANFIS, SVM, GPR, and MARS approaches. Acta Geotech. https://doi.org/10.1007/s11440-021-01303-9
Fathipour-Azar H (2021) Data-driven estimation of joint roughness coefficient (JRC). J Rock Mech Geotech Eng 13(6):1428–1437. https://doi.org/10.1016/j.jrmge.2021.09.003
Fathipour-Azar H, Saksala T, Jalali SME (2017) Artificial neural networks models for rate of penetration prediction in rock drilling. J Struct Mech 50(3):252–255. https://doi.org/10.23998/rm.64969
Fathipour-Azar H, Wang J, Jalali SME, Torabi SR (2020) Numerical modeling of geomaterial fracture using a cohesive crack model in grain-based DEM. Comput Part Mech 7:645–654. https://doi.org/10.1007/s40571-019-00295-4
Frank E, Mayo M, Kramer S (2015) Alternating model trees. In: Proceedings of the 30th annual ACM symposium on applied computing, pp 871–878. https://doi.org/10.1145/2695664.2695848
Friedman JH (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1–67. https://doi.org/10.1214/aos/1176347963
Goh AT, Zhang Y, Zhang R, Zhang W, Xiao Y (2017) Evaluating stability of underground entry-type excavations using multivariate adaptive regression splines and logistic regression. Tunn Undergr Space Technol 70:148–154. https://doi.org/10.1016/j.tust.2017.07.013
Grasselli G (2001) Shear strength of rock joints based on quantified surface description. Dissertation, Swiss Federal Institute of Technology
Hasanipanah M, Meng D, Keshtegar B, Trung NT, Thai DK (2020) Nonlinear models based on enhanced Kriging interpolation for prediction of rock joint shear strength. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05252-4
Homand F, Belem T, Souley M (2001) Friction and degradation of rock joint surfaces under shear loads. Int J Numer Anal Meth Geomech 25(10):973–999. https://doi.org/10.1002/nag.163
Houborg R, McCabe MF (2018) A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning. ISPRS J Photogramm Remote Sens 135:173–188. https://doi.org/10.1016/j.isprsjprs.2017.10.004
Huang J, Zhang J, Gao Y (2021) Intelligently predict the rock joint shear strength using the support vector regression and firefly algorithm. Lithosphere. https://doi.org/10.2113/2021/2467126
Jaeger JC (1971) Friction of rocks and stability of rock slopes. Geotechnique 21(2):97–134. https://doi.org/10.1680/geot.1971.21.2.97
Jing L, Stephansson O (2007) Constitutive models of rock fractures and rock masses—the basics. Dev Geotech Eng 85:47–109. https://doi.org/10.1016/S0165-1250(07)85003-6
Kuhn M, Johnson K (2013) Applied predictive modeling 26. Springer, New York
Kulatilake PHSW, Shou G, Huang TH, Morgan RM (1995) New peak shear strength criteria for anisotropic rock joints. Int J Rock Mech Mining Sci Geomech Abstr 32(7):673–697. https://doi.org/10.1016/0148-9062(95)00022-9
Ladanyi B, Archambault G (1969) Simulation of shear behavior of a jointed rock mass. In: Proceedings of the 11th US symposium on rock mechanics (USRMS), Berkeley, CA, pp 105–125
Lanaro F, Stephansson O (2003) A unified model for characterisation and mechanical behaviour of rock fractures. Pure Appl Geophys 160(5):989–998. https://doi.org/10.1007/PL00012577
Li Y, Tang C, Li D, Wu C (2020) A new shear strength criterion of three-dimensional rock joints. Rock Mech Rock Eng 53(3):1477–1483. https://doi.org/10.1007/s00603-019-01976-5
Li Y, Xu Q, Aydin A (2017) Uncertainties in estimating the roughness coefficient of rock fracture surfaces. Bull Eng Geol Env 76(3):1153–1165. https://doi.org/10.1007/s10064-016-0994-z
Maksimović M (1996) The shear strength components of a rough rock joint. Int J Rock Mech Min Sci Geomech Abstr 33(8):769–783. https://doi.org/10.1016/0148-9062(95)00005-4
Milborrow S (2014) Notes on the earth package. http://www.milbo.org/doc/earth-notes.pdf
Milborrow S (2021) Notes on the earth package. http://www.milbo.org/doc/earthnotes.pdf
Misra A (2002) Effect of asperity damage on shear behavior of single fracture. Eng Fract Mech 69(17):1997–2014. https://doi.org/10.1016/S0013-7944(02)00073-5
Patton FD (1966) Multiple modes of shear failure in rock. In: Proceedings of the 1st ISRM congress, pp 509–513
Peng K, Amar MN, Ouaer H, Motahari MR, Hasanipanah M (2020) Automated design of a new integrated intelligent computing paradigm for constructing a constitutive model applicable to predicting rock fractures. Eng Comput. https://doi.org/10.1007/s00366-020-01173-x
Quinlan JR (1992) Learning with continuous classes. In: 5th Australian joint conference on artificial intelligence, vol 92, pp 343–348
Quinlan JR (1993) Combining instance-based and model-based learning. In: Proceedings of the tenth international conference on machine learning, pp 236–243
Rasmussen CE, Williams C (2006) Gaussian processes for machine learning. MIT Press, Cambridge
Singh HK, Basu A (2018) Evaluation of existing criteria in estimating shear strength of natural rock discontinuities. Eng Geol 232:171–181. https://doi.org/10.1016/j.enggeo.2017.11.023
Tang ZC, Jiao YY, Wong LNY, Wang XC (2016) Choosing appropriate parameters for developing empirical shear strength criterion of rock joint: review and new insights. Rock Mech Rock Eng 49(11):4479–4490. https://doi.org/10.1007/s00603-016-1014-0
Tatone BS (2009) Quantitative characterization of natural rock discontinuity roughness in-situ and in the laboratory. Master’s thesis, Department of Civil Engineering, University of Toronto, Canada
Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res Atmos 106(D7):7183–7192. https://doi.org/10.1029/2000JD900719
Tian Y, Liu Q, Liu D, Kang Y, Deng P, He F (2018) Updates to Grasselli’s peak shear strength model. Rock Mech Rock Eng 51(7):2115–2133. https://doi.org/10.1007/s00603-018-1469-2
Xia CC, Tang ZC, Xiao WM, Song YL (2014) New peak shear strength criterion of rock joints based on quantified surface description. Rock Mech Rock Eng 47(2):387–400. https://doi.org/10.1007/s00603-013-0395-6
Xia C, Huang M, Qian X, Hong C, Luo Z, Du S (2019) Novel intelligent approach for peak shear strength assessment of rock joints on the basis of the relevance vector machine. Math Probl Eng. https://doi.org/10.1155/2019/3182736
Yang J, Rong G, Cheng L, Hou D, Wang X (2015) Experimental study of peak shear strength of rock joints. Chin J Rock Mech Eng 34(5):884–894
Yang J, Rong G, Hou D, Peng J, Zhou C (2016) Experimental study on peak shear strength criterion for rock joints. Rock Mech Rock Eng 49(3):821–835. https://doi.org/10.1007/s00603-015-0791-1
Zhang WG, Goh ATC (2013) Multivariate adaptive regression splines for analysis of geotechnical engineering systems. Comput Geotech 48:82–95. https://doi.org/10.1016/j.compgeo.2012.09.016
Zhang W, Goh AT, Zhang Y (2016) Multivariate adaptive regression splines application for multivariate geotechnical problems with big data. Geotech Geol Eng 34(1):193–204. https://doi.org/10.1007/s10706-015-9938-9
Zhang W, Zhang R, Wu C, Goh ATC, Lacasse S, Liu Z, Liu H (2020) State-of-the-art review of soft computing applications in underground excavations. Geosci Front 11(4):1095–1106. https://doi.org/10.1016/j.gsf.2019.12.003
Zhao J (1997) Joint surface matching and shear strength part B: JRC-JMC shear strength criterion. Int J Rock Mech Min Sci 34(2):179–185. https://doi.org/10.1016/S0148-9062(96)00063-0
Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc Ser B (Stat Methodol) 67(2):301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fathipour-Azar, H. New interpretable shear strength criterion for rock joints. Acta Geotech. 17, 1327–1341 (2022). https://doi.org/10.1007/s11440-021-01442-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11440-021-01442-z