摘要
瓦斯富集一直以来都是威胁煤矿安全生产的重要因素,如何对其精准预测是值得深入探究的问题.为此,本文以沁水盆地南缘某矿的3#煤层为研究对象,基于叠前地震数据体提取的AVO属性预测目标煤层的瓦斯含量.先通过对叠前三维地震数据进行超道集计算和角道集抽取等的处理,计算叠前AVO属性,得到截距(P)、梯度(G)、流体因子(P*G)、拟泊松比(P+G)、横波反射系数(P-G)等多个属性参数的沿层切片.再通过蝙蝠(BA)算法优化BP神经网络的权值和阈值来优化预测模型,构建AVO属性与瓦斯含量间的非线性映射关系,并利用井数据训练非线性预测模型.最终,基于训练后的BA-BP神经网络模型预测研究区内3#煤层的瓦斯含量.通过对比分析研究区内目标煤层9口钻井处的预测结果与实测结果,显示该方法的预测误差较小;表明基于BA-BP神经网络预测模型,以AVO属性为输入,进行煤层瓦斯含量的非线性预测是可行的.
Gas enrichment has always been an important factor threatening the safety of coal mine production.How to accurately predict gas enrichment is always a problem worthy of in-depth study.To this end,this paper takes the No.3 coal seam of a mine in the southern margin of Qinshui basin as the research object,and predicts the gas content of target coal seam based on AVO attribute extracted from pre-stack seismic data body.Firstly,through the superchannel set calculation and corner channel set extraction of pre-stack 3 d seismic data,the pre-stack AVO attribute was calculated,and the slice along the layer of multiple attribute parameters such as intercept(P),gradient(G),fluid factor(P*G),quasi-poisson’s ratio(P+G),shear reflection coefficient(P-G)was obtained.Then the bat(BA)algorithm was used to optimize the weight and threshold of BP neural network to optimize the prediction model,construct the nonlinear mapping relationship between AVO attribute and gas content,and train the nonlinear prediction model with well data.Finally,based on the trained BA-BP neural network model,the gas content of No.3 coal seam in the study area was predicted.Through the comparative analysis of the prediction results and the measured results of 9 wells in the target coal seam,it is shown that the prediction error of this method is small.It shows that the nonlinear prediction of coal seam gas content based on the BA-BP neural network prediction model with AVO attribute as input is feasible.
作者
章静
吴海波
张平松
董守华
臧子婧
ZHANG Jing;WU Hai-bo;ZHANG Ping-song;DONG Shou-hua;ZANG Zi-jing(School of Earth and Environment,Anhui University of Science and Technology,Huainan 232001,China;School of Resources and Earth Sciences,China University of Mining and Technology,Xuzhou 221116,China)
出处
《地球物理学进展》
CSCD
北大核心
2020年第5期2033-2039,共7页
Progress in Geophysics
基金
安徽省自然科学基金(1908085QD169)
国家自然科学基金(41902167)
安徽省重点研究与开发计划项目(1804a0802203)联合资助.
