极限训练机在矿山开采最大下沉值估算中的应用  

Application of Extreme Leaning Machine in predicting maximum surface subsidence of mining

作　　者：李骅锦[1] 何雨森[2] LI Huajin HE Yusen(State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China Intelligent Systems Laboratory, The University of Iowa, Iowa City 52242, USA)

机构地区：[1]成都理工大学地质灾害防治与地质环境保护国家重点实验室,四川成都610059 [2]爱荷华大学智能系统研究实验室,美国爱荷华城52242

出　　处：《人民长江》2017年第8期68-72,共5页Yangtze River

摘　　要：矿山开采过程中采空区地表往往会发生形变,研究其最大下沉值对安全生产具有重要意义,现有的开采最大下沉估算方法还有提升的空间。基于岩移数据决策与极限训练机(Extreme learning machine,ELM)算法,提出了一种估计最大下沉的新方法。该方法将采厚、倾角、平均采深、走向长度、倾向长度和覆岩岩性确定为最大下沉值影响因素;应用以Sigmoid方程为核函数、隐含层神经元个数为114的ELM模型对最大下沉值进行了估算。通过案例分析,ELM模型得到了优于传统算法如CHAID、Boosted Tree、ANN、BPNN和SVM的RMSE、MAE、MAPE、最大残差及秩相关系数,故认为该模型是一种有效的矿山开采最大下沉估算方法。Surface deformation is a common phenomenon in mining area. Estimating the maximal surface subsidence has strong significance to ensuring the safety of ore mining. However the traditional prediction methods have some space for improving accuracy. A new data-driven methodology is proposed based on data-mining algorithms and Extreme Learning Machine（ ELM）with data of rock displacement records to predict the maximal surface subsidence. In the proposed methodology,the input parameters are mining thickness,dip-angle,average mining depth,strike length,dip length and overburden lithology. An ELM model including 114 hidden nodes and with sigmoid function as the kernel function is constructed to predict the maximum value of surface subsidence. By case study,ELM performs better than traditional methods including CHAID,Boosted Tree,ANN,BPNN,and SVM in terms of RMSE,MAE,MAPE,maximum residue and rank correlation coefficient. Hence,this framework is valuable for predicting maximum surface subsidence.

关 键 词：最大下沉值估算 岩移数据决策 极限训练机 矿山开采 

分 类 号：P642[天文地球—工程地质学]