基于长短期记忆神经网络的随钻地层倾角解释方法  

Logging-while-drilling formation dip interpretation based on long short-term memory

作　　者：孙歧峰[1] 李娜[1] 段友祥[1] 李洪强[2] 唐海全[3] SUN Qifeng;LI Na;DUAN Youxiang;LI Hongqiang;TANG Haiquan(College of Computer Science and Technology in China University of Petroleum,Qingdao 266580,China;Drilling Technology Research Institute of Shengli Petroleum Engineering Corporation Limited,Sinopec,Dongying 257000,China;Measurement and Control Technology Research Institute of Shengli Petroleum Engineering Corporation Limited,Dongying 257000,China)

机构地区：[1]中国石油大学(华东)计算机科学与技术学院,山东青岛266580 [2]中国石化胜利石油工程有限公司钻井工艺研究院,山东东营257000 [3]中国石化胜利石油工程有限公司测控技术研究院,山东东营257000

出　　处：《石油勘探与开发》2021年第4期843-850,共8页Petroleum Exploration and Development

基　　金：中国石油重大科技项目(ZD2019-183-006);中央高校基本科研业务费专项资金(20CX05017A);国家科技重大专项“低渗透油气深层高温高压随钻测控技术”(2016ZX05021-001)。

摘　　要：鉴于随钻方位伽马测井面临实时数据传输的信息有限且解释难度大的问题,将人工智能与随钻测井解释相结合以提高实时数据处理的准确性和效率,阐述了具体方法并对提出的方法进行了验证和应用。通过研究方位伽马测井曲线的地层响应特征,基于小波变换模极大值的方法初步判断地层变化位置并确定动态阈值,进而得到描述地层边界的轮廓点集合。基于长短期记忆神经网络设计地层识别分类器模型,判定轮廓点集合描述地层信息的真伪,提高地层识别的准确度。结合非线性最小二乘法实现地层相对倾角的计算。方位伽马数据解释与随钻实时数据处理两方面的应用结果表明:提出的方法在有效、准确地判断地层变化的同时,提高了倾角解释的准确率,且能够满足随钻实时地质导向的需要。图8表3参27。Azimuth gamma logging-while-drilling(LWD)is one of the important technologies of geosteering but the information of real-time data transmission is limited and the interpretation is difficult.This study proposes a method of applying artificial intelligence in the LWD data interpretation to enhance the accuracy and efficiency of real-time data processing.By examining formation response characteristics of azimuth gamma ray(GR)curve,the preliminary formation change position is detected based on wavelet transform modulus maxima(WTMM)method,then the dynamic threshold is determined,and a set of contour points describing the formation boundary is obtained.The classification recognition model based on the long short-term memory(LSTM)is designed to judge the true or false of stratum information described by the contour point set to enhance the accuracy of formation identification.Finally,relative dip angle is calculated by nonlinear least square method.Interpretation of azimuth gamma data and application of real-time data processing while drilling show that the method proposed can effectively and accurately determine the formation changes,improve the accuracy of formation dip interpretation,and meet the needs of real-time LWD geosteering.

关 键 词：随钻测井 方位伽马 地层识别 人工智能 长短期记忆神经网络 小波变换 

分 类 号：P631.84[天文地球—地质矿产勘探] TP391.7[天文地球—地质学]