Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2021, Vol. 61 Issue (6): 543-555    DOI: 10.16511/j.cnki.qhdxxb.2021.22.013
  防灾减灾 本期目录 | 过刊浏览 | 高级检索 |
基于过采样和客观赋权法的岩爆预测
汤志立1, 王雪2, 徐千军3
1. 北京京投城市管廊投资有限公司, 北京 100027;
2. 桂林市水利局, 桂林 541001;
3. 清华大学 水沙科学与水利水电工程国家重点实验室, 北京 100084
Rockburst prediction based on oversampling and objective weighting method
TANG Zhili1, WANG Xue2, XU Qianjun3
1. Beijing Jingtou Urban Utility Tunnel Investment Co., Ltd., Beijing 100027, China;
2. Guilin Water Resources Bureau, Guilin 541001, China;
3. State Key Laboratory of Hydroscience and Engineering, Tsinghua University, Beijing 100084, China
全文: PDF(7941 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 为解决基于机器学习的岩爆预测中存在的数据不均衡问题,提高模型泛化能力,进而提高岩爆预测性能,该文构建了由246组岩爆案例组成的岩爆预测数据集,优选了单轴抗压强度与单轴抗拉强度之比、最大切应力、最大切向应力与单轴抗压强度之比、单轴抗压强度、单轴抗拉强度、弹性能指数6个常用岩爆等级判别特征。通过引入9种经典机器学习算法,建立了9个考虑多因素的岩爆预测模型,研究了5种过采样方法及5种客观赋权方法对模型预测性能的影响。研究结果表明:数据在过采样处理后,模型准确率提高了11.8%~52.3%、宏平均F1值提高了13.0%~50.0%;随机过采样方法对模型性能提升效果最佳,最能解决数据不均衡问题;随机过采样均衡化数据集后,客观赋权作用因模型而异,只能提升基于极限梯度提升算法、随机森林、决策树、极限树构建的模型的准确率(分别提高1.1%、2.1%、10.7%、12.9%)及宏平均F1值(分别提高1.2%、2.3%、11.8%、12.8%);基于随机过采样的多层感知机算法模型是最优的岩爆预测模型,其准确率及宏平均F1值均最高,分别为0.917、0.920。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
汤志立
王雪
徐千军
关键词 岩爆预测机器学习数据不均衡过采样客观赋权法    
Abstract:Machine learning rockburst predictions seek to solve the data imbalance problem and improve the prediction accuracy and model generalization. This work optimized a rockburst prediction algorithm using a dataset containing 246 rockburst cases and 6 rockburst indicators, B1, MTS, SCF, UCS, UTS and Wet. Nine rockburst prediction models were developed based on machine learning algorithms to study the effects of 5 oversampling methods and 5 objective weighting methods on the model predictions. The results show that data oversampling improves the model accuracy by 11.8% to 52.3% and increases the macro average F1 by 13.0% to 50.0%. Random oversampling gives the best improvements to resolve the data imbalance problem. After randomly oversampling the data set, objective date weighting only increases the accuracy and the macro average F1 of the extreme gradient boosting algorithm (XGBoost) model by 1.1% and 1.2%, the random forest (RF) model by 2.1% and 2.3%, the decision tree (DT) model by 10.7% and 11.8%, and the extremely randomized trees (ET) model by 12.9% and 12.8%. The multi-layer perception (MLP) algorithm model based on random oversampling is the best rockburst prediction model with an accuracy of 0.917 and a macro average F1 of 0.920.
Key wordsrockburst prediction    machine learning    data imbalance    oversampling    objective weighting method
收稿日期: 2020-12-16      出版日期: 2021-04-28
基金资助:“十三五”国家重点研发计划(2017YFC0804602);国家自然科学基金项目(52090084,51879141);清华大学水沙科学与水利水电工程国家重点实验室自主科研课题(2019-KY-03)
通讯作者: 徐千军,教授,E-mail:qxu@tsinghua.edu.cn      E-mail: qxu@tsinghua.edu.cn
作者简介: 汤志立(1991-),男,博士。
引用本文:   
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. Journal of Tsinghua University(Science and Technology), 2021, 61(6): 543-555.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2021.22.013  或          http://jst.tsinghuajournals.com/CN/Y2021/V61/I6/543
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
[1] 冯夏庭, 肖亚勋, 丰光亮, 等. 岩爆孕育过程研究[J]. 岩石力学与工程学报, 2019, 38(4):649-673. FENG X T, XIAO Y X, FENG G L, et al. Study on the development process of rockbursts[J]. Chinese Journal of Rock Mechanics and Engineering, 2019, 38(4):649-673. (in Chinese)
[2] 徐林生, 王兰生, 李天斌. 国内外岩爆研究现状综述[J]. 长江科学院院报, 1999, 16(4):24-27. XU L S, WANG L S, LI T B. Present situation of rockburst research at home and abroad[J]. Journal of Yangtze River Scientific Research Institute, 1999, 16(4):24-27. (in Chinese)
[3] COOK N G W. The failure of rock[J]. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 1965, 2(4):389-403.
[4] ZHOU J, LI X B, MITRI H S. Evaluation method of rockburst:State-of-the-art literature review[J]. Tunnelling and Underground Space Technology, 2018, 81:632-659.
[5] WANG J A, PARK H D. Comprehensive prediction of rockburst based on analysis of strain energy in rocks[J]. Tunnelling and Underground Space Technology, 2001, 16(1):49-57.
[6] TAO Z Y. Support design of tunnels subjected to rockbursting[C]//ISRM International Symposium. Madrid, Spain, 1988:407-411.
[7] ZHANG J J, FU B J, LI Z K, et al. Criterion and classification for strain mode rockbursts based on five-factor comprehensive method[C]//Harmonising Rock Engineering and the Environment:Proceedings of the 12th ISRM International Congress on Rock Mechanics. Beijing, 2011:1435-1440.
[8] 王元汉, 李卧东, 李启光, 等. 岩爆预测的模糊数学综合评判方法[J]. 岩石力学与工程学报, 1998, 17(5):493-501. WANG Y H, LI W D, LI Q G, et al. Method of fuzzy comprehensive evaluations for rockburst prediction[J]. Chinese Journal of Rock Mechanics and Engineering, 1998, 17(5):493-501. (in Chinese)
[9] CHEN B R, FENG X T, LI Q P, et al. Rock burst intensity classification based on the radiated energy with damage intensity at Jinping II Hydropower Station, China[J]. Rock Mechanics and Rock Engineering, 2015, 48(1):289-303.
[10] AUBERTIN M, GILL D E, SIMON R. On the use of the brittleness index modified (BIM) to estimate the post-peak behavior of rocks[C]//Proceedings of the 1st North American Rock Mechanics Symposium:Models and Measurements Challenges from Industry. Austin, USA, 1994:945-952.
[11] PU Y Y, APEL D B, LIU V, 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.
[12] TANG L Z, XIA K W. Seismological method for prediction of areal rockbursts in deep mine with seismic source mechanism and unstable failure theory[J]. Journal of Central South University of Technology, 2010, 17(5):947-953.
[13] ZHOU J, LI X B, SHI X 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.
[14] LI N, JIMENEZ R. A logistic regression classifier for long-term probabilistic prediction of rock burst hazard[J]. Natural Hazards, 2018, 90(1):197-215.
[15] FENG X T, WANG L N. Rockburst prediction based on neural networks[J]. Journal of Railway Science and Engineering, 1994, 4(1):7-14.
[16] ADOKO A C, GOKCEOGLU C, WU L, et al. Knowledge-based and data-driven fuzzy modeling for rockburst prediction[J]. International Journal of Rock Mechanics and Mining Sciences, 2013, 61:86-95.
[17] AFRAEI S, SHAHRIAR K, MADANI S H. Statistical assessment of rock burst potential and contributions of considered predictor variables in the task[J]. Tunnelling and Underground Space Technology, 2018, 72:250-271.
[18] 葛启发, 冯夏庭. 基于AdaBoost组合学习方法的岩爆分类预测研究[J]. 岩土力学, 2008, 29(4):943-948. GE Q F, FENG X T. Classification and prediction of rockburst using AdaBoost combination learning method[J]. Rock and Soil Mechanics, 2008, 29(4):943-948. (in Chinese)
[19] 王迎超, 尚岳全, 孙红月, 等. 基于功效系数法的岩爆烈度分级预测研究[J]. 岩土力学, 2010, 31(2):529-534. WANG Y C, SHANG Y Q, SUN H Y, et al. Study of prediction of rockburst intensity based on efficacy coefficient method[J]. Rock and Soil Mechanics, 2010, 31(2):529-534. (in Chinese)
[20] ZHOU J, LI X B, 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.
[21] AFRAEI S, SHAHRIAR K, MADANI S H. Developing intelligent classification models for rock burst prediction after recognizing significant predictor variables, Section 2:Designing classifiers[J]. Tunnelling and Underground Space Technology, 2019, 84:522-537.
[22] AFRAEI S, SHAHRIAR K, MADANI S H. Developing intelligent classification models for rock burst prediction after recognizing significant predictor variables, Section 1:Literature review and data preprocessing procedure[J]. Tunnelling and Underground Space Technology, 2019, 83:324-353.
[23] LI N, JIMENEZ R, FENG X D. The influence of Bayesian networks structure on rock burst hazard prediction with incomplete data[J]. Procedia Engineering, 2017, 191:206-214.
[24] GUO H X, LI Y J, SHANG J, et al. Learning from class-imbalanced data:Review of methods and applications[J]. Expert Systems with Applications, 2017, 73:220-239.
[25] SUN Y M, WONG A K C, KAMEL M S. Classification of imbalanced data:A review[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2009, 23(4):687-719.
[26] GARCÍA V, SÁNCHEZ J S, MOLLINEDA R A. On the effectiveness of preprocessing methods when dealing with different levels of class imbalance[J]. Knowledge-Based Systems, 2012, 25(1):13-21.
[27] GALAR M, FERNANDEZ A, BARRENECHEA E, et al. A review on ensembles for the class imbalance problem:Bagging-, boosting-, and hybrid-based approaches[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2012, 42(4):463-484.
[28] PRATI R C, BATISTA G E A P A, SILVA D F. Class imbalance revisited:A new experimental setup to assess the performance of treatment methods[J]. Knowledge and Information Systems, 2015, 45(1):247-270.
[29] KRAWCZYK B. Learning from imbalanced data:Open challenges and future directions[J]. Progress in Artificial Intelligence, 2016, 5(4):221-232.
[30] 李艳霞, 柴毅, 胡友强, 等. 不平衡数据分类方法综述[J]. 控制与决策, 2019, 34(4):673-688. LI Y X, CHAI Y, HU Y Q, et al. Review of imbalanced data classification methods[J]. Control and Decision, 2019, 34(4):673-688. (in Chinese)
[31] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE:Synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16(1):321-357.
[32] HAN H, WANG W Y, MAO B H. Borderline-SMOTE:A new over-sampling method in imbalanced data sets learning[C]//International Conference on Intelligent Computing. Hefei, 2005:878-887.
[33] 肖学沛. 锦屏二级水电站交通隧道岩爆预测及防治研究[D]. 成都:成都理工大学, 2005. XIAO X P. A study on the prediciton and prevention of rockburst in the traffic tunnel of Jinping II Hydropower Station[D]. Chengdu:Chengdu University of Technology, 2005. (in Chinese)
[34] QIU D H, LI T B, XUE Y G, et al. Rockburst prediction based on distance discrimination method and optimization technology-based weight calculation method[J]. Electronic Journal of Geotechnical Engineering, 2014, 19:1843-1854.
[35] 贾月卿. 改建铁路成昆线老鼻山隧道岩爆倾向性预测分析与防治技术研究[D]. 西安:西安建筑科技大学, 2018. JIA Y Q. Study on the tendency prediction and control techniques of rock burst in Laobi mountain tunnel of Chengdu to Kunming railway[D]. Xi'an:Xi'an University of Architecture and Technology, 2018. (in Chinese)
[36] 王羽, 许强, 柴贺军, 等. 工程岩爆灾害判别的RBF-AR耦合模型[J]. 吉林大学学报(地球科学版), 2013, 43(6):1943-1949. WANG Y, XU Q, CAI H J, et al. Rock burst prediction in deep shaft based on RBF-AR model[J]. Journal of Jilin University (Earth Science Edition), 2013, 43(6):1943-1949. (in Chinese)
[37] XUE Y G, LI Z Q, LI S 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.
[38] 王超圣. 北山花岗岩岩爆特征实验研究及现场综合监测分析[D]. 北京:中国矿业大学, 2018. WANG C S. Experimental study and site comprehensive monitoring analysis on rockburst characteristics of Beishan granite[D]. Beijing:China University of Mining and Technology, 2018. (in Chinese)
[39] 汤志立, 徐千军. 基于9种机器学习算法的岩爆预测研究[J]. 岩石力学与工程学报, 2020, 39(4):773-781. TANG Z L, XU Q J. Rockburst prediction based on nine machine learning algorithms[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(4):773-781. (in Chinese)
[1] 吴浩, 牛风雷. 高温球床辐射传热中的机器学习模型[J]. 清华大学学报(自然科学版), 2023, 63(8): 1213-1218.
[2] 代鑫, 黄弘, 汲欣愉, 王巍. 基于机器学习的城市暴雨内涝时空快速预测模型[J]. 清华大学学报(自然科学版), 2023, 63(6): 865-873.
[3] 任建强, 崔亚鹏, 倪顺江. 基于机器学习的新冠肺炎疫情趋势预测方法[J]. 清华大学学报(自然科学版), 2023, 63(6): 1003-1011.
[4] 安健, 陈宇轩, 苏星宇, 周华, 任祝寅. 机器学习在湍流燃烧及发动机中的应用与展望[J]. 清华大学学报(自然科学版), 2023, 63(4): 462-472.
[5] 赵祺铭, 毕可鑫, 邱彤. 基于机器学习的乙烯裂解过程模型比较与集成[J]. 清华大学学报(自然科学版), 2022, 62(9): 1450-1457.
[6] 曹来成, 李运涛, 吴蓉, 郭显, 冯涛. 多密钥隐私保护决策树评估方案[J]. 清华大学学报(自然科学版), 2022, 62(5): 862-870.
[7] 王豪杰, 马子轩, 郑立言, 王元炜, 王飞, 翟季冬. 面向新一代神威超级计算机的高效内存分配器[J]. 清华大学学报(自然科学版), 2022, 62(5): 943-951.
[8] 陆思聪, 李春文. 基于场景与话题的聊天型人机会话系统[J]. 清华大学学报(自然科学版), 2022, 62(5): 952-958.
[9] 李维, 李城龙, 杨家海. As-Stream:一种针对波动数据流的算子智能并行化策略[J]. 清华大学学报(自然科学版), 2022, 62(12): 1851-1863.
[10] 刘强墨, 何旭, 周佰顺, 吴昊霖, 张弛, 秦羽, 沈晓梅, 高小榕. 基于机器学习和瞳孔响应的简易高性能自闭症分类模型[J]. 清华大学学报(自然科学版), 2022, 62(10): 1730-1738.
[11] 马晓悦, 孟啸. 用户参与视角下多图推文的图像位置和布局效应[J]. 清华大学学报(自然科学版), 2022, 62(1): 77-87.
[12] 王志国, 章毓晋. 监控视频异常检测:综述[J]. 清华大学学报(自然科学版), 2020, 60(6): 518-529.
[13] 宋宇波, 祁欣妤, 黄强, 胡爱群, 杨俊杰. 基于二阶段多分类的物联网设备识别算法[J]. 清华大学学报(自然科学版), 2020, 60(5): 365-370.
[14] 芦效峰, 蒋方朔, 周箫, 崔宝江, 伊胜伟, 沙晶. 基于API序列特征和统计特征组合的恶意样本检测框架[J]. 清华大学学报(自然科学版), 2018, 58(5): 500-508.
[15] 邹权臣, 张涛, 吴润浦, 马金鑫, 李美聪, 陈晨, 侯长玉. 从自动化到智能化:软件漏洞挖掘技术进展[J]. 清华大学学报(自然科学版), 2018, 58(12): 1079-1094.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn