煤矿智能化顶板矿压预警技术研究  

Early warning technology of coal mine roof pressure based on machine learning

作　　者：卢振龙 徐刚[1,2] 尹希文 刘前进[1,2] LU Zhenlong;XU Gang;YIN Xiwen;LIU Qianjin(CCTEG Coal Mining Research Institute,Beijing 100013,China;Coal Mining and Designing Department,Tiandi Science and Technology Co.,Ltd.,Beijing 100013,China)

机构地区：[1]中煤科工开采研究院有限公司,北京100013 [2]天地科技股份有限公司开采设计事业部,北京100013

出　　处：《煤炭工程》2023年第12期22-27,共6页Coal Engineering

基　　金：国家自然科学基金面上项目(52174118)。

摘　　要：为了解决现有煤矿顶板矿压预警技术可靠性低、准确性差、智能化不足的问题,研究了基于机器学习的工作面矿压预警指标分析方法,并分别采用了线性回归、系统聚类方法对液压支架循环内载荷以及周期来压步距进行分析,构建了顶板灾害预警算法,实现了工作面顶板灾害监测关键指标的自动分析和预测预警。现场应用结果表明:预警系统运行可靠性高、分析预警功能全且准确性高,在示范矿井进行顶板来压实际次数统计,其中预测准确次数不低于90%。能够为煤矿顶板灾害防治提供重要支持。To address the issues of low reliability, poor accuracy and insufficient intelligence of the existing coal mine roof rock pressure early warning technology, we investigated a machine learning-based approach for analyzing roof pressure warning indicators on the working face. Linear regression and systematic clustering methods were employed to analyze the cyclic internal load of the hydraulic support and the periodic weighting interval, respectively. A roof pressure analysis and warning model was constructed to enable automatic analysis and prediction of key indicators for roof disaster monitoring on the working face. Field application results demonstrated that the warning system exhibited high reliability, comprehensive analysis and warning functionality, and high accuracy. In the statistical analysis of roof periodic weighting actual occurrences in the demonstration mine, the prediction accuracy was no less than 90%. This system can provide important support for the prevention and control of roof disasters in coal mines.

关 键 词：顶板灾害 矿压预警 机器学习 不保压率 周期来压 等值线云图 

分 类 号：TD353[矿业工程—矿井建设]