摘要
为防治煤层底板水害,在总结矿压破坏带深度预测方法和理论的基础上,分析了影响矿压破坏深度的各项因素,选取华北型石炭二叠系煤田典型工作面综采条件下的矿压破坏深度实测数据;通过运用MATLAB软件对实测数据进行训练和拟合验证,构建了基于遗传算法优化BP神经网络的矿压破坏带深度预测模型。经过对比传统人工神经网络模型,优化模型与实际吻合更好,预测精度更高。基于MATLAB进一步开发了可视化预测预报系统,使得操作更为便捷。研究成果为防治煤层底板水害提供了技术支撑和依据。
In order to prevent and control the water damage of the coal seam floor,the methods and theory were summarized for the depth prediction of the mining pressure failure zone.On this basis,the factors affecting the depth of the mining pressure failure zone were analyzed,and the measured data of the depth of the mining pressure failure zone at the typical working face in the North China Carboniferous Permian coalfield under comprehensive mining conditions was selected.Then,Matlab software was used to train and fit the measured data,and a depth prediction model of mining pressure failure zone was constructed based on genetic algorithm optimization BP neural network.Compared with the traditional artificial neural network model,the optimized model was better in accordance with the actual situation,and the prediction accuracy was higher.Based on MATLAB,a visual prediction system was further developed,which made the operation more convenient.The research results can provide a technical support and basis for the prevention and control of water disaster in coal seam floor.
作者
赵铭生
刘守强
纪润清
刘德民
曹欢
胡棉舒
ZHAO Mingsheng;LIU Shouqiang;JI Runqing;LIU Demin;CAO Huan;HU Mianshu(National Engineering Research Center of Coal Mine Water Hazard Control,Beijing 100083,China;Co liege of Geosciences and Surveying Engineering,China University of Mining and Technology(Beijing),Beijing 100083,China;Datong Coal Mine Group Company,Datong,Shanxi 037000,China;Hebei State Key Laboratory of Mine Disaster Prevention,North China Institute of Science and Technology,Beijing 101601,China)
出处
《矿业研究与开发》
CAS
北大核心
2020年第6期89-93,共5页
Mining Research and Development
基金
国家自然科学基金项目(41602262,41572222)
国家重点研发计划项目(2017YFC0804104)
河北省矿井灾害防治重点实验室开放基金项目(KJZH2017K05)
中央高校基本科研业务费专项资金项目(2013QD04)
中国矿业大学(北京)大学生创新训练项目(C201802762).
关键词
华北型煤田
矿压破坏带
遗传算法
人工神经网络
可视化
North China coalfield
Zone destroyed by underground pressure
Genetic algorithm
Artificial neural network
Visualization
