基于Probit回归模型的煤矿底板突水预测  

Coalmine Floor Water Bursting Prediction Based on Probit Regression Model

作　　者：王江荣[1] 赵睿[1] 文晖[1] 罗资琴[2] 

机构地区：[1]兰州石化职业技术学院信息处理与控制工程系,甘肃兰州730060 [2]兰州石化职业技术学院石油化学工程系,甘肃兰州730060

出　　处：《中国煤炭地质》2015年第3期40-42,48,共4页Coal Geology of China

基　　金：甘肃省科技厅项目:石油化工企业应急演练系统;1204GKCA004;甘肃省财政厅专项资金立项资助(甘财教[2013]116号)

摘　　要：针对矿井底板突水预测精确度要求高的特点,提出了二值Probit回归矿井突水预测模型。依据概率论的相关知识构建模型参数的极大似然估计法,并通过遗传算法求模型参数的最优解。利用所建模型对建模样本的突水性进行反向识别,对测试样本的突水性进行预测识别,正确率分别为90%和100%,表明该模型具有很高的精确度。另外,所建模型结构简单、便于操作和使用,有一定的参考价值。In allusion to characteristic of high requirements on mine floor water bursting prediction precision, a binary Probit regression mine water bursting prediction model has been put forward. According to relevant knowledge of probability theory modeling parameters maximum likelihood estimation and genetic algorithm find out optimal solution of modeling parameters. Using the established model carried out reverse identification of modeling samples water bursting property, and predicted identification of tested samples water bursting property, their accuracies are 90% and 100% respectively. Thus demonstrated that the model has very high definition. Besides, the model has simple structure, practical and easy to use; thus has certain reference value.

关 键 词：煤矿底板突水 二值Probit回归模型 极大似然函数 遗传算法 预测 

分 类 号：TD745.21[矿业工程—矿井通风与安全]