中国安全科学学报 ›› 2020, Vol. 30 ›› Issue (7): 166-172.doi: 10.16265/j.cnki.issn1003-3033.2020.07.025

• 防灾减灾技术与工程 • 上一篇    下一篇

RF-AHP-云模型下岩爆烈度分级预测模型

田睿1 工程师, 孟海东1 教授, 陈世江1 教授, 王创业1 教授, 石磊2   

  1. 1 内蒙古科技大学 矿业研究院,内蒙古 包头 014010;
    2 内蒙古自治区地质环境监测院,内蒙古 呼和浩特 010020
  • 收稿日期:2020-04-25 修回日期:2020-06-15 出版日期:2020-07-28 发布日期:2021-07-15
  • 作者简介:田 睿 (1988—),男,内蒙古四子王旗人,博士研究生,工程师,主要研究方向为岩石力学与数据挖掘。E-mail:tianrui6251@126.com。
  • 基金资助:
    国家自然科学基金资助(51564038,51464036);内蒙古自治区自然科学基金资助(2018MS05037);内蒙古自治区博士研究生科研创新项目(B20171012702)。

Prediction model of rockburst intensity classification based on RF-AHP-Cloud model

TIAN Rui1, MENG Haidong1, CHEN Shijiang1, WANG Chuangye1, SHI Lei2   

  1. 1 Institute of Mining Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China;
    2 Inner Mongolia Institute of Geological Environmental Monitoring, Hohhot Inner Mongolia 010020, China
  • Received:2020-04-25 Revised:2020-06-15 Online:2020-07-28 Published:2021-07-15

摘要: 为准确可靠地预测岩爆灾害,将随机森林(RF)与层次分析法(AHP)结合,在RF分析指标重要性的基础上优化AHP法,构建RF-AHP指标权重计算方法;结合云模型理论,建立基于RF-AHP-云模型的岩爆烈度分级预测模型;通过文献调研法,建立包含301组岩爆工程实例的数据库作为岩爆烈度分级预测的样本数据,并分析25组预测样本的岩爆预测结果。结果表明:所提模型预测准确率达88%以上,可判定预测样本的岩爆烈度等级;经验证,作为预测模型核心的RF-AHP指标权重计算方法具备一定的合理性。

关键词: 随机森林(RF), 层次分析法(AHP), 云模型, 岩爆烈度, 预测模型

Abstract: In order to accurately and reliably predict rockburst disasters, AHP was optimized based on importance of analysis index of RF, and an RF-AHP weight calculation method was constructed. Then, a prediction model of rockburst intensity classification based on RF-AHP-Cloud model was established. Finally, through literature survey, a database containing 301 groups of engineering instances was established as sample data for rockburst prediction, and prediction results of 25 sets of samples were analyzed. The results show that the proposed model has an prediction accuracy of more than 88%, and it can determine rockburst intensity grade of samples. And rationality of RF-AHP index weight calculation method as core of prediction model is also verified.

Key words: random forest(RF), analytic hierarchy process(AHP), cloud model, rockburst intensity, prediction model

中图分类号: