煤矿立井井筒非采动破裂预测  

Forecast for non-mining fracture of shaft-lining of mine

作　　者：邵良杉[1] 张宇[1] 

机构地区：[1]辽宁工程技术大学系统工程研究所,辽宁阜新123000

出　　处：《煤炭学报》2009年第2期184-186,共3页Journal of China Coal Society

摘　　要：利用组合技术对KNN算法进行改进,并将其应用于煤矿立井井筒非采动破裂的预测.选取表土层厚度、底板含水层厚度、底板含水层水位速降、井筒外径、井壁厚度和井筒投入使用时间作为井筒破裂的特征属性,以工程实测数据作为训练样本,建立基于组合技术的KNN预测模型,并使用测试数据对模型进行测试.实验结果表明,该模型预测精度较高,错误率很低.Improved KNN algorithm by using the combination technology, and applied it to the forecast of non-mining fracture of shaft-lining of mine. Six factor indexes irlcuding thickness of surface soil, thickness of basal aquifers, falling rate of basal aquifer water level, outer diameters of wellbore, thickness of shaft wall and service time of wellbore were regarded as attributes of shaft-lining fracture. The KNN forecast model based on the combination technology was trained by training samples which was received from a set of engineering data, and was tested by test samples. The results show that the model has high prediction accuracy and low error rate.

关 键 词：立井井筒 非采动破裂 组合技术 KNN算法 

分 类 号：TD262.5[矿业工程—矿井建设]