Model of coal gas permeability prediction based on random forest

被引：0

作者：

Yongkui, Shi ^{[1
,2
]}

Pengrui, Li ^{[2
]}

Jingyu, Zhang ^{[2
]}

机构：

[1] State Key Laboratory Breeding Base for Mining Disaster Prevention and Control, Shandong University of Science and Technology, Qingdao, China

[2] College of Mining and Safety Engineering, Shandong University of Science and Technology, Qingdao, China

来源：

Electronic Journal of Geotechnical Engineering | 2015年 / 20卷 / 19期

关键词：

Coal mines - Sampling - Decision trees - Coal - Forecasting - Coal deposits - Compressive strength - Disaster prevention;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

This paper analyzed and summarized four main influential factors affecting coal gas permeability, which were effective stress, gas pressure, temperature and coal compressive strength. Thirty groups representative coal gas permeability data under different conditions were used for building training samples, and the first twenty-two groups were training samples, the others were to be tested. Then the accuracy of the model was tested by node error rate, detailed accuracy by class, confusion matrix, and so on. The eight groups of sample data to be tested are predicted completely correct. Effective prediction on coal gas permeability will provide theoretical guidance for gas drainage and gas disaster prevention. © 2015 ejge.

引用

页码：11199 / 11207