基于模态分解与LSTM注意表征的测井曲线重构研究

刘梦; 韩建; 曹志民; 刘兴斌

doi:10.12263/DZXB.20220887

您当前的位置：

首页 >

文章列表页 >

基于模态分解与LSTM注意表征的测井曲线重构研究

学术论文 | 更新时间：2025-12-08

- 基于模态分解与LSTM注意表征的测井曲线重构研究
- Logging Curves Reconstruction Based on Mode Decomposition and LSTM-Attention Model
- 电子学报 2024年52卷第4期页码：1399-1410
- 作者机构：
  
  1.东北石油大学物理与电子工程学院,黑龙江大庆 163319
  2.东北石油大学黑龙江省高校共建测试计量技术及仪器仪表研发中心,黑龙江大庆 163319
- 作者简介：
  
  [ "刘梦女，1997年生，江苏徐州人.东北石油大学硕士研究生.主要研究方向为机器学习与多源异构时序信号处理等.E-mail: m18362087659@163.com" ]
  [ "韩建男，1976年生，黑龙江大庆人.东北石油大学物理与电子工程学院教授，博士生导师.主要研究方向为油田智能感知、油田大数据和智能检测等.E-mail: hanjian@nepu.edu.cn" ]
  [ "曹志民男，1980年生，北京人.东北石油大学物理与电子工程学院副教授，硕士生导师.主要研究方向为多源异构大数据模式识别与人工智能处理、勘探开发大数据分析方法及应用、计算机视觉等.E-mail: caozhimin@nepu.edu.cn" ]
  [ "刘兴斌男，1964年生，黑龙江绥化人.东北石油大学物理与电子工程学院教授，硕士生导师.主要研究方向为水平井油水两相流测量、采油井油气水三相流测量传感器研究等.E-mail: liuxingbin256321@163.com" ]
- 基金信息：
  
  国家自然科学基金(52174021)
- DOI：10.12263/DZXB.20220887
  中图分类号： TN911.7;TP391
- 收稿：2022-07-25，
  
  修回：2022-09-08，
  
  纸质出版：2024-04-25
- 稿件说明：
移动端阅览
刘梦, 韩建, 曹志民, 等. 基于模态分解与LSTM注意表征的测井曲线重构研究[J]. 电子学报, 2024, 52(04): 1399-1410.

LIU Meng, HAN Jian, CAO Zhi-min, et al. Logging Curves Reconstruction Based on Mode Decomposition and LSTM-Attention Model[J]. Acta Electronica Sinica, 2024, 52(04): 1399-1410.
刘梦, 韩建, 曹志民, 等. 基于模态分解与LSTM注意表征的测井曲线重构研究[J]. 电子学报, 2024, 52(04): 1399-1410. DOI：10.12263/DZXB.20220887

LIU Meng, HAN Jian, CAO Zhi-min, et al. Logging Curves Reconstruction Based on Mode Decomposition and LSTM-Attention Model[J]. Acta Electronica Sinica, 2024, 52(04): 1399-1410. DOI：10.12263/DZXB.20220887

摘要

测井曲线记录着地层物理性质随深度变化的幅值范围，是测井与地震资料之间的纽带，对储层岩性分析与识别和后续的油气勘探工程十分重要.然而，在实际的测井过程中仪器故障等原因会造成测井曲线缺失的问题，重新测井不仅价格昂贵而且难以实现.针对地质勘探时测井数据时常缺失的问题，本文提出了一种LSTM（Long Short-Term Memory）注意力表征的测井曲线重构方法.同时，对原始测井信号进行两种模态分解，计算分解后得到模态分量与原始信号之间的相关性，去除冗余分量，实现对缺失的测井曲线高效、高精度的人工补全.将该方法用于声波（ACoustic，AC）与密度（DENsity，DEN）曲线重构实验，并将实验结果与LSTM网络和BP（Back Propagation）神经网络预测的结果进行对比分析.结果表明，LSTM-Attention模型有着更为优异的预测效果，重构后的AC和DEN与原始曲线之间的相关性分别达到了86.8%和74.8%，高于传统LSTM和BP神经网络预测方法.在去除冗余的信号分量后，相关系数分别提高了1.4%和4.0%.同时，本文所提方法预测出的测井曲线具有最低的预测误差.因此，基于LSTM注意表征的网络结构对测井曲线重构具有较好的预测精度.

Abstract

The well logging curve records the amplitude range of geophysical properties changing with depth and is the bond between well log and seismic data. It is also significant for reservoir lithology analysis and subsequent oil and gas exploration projects. However

instrument failure and other reasons will cause well-logging curves to be missing in the actual logging process. Re-logging is not only expensive but also difficult to achieve. Aiming at the problem that logging data is often missing during geological exploration

this paper proposes a logging curve reconstruction method based on the LSTM(Long Short-Term Memory)-attention model. At the same time

EMD-VMD (Empirical Mode Decomposition-Variational Mode Decomposition) decomposition is performed on the original logging signal and then the correlation between the components and the original curve is calculated. Some excrescent components are deletedto promote efficient and high-precision manual completion. This proposed method is applied to reconstruct missing logs acoustic (AC) and density (DEN)

and the prediction results are compared with those predicted by LSTM and BP (Back Propagation) neural network. The results show that the LSTM-attention model has a better prediction performance

and the correlations between predictive and the original curves can reach 86.8% (AC) and 74.8% (DEN)

higher than the traditional LSTM and BP neural network. After removing redundant signal components

the correlation coefficients increased by 1.4% (AC) and 4.0% (DEN). At the same time

the logging curve predicted by the proposed method has the lowest prediction error. Therefore

the representation learning based on LSTM with an attention mechanism has better prediction accuracy for well-logging curve reconstruction.

关键词

Keywords

references

张美玲 , 丛琳 , 张士奇 , 等 . 大庆外围扶杨油层组低孔渗储层饱和度计算方法 [J ] . 大庆石油学院学报 , 2011 , 35 ( 6 ): 9 - 12, 27, 122 .

ZHANG M L , CONG L , ZHANG S Q , et al . Calculation of saturation in Daqing Fuyang low permeability and porosity reservoirs [J ] . Journal of Daqing Petroleum Institute , 2011 , 35 ( 6 ): 9 - 12, 27, 122 . (in Chinese)

王俊瑞 , 梁力文 , 邓强 , 等 . 基于多元回归模型重构测井曲线的方法研究及应用 [J ] . 岩性油气藏 , 2016 , 28 ( 3 ): 113 - 120 .

WANG J R , LIANG L W , DENG Q , et al . Research and application of log reconstruction based on multiple regression model [J ] . Lithologic Reservoirs , 2016 , 28 ( 3 ): 113 - 120 . (in Chinese)

ZHANG Z W , YI W , KONG L J . Target detection and localization using multi-frame information for noncoherent MIMO radar [C ] // IET International Radar Conference . London : IET , 2016 : 1 - 6 .

BANCHS R , JIMÉNEZ J R , DEL PINO E . Nonlinear estimation of missing logs from existing well log data [C ] // SEG Technical Program Expanded Abstracts 2001 . Houston : Society of Exploration Geophysicists , 2001 : 598 - 600 .

吕晶 , 谢润成 , 周文 , 等 . LM-BP神经网络在泥页岩地层横波波速拟合中的应用 [J ] . 中国石油大学学报(自然科学版) , 2017 , 41 ( 3 ): 75 - 83 .

LÜ J , XIE R C , ZHOU W , et al . Application of LM-BP neural network in simulation of shear wave velocity of shale formation [J ] . Journal of China University of Petroleum (Edition of Natural Science) , 2017 , 41 ( 3 ): 75 - 83 . (in Chinese)

SHI Y L , WANG Y T , LIU X J , et al . Prediction of oil and gas distribution in K area by inheritance classification [J ] . IOP Conference Series: Earth and Environmental Science , 2021 , 660 ( 1 ): 012135 .

侯斌 , 桂志先 , 许辉群 , 等 . 应用多属性神经网络方法预测油气 [J ] . 岩性油气藏 , 2010 , 22 ( 3 ): 118 - 120 .

HOU B , GUI Z X , XU H Q , et al . Application of multi-attribute and neural network method to hydrocarbon reservoir prediction [J ] . Lithologic Reservoirs , 2010 , 22 ( 3 ): 118 - 120 . (in Chinese)

李守巨 , 刘迎曦 . 基于分形理论的煤层瓦斯渗透率参数估计方法 [J ] . 西安石油大学学报(自然科学版) , 2007 ( 2 ): 113 - 115, 180 .

LI S J , LIU Y X . Estimation method of the methane gas permeability in coal seam based on fractal theory [J ] . Journal of Xi’an Shiyou University (Natural Science Edition) , 2007 ( 2 ): 113 - 115, 180 . (in Chinese)

ARAKAWA K , KROTKOV E . Fractal surface reconstruction with uncertainty estimation: Modeling natural terrain [C ] // Proceedings of IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 1993 : 314 - 320 .

REZAEI M , FAZEL ZARANDI M H . Facility location via fuzzy modeling and simulation [J ] . Applied Soft Computing , 2011 , 11 ( 8 ): 5330 - 5340 .

ALMARAASHI M , JOHN R . Tuning of Type-2 fuzzy systems by simulated annealing to predict time series [C ] // Proceedings of the World Congress on Engineering 2011 Vol II . London : WCE , 2011 : 1 - 5 .

HA H , OLSON J R , BIAN L , et al . Analysis of heavy metal sources in soil using kriging interpolation on principal components [J ] . Environmental Science & Technology , 2014 , 48 ( 9 ): 4999 - 5007 .

BATEMAN R M . Openhole Log Analysis and Formation Evaluation [M ] . Richardson : Society of Petroleum Engineers , 2012 .

ASQUITH G B , KRYGOWSKI D , HENDERSON S , et al . Basic Well Log Analysis [M ] . Tulsa : American Association of Petroleum Geologists , 2004 .

ROLON L , MOHAGHEGH S D , AMERI S , et al . Using artificial neural networks to generate synthetic well logs [J ] . Journal of Natural Gas Science and Engineering , 2009 , 1 ( 4/5 ): 118 - 133 .

杨志力 , 周路 , 彭文利 , 等 . BP神经网络技术在声波测井曲线重构中的运用 [J ] . 西南石油大学学报(自然科学版) , 2008 , 30 ( 1 ): 63 - 66, 13 .

YANG Z L , ZHOU L , PENG W L , et al . Application of bp neural network technology in sonic log data rebuilding [J ] . Journal of Southwest Petroleum University (Science & Technology Edition) , 2008 , 30 ( 1 ): 63 - 66, 13 . (in Chinese)

张东晓 , 陈云天 , 孟晋 . 基于循环神经网络的测井曲线生成方法 [J ] . 石油勘探与开发 , 2018 , 45 ( 4 ): 598 - 607 .

ZHANG D X , CHEN Y T , MENG J . Synthetic well logs generation via recurrent neural networks [J ] . Petroleum Exploration and Development , 2018 , 45 ( 4 ): 598 - 607 . (in Chinese)

王俊 , 曹俊兴 , 尤加春 . 基于GRU神经网络的测井曲线重构 [J ] . 石油地球物理勘探 , 2020 , 55 ( 3 ): 510 - 520, 468 .

WANG J , CAO J X , YOU J C . Reconstruction of logging traces based on GRU neural network [J ] . Oil Geophysical Prospecting , 2020 , 55 ( 3 ): 510 - 520, 468 . (in Chinese)

郑艳秋 . 基于经验模式分解和神经网络的短期电力负荷预测方法研究 [D ] . 重庆 : 重庆大学 , 2009 .

ZHENG Y Q . Research on Short-term Power Load Forecasting Based on Empirical Mode Decomposition and Artificial Neural Network [D ] . Chongqing : Chongqing University , 2009 . (in Chinese)

刘建华 , 李锦程 , 杨龙月 , 等 . 基于EMD-SLSTM的家庭短期负荷预测 [J ] . 电力系统保护与控制 , 2019 , 47 ( 6 ): 40 - 47 .

LIU J H , LI J C , YANG L Y , et al . Short-term household load forecasting based on EMD-SLSTM [J ] . Power System Protection and Control , 2019 , 47 ( 6 ): 40 - 47 . (in Chinese)

刘兴杰 , 米增强 , 杨奇逊 , 等 . 一种基于EMD的短期风速多步预测方法 [J ] . 电工技术学报 , 2010 , 25 ( 4 ): 165 - 170 .

LIU X J , MI Z Q , YANG Q X , et al . A novel multi-step prediction for wind speed based on EMD [J ] . Transactions of China Electrotechnical Society , 2010 , 25 ( 4 ): 165 - 170 . (in Chinese)

AN X L , YANG J J . Denoising of hydropower unit vibration signal based on variational mode decomposition and approximate entropy [J ] . Transactions of the Institute of Measurement and Control , 2016 , 38 ( 3 ): 282 - 292 .

ALI M , KHAN A , REHMAN N U . Hybrid multiscale wind speed forecasting based on variational mode decomposition [J ] . International Transactions on Electrical Energy Systems , 2018 , 28 ( 1 ): e2466 .

陈强伟 , 蔡文皓 , 牛春光 , 等 . 基于VMD的APF谐波检测算法 [J ] . 电力科学与技术学报 , 2018 , 33 ( 1 ): 120 - 124 .

CHEN Q W , CAI W H , NIU C G , et al . A APF harmonics detection method based on VMD [J ] . Journal of Electric Power Science and Technology , 2018 , 33 ( 1 ): 120 - 124 . (in Chinese)

王俊 , 李霞 , 周昔东 , 等 . 基于VMD和LSTM的超短期风速预测 [J ] . 电力系统保护与控制 , 2020 , 48 ( 11 ): 45 - 52 .

WANG J , LI X , ZHOU X D , et al . Ultra-short-term wind speed prediction based on VMD-LSTM [J ] . Power System Protection and Control , 2020 , 48 ( 11 ): 45 - 52 . (in Chinese)

李鑫 , 王娟 , 邱亚 , 等 . 基于VMD的混合储能容量优化配置 [J ] . 太阳能学报 , 2022 , 43 ( 2 ): 88 - 96 .

LI X , WANG J , QIU Y , et al . Optimal allocation of hybrid energy storage capacity based on variational mode decomposition [J ] . Acta Energiae Solaris Sinica , 2022 , 43 ( 2 ): 88 - 96 . (in Chinese)

陈云天 . 基于机器学习的测井曲线补全与生成研究 [D ] . 北京 : 北京大学 , 2020 .

CHEN Y T . Research on Well Log Completion and Generation Based on Machine Learning [D ] . Beijing : Peking University , 2020 . (in Chinese)

王薪凯 , 于忠清 . 基于LSTM神经网络模型的泵站能耗预测 [J ] . 青岛大学学报(自然科学版) , 2022 , 35 ( 1 ): 11 - 18 .

WANG X K , YU Z Q . Energy consumption prediction of pumping station based on LSTM neural network model [J ] . Journal of Qingdao University (Natural Science Edition) , 2022 , 35 ( 1 ): 11 - 18 . (in Chinese)

SUBAKAN C , RAVANELLI M , CORNELL S , et al . Attention is all You need in speech separation [C ] // ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE , 2021 : 21 - 25 .

WANG F , JIANG M Q , QIAN C , et al . Residual attention network for image classification [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 6450 - 6458 .

徐延勇 , 邹冠贵 , 曹文彦 , 等 . 测井曲线标准化方法对比研究及应用 [J ] . 中国煤炭地质 , 2013 , 25 ( 1 ): 53 - 57 .

XU Y Y , ZOU G G , CAO W Y , et al . Comparative study and application of logging standardization methods [J ] . Coal Geology of China , 2013 , 25 ( 1 ): 53 - 57 . (in Chinese)

卢元磊 , 何佳洲 , 安瑾 . 目标预测中的野值剔除方法研究 [J ] . 计算机与数字工程 , 2013 , 41 ( 5 ): 722 - 725 .

LU Y L , HE J Z , AN J . Outlier-discrimination algorithm in target-prediction [J ] . Computer & Digital Engineering , 2013 , 41 ( 5 ): 722 - 725 . (in Chinese)

曹志民 , 路成辉 , 刘爽 , 等 . 基于二分空间拉依达法的野值点剔除研究 [J ] . 化工自动化及仪表 , 2018 , 45 ( 2 ): 137 - 140, 171 .

CAO Z M , LU C H , LIU S , et al . Research on outliers elimination based on binary-split space pauta method [J ] . Control and Instruments in Chemical Industry , 2018 , 45 ( 2 ): 137 - 140, 171 . (in Chinese)

刘明阳 . 基于LSTM模型的现代有轨电车到站时间预测方法研究 [D ] . 南京 : 东南大学 , 2020 .

LIU M Y . Research on the Arrival Time Prediction Method of Modern Streetcar Based on the LSTM Model [D ] . Nanjing : Southeast University , 2020 . (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

采用EMD方法消除瞬态散射回波中的高斯白噪声干扰

长短包混合传输的互惠共生无线电系统资源分配方法研究

基于VLM凸优化的网络直播视频场景图生成

结合频域物理感知与高阶语义融合的一体化遥感图像复原框架

基于TCAD与DNN的FinFET器件辐射总剂量效应模型