Vol. 45 No. 4 Aug 2018
矿业安全与环保
MINING SAFETY & ENVIRONMENTAL PROTECTION
王超.基于GRA-DDA加权据合模型的煤层突出危险性评价[J].矿业安全与环保,2018,45(4);98-101 文章编号：10084495(2018)040098-04
第45卷第4期 2018年8月
基于GRA-DDA加权耦合模型的煤层突出危险性评价
王超
（昆明理工大学国土资源工程学院，云南昆明650093）
摘要：为了提高煤层突出危险性评价的效率和准确度，引入距高判别分析法（DDA），选用煤层瓦斯放散初速度、煤的坚固性系数、煤层瓦斯压力、煤体破坏类型和开采深度作为判别因子，并运用灰色关联分析(GRA)计算权重矩阵，建立了煤层突出危险性评价的加权距离耦合判别模型。将30个煤与瓦斯突出实例作为学习样本进行训练，建立相应的判别准则，经过训练后的模型误判率为0。利用该模型对10个煤与瓦斯突出实例进行评判，并将评判结果与单项指标法、BP神经网络法和未加权距离判别法进行对比分析，结果表明GRA-DDA耦合模型的评判结果准确，符合现场实际情况。
关键词：煤与瓦斯突出；马氏距离；耦合加权评价模型；灰色关联分析；距离判别法
中图分类号：TD713*.2
文献标志码：A
Evaluation of Coaland Gas OutburstRiskBased on GRA-DDA
Weighted CouplingModel
WANG Chao
( Facalty of Land Resotzrce Engineering, Kanming Uninersity of Science and Technology, Kunming 650093, China)
Abstract: In order to improve the efficiency and accuracy of coal seam outburst risk assessment, Distance Discriminant Analysis ( DDA) was introxduced, five indexes including initial speed of methane diffusion, the coeflicient of solidity of coal, coal seam gas pressure, type of ooal body failure and mining depth, were regarded as diseriminant factors. Grey Relational Analysis( GRA) was used to calculate the weight matrioes, a weighted distanoe coupled discriminant model for coal seam outburst risk assessment was established. 30 examples of coal and gas outburst were trained as learming samples, corresponding discriminan criteria was set up, and the ratio of mistakedistinguish was zero after training. The GRADDA model was used to evaluate 10 coal and gas outburst cases, and the evaluation results of this model was verified by comparing with the single index method, BP neural network method and unweighted distance discriminant analysis method. The results showed that the evaluation results of the GRADDA model are accurate and accord with the actual situation.
Keywords: coal and gas outburst; mahalanobis distance; coupled evaluation model; Grey Relational Analysis ( GRA ) ; Distance Discriminant Analysis (DDA)
煤与瓦斯突出是一种非常复杂的矿井煤岩动力灾害现象，严重影响了煤矿的正常生产，并造成了大量的人员伤亡[]。笔者统计了2007—2016年我国近 10年来发生的168起煤与瓦斯突出事故，共计死亡 1371人，其中发生重特大事故36起，死亡762人。随着我国煤矿开采深度的逐年增加，煤与瓦斯突出、冲
收稿日期：201708-21;2017-10-29修订
基金项目：国家自然科学基金项目（41672303）；云南省省股人培资助项目（KKSY201421030）
作者简介：王超（1984一），男，山东济宁人，博士，讲师，项士生导师，主要从事矿山煤岩动力灾害防治方面的研究工作。Email：chaobest@163.com。
· 98 · 万方数据
击地压、项板冒落等灾害将越来越严重。及时准确地评价煤层突出危险性并采取相应措施，是防治煤与瓦斯突出的前提条件
煤与瓦斯突出的评价指标和方法众多。我国常用的评价指标和方法包括瓦斯放散初速度△P、坚固性系数、煤体破坏类型、瓦斯压力P、瓦斯含量W、钻屑量S、钻屑瓦斯解吸指标K，或△hz、综合指标D与 K法、R值指标法、瓦斯地质统计法、声发射法和电磁辐射法等[2-7]。由于煤与瓦斯突出的影响因素众多为了准确评价煤层突出危险性，需要综合考虑多项因素。近年来多指标综合评价方法在煤与瓦斯突出评价中得到了广泛应用，国内外许多学者采用模糊数