摘要
在岩芯裂缝观测基础上,应用岩芯标定测井,分岩性建立了测井解释模型,分析了裂缝发育段在常规测井曲线上的响应特征,并结合钻井泥浆漏失、放空及开发动态资料,识别出典型裂缝段,将其测井响应作为训练样本集,应用神经网络模式识别技术的并行处理、分布式的信息存储、极强的自学习功能和自动调整权值的能力,对齐家古潜山76口井进行了裂缝段的识别,探索出一套综合岩芯、常规测井、测试与动态等信息进行裂缝分布预测的新方法,经钻探证实,效果良好。
Based on lithologic logging interpretation, the authors identified typical fracture sections according to their logging response calibrated by core data integrating drilling mud leakage, drilling break and production data. Then the typical logging response of fracture section was employed as training samples for Artificial Neural Network Pattern Recognition (NNPR). All the 76 wells in the Qijia buried hill were processed by applying the ability of NNPR including paralleling process, distribution information storage, powerful selfstudy and automatic weight value adjustment. Finally, a new fracture prediction method integrating core, conventional logging, test and production data was formulated, which has been proved to be effective by drilling.
出处
《物探与化探》
CAS
CSCD
2007年第2期160-163,共4页
Geophysical and Geochemical Exploration
关键词
齐家古潜山
神经网络模式识别
裂缝
测井解释
Qijia buried hill
artificial neural network pattern recognition
fracture
logging interpretation