摘要
阐述了在突水水压、突水量、封堵过水通道长度、注浆压力4个影响因素下,运用MATLAB并基于BP神经网络构建矿井突水点注浆量预测模型的方法.运用MATLAB软件绘制了相对误差散点图以及预测注浆量值和实际注浆量值前后对比图,平均相对误差值4.4%.将建立的BP神经网络模型应用于煤矿的实际工作面,预测出的结果与实际结果很接近,为煤矿矿井水的防治以及深部区域的采煤安全提供理论指导.
Expounded the method of constructing the grouting quantity prediction model of mine water inrush point based on BP neural network using MATLAB and four influencing factors of water pressure,water inrush,length of blocked water passage,and grouting pressure.The relative error scatter plots were plotted using MATLAB software,and the pre-and post-contrast plots for predicting grouting volume and actual grouting volume were compared.The average relative error was 4.4%.The BP neural network model established will be applied to the actual working face of coal mines.The predicted results are close to the actual results,providing theoretical guidance for the prevention and control of coal mine water and coal mining safety in deep regions.
作者
施龙青
黄纪云
高卫富
魏凯
郭玉成
SHI Long-qing;HUANG Ji-yun;GAO Wei-fu;WEI Kai;GUO Yu-cheng(College of Earth Sciences and Engineering,Shandong University of Science and Technology,Qingdao 266590,China;Shanxian Energy Co.,Ltd.,Feicheng Mining Group,Heze 274300,China;Feicheng Baizhuang Coal Mine Co.,Ltd.,Tai'an 271000,China)
出处
《煤炭技术》
CAS
2019年第7期101-103,共3页
Coal Technology
基金
国家自然科学基金(41572244)
泰山学者建设工程专项经费资助
