摘要
为了加强尾矿库的安全稳定管理,提高溃坝预测预警水平,以坝体位移为研究对象,安全监测数据为研究基础,提出一种基于特征递归消除与随机森林和极限梯度提升的尾矿坝坝体位移预测模型,并与XGBoost、LSTM神经网络、BP神经网络、SVR等预测模型对比,以验证其预测效果.结果表明:所提出模型平均相对误差低于XGBoost模型3.93%,并考虑了外部因素对坝体形变的影响.该结果对于矿山施工决策、安全管理、环境保护,减少溃坝事故具有一定的参考意义.
In order to strengthen the safety management of tailing pond and improve the level of dam break warning,based on the dam displacement and safety monitoring data,a prediction model of tailing dam displacement based on Recursive Feature Elimination(RFE)and Random Forest(RF)and Extreme Gradient Boosting(XGBoost)is proposed,and compared with XGBoost,LSTM neural network,BP neural network and SVR prediction model to verify its prediction effect.The results show that the mean relative error of the proposed model is less than 3.13%of the XGBoost model,and the influence of external factors on dam deformation is considered.The research results have certain reference significance for mine construction decision-making,safety management,environmental protection and reducing dam-break accidents.
作者
王昕宇
杨鹏
戴健非
WANG Xin-yu;YANG Peng;DAI Jian-fei(Beijing Key Laboratory of Information Service Engineering,Beijing Union University,Beijing 100101,China;School of Civil and Resource Engineering,University of Science and Technology Beijing,Beijing 100083,China)
出处
《东北师大学报（自然科学版）》
CAS
北大核心
2021年第2期60-66,共7页
Journal of Northeast Normal University(Natural Science Edition)
基金
国家自然科学基金资助项目(51774045)
“十三五”国家重点研发计划课题(2017YFC0804604).
关键词
尾矿库
坝体位移
随机森林
极限梯度提升
预测模型
tailing pond
dam displacement
Random Forest
Extreme Gradient Boosting
prediction model
作者简介
王昕宇(1995—),男,硕士,主要从事尾矿库安全工程研究;通信作者:杨鹏(1965—),男,博士,教授,博士研究生导师,主要从事矿业及安全工程研究.
