To guarantee safe and efficient tunneling of a tunnel boring machine (TBM), rapid and accurate judgment of the rock mass condition is essential. Based on fuzzy C-means clustering, this paper proposes a grouped machine learning method for predicting rock mass parameters. An elaborate data set on field rock mass is collected, which also matches field TBM tunneling. Meanwhile, target stratum samples are divided into several clusters by fuzzy C-means clustering, and multiple submodels are trained by samples in different clusters with the input of pretreated TBM tunneling data and the output of rock mass parameter data. Each testing sample or newly encountered tunneling condition can be predicted by multiple submodels with the weight of the membership degree of the sample to each cluster. The proposed method has been realized by 100 training samples and verified by 30 testing samples collected from the C1 part of the Pearl Delta water resources allocation project. The average percentage error of uniaxial compressive strength and joint frequency (Jf) of the 30 testing samples predicted by the pure back propagation (BP) neural network is 13.62% and 12.38%, while that predicted by the BP neural network combined with fuzzy C-means is 7.66% and 6.40%, respectively. In addition, by combining fuzzy C-means clustering, the prediction accuracies of support vector regression and random forest are also improved to different degrees, which demonstrates that fuzzy C-means clustering is helpful for improving the prediction accuracy of machine learning and thus has good applicability. Accordingly, the proposed method is valuable for predicting rock mass parameters during TBM tunneling.
| [1] |
Armaghani DJ, Mohamad ET, Narayanasamy MS, Narita N, Yagiz S. Development of hybrid intelligent models for predicting TBM penetration rate in hard rock condition. Tunnel Undergr Space Technol. 2017; 63: 29-43.
|
| [2] |
Bashari A, Beiki M, Talebinejad A. Estimation of deformation modulus of rock masses by using fuzzy clustering-based modeling. Int J Rock Mech Mining Sci. 2011; 48(8): 1224-1234.
|
| [3] |
Cordes T, Schneider-Muntau B, Reinhold C, Grüllich S, Himmelsbach C, Wehrmeyer G. Analyses of TBM disc cutter forces—application possibilities. Geomech Tunnel. 2019; 12(5): 586-594.
|
| [4] |
Cui X, Yan E. A clustering algorithm based on differential evolution for the identification of rock discontinuity sets. Int J Rock Mech Mining Sci. 2020; 126:104181.
|
| [5] |
Fattahi H. Adaptive neuro fuzzy inference system based on fuzzy C-means clustering algorithm, a technique for estimation of TBM penetration rate. Iran Univ Sci Technol. 2016a; 6(2): 159-171.
|
| [6] |
Fattahi H. Indirect estimation of deformation modulus of an in situ rock mass: an ANFIS model based on grid partitioning, fuzzy C-means clustering and subtractive clustering. Geosci J. 2016b; 20(5): 681-690.
|
| [7] |
Fattahi H, Babanouri N. Applying optimized support vector regression models for prediction of tunnel boring machine performance. Geotech Geol Eng. 2017; 35(5): 2205-2217.
|
| [8] |
Gao F, Chen D, Zhou K, Niu W, Liu H. A fast clustering method for identifying rock discontinuity sets. KSCE J Civil Eng. 2018; 23(2): 556-566.
|
| [9] |
Goh T, Samsudin A, Rafek A. Application of spectral analysis of surface waves (SASW) method: rock mass chara terization. Sains Malaysiana. 2011; 40(5): 425-430.
|
| [10] |
Gong Q, Lu J, Xu H. A modified rock mass classification system for TBM tunnels and tunneling based on the HC method of China. Int J Rock Mech Mining Sci. 2020; 137(4):104551.
|
| [11] |
Gong Q, Zhao J. Development of a rock mass characteristics model for TBM penetration rate prediction. Int J Rock Mech Mining Sci. 2009; 46(1): 8-18.
|
| [12] |
Gong QM, Zhao J, Jiang YS. In situ TBM penetration tests and rock mass boreability analysis in hard rock tunnels. Tunnel Undergr Space Technol. 2007; 22(3): 303-316.
|
| [13] |
Kitzig MC, Kepic A, Kieu DT. Testing cluster analysis on combined petrophysical and geochemical data for rock mass classification. Explor Geophys. 2017; 48(3): 344-352.
|
| [14] |
Kong F, Shang J. A validation study for the estimation of uniaxial compressive strength based on index tests. Rock Mech Rock Eng. 2018; 51(7): 2289-2297.
|
| [15] |
Li, B, Hu M, Zhang, B, et al. Numerical simulation and experimental studies of rock-breaking methods for pre-grooving-assisted disc cutter. Bull Eng Geol Environ. 2022; 81(3): 1-15.
|
| [16] |
Li, B, Zhang, B, Hu M, Liu B, Cao, W, Xu, B. Full-scale linear cutting tests to study the influence of pre-groove depth on rock-cutting performance by TBM disc cutter. Tunnel Undergr Space Technol. 2022; 122:104366.
|
| [17] |
Li L, Li Y, Chen J. Evaluation of the structural similarity of fractured rock masses based on multiple fracture parameters. Bull Eng Geol Environ. 2021; 80(3): 2189-2198.
|
| [18] |
Li X, Wang Z, Peng K, Liu Z. Ant colony ATTA clustering algorithm of rock mass structural plane in groups. J Central South Univ. 2014; 21(21): 709-714.
|
| [19] |
Liang J, Zhao JH, Han XQ, Li B. Automatic statistic of rock mass discontinuity attitude elements based on k-mean clustering analysis. Appl Mech Mater. 2012; 170-173: 348-351.
|
| [20] |
Liu B, Wang R, Guan Z, et al. Improved support vector regression models for predicting rock mass parameters using tunnel boring machine driving data. Tunnel Undergr Space Technol. 2019; 91:102958.
|
| [21] |
Liu B, Wang R, Zhao G, et al. Prediction of rock mass parameters in the TBM tunnel based on BP neural network integrated simulated annealing algorithm. Tunnel Undergr Space Technol. 2020; 95:103103.
|
| [22] |
Liu Q, Zhao Y, Zhang X, Kong X. Study and discussion on point load test for evaluating rock strength of TBM tunnel constructed in limestone. Rock Soil Mech. 2018; 39(3): 977-984.
|
| [23] |
Lussu A, Grüllich S, Kaiser C, Fontana A. 15 km TBM exploratory tunnel excavation in the construction lot H33 of the brenner base tunnel. Geomech Tunnel. 2019; 12(5): 595-603.
|
| [24] |
Mahdevari S, Shahriar K, Yagiz S, Shirazi M. A support vector regression model for predicting tunnel boring machine penetration rates. Int J Rock Mech Mining Sci. 2014; 72: 214-229.
|
| [25] |
Majdi A, Beiki M. Applying evolutionary optimization algorithms for improving fuzzy C-means clustering performance to predict the deformation modulus of rock mass. Int J Rock Mech Mining Sci. 2019; 113: 172-182.
|
| [26] |
Minh VT, Katushin D, Antonov M, Veinthal R. Regression models and fuzzy logic prediction of TBM penetration rate. Open Eng. 2017; 7(1): 60-68.
|
| [27] |
Naeimipour A, Rostami J, Buyuksagis I. Applications of rock strength borehole probe (RSBP) in underground openings. ISRM International Symposium-EUROCK 2016. International Society for Rock Mechanics and Rock Engineering; 2016: 1213-1218.
|
| [28] |
Nikafshan Rad H, Jalali Z. Modification of rock mass rating system using soft computing techniques. Eng Comp. 2019; 35(4): 1333-1357.
|
| [29] |
Poisel R, Tentschert E, Preh A, Ostermann V, Chwatal W. The interaction of machine and rock mass analysed using TBM data and rock mass parameters. Geomech Tunnel. 2010; 3(5): 510-519.
|
| [30] |
Saeidi O, Torabi SR, Ataei M. Prediction of the rock mass diggability index by using fuzzy clustering-based, ANN and multiple regression methods. Rock Mech Rock Eng. 2014; 47(2): 717-732.
|
| [31] |
Salimi A, Faradonbeh RS, Monjezi M, Moormann C. TBM performance estimation using a classification and regression tree (CART) technique. Bull Eng Geol Environ. 2018; 77(1): 429-440.
|
| [32] |
Shi M, Zhang T, Zhang L, Sun W, Song X. A fuzzy c-means algorithm based on the relationship among attributes of data and its application in tunnel boring machine. Knowl Based Syst. 2020; 191:105229.
|
| [33] |
Sinaga KP, Yang MS. Unsupervised K-means clustering algorithm. IEEE Access. 2020; 8: 80716-80727.
|
| [34] |
Song X, Shi M, Wu J, Sun W. A new fuzzy C-means clustering-based time series segmentation approach and its application on tunnel boring machine analysis. Mech Syst Signal Process. 2019; 133:106279.
|
| [35] |
Wang J, Zheng J, Lv Q, Guo J, He M, Deng J. A multidimensional clustering analysis method for dividing rock mass homogeneous regions based on the shape dissimilarity of trace maps. Rock Mech Rock Eng. 2020; 53(9): 3937-3952.
|
| [36] |
Wang Q, Gao H, Jiang B, Li S, Zhang C. Development and application of a multifunction true triaxial rock drilling test system. J Test Eval. 2020; 48(5): 3450-3467.
|
| [37] |
Wu D, Zhang H, Nie F, et al. Double-attentive principle component analysis. IEEE Signal Process Lett. 2020; 27: 1814-1818.
|
| [38] |
Xu B, Huang X, Li B, et al. The effect of laser irradiation on the compressive strength of granite under uniaxial compression. Rock Mech Rock Eng. 2023.
|
| [39] |
Xue Y, Li X, Diao Z, Zhao F, Zhao H. A dynamic rock mass classification method for TBM tunnel. 4th GeoShanghai International Conference on Rock Mechanics and Rock Engineering, 2018: 319-328.
|
| [40] |
Yagiz S, Karahan H. Prediction of hard rock TBM penetration rate using particle swarm optimization. Int J Rock Mech Mining Sci. 2011; 48: 427-433.
|
| [41] |
Yang MS, Sinaga KP. A feature-reduction multi-view K-means clustering algorithm. IEEE Access. 2019; 7: 114472-114486.
|
| [42] |
Zare Naghadehi M, Ramezanzadeh A. Models for estimation of TBM performance in granitic and mica gneiss hard rocks in a hydropower tunnel. Bull Eng Geol Environ. 2017; 76(4): 1627-1641.
|
| [43] |
Zare Naghadehi M, Samaei M, Ranjbarnia M, Nourani V. State-of-the-art predictive modeling of TBM performance in changing geological conditions through gene expression programming. Measurement. 2018; 126: 46-57.
|
RIGHTS & PERMISSIONS
2024 The Authors. Deep Underground Science and Engineering published by John Wiley & Sons Australia, Ltd on behalf of China University of Mining and Technology.
PDF
