Accurate prediction of rockburst is fundamental for mitigating rockburst hazards and holds significant importance for the safety of deep underground engineering. A data set containing 241 rockbursts was constructed. Uniaxial compressive strength (UCS), uniaxial tensile strength (UTS), brittle-coefficient (BI), maximum tangential stress (MTS), elastic energy index (Wet), and the ratio of maximum tangential stress to uniaxial compressive strength (SCF) were selected as the prediction indexes of rockburst. Statistical analysis of the original dataset initially identified outliers through coefficient of variation. The t-distributed stochastic neighbor embedding(t-SNE) method was employed to reduce data dimensionality to three dimensions for visualization, which intuitively revealed data imbalance and outliers. Subsequently, Borderline-SMOTE oversampling was applied to balance the dataset, followed by Yeo-Johnson transformation for data normalization. Through different data preprocessing strategies, three random forest models were developed: the RF model, SMOTE-RF model, and Borderline-SMOTE-RF model. Grid search combined with 10-fold cross-validation was implemented for parameter optimization, and model performance was evaluated using confusion matrices and multiple metrics. Results demonstrate that the Borderline-SMOTE-RF model achieves the highest prediction accuracy of 82.7%. The proposed model was ultimately applied to rockburst prediction in the headrace tunnel of Jiangbian hydropower station, showing high consistency with actual situation. The research findings can provide valuable insights for rockburst disaster prediction.
FengXiating, XiaoYaxun, FengGuangliang, et al. Study on the development process of rockbursts[J]. Chinese Journal of Rock Mechanics and Engineering, 2019, 38(4): 649-673.
SunFengwei, QiaoDonglei, AnYanjun, et al. Characteristic analysis of high in-situ stress field and rockburst prediction of deep-buried highway tunnel[J]. Science Technology and Engineering, 2022, 22(26): 11592-11600.
JiangFanzhi, XiangXiaodong, ZhuDongsheng. The current status and developing tendency of rock blasting forecast at home and abroad[J]. Industrial Safety and Environmental Protection, 2003, 29(8): 19-22.
ZhangRun, WangYongbin. Research on machine learning with algorithm and development[J]. Journal of Communication University of China (Science and Technology), 2016, 23(2): 10-18, 24.
SuGuoshao, ZhangXiaofei, YanLiubin. Rockburst prediction method based on case reasoning pattern recognition[J]. Journal of Mining and Safety Engineering, 2008, 25(1): 63-67.
[15]
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.
TanWenkan, YeYicheng, HuNanyan, et al. Severe rock burst prediction based on the combination of LOF and improved SMOTE algorithm[J]. Chinese Journal of Rock Mechanics and Engineering, 2021, 40(6): 1186-1194.
TangZhili, XuQianjun. Rockburst prediction based on nine machine learning algorithms[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(4): 773-781.
LiBo, DaiYunyun. Comprehensive prediction of rock burst in Dayan Bay high-speed railway tunnel[J]. Science Technology and Engineering, 2014, 14(4): 278-283.
FuZiguo, LiHua, DengJianhui, et al. Application of self-organizing feature map in rockburst classification[J]. Chinese Journal of Underground Space and Engineering, 2023, 19(1): 334-342.
[24]
RussenesB F. Analysis of rock spalling for tunnels in steep valley sides (in Norwegian)[D]. Trondheim: Norwegian Institute of Technology, 1974.
FengXiating, ChenBingrui, ZhangChuanqing, et al. Mechanism, warning and dynamic control of rockburst development processes[M]. Beijing: Science Press, 2013.
HanCe, ZhaiYue, QuLu, et al. Analysis of rockburst indicators based on machine learning interpretability algorithm[J]. Science Technology and Engineering, 2023, 23(18): 7895-7902.
YangYingchun, ZhuJing. A new model for classified prediction of rockburst and its application[J]. Journal of China Coal Society, 2000, 25(2): 169-172.
[31]
ZhouJ, LiX, MitriH S. Classification of rockburst in underground projects: comparison of ten supervised learning methods[J]. Journal of Computing in Civil Engineering, 2016, 30(5): 1-19.
WuShunchuan, ZhangChenxi, ChengZiqiao. Prediction method of rockburst intensity classification based on PCA-PNN principle[J]. Journal of China Coal Society, 2019, 44(9): 2767-2776.
WenTingxin, WangZefeng. Prediction model of rockburst intensity levels based on K-means SMOTE and IDBO-RF[J]. Journal of Safety Science and Technology, 2024, 20(6): 140-146.
[36]
MaatenL V D, HintonG. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(86): 2579-2605.
WuMinhao, WangJiangong, ZhuYinggang, et al. Online identification of active distribution network operation mode based on t-SNE dimensionality reduction and clustering[J]. Electric Power Construction, 2023, 44(8): 52-60.
GuoYanping, GaoYun, LüBingdong. Data visualization analysis based on t-SNE dimension reduction[J]. Electronic Technology and Software Engineering, 2021(21): 166-170.
[41]
郇兆鑫. 基于深度几何特征的人脸表情识别研究[D]. 南京: 南京大学, 2020.
[42]
HuanZhaoxin. Facial expression recognition based on deep geometric features[D]. Nanjing: Nanjing University, 2020.
ShiDongyu, HuWenqiang, LiGang, et al. Study on visualization method of electrical distance in power system using t-SNE[J]. Electric Power Engineering Technology, 2018, 37(2): 78-82.
[45]
YeoI K, JohnsonR A. A new family of power transformations to improve normality or symmetry[J]. Biometrika, 2000, 87(4): 954-959.
TanWenkan, HuNanyan, YeYicheng, et al. Rockburst intensity classification prediction based on four ensemble learning[J]. Chinese Journal of Rock Mechanics and Engineering, 2022, 41(S2): 3250-3259.
[48]
ChawlaN V, BowyerK W, HallL O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16(1): 321-357.
ChenBin, SuYidan, HuangShan. Classification of imbalance data based on KM-SMOTE algorithm and random forest[J]. Computer Technology and Development, 2015, 25(9): 17-21.
[51]
HanH, WangW Y, MaoB H. Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning[C]// Advances in Intelligent Computing. Berlin, Heidelberg: Springer, 2005: 878-887.
ShiHongbo, ChenYuwen, ChenXin. Summary of research on SMOTE oversampling and its improved algorithms[J]. CAAI Transactions on Intelligent Systems, 2019, 14(6): 1073-1083.
[54]
BreimanL. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[55]
董师师, 黄哲学. 随机森林理论浅析[J]. 集成技术, 2013, 2(1): 1-7.
[56]
DongShishi, HuangZhexue. A brief theoretical overview of random forests[J]. Journal of Integration Technology, 2013, 2(1): 1-7.
ChangXingbing, ZhangFangan, TangYanjie. Rock burst characteristics of headrace tunnel for Jiangbian hydropower project and counter measures[J]. Northwest Hydropower, 2010(2): 57-59.
[59]
XueY G, BaiC H, QiuD H, et al. Predicting rockburst with database using particle swarm optimization and extreme learning machine[J]. Tunnelling and Underground Space Technology, 2020, 98: 103287.
ZhangLewen, ZhangDeyong, QiuDaohong. Application of extension evaluation method in rockburst prediction based on rough set theory[J]. Journal of China Coal Society, 2010, 35(9): 1461-1465.
LinJinhong, HuJianxun, MengYongxu, et al. Study and treatment measures of Jiangbian hydropower station deep underground workings rock burst characters[C]// The Proceedings of 9th National Congress of Engineering Geology. Qingdao: Engineering Geology Professional Committee of Geological Society of China, 2012: 610-616.