摘要
为解决煤矿瓦斯涌出量预测过程中存在的指标繁杂致使预测精度低的问题,运用R语言主成分分析法对瓦斯涌出量影响因素进行降维分析,结合多种多元回归模型,最终选用多元线性回归进行瓦斯涌出量预测。结果表明:主成分分析法能有效减少预测变量个数,经主成分旋转后构建的多元回归预测模型精度较高,其平均误差绝对值为2.67%。主成分分析法与多元线性回归相结合的方法适用于瓦斯涌出量预测。
In order to solve the problem that the complicated indicators affect the prediction accuracy in the coal mine gas emission prediction process,the R language principal component analysis method is used to analyze the factors affecting the gas emission,combined with multiple regression models,multivariate linear regression is used to predict gas emission. The results showed that the principal component analysis method can effectively reduce the number of predictors,and the multivariate regression prediction model constructed by the principal component rotation has high precision,and the average error is 2.67%. The combination of principal component analysis and multiple linear regression is applicable to the prediction of gas emission in coal.
引文
[1]孙林,杨世元.基于LS-SVM的回采工作面瓦斯涌出量预测[J].煤炭学报,2008,33(12):1 377-1 380.
[2]黄为勇,童敏明,任子晖.基于SVM的瓦斯涌出量非线性组合预测方法[J].中国矿业大学学报,2009,38(2):234-239.
[3]肖鹏,李树刚,宋莹,等.瓦斯涌出量的灰色建模及其预测[J].采矿与安全工程学报,2009,26(3):318-321.
[4]谷松,张振文,李国军.矿井瓦斯涌出量的灰色小波神经网络预测模型[J].煤炭技术,2009,28(10):123-125.
[5]李润求,吴莹莹,施式亮,等.煤矿瓦斯涌出时序预测的自组织数据挖掘方法[J].中国安全生产科学技术,2017,13(7):18-23.
[6]李树刚,马彦阳,林海飞,等.基于因子分析法的瓦斯涌出量预测指标选取[J].西安科技大学学报,2017,37(4):461-466.
[7]张延飞,魏久传,谢道雷,等.基于相关分析法的工作面瓦斯涌出量预测[J].煤炭技术,2016,35(5):163-165.
[8]陶云奇,许江,李树春.改进的灰色马尔柯夫模型预测采煤工作面瓦斯涌出量[J].煤炭学报,2007,32(4):391-395.
[9]朱红青,常文杰,张彬.回采工作面瓦斯涌出BP神经网络分源预测模型及应用[J].煤炭学报,2007,32(5):504-508.
[10]赵国彦,梁伟章,王少锋,等.基于量纲分析的巷道围岩松动圈预测模型[J].岩土力学,2016,37(S2):273-278,300.
