基于PCA-SaDE-ELM优化算法的煤层底板破坏深度预测及工程应用  

Prediction of Failure Depth of Coal Seam Floor Based on PCA-SaDEELM Optimization Algorithm and Engineering Application

作　　者：刘世伟 赵家鑫 孙利辉[2] 袁乐忠 杨江华 王中海 LIU Shiwei;ZHAO Jiaxin;SUN Lihui;YUAN Lezhong;YANG Jianghua;WANG Zhonghai(College of Water Conservancy and Hydropower,Hebei University of Engineering,Handan 056038,China;College of Mining and Geomatics Engineering,Hebei University of Engineering,Handan 056038,China;Wu'an Yunjialing Mine,Heibei Jizhong Hanfeng Mining Co.,Ltd.,Handan 056038,China)

机构地区：[1]河北工程大学水利水电学院,河北邯郸056038 [2]河北工程大学矿业与测绘学院,河北邯郸056038 [3]河北冀中邯峰矿业有限公司武安云驾岭矿,河北邯郸056038

出　　处：《煤炭技术》2024年第6期69-73,共5页Coal Technology

基　　金：河北省自然科学基金(E2021402023);河北省高等学校科学技术研究项目资助(QN2021030)。

摘　　要：基于煤层底板破坏深度实测结果统计分析,通过优化数据样本空间,引入自适应差分进化改进的极限学习机算法,构建了煤层底板破坏深度预测模型,与实测结果对比分析验证,并应用于云驾岭煤矿9^(#)煤层底板破坏深度预测。结果表明:模型预测的最大绝对误差不超过0.7 m,相比现有其他预测模型,该模型预测精度提高约70%;云驾岭煤矿19101、19103和19105这3个典型工作面的破坏深度分别为10.80、10.94、11.34 m,介于规范方法和滑移场理论预测结果之间,进一步反映了模型的可靠性;建议对9#煤层底板加固改造后再进行回采。相关研究成果可为我国煤层底板破坏风险管理和煤炭资源的优化回采布置提供一定的理论支撑。Based on the statistical analysis of the measured results of the failure depth of a large number of coal seam floors,the prediction model of the failure depth of the coal seam floor is constructed by optimizing the sample space of the data set and introducing the adaptive differential evolution improved extreme learning machine algorithm.The model is compared with the measured results and applied to the prediction of the failure depth of No.9 coal seam floor in Yunjialing coal mine.The results show that the average absolute error of the model prediction is less than 0.7 m,and the prediction accuracy of the model is improved by about 70%compared with other existing prediction models.The failure depths of three typical working faces of 19101,19103 and 19105 in Yunjialing coal mine are 10.80 m,10.94 m and 11.34 m respectively,which are between the standard method and the prediction results of slip field theory,further reflecting the reliability of the model.It is suggested that the mining should be carried out after the reinforcement and transformation of No.9 coal seam floor.The relevant research results can provide some theoretical support for the risk management of coal seam floor failure and the optimal mining layout of coal resources in China.

关 键 词：自适应差分进化算法 极限学习机 底板破坏深度 预测模型 

分 类 号：TD327[矿业工程—矿井建设]