Risk assessment of rockburst using SMOTE oversampling and integration algorithms under GBDT framework

Abstract

Rockburst is a common geological disaster in underground engineering, which seriously threatens the safety of personnel, equipment and property. Utilizing machine learning models to evaluate risk of rockburst is gradually becoming a trend. In this study, the integrated algorithms under Gradient Boosting Decision Tree (GBDT) framework were used to evaluate and classify rockburst intensity. First, a total of 301 rock burst data samples were obtained from a case database, and the data were preprocessed using synthetic minority over-sampling technique (SMOTE). Then, the rockburst evaluation models including GBDT, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Features Gradient Boosting (CatBoost) were established, and the optimal hyperparameters of the models were obtained through random search grid and five-fold cross-validation. Afterwards, use the optimal hyperparameter configuration to fit the evaluation models, and analyze these models using test set. In order to evaluate the performance, metrics including accuracy, precision, recall, and F1-score were selected to analyze and compare with other machine learning models. Finally, the trained models were used to conduct rock burst risk assessment on rock samples from a mine in Shanxi Province, China, and providing theoretical guidance for the mine’s safe production work. The models under the GBDT framework perform well in the evaluation of rockburst levels, and the proposed methods can provide a reliable reference for rockburst risk level analysis and safety management.

References

[1] HeJ, DouL-M, GongS-Y, et al. . Rock burst assessment and prediction by dynamic and static stress analysis based on micro-seismic monitoring [J]. International Journal of Rock Mechanics and Mining Sciences, 2017, 93: 46-53

[2] LiN, FengX-D, JimenezR. Predicting rock burst hazard with incomplete data using Bayesian networks [J]. Tunnelling and Underground Space Technology Incorporating Trenchless Technology Research, 2017, 61: 61-70

[3] SiX-F, GongF-Q. Strength-weakening effect and shear-tension failure mode transformation mechanism of rockburst for fine-grained granite under triaxial unloading compression [J]. International Journal of Rock Mechanics and Mining Sciences, 2020, 131: 104347

[4] GongF-Q, SiX-F, LiX-B, et al. . Experimental investigation of strain rockburst in circular Caverns under deep three-dimensional high-stress conditions [J]. Rock Mechanics and Rock Engineering, 2019, 52(5): 1459-1474

[5] ZhouJ, LiX-B, ShiX-Z. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines [J]. Safety Science, 2012, 50(4): 629-644

[6] BaltzR, HuckeA. Rockburst prevention in the German coal industry[C]. Proceedings of the 27th International Conference on Ground Control in Mining, 2008Morgantown, West Virginia, USAWest Virginia University46-50

[7] CaiW, DouL-M, ZhangM, et al. . A fuzzy comprehensive evaluation methodology for rock burst forecasting using microseismic monitoring [J]. Tunnelling and Underground Space Technology Incorporating Trenchless Technology Research, 2018, 80: 232-245

[8] KenetiA, SainsburyB A. Review of published rockburst events and their contributing factors [J]. Engineering Geology, 2018, 246: 361-373

[9] BlakeW, HedleyD. Rockbursts, case studies from North American Hardrock Mines[M], 2003New YorkSociety for Mining Metallurgy, and Exploration

[10] PuY-Y, ApelD B, XuH-W. Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier [J]. Tunnelling and Underground Space Technology, 2019, 90: 12-18

[11] GongF-Q, WangY-L, LuoS. Rockburst proneness criteria for rock materials: Review and new insights [J]. Journal of Central South University, 2020, 27(10): 2793-2821

[12] WuS-C, WuZ-G, ZhangC-X. Rock burst prediction probability model based on case analysis [J]. Tunnelling and Underground Space Technology Incorporating Trenchless Technology Research, 2019, 93: 103069

[13] RussenesB. Analysis of rock spalling for tunnels in steep valley sides[D], 1974

[14] BartonN, LienR, LundeJ. Engineering classification of rock masses for the design of tunnel support [J]. Rock Mechanics, 1974, 6(4): 189-236

[15] TurchaninovI. Condition of extra hard rock into weak under the influence of tectonic stress of massifs [C]. Proceedings of International Symposium Weak Rock, 1981555-559

[16] HoekE, BrownE T. Underground excavations in rock [M], 1980LondonInstitution of Mining and Metallurgy

[17] KidybińskiA. Bursting liability indices of coal [J]. International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstracts, 1981, 18(4): 295-304

[18] TANG Li-zhong, WANG Wen-xing. New rock burst proneness index[J]. Chinese Journal of Rock Mechanics and Engineering, 2002(6): 874–878. (in Chinese)

[19] MitriH. FE modelling of mining-induced energy release and storage rates [J]. Journal of the Southern African Institute of Mining and Metallurgy, 1999, 99(2): 103-110

[20] WangJ A, ParkH D. Comprehensive prediction of rockburst based on analysis of strain energy in rocks [J]. Tunnelling and Underground Space Technology, 2001, 16(1): 49-57

[21] TarasovB G, RandolphM F. Superbrittleness of rocks and earthquake activity [J]. International Journal of Rock Mechanics and Mining Sciences, 2011, 48(6): 888-898

[22] LuJ. Research on rock burst mechanism in hydraulic diversion tunnel [C]. Proceedings of the First National Symposium on Numerical Calculation and Model Test of Rock Mechanics, 1986ChengduSouthwest Jiaotong University Press210-214

[23] SinghS P. The influence of rock properties on the occurrence and control of rockbursts [J]. Mining Science and Technology, 1987, 5(1): 11-18

[24] HouF, LiuX, WangM. Reanalysis of rockburst genesis and discussion on intensity division [C]. Proceedings of the Third National Conference on Rock Dynamics, 1992WuhanWuhan University of Surveying and Mapping Science and Technology Press448-457

[25] PengZ, WangH-Y, LiT-J. Griffith theory and the criterion of rockburst [J]. Chinese Journal of Rock Mechanics and Engineering, 1996, 15(S1): 491-495(in Chinese)

[26] BukowskaM. The probability of rockburst occurrence in the Upper Silesian Coal Basin Area dependent on natural mining conditions [J]. Journal of Mining Science, 2006, 42(6): 570-577

[27] DongL-J, YanX-H, WangJ, et al. . Case study of microseismic tomography and multi-parameter characteristics under mining disturbances [J]. Journal of Central South University, 2023, 30(7): 2252-2265

[28] DongL-J, ShuH-M, TangZ, et al. . Microseismic event waveform classification using CNN-based transfer learning models [J]. International Journal of Mining Science and Technology, 2023, 33(10): 1203-1216

[29] DongL-J, TangZ, LiX-B, et al. . Discrimination of mining microseismic events and blasts using convolutional neural networks and original waveform [J]. Journal of Central South University, 2020, 27(10): 3078-3089

[30] ZhouJ, LiX-B, MitriH S. Evaluation method of rockburst: State-of-the-art literature review [J]. Tunnelling and Underground Space Technology, 2018, 81: 632-659

[31] WangJ-C, HuangM-J, GuoJ. Rock burst evaluation using the CRITIC algorithm-based cloud model [J]. Frontiers in Physics, 2021, 8: 593701

[32] ZhouK-P, LinY, DengH-W, et al. . Prediction of rock burst classification using cloud model with entropy weight [J]. Transactions of Nonferrous Metals Society of China, 2016, 26(7): 1995-2002

[33] GuoJ, ZhangW-X, ZhaoY. A multidimensional cloud model for rockburst prediction [J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(5): 1199-1206(in Chinese)

[34] LiangW-Z, ZhaoG-Y, WuH, et al. . Risk assessment of rockburst via an extended MABAC method under fuzzy environment [J]. Tunnelling and Underground Space Technology, 2019, 83: 533-544

[35] HeS-Q, SongD-Z, MitriH, et al. . Integrated rockburst early warning model based on fuzzy comprehensive evaluation method [J]. International Journal of Rock Mechanics and Mining Sciences, 2021, 142: 104767

[36] XueY-G, LiZ-Q, LiS-C, et al. . Prediction of rock burst in underground Caverns based on rough set and extensible comprehensive evaluation [J]. Bulletin of Engineering Geology and the Environment, 2019, 78(1): 417-429

[37] LiuL, ChenZ-Q, WangL-G. Rock burst laws in deep mines based on combined model of membership function and dominance-based rough set [J]. Journal of Central South University, 2015, 22(9): 3591-3597

[38] LiuR, YeY-C, HuN-Y, et al. . Classified prediction model of rockburst using rough sets-normal cloud [J]. Neural Computing and Applications, 2019, 31(12): 8185-8193

[39] DongL-J, ShuW-W, LiX-B, et al. . Quantitative evaluation and case studies of cleaner mining with multiple indexes considering uncertainty factors for phosphorus mines [J]. Journal of Cleaner Production, 2018, 183: 319-334

[40] DongL-J, ZhouY, DengS-J, et al. . Evaluation methods of man-machine-environment system for clean and safe production in phosphorus mines: A case study [J]. Journal of Central South University, 2021, 28(12): 3856-3870

[41] XiaoY-X, WanR-J, FengG-L, et al. . Stiffness theory of rockburst: Research progress and trends [J]. Journal of Central South University, 2023, 30(12): 4230-4251

[42] DongL-J, WangJ, WangJ-C, et al. . Safe and intelligent mining: Some explorations and challenges in the era of big data [J]. Journal of Central South University, 2023, 30(6): 1900-1914

[43] Ribeiro e SousaL, MirandaT, Leal e SousaR, et al. . The use of data mining techniques in rockburst risk assessment [J]. Engineering, 2017, 3(4): 552-558

[44] DongL-J, LiX-B, PengK. Prediction of rockburst classification using random forest [J]. Transactions of Nonferrous Metals Society of China, 2013, 23(2): 472-477

[45] ZhangL-W, ZhangX-Y, WuJ, et al. . Rockburst prediction model based on comprehensive weight and extension methods and its engineering application [J]. Bulletin of Engineering Geology and the Environment, 2020, 79(9): 4891-4903

[46] ZhaoH-B. Classification of rockburst using support vector machine [J]. Rock and Soil Mechanics, 2005, 26(4): 642-644(in Chinese)

[47] Shirani FaradonbehR, TaheriA. Long-term prediction of rockburst hazard in deep underground openings using three robust data mining techniques [J]. Engineering with Computers, 2019, 35(2): 659-675

[48] DongL-J, WesselooJ, PotvinY, et al. . Discriminant models of blasts and seismic events in mine seismology [J]. International Journal of Rock Mechanics and Mining Sciences, 2016, 86: 282-291

[49] DongL-J, WesselooJ, PotvinY, et al. . Discrimination of mine seismic events and blasts using the fisher classifier, naive Bayesian classifier and logistic regression [J]. Rock Mechanics and Rock Engineering, 2016, 49(1): 183-211

[50] LiangW-Z, SariY A, ZhaoG-Y, et al. . Probability estimates of short-term rockburst risk with ensemble classifiers [J]. Rock Mechanics and Rock Engineering, 2021, 54(4): 1799-1814

[51] XieX-B, JiangW, GuoJ. Research on rockburst prediction classification based on GA-XGB model [J]. IEEE Access, 2021, 9: 83993-84020

[52] ZhuX, ChuJ, WangK-D, et al. . Prediction of rockhead using a hybrid N-XGBoost machine learning framework [J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6): 1231-1245

[53] WangY-Y, SunS-F, ChenX-Q, et al. . Short-term load forecasting of industrial customers based on SVMD and XGBoost [J]. International Journal of Electrical Power & Energy Systems, 2021, 129: 106830

[54] LiangW-Z, LuoS-Z, ZhaoG-Y, et al. . Predicting hard rock pillar stability using GBDT, XGBoost, and LightGBM algorithms [J]. Mathematics, 2020, 8(5): 765

[55] WangS-M, ZhouJ, LiC-Q, et al. . Rockburst prediction in hard rock mines developing bagging and boosting tree-based ensemble techniques [J]. Journal of Central South University, 2021, 28(2): 527-542

[56] LuC-G, ZhangS-A, XueD, et al. . Improved estimation of coalbed methane content using the revised estimate of depth and CatBoost algorithm: A case study from southern Sichuan Basin, China [J]. Computers and Geosciences, 2022, 158: 104973

[57] WangY-H, LiW-D, LiQ-G, et al. . Fuzzy comprehensive evaluation method for rockburst prediction [J]. Chinese Journal of Rock Mechanics and Engineering, 1998, 17(5): 15-23(in Chinese)

[58] BAI Ming-zhou, WANG Lian-jun, XU Zhao-yi. Study on a neutral network model and its application in predicting the risk of rock blast [J]. China Safety Science Journal, 2002(4): 68–72. DOI: https://doi.org/10.16265/j.cnki.issn1003-3033.2002.04.016. (in Chinese)

[59] GongF-Q, LiX-B. A distance discriminant analysis method for prediction of possibility and classification of rockburst and its application [J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(5): 1012-1018(in Chinese)

[60] WangJ-L, ChenJ-P, YangJ, et al. . Method of distance discriminant analysis for determination of classification of rockburst [J]. Rock and Soil Mechanics, 2009, 30(7): 2203-2208(in Chinese)

[61] GongF-Q, LiX-B, ZhangW. Rockburst prediction of underground engineering based on Bayes discriminant analysis method [J]. Rock and Soil Mechanics, 2010, 31(S1): 370-377(in Chinese)

[62] KangY. Research on the failure mechanism of surrounding rock in deep tunnels [D], 2006ChongqingChongqing University(in Chinese)

[63] HE Zheng, LI Xiao-hong, LU Yi-yu, et al. Application of BP neural network model in rockburst prediction in deep tunnels [J]. Chinese Journal of Underground Space and Engineering, 2008(3): 494–498. (in Chinese)

[64] ZhangL-W, ZhangD-Y, QiuD-H. Application of extension evaluation method in rockburst prediction based on rough set theory [J]. Journal of China Coal Society, 2010, 35(9): 1461-1465(in Chinese)

[65] YiY-L, CaoP, PuC-Z. Multi-factorial comprehensive estimation for Jinchuan’s deep typical rockburst tendency [J]. Science & Technology Review, 2010, 28(2): 76-80(in Chinese)

[66] DingX-D, WuJ-M, LiJ, et al. . Artificial neural network for forecasting and classification of rockbursts [J]. Journal of Hohai University (Natural Sciences), 2003, 31(4): 424-427(in Chinese)

[67] YangJ-L, LiX-B, ZhouZ-L, et al. . A Fuzzy assessment method of rock-burst prediction based on rough set theory [J]. Metal Mine, 2010, 39(6): 26-29(in Chinese)

[68] FengX-T, WangL-N. Rockburst prediction based on neural networks [J]. Transactions of Nonferrous Metals Society of China, 1994, 1(1): 7-14

[69] ZhangJ-J, FuB-J. Rockburst and its criteria and control [J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(10): 2034-2042(in Chinese)

[70] JoshaghaniA, BalapourM, RamezanianpourA A. Effect of controlled environmental conditions on mechanical, microstructural and durability properties of cement mortar [J]. Construction and Building Materials, 2018, 164: 134-149

[71] RaoH-D, ShiX-Z, RodrigueA K, et al. . Feature selection based on artificial bee colony and gradient boosting decision tree [J]. Applied Soft Computing, 2019, 74: 634-642

[72] ChenT-Q, GuestrinC. XGBoost: A scalable tree boosting system [C]. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016San Francisco, California, USAACM785-794

[73] KeG-L, MengQ, FinleyT, et al. . Lightgbm: A highly efficient gradient boosting decision tree [J]. Advances in Neural Information Processing Systems, 2017, 30: 52

[74] ZengH, YangC, ZhangH, et al. . A LightGBM-based EEG analysis method for driver mental states classification [J]. Computational Intelligence and Neuroscience, 2019, 2019: 3761203

[75] KodazH, özşenS, ArslanA, et al. . Medical application of information gain based artificial immune recognition system (AIRS): Diagnosis of thyroid disease [J]. Expert Systems with Applications, 2009, 36(2): 3086-3092

[76] DOROGUSH A V, ERSHOV V, GULIN A. CatBoost: Gradient boosting with categorical features support [OL]. arXiv preprint arXiv. DOI: https://doi.org/10.48550/arXiv.1810.11363.

[77] PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features [OL]. arXiv preprint arXiv. DOI: https://doi.org/10.48550/arXiv.1706.09516.

[78] MaK, ShenQ-Q, SunX-Y, et al. . Rockburst prediction model using machine learning based on microseismic parameters of Qinling water conveyance tunnel [J]. Journal of Central South University, 2023, 30(1): 289-305

[79] ChawlaN V, BowyerK W, HallL O, et al. . SMOTE: Synthetic minority over-sampling technique [J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357

[80] BergstraJ, BengioY. Random search for hyperparameter optimization [J]. Journal of Machine Learning Research, 2012, 13: 281-305

[81] WuJ, ChenX-Y, ZhangH, et al. . Hyperparameter optimization for machine learning models based on Bayesian optimization [J]. Journal of Electronic Science and Technology, 2019, 17: 26-40

[82] HanJ H, ChoiD J, ParkS U, et al. . Hyperparameter optimization for multi-layer data input using genetic algorithm [C]. 2020 IEEE 7th International Conference on Industrial Engineering and Applications (ICIEA), 2020Bangkok, ThailandIEEE701-704

[83] NakisaB, RastgooM N, RakotonirainyA, et al. . Long short term memory hyperparameter optimization for a neural network based emotion recognition framework [J]. IEEE Access, 2018, 6: 49325-49338

[84] TsaiC W, HsiaC H, YangS-J, et al. . Optimizing hyperparameters of deep learning in predicting bus passengers based on simulated annealing [J]. Applied Soft Computing, 2020, 88: 106068

[85] LiashchynskyiP, LiashchynskyiP. Grid search, random search, genetic algorithm: A big comparison for NAS [EB/OL], 2019arXiv: 1912.06059

[86] JungY. Multiple predicting K-fold cross-validation for model selection [J]. Journal of Nonparametric Statistics, 2018, 30(1): 197-215

[87] Machine learning quick reference: Quick and essential machine learning hacks for training smart data models. [M]. Birmingham: Packt Publishing Ltd, 2019.

[88] LiuZ-X, WangW, LuoJ-A, et al. . Method of energy evolution of rock under uniaxial compression test[J]. Journal of China Coal Society, 2020, 45(9): 3131-3139(in Chinese)

[89] ZhangC-Q, LuJ-J, ChenJ, et al. . Discussion on rock burst proneness indexes and their relation [J]. Rock and Soil Mechanics, 2017, 38(5): 1397-1404(in Chinese)