[1]齐石,李墨潇,吕伟,等.基于L-XGB算法的岩爆倾向等级预测模型*[J].中国安全生产科学技术,2023,19(9):33-38.[doi:10.11731/j.issn.1673-193x.2023.09.005]
QI Shi,LI Moxiao,LYU Wei,et al.Prediction model of rockburst tendency grade based on L-XGB algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(9):33-38.[doi:10.11731/j.issn.1673-193x.2023.09.005]
点击复制
基于L-XGB算法的岩爆倾向等级预测模型*
QI Shi,LI Moxiao,LYU Wei,et al.Prediction model of rockburst tendency grade based on L-XGB algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(9):33-38.[doi:10.11731/j.issn.1673-193x.2023.09.005]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 19
- 期数:
- 2023年9期
- 页码:
- 33-38
- 栏目:
- 学术论著
- 出版日期:
- 2023-09-30
文章信息/Info
- Title:
- Prediction model of rockburst tendency grade based on L-XGB algorithm
- 文章编号:
- 1673-193X(2023)-09-0033-06
- Keywords:
- rockburst prediction; XGBoost; prediction model; outlier
- 分类号:
- X936
- 文献标志码:
- A
- 摘要:
- 为解决岩爆预测复杂性、特殊性、随机性特征导致样本要求高、预测精度低的缺点，基于LOF（局部离群因子检测方法）结合XGBoost（极限梯度提升树）方法，通过网格搜索和曲线搜索拟合内部学习参数，构建L-XGB岩爆趋势预测模型。使用国内外260组岩爆实例数据对模型预测结果进行验证，与XGBoost、随机森林、KNN和支持向量机算法的预测结果进行对比分析研究。研究结果表明：该模型预测率94.2%，为岩爆预测提供了更加合理可靠的预测模型。研究结果可为岩爆预测提供方法以及岩爆的事前风险管理与防治提供理论基础。
- Abstract:
- In order to solve the shortcomings of high sample requirements and low prediction accuracy caused by the complexity,particularity and randomness characteristics of rockburst prediction,based on the detection method of LOF (Local outlier factor) combined with the XGBoost (Extreme gradient boosting tree) method,the L-XGB rockburst trend prediction model was constructed by fitting the internal learning parameters through grid search and curve search.260 sets of rockburst case data at home and abroad were used to verify the prediction results of the model,and the prediction results were compared and analyzed with those of XGBoost,random forest,KNN and support vector machine.The research results showed that the prediction rate of this model is 94.113%,which provides a more reasonable and reliable prediction model for rockburst prediction.The research results can provide theoretical basis for the advanced risk management and prevention of rockburst.
参考文献/References:
［1］殷欣,刘泉声,丁自伟,等.面向地下工程岩爆灾害智能化预警:基于模糊理论改进的多属性群决策模型［J］.应用基础与工程科学学报,2022,30(2):374-395.
YIN Xin,LIU Quansheng,DING Ziwei,et al.Intelligent early warning for underground engineering rockburst disaster:an improved multi-attribute group decision-making model based on fuzzy theory ［J］.Journal of Basic Science and Engineering,2022,30(2):374-395.
［2］ZHANG J F,JIANG F X,YANG J B.Rockburst mechanism in soft coal seam within deep coal mines［J］.International Journal of Mining Science and Technology,2017,27(3):551-556.
［3］谭文侃,叶义成,胡南燕,等.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):1186-1194.
TAN Wenkan,YE Yicheng,HU Nanyan,et al.Strong rock burst prediction based on LOF and improve SMOTE algorithm ［J］.Chinese Journal of Rock Mechanics and Engineering,2021,40(6):1186-1194.
［4］CHEN L,WU S.Study on the integrated planning of deep mining considering rock burst prediction［J］.IOP Conference Series:Earth and Environmental Science,2020,570(4):42-47.
［5］吴枋胤,何川,汪波,等.基于洞壁实测信息的FA-PP岩爆预测模型应用研究［J］.中国公路学报,2020,33(11):215-225.
WU Fangyin,HE Chuan,WANG Bo,et al.Application of FA-PP rockburst prediction model based on measured information of tunnel wall ［J］.China Journal of Highway and Transport,2020,33(11):215-225.
［6］ZHANG X L,HOANG N,XUAN N B.Novel soft computing model for predicting blast-induced ground vibration in optimition based on particle swarm optimization and Xgboost［J］.Natural Resources Research,2020,29(2):711-721.
［7］张保同.基于PPA-正态云的深埋隧洞岩爆分级预测［J］.人民黄河,2017,39(9):121-124.
ZHANG Baotong.Classification prediction of rockburst in deep buried tunnel based on PPA normal cloud ［J］.Yellow River,2017,39(9):121-124.
［8］杨悦增,邓红卫,虞松涛,等.基于随机森林模型的岩爆等级预测研究［J］.矿冶工程,2017,37(4):23-27.
YANG Yuezeng,DENG Hongwei,YU Songtao,et al.Study on rock burst grade prediction based on random forest model ［J］.Mining and Metallurgical Engineering,2017,37(4):23-27.
［9］徐佳,陈俊智,刘晨毓,等.DHNN模型在岩爆烈度分级预测中的应用研究［J］.工矿自动化,2018,44(1):84-88.
XU Jia,CHEN Junzhi,LIU Chenyu,et al.Study on the application of DHNN model in the classification prediction of rockburst intensity ［J］.Industrial and Mining Automation,2018,44(1):84-88.
［10］TIAN R,MENG H D,CHEN S J,et al.Classification prediction model of rockburst intensity based on RF AHP cloud model ［J］.China Safety Science Journal,2020,30(7):166-172.
［11］田冰,黄山,孙晔,等.基于SOM神经网络聚类和灰度TOPSIS评价法的岩爆预测［J］.中国矿业,2021,30(1):188-192.
TIAN Bing,HUANG Shan,SUN Ye,et al.Rockburst prediction based on SOM neural network clustering and grey TOPSIS evaluation method ［J］.China Mining Magazine,2021,30(1):188-192.
［12］WANG C L,WU A X,LU H.Predicting rockburst tendency based on fuzzy matter-element model［J］.International Journal of Rock Mechanics and Mining Sciences,2015,75(75):224-232.
［13］刘晓悦,杨伟,张雪梅,等.基于改进层次法与CRITIC法的多维云模型岩爆预测［J］.湖南大学学报,2021,48(2):118-124.
LIU Xiaoyue,YANG Wei,ZHANG Xuemei,et al.Multidimensional cloud model rockburst prediction based on Improved AHP and critical method ［J］.Journal of Hunan University,2021,48(2):118-124.
［14］张钧博,何川,严健,等.基于交叉验证的Xgboost算法在岩爆烈度分级预测中的适用性探讨［J］.隧道建设,2020,40(1):247-253.
ZHANG Junbo,HE Chuan,YAN Jian,et al.Discussion on applicability of Xgboost algorithm based on cross validation in classification prediction of rock burst intensity ［J］ Tunnel Construction,2020,40(1):247-253.
［15］谢学斌,李德玄,孔令燕,等.基于CRITIC-XGB算法的岩爆倾向等级预测模型［J］.岩石力学与工程学报,2020,39(10):1975-1982.
XIE Xuebin,LI Dexuan,KONG Lingyan,et al.Prediction model of rockburst tendency grade based on CRITIC-XGB algorithm ［J］.Journal of Rock Mechanics and Engineering,2020,39(10):1975-1982.
［16］JUAN A B,DIMITRIS C,IDHAM A,et al.IForest:exploring crowd-based intelligence as a means of improving the human-computer interface in the cloud-of-things［J］.Ambient Intelligence and Smart Environments,2013,17(17):238-245.
相似文献/References:
[1]黎昕,周宗红,金小川,等.白云岩单轴压缩试验声发射特性研究[J].中国安全生产科学技术,2013,9(10):10.[doi:10.11731/j.issn.1673-193x.2013.10.002]
LI Xin,ZHOU Zong hong,JIN Xiao chuan,et al.Research on acoustic emission characteristics of dolomites based on uniaxial compression test[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(9):10.[doi:10.11731/j.issn.1673-193x.2013.10.002]
[2]宋英华,庞昭胜,李墨潇,等.基于反赋权与MBCT-SR多维云模型算法岩爆预测研究*[J].中国安全生产科学技术,2022,18(3):39.[doi:10.11731/j.issn.1673-193x.2022.03.006]
SONG Yinghua,PANG Zhaosheng,LI Moxiao,et al.Research on rockburst prediction based on anti-weighting and MBCT-SR multi-dimensional cloud model algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(9):39.[doi:10.11731/j.issn.1673-193x.2022.03.006]
备注/Memo
- 备注/Memo:
-
收稿日期： 2022-06-24
* 基金项目： 国家自然科学基金项目（52209146）
作者简介： 齐石，硕士研究生，主要研究方向为岩爆预测。
通信作者： 吕伟，博士，教授，主要研究方向为安全科学与灾害防治，建筑科学与工程。
