
第45卷第3期 2018年6月
矿业安全与环保
MINING SAFETY & ENVIRONMENTAL PROTECTION
Vol. 45 No. 3 Jun.2018
陈建平,董军,吕相伟.基于PCA-Fisher判别分析模型的煤与瓦斯突出危险等级预测方法研究[J],矿业安全与环保,2018,45(3): 99-19
文章编号:10084495(2018)030061-06
基于PCA-Fisher判别分析模型的煤与瓦斯突出
危险等级预测方法研究
陈建平,董军,吕相伟
(辽宁工程技术大学矿业学院,辽宁阜新123000)
摘要:为了提高煤与瓦斯突出预测精度,选取瓦斯含量、瓦斯压力、瓦斯放散初速度等11个因素作为判别指标,将煤与瓦斯突出强度分为无突出、小型突出、中型突出、大型突出4个等级。利用贵州黔西北煤矿资料中的28组数据作为训练学习样本,建立了煤与瓦斯突出危险等级预测的PCA-Fisher判别分析模型,再利用资料中其余6组数据作为预测样本,对该模型进行检验和应用,并与BP神经网络模型和Fisher判别模型的判别结果进行比较。结果表明:PCA-Fisher判别模型具有更高的准确性和可靠性,可以对煤与瓦斯突出危险等级进行有效预测。
关键词:瓦斯含量;瓦斯压力;煤与瓦斯突出;PCA-Fisher判别分析;BP神经网络;危险等级预测
中图分类号:TD713+.2
文献标志码:B
Research onRisk Level of Coal and Gas OutburstPrediction Based on
PCA-Fisher Discriminant Analysis Model
CHEN Jianping,DONG Jun,LYU Xianguei
( Gollege of Mining Engineering, Liaoning Technical Unirersily, Fauxin 123000, China)
Abstract : In order to improve the accuracy of coal and gas outburst prediction. 11 factors, including gas content, gas pressure and initial velocity of gas, were selected as the discriminant indicators. The outburst intensity of coal and gas was divided into four grades : no outburst, small outburst, medium outburst and large outburst. 28 sets of data of Qianxibei Coal Mine in Guizhou were used as training samples to establish a PCAFisher discriminant analysis model for risk level prediction of coal and gas outburst. Using the remaining 6 sets of data as a prediction sample to test and apply the model, the discriminant result was compared with that of BP neural network model and Fisher discriminant model. The results showed that PCA Fisher discriminant model has higher accuracy and reliability, it can predict the risk level of coal and gas outburst effectively
Keywords : gas content ; gas pressure;coal and gas outbunst ; PCAFisher diseriminant analysis ; BP neural network ;risk level prediction
煤与瓦斯突出是煤层中存储的破碎的煤岩和瓦
斯的失稳释放,表现为在极短的时间内向生产空间抛出大量煤岩和瓦斯,并有可能诱发瓦斯爆炸,产生更大的灾难]。煤与瓦斯突出已成为我国煤矿开采中的重要灾害之一,并随着煤矿开采深度的逐年加大和并采机械化水平的不断提高,呈现突出矿并数量逐年增多和突出次数逐年增加的趋势。煤与瓦斯
收稿日期:20170523;20170907修订
作者简介:陈建平(1972一),男,山西保德人,博士,副教投,主要从事环境工程、地质工程等方面的教学与科研工
作。Email;chenjianp@ tom.com。万方数据
突出严重威胁着煤矿生产安全,准确预测和防治突出的发生,对提高煤矿企业的社会效益和经济效益其有重要意义[2]。目前,我国煤与瓦斯突出危险等级预测和评判多采用距离判别分析法[3]、BP神经网络[4]、支持向量机(5]、Fisher判别分析[6]等方法。由于导致煤与瓦斯突出发生的因系极为复黎,突出的因素和突出事件之间具有不确定性、非线性的关系,以往的预测方法主要采用回归分析方法,其缺点是只考患影响煤与瓦斯突出的个别因系,没有全面考虑影响突出因素与瓦斯突出之间复杂的非线性关系[7]。笔者提出PCA-Fisher判别分析法,首先利用
+ 61 ·