应用地震属性预测煤层顶板泥岩百分比含量分布
应用地震属性预测煤层顶板泥岩百分比含量分布孟召平1 ,2 , 郭彦省2 ,马 辉2
(1.三峡大学三峡库区地质灾害教育部重点实验室, 湖北宜昌 443002 ;2. 中国矿业大学资源与安全工程学院, 北京 100083)
Prediction of Mudstone Percentage Content for CoalusingSeismic Att- ributions
MENG Zhao-ping1,2 , GUO Yan-sheng2 , MA Hui2
(1. ChinaThree Gorges University , Key Laboratory of Geological Hazards on Three GorgesReservoir Area , Ministry of Education , Yichang ,Hubei 443002 , China ;
2. School ofResources and Safety Engineering , China University of Mining &Technology ,Beijing 100083 , China)
摘要: 从地震属性分析入手,提出了用于煤层顶板泥岩百分比含量预测的地震属性分析方法和BP 人工神经网络岩性预测方法.
Abstract: Based on theanalysis on seismic attributions , an analysis method of seismic attributes andprediction method of lithologic characters based on a BP artificial neuralnetwork were proposed for forecasting the mudstone percentage content of coalroof .
以淮南矿区潘东西四采区三维地震勘探区为依托,
优选出平均瞬时相位、主频序列1 ,能量半衰时和主频斜率等4 种地震属性作为13-1 煤层顶板岩性预测分析的基本参数,结合已知钻孔资料,
Four usableseismic attributes , including average instantaneous phase , dominant frequency1 , energy half-time and spectral slope from peak to maximum frequency ,were selected as the basic analysis parameters of prediction models of the rooflithologic character of 13-1 coal seam based on 3D seismic exploration area ofmining section 4 in West Pandong of Huainan coal mining area.
建立了煤层顶板泥岩百分比含量BP 人工神经网络预测模型,
Combined withthe real drill data , a BP artificial neural network prediction model of themudstone percentage content of coal roof was established.
运用训练好的网络对研究区13-1 煤层顶板泥岩百分比含量进行了预测分析.
Using a goodtraining network model to predict and analyse roof lithologic character of 13-1coal seam.
结果表明,BP 神经网络模型具有极强的非线性逼近能力,能真实反映煤层顶板岩性与地震属性之间的非线性关系,
The result sshow that the BP neural network has strong nonlinear approaching ability whichcan truly reflects the non-linear relationship between the lithologic characters ofcoal roof and seismic attributes.
预测结果与实测值之间误差小,相对误差一般小于10 % ,地震属性可以用于煤层顶板岩性分布预测.
The relative error between predicted valuesand measured values is less than 10 %, which indicate that the seismic attributecan be used in the distributing prediction of coal roof lithologic character .
关键词: 地震属性; 煤层顶板; 泥岩百分比含量; 人工神经网络; 预测方法
Keywords : seismic attribute; coal roof ; lithologic characters ; artificial neural network ; predictionmethod
页:
[1]