Rockburst prediction model using machine learning based on microseismic parameters of Qinling water conveyance tunnel

Abstract

The frequency and intensity of rockburst in underground engineering have increased with excavation depth. In order to predict rockburst intensity grade, this paper introduces six machine learning algorithms to establish six rockburst prediction models. Based on 289-day microseismic monitoring data and rockburst events of Qinling water conveyance tunnel, the rockburst intensity grade prediction dataset is constructed. In the process of model establishment, the impact of data imbalance on model performance is discussed first, and it is concluded that Borderline-SMOTE1 is the most effective method to eliminate data imbalance. Secondly, the analysis of six models’ performance indicators shows that the rockburst prediction model based on the Adaboost algorithm has the best performance, with the highest accuracy, macro-F₁, and micro-F₁, which are 0.938, 0.937, and 0.938, respectively. Finally, the Borderline-SMOTE1-Adaboost model was applied to the prediction of the rockburst intensity grade of Qinling water conveyance tunnel from June 1, 2020 to June 10, 2020. All ten strong rockbursts are accurately predicted, which verifies the effectiveness of predicting rockburst intensity grade through microseismic parameters. The results show that the Borderline-SMOTE1-Adaboost rockburst prediction model can provide a reference for the early warning of rockburst disasters during the construction of deep-buried tunnels.

Keywords

microseismic / rockburst prediction / machine learning / over sampling

References

[1] LiP, FengX, FengG, et al. . Rockburst and microseismic characteristics around lithological interfaces under different excavation directions in deep tunnels [J]. Engineering Geology, 2019, 260: 105209

[2] PuY, ApelD B, XuH. Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier [J]. Tunnelling and Underground Space Technology, 2019, 9012-18

[3] LiX, MaoH, LiB, et al. . Dynamic early warning of rockburst using microseismic multi-parameters based on Bayesian network [J]. Engineering Science and Technology, an International Journal, 2021, 24(3): 715-727

[4] XueY, BaiC, KongF, et al. . A two-step comprehensive evaluation model for rockburst prediction based on multiple empirical criteria [J]. Engineering Geology, 2020, 268: 105515

[5] HockE, BrownE TUnderground excavation in rock [M], 1980, London, The Institute of Mining and Metallurgy: 382-395

[6] RUSSENES B F. Analysis of rock spalling for tunnels in steep valley sides [D]. Norwegian Institute of Technology, 1974. (in Nonvegian)

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

[8] WangY, LiW, LeeP K K, et al. . Method of fuzzy comprehensive evaluations for rockburst prediction [J]. Chinese Journal of Rock Mechanics and Engineering, 1998, 17(5): 15-23(in Chinese)

[9] XuC, LiuX, WangE, et al. . Rockburst prediction and classification based on the ideal-point method of information theory [J]. Tunnelling and Underground Space Technology, 2018, 81: 382-390

[10] QiuD, LiS, ZhangL. Study on rockburst intensity prediction based on efficacy coefficient method [J]. Applied Mechanics and Materials, 2013, 353–356: 1277-1280

[11] ZhangL, ZhangX, 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

[12] ZhouH, ChenS, LiH, et al. . Rockburst prediction for hard rock and deep-lying long tunnels based on the entropy weight ideal point method and geostress field inversion: A case study of the Sangzhuling Tunnel [J]. Bulletin of Engineering Geology and the Environment, 2021, 80(5): 3885-3902

[13] LiuF, TangC, MaT, et al. . Characterizing rockbursts along a structural plane in a tunnel of the Hanjiang-to-Weihe River diversion project by microseismic monitoring [J]. Rock Mechanics and Rock Engineering, 2019, 52(6): 1835-1856

[14] GuS, WangC, JiangB, et al. . Field test of rock burst danger based on drilling pulverized coal parameters [J]. Disaster Advances, 2012, 5(4): 237-240

[15] LiuC, LiH, YuS, et al. . Rockburst prediction technology combining rock mass structure analysis and electromagnetic emission monitoring: A case study of Uzbekistan Kamchik tunnel [J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(2): 349-358(in Chinese)

[16] PuY, ApelD B, LiuV, et al. . Machine learning methods for rockburst prediction-state-of-the-art review [J]. International Journal of Mining Science and Technology, 2019, 29(4): 565-570

[17] FENG Xia-ting, ZHAO Hong-bo. Prediction of rockburst using support vector machine [J]. Journal of Northeastern University, 2002(1): 57–59. (in Chinese)

[18] GE Qi-fa, FENG Xia-ting. Classification and prediction of rockburst using AdaBoost combination learning method [J]. Rock and Soil Mechanics, 2008(4): 943–948. DOI: https://doi.org/10.16285/j.rsm.2008.04.031. (in Chinese)

[19] WangY. Prediction of rockburst risk in coal mines based on a locally weighted C4.5 algorithm [J]. IEEE Access, 2021, 9: 15149-15155

[20] WuT, GaoY, ZhouY, et al. . A novel comprehensive quantitative method for various geological disaster evaluations in underground engineering: Multidimensional finite interval cloud model (MFICM) [J]. Environmental Earth Sciences, 2021, 80(20): 1-18

[21] KeB, KhandelwalM, AsterisP G, et al. . Rock-burst occurrence prediction based on optimized naïve Bayes models [J]. IEEE Access, 2021, 9: 91347-91360

[22] XueY, BaiC, QiuD, et al. . Predicting rockburst with database using particle swarm optimization and extreme learning machine [J]. Tunnelling and Underground Space Technology, 2020, 98: 103287

[23] WuS, WuZ, ZhangC. Rock burst prediction probability model based on case analysis [J]. Tunnelling and Underground Space Technology, 2019, 93103069

[24] TangZ, WangX, XuQ. Rockburst prediction based on oversampling and objective weighting method [J]. Journal of Tsinghua University (Science and Technology), 2021, 61(6): 543-555(in Chinese)

[25] PapadopoulosD, BenardosA. Enhancing machine learning algorithms to assess rock burst phenomena [J]. Geotechnical and Geological Engineering, 2021, 39(8): 5787-5809

[26] YinX, LiuQ, HuangX, et al. . Real-time prediction of rockburst intensity using an integrated CNN-Adam-BO algorithm based on microseismic data and its engineering application [J]. Tunnelling and Underground Space Technology, 2021, 117104133

[27] YinX, LiuQ, PanY, et al. . Strength of stacking technique of ensemble learning in rockburst prediction with imbalanced data: Comparison of eight single and ensemble models [J]. Natural Resources Research, 2021, 30(2): 1795-1815

[28] ZhouJ, LiX, MitriH S. Evaluation method of rockburst: State-of-the-art literature review [J]. Tunnelling and Underground Space Technology, 2018, 81632-659

[29] TangZ, XuQ. Rockburst prediction based on nine machine learning algorithms [J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(4): 773-781(in Chinese)

[30] FengG, FengX, ChenB, et al. . A microseismic method for dynamic warning of rockburst development processes in tunnels [J]. Rock Mechanics and Rock Engineering, 2015, 48(5): 2061-2076

[31] LiGRockburst prediction based on neural network and microseismic information [D], 2011, Shenyang, Northeastern University(in Chinese)

[32] SenatorskiP. Apparent stress scaling and statistical trends [J]. Physics of the Earth and Planetary Interiors, 2007, 160(3–4): 230-244

[33] LiuJ, FengX, LiY, et al. . Studies on temporal and spatial variation of microseismic activities in a deep metal mine [J]. International Journal of Rock Mechanics and Mining Sciences, 2013, 60: 171-179

[34] ZornE, HammackR, HarbertW, et al. . Geomechanical lithology-based analysis of microseismicity in organic shale sequences: A Pennsylvania Marcellus Shale example [J]. The Leading Edge, 2017, 36(10): 845-851

[35] GutenbergB, RichterC F. Frequency of earthquakes in California [J]. Bulletin of the Seismological Society of America, 1944, 34(4): 185-188

[36] HoodaS, MannS. Distributed synthetic minority oversampling technique [J]. International Journal of Computational Intelligence Systems, 2019, 12(2): 929-936

[37] HanH, WangW, MaoB. Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning [C]. Advances in Intelligent Computing, 2005, 3664: 878-887

[38] NguyenH M, CooperE W, KameiK. Borderline over-sampling for imbalanced data classification [J]. International Journal of Knowledge Engineering and Soft Data Paradigms, 2011, 3(1): 4-21

[39] PuY, ApelD B, WangC, et al. . Evaluation of burst liability in kimberlite using support vector machine [J]. Acta Geophysica, 2018, 66(5): 973-982

[40] ZhaoX, WuB, YuL, et al. . Influence of discontinuities on rock failure under blasting at Shuangjiangkou hydropower station [J]. Shock and Vibration, 2021, 2021: 5808248

[41] FanY, LiY, BaoX, et al. . Development of machine learning models for predicting postoperative delayed remission in patients with Cushing’s disease [J]. The Journal of Clinical Endocrinology & Metabolism, 2020, 106(1): e217-e231

[42] LinY, ZhouK, LiJ. Application of cloud model in rock burst prediction and performance comparison with three machine learning algorithms [J]. IEEE Access, 2018, 630958-30968