Rock burst intensity grading prediction based on the combination of PCA，CBLOF and SVMSMOTE algorithms
YAO Nan1，2，ZHANG Yili1，LIU Yang1，2，YE Yicheng1，2，LUO Xiaobing3，FENG Jie3，HUANG Zhaoyun4
(1. School of Resource and Environmental Engineering，Wuhan University of Science and Technology，Wuhan，Hubei 430081，China；2. Hubei Key Laboratory for Efficient Utilization and Agglomeration of Metallergic Mineral Resource，Wuhan，
Hubei 430081，China；3. Hubei Provincial Emergency Rescue Center，Wuhan，Hubei 430000，China；
4. Hubei Jingshen Safety Technology Co.，Ltd.，Yichang，Hubei 443000，China)
Abstract：To reduce the correlation among feature parameters in rock burst sample data，eliminate outliers and balance the number of various rock burst levels in the dataset，a method combining principal component analysis (PCA)，cluster-based local outlier factor(CBLOF) and support vector machine synthetic minority over-sampling technique(SVMSMOTE) is proposed to enhance the quality of the rock burst database. Initially，a total of 343 rock burst cases are collected from both domestic and international sources to build the original dataset. PCA is employed for dimensionality reduction，CBLOF is used to identify and eliminate outliers within each rock burst level，and SVMSMOTE synthesizes new minority samples near the boundaries of each rock burst level. The processed and original rock burst databases are subsequently used to train six different machine learning models to validate the effectiveness of the PCA，CBLOF，and SVMSMOTE combination. The results show that the accuracy of models trained on the processed database significantly improved：AdaBoost by 29%，CatBoost by 28.5%，LightGBM by 34%，Gradient Boosting by 28%，ExtraTrees by 26.5% and Random Forest by 24%，compared to models trained on the original database. Therefore，processing the rock burst database using the combined PCA，CBLOF and SVMSMOTE algorithms effectively enhances the quality of the database and im-proves the performance of machine learning prediction models.
姚 囝1，2，张义礼1，刘 洋1，2，叶义成1，2，骆效兵3，冯 杰3，黄兆云4. 基于PCA，CBLOF和SVMSMOTE算法组合的岩爆烈度等级分级预测[J]. 岩石力学与工程学报, 2025, 44(5): 1230-1241.
YAO Nan1，2，ZHANG Yili1，LIU Yang1，2，YE Yicheng1，2，LUO Xiaobing3，FENG Jie3，HUANG Zhaoyun4. Rock burst intensity grading prediction based on the combination of PCA，CBLOF and SVMSMOTE algorithms. , 2025, 44(5): 1230-1241.
[1] 李夕兵，姚金蕊，宫凤强. 硬岩金属矿山深部开采中的动力学问题[J]. 中国有色金属学报，2011，21(10)：2 551–2 563.(LI Xibing，YAO Jinrui，GONG Fengqiang. Dynamic problems in deep exploitation of hard rock metal mines[J]. The Chinese Journal of Non-ferrous Metals，2011，21(10)：2 551–2 563.(in Chinese))
[2] 李夕兵，周 健，王少锋，等. 深部固体资源开采评述与探索[J]. 中国有色金属学报，2017，27(6)：1 236–1 262.(LI Xibing，ZHOU Jian，WANG Shaofeng，et al. Review and practice of deep mining for solid mineral resources[J]. The Chinese Journal of Nonfer-rous Metals，2017，27(6)：1 236–1 262.(in Chinese))
[3] 吴顺川，张晨曦，成子桥. 基于PCA-PNN原理的岩爆烈度分级预测方法[J]. 煤炭学报，2019，44(9)：2 767–2 776.(WU Shuchuan，ZHANG Chenxi，CHENG Ziqiao. Prediction method of rock burst intensity classification based on PCA-PNN principle[J]. Journal of China Coal Society，2019，44 (9)：2 767–2 776.(in Chinese))
[4] 汤志立，王 雪，徐千军. 基于过采样和客观赋权法的岩爆预测[J]. 清华大学学报：自然科学版，2021，61(6)：543–555.(TANG Zhili，WANG Xue，XU Qianjun. Rockburst prediction based on oversampling and objective weighting method[J]. Journal of Tsinghua University：Science and Technology，2021，61(6)：543–555.(in Chinese))
[5] 詹术霖，黄明清，陈 霖. 基于3种机器学习模型的岩爆类型预测[J]. 福州大学学报：自然科学版，2023，51(6)：879–886.(ZHAN Shulin，HUANG Mingqing，CHEN Lin. Prediction of rockburst type based on three machine learning models[J]. Journal of Fuzhou University：Natural Science，2023，51(6)：879–886.(in Chinese))
[6] LIU Q，XUE Y，LI G，et al. Application of KM-SMOTE for rockburst intelligent prediction[J]. Tunnelling and Underground Space Technology 2023，138(8)：105180.
[7] 吴 菡，郭永刚，何军杰. 基于主成分和改进支持向量机的岩爆倾向性预测[J]. 工业建筑，2023，53(10)：119–125.(WU Han，GUO Yonggang，HE Junjie，et al. Rockburst propensity prediction based on principal component analysis and improved support vector machine[J]. Industrial Construction，2023，53(10)：119–125.(in Chinese))
[8] 谭文侃，叶义成，胡南燕. LOF与改进SMOTE算法组合的强烈岩爆预测[J]. 岩石力学与工程学报，2021，40(6)：1 186–1 194.(TAN Wenkan，YE Yicheng，HU Nanyan，et al. Prediction of severe rockburst using a combination of lof and improved SMOTE al-gorithm[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(6)：1 186–1 194.(in Chinese))
[9] AHMAD M，KATMAN H Y，AL-MANSOB R A，et al. Prediction of rockburst intensity grade in deep underground excavation using adaptive boosting classifier[J]. Complexity，2022，24(5)：1–10.
[10] GUO J，GUO J，ZHANG Q，et al. Research on Rockburst classifi-cation prediction based on BP-SVM model[J]. IEEE Access，2022，10： 50 427–50 447.
[11] ADOKO A C，GOKCEOGLU C，WU L，et al. Knowledge-based and data-driven fuzzy modeling for rockburst prediction[J]. Interna-tional Journal of Rock Mechanics and Mining Sciences，2013，61(6)：86–95.
[12] ZHOU J，LI X，MITRI H S. Classification of rockburst in underground projects：comparison of ten supervised learning methods[J]. Journal of Computing in Civil Engineering，2016，30(5)：04016003.
[13] DONG L J，LI X B，KANG P. Prediction of rockburst classification using random forest[J]. Transactions of Nonferrous Metals Society of China，2013，23(2)：472–477.
[14] LI N，JIMENEZ R. A logistic regression classifier for long-term probabilistic prediction of rock burst hazard[J]. Natural Hazards，2018，90：197–215.
[15] 张俊峰. 大相岭隧道岩爆灾害分阶段预测与控制技术研究[硕士学位论文][D]. 成都：西南交通大学，2010.(ZHANG Junfeng. Re-search on staged prediction and control technology of rockburst disas-ters in Daxiangling tunnel[M. S. Thesis][D]. Chengdu：Southwest Jiaotong University，2010.(in Chinese))
[16] ZHOU J，LI X，SHI X. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines[J]. Safety Science，2012，50(4)：629–644.
[17] XUE Y，LI Z，LI S，et al. Prediction of rock burst in underground caverns based on rough set and extensible comprehensive evalua-tion[J]. Bulletin of Engineering Geology and the Environment，2019，78(7)：417–429.
[18] 衣永亮，曹 平，蒲成志. 金川深部典型岩石岩爆倾向性多因素综合评判[J]. 科技导报，2010，28(2)：76–80.(YI Yongliang，CAO Ping，PU Chengzhi. Comprehensive evaluation of rockburst propensity of typical rocks in deep areas of Jinchuan[J]. Science and Technology Review，2010，28(2)：76–80.(in Chinese))
[19] 宫凤强，李夕兵. 岩爆发生和烈度分级预测的距离判别方法及应用[J]. 岩石力学与工程学报，2007，26(5)：1 012–1 018.(GONG Fengqiang，LI Xibing. Distance discrimination method and applica-tion for predicting rockburst occurrence and intensity grading[J]. Chi-nese Journal of Rock Mechanics and Engineering，2007，26(5)：1 012–1 018.(in Chinese))
[20] 张金明，朱晓源，程 鹏. 拉森斯(Russenses)岩爆判据研究[J]. 浙江水利科技，2004，42(1)：9–11.(ZHANG Jinming，ZHU Xiaoyuan，CHENG Peng. Study on Russenses rockburst criteria[J]. Zhejiang Water Conservancy Science and Technology，2004，42(1)：9–11.(in Chinese))
[21] NGUYEN H M，COOPER E W，KAMEI K，et al. Borderline over-sampling for imbalanced data classification[J]. International Journal of Knowledge Engineering，2011，3(1)：4–21.
[22] 刘 波，梁龙跃. 基于KM-SVMSMOTE-CNN的信用卡欺诈检测[J]. 计算机系统应用，2022，31(6)：361–367.(LIU Bo，LIANG Longyue. Credit card fraud detection based on KM-SVMSMOTE-CNN[J]. Computer Systems Applications，2022，31(6)：361–367.(in Chinese))
[23] 汤立志，徐千军. 基于九种机器学习的岩爆预测研究[J]. 岩石力学与工程学报，2020，39(4)：773–781.(TANG Lizhi，XU Qi-anjun. Rock burst prediction based on nine machine learning algo-rithms[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(4)：773–781.(in Chinese))
[24] YANG L，SHAMI A J N. On hyperparameter optimization of ma-chine learning algorithms：theory and practice[J]. Neurocomputing，2020，415(12)：295–316.
[25] 贺隆平，姚 囝，王其虎，等. 基于自动机器学习的岩爆烈度分级预测模型[J]. 岩土力学，2024，35(9)：1–10.(HE Longping，YAO Nan，WANG Qihu，et al. Rockburst intensity classification prediction model based on automated machine learning[J]. Rock and Soil Mechanics，2024，35(9)：1–10.(in Chinese))
2025, Vol. 44 
