[1]尚福华,卢玉莹,曹茂俊.基于改进 LSTM 神经网络的测井曲线重构方法[J].计算机技术与发展,2022,32(06):198-202.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 033]
　SHANG Fu-hua,LU Yu-ying,CAO Mao-jun.Well Logging Curve Reconstruction Method Based on Improved LSTM Neural Network[J].,2022,32(06):198-202.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 033]
点击复制

基于改进 LSTM 神经网络的测井曲线重构方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年06期
页码:
198-202
栏目:
应用前沿与综合
出版日期:
2022-06-10

文章信息/Info

Title:
Well Logging Curve Reconstruction Method Based on Improved LSTM Neural Network
文章编号:
1673-629X(2022)06-0198-05
作者:
尚福华; 卢玉莹; 曹茂俊
东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318
Author(s):
SHANG Fu-hua; LU Yu-ying; CAO Mao-jun
School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China
关键词:
测井曲线重构; 长短期记忆神经网络; 测井领域知识; 深度学习; 注意力机制
Keywords:
well logging curve reconstruction; long and short term memory neural network; logging domain knowledge; deep learning; attentional mechanism
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 033
摘要:
地球物理测井过程中,由于仪器测量或者井眼原因等经常会造成部分测井曲线失真或缺失的情况,针对失真或缺失部分测井曲线的补全与生成问题,对测井领域知识和长短期记忆神经网络( LSTM) 进行了研究,提出联合领域知识与深度学习的测井曲线重构模型( DK-LSTM) 。 利用测井领域知识中的地层岩性特征指数筛选数据得到高质量的训练样本,并将其作为深度学习重构测井曲线的依据;构建并训练带有领域知识约束层的长短期记忆神经网络模型;基于测井曲线间的强依赖关系在重构模型中引入注意力机制,进而生成并补全测井曲线中失真或缺失的信息。 实验结果表明 DK -LSTM 测井曲线重构模型较标准长短期记忆神经网络和串级长短期记忆神经网络具有更准确的预测效果,为测井曲线重构提供了一种新思路。
Abstract:
In the process of geophysical logging,some well logging curves are often distorted or missing due to instrument measurement orborehole reasons. For the problem of completion and generation of the distorted or missing logging curve,the logging domain knowledgeand LSTM ( long and short term memory) are studied. A well logging curve reconstruction model ( DK - LSTM) combining domainknowledge and deep learning is proposed. The high quality training samples are obtained by selecting the data of formation lithologycharacteristic index in logging domain knowledge,which are used as the basis for deep learning to reconstruct well logging curves. Theneural network model of long and short term memory with domain knowledge constraint layer is constructed and trained. The attentionmechanism is introduced into the reconstruction model based on the strong dependence between logging curves to generate and completethe distorted or missing information in well logging curves. The experiment shows that the DK - LSTM model has more accurateprediction effect than the standard LSTM and the cascade LSTM,which provides a new idea for well logging curve reconstruction.

相似文献/References:

[1]蒋锐鹏,姑丽加玛丽·麦麦提艾力,安丽娜.基于长短期记忆神经网络的手写数字识别[J].计算机技术与发展,2020,30(02):94.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 019]
　JIANG Rui-peng,Gulijiamali·MAIMAITIAILI,AN Li-na.Handwritten Number Recognition Based on Long Short-term Memory Neural Network[J].,2020,30(06):94.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 019]
[2]甄俊涛,刘 臣.高维数据多标签分类的食品安全预警研究[J].计算机技术与发展,2020,30(09):109.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 020]
　ZHEN Jun-tao,LIU Chen.Research on Food Safety Early Warning of Multi-label Classification of High Dimensional Data[J].,2020,30(06):109.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 020]
[3]刘高军,王小宾.基于 CNN+LSTMAttention 的营销新闻文本分类[J].计算机技术与发展,2020,30(11):59.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 011]
　LIU Gao-jun,WANG Xiao-bin.Marketing News Text Classification Incorporating CNN+LSTMAttention[J].,2020,30(06):59.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 011]
[4]刘兴霖,黄 超,王 龙,等.基于聚类和 LSTM 的光伏功率日前逐时鲁棒预测[J].计算机技术与发展,2023,33(03):120.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 018]
　LIU Xing-lin,HUANG Chao,WANG Long,et al.Clustering and LSTM-based Robust Day-ahead Hourly Forecasting of Photovoltaic Power[J].,2023,33(06):120.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 018]
[5]吴春燕,李 理,黄鹏程,等.融合动态卷积注意力的机器阅读理解研究[J].计算机技术与发展,2023,33(07):160.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 024]
　WU Chun-yan,LI Li,HUANG Peng-cheng,et al.Study on Machine Reading Comprehension Hybriding Dynamic Convolution Attention[J].,2023,33(06):160.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 024]
[6]陈 刚.基于改进 GRU 的高速公路交通流量预测模型[J].计算机技术与发展,2023,33(07):208.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 031]
　CHEN Gang.Highway Traffic Flow Prediction Model Based on Improved GRU[J].,2023,33(06):208.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 031]

更新日期/Last Update: 2022-06-10