Abstract:As the basis for the development and evaluation of oil and gas fields,logging data is of great significance to determine the location of underground oil and gas reservoirs,and calculate and evaluate the oil and gas reserves. However,on the one hand,several logging data at some depths are often distorted or missing due to wellbore collapse and instrument failure during actual mining. On the other hand,the re-logging cost is too high with difficult construction. Therefore,this paper proposes a logging data reconstruction method based on a cascade bidirectional long short-term memory neural network (CBi-LSTM). This method fully considers the two-way correlation between the precursor and successor of missing data points and the correlation between logging curves without adding additional mea-surement cost. Firstly, the cascade system is applied to combine the estimated value and the known logging curve into a new input. Then,the iterative update strategy is employed to reconstruct the missing data block. Finally,the logging data of 4 wells in the Sulige gas field are supplemented and reconstructed. Experimental results show that the proposed method features high data reconstruction accuracy,and the model has better robustness and generalization abilities.
何旭,李忠伟,刘昕,等.应用卷积神经网络识别测井相[J]. 石油地球物理勘探,2019,54(5): 1159-1165.HE Xu,LI Zhongwei,LIU Xin,et al. Log facies re-cognition based on convolutional neural network[J]. Oil Geophysical Prospecting,2019,54(5): 1159-1165.
[2]
张岩,李新月,王斌,等. 基于深度学习的鲁棒地震数据去噪[J]. 石油地球物理勘探,2022,57(1): 12-25.ZHANG Yan,LI Xinyue,WANG Bin,et al. Robust seismic data denoising based on deep learning[J]. Oil Geophysical Prospecting,2022,57(1): 12-25.
[3]
匡立春,刘合,任义丽,等.人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发,2021,48(1): 1-11.KUANG Lichun,LIU He,REN Yili,et al. Application and development trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development,2021,48(1): 1-11.
[4]
韩明亮,邹志辉,马锐. 利用反射地震资料和多尺度训练集的深度学习速度建模[J]. 石油地球物理勘探,2021,56(5): 935-946.HAN Mingliang,ZOU Zhihui,MA Rui. Deep lear-ning-driven velocity modeling based on seismic reflection data and multi-scale training sets[J]. Oil Geophysical Prospecting,2021,56(5): 935-946.
[5]
常德宽,雍学善,王一惠,等. 基于深度卷积神经网络的地震数据断层识别方法[J]. 石油地球物理勘探,2021,56(1): 1-8.CHANG Dekuan,YONG Xueshan,WANG Yihui,et al. Seismic fault interpretation based on deep convolutional neural networks[J]. Oil Geophysical Prospecting,2021,56(1): 1-8.
[6]
HE S M,LIU L W. Using the improved genetic BP neural network algorithm for lithologic identification[J]. Advanced Materials Research,2014,1037: 389-392.
[7]
LUO H,LAI F Q,DONG Z,et al. A lithology identification method for continental shale oil reservoir based on BP neural network[J]. Journal of Geophy-sics and Engineering,2018,15(3): 895-908.
[8]
刘为付,朱筱敏. 利用模糊数学识别鄂尔多斯盆地气藏岩性[J]. 断块油气田,2005,12(5): 7-9.LIU Weifu,ZHU Xiaomin. Identifying lithology of natural gas pool by fuzzy mathematics in Ordos basin[J]. Fault-block Oil & Gas Field,2005,12(5): 7-9.
[9]
李洪奇,谭锋奇,许长福,等. 基于决策树方法的砾岩油藏岩性识别[J]. 测井技术,2010,34(1): 16-21.LI Hongqi,TAN Fengqi,XU Changfu,et al. Lithology identification of conglomerate reservoir based on decision tree method[J]. Well Logging Technology,2010,34(1): 16-21.
[10]
DENG C X,PAN H P,FANG S N,et al. Support vector machine as an alternative method for lithology classification of crystalline rocks[J]. Journal of Geophysics and Engineering,2017,14(2): 341-349.
[11]
周游,张广智,高刚,等.核主成分分析法在测井浊积岩岩性识别中的应用[J]. 石油地球物理勘探,2019,54(3): 667-675.ZHOU You,ZHANG Guangzhi,GAO Gang,et al. Application of kernel principal component analysis in well logging turbidite lithology identification[J]. Oil Geophysical Prospecting,2019,54(3): 667-675.
[12]
ZHENG J,LIU J R, PENG S P, et al. An automatic microseismic or acoustic emission arrival identification scheme with deep recurrent neural networks[J]. Geophysical Journal International,2018,212(2): 1389-1397.
[13]
XIE Y X,ZHU C Y,ZHOU W,et al. Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances[J]. Journal of Petroleum Science and Engineering,2018,160: 182-193.
[14]
JAIN G,SHARMA M,AGARWAL B. Spam detection in social media using convolutional and long short term memory neural network[J]. Annals of Mathematics and Artificial Intelligence,2019,85(1): 21-44
[15]
LI H,MISRA S. Long short-term memory and variational autoencoder with convolutional neural networks for generating NMR T2 distributions[J]. IEEE Geoscience and Remote Sensing Letters,2019,16(2): 192-195.
[16]
PALANGI H, DENG L,SHEN Y L,et al. Deep sentence embedding using long short-term memory networks: analysis and application to information retrie-val[J]. IEEE/ACM Transactions on Audio,Speech,and Language Processing,2016,24(4): 694-707.
[17]
ATEF S,ELTAWIL A B. Assessment of stacked unidirectional and bidirectional long short-term me-mory networks for electricity load forecasting[J]. Electric Power Systems Research,2020,187(5): 106489.
[18]
BHASKAR N,SUCHETHA M,PHILIP N Y. Time series classification-based correlational neural network with bidirectional LSTM for automated detection of kidney disease[J]. IEEE Sensors Journal,2021,21(4): 4811-4818.
[19]
周雪晴,张占松,朱林奇,等.基于双向长短时记忆网络的流体高精度识别新方法[J]. 中国石油大学学报(自然科学版),2021,45(1): 69-76.ZHOU Xueqing,ZHANG Zhansong,ZHU Linqi,et al. A new method for high-precision fluid identification in bidirectional long short-term memory network[J]. Journal of China University of Petroleum (Edition of Natural Science),2021,45(1): 69-76.
[20]
周欣,曹俊兴,王兴建,等. 基于双向门控循环单元神经网络的声波测井曲线重构技术[J]. 地球物理学进展, 2022,37(1): 357-366.ZHOU Xin,CAO Junxing,WANG Xingjian,et al.Acoustic log reconstruction based on bidirectional gated recurrent unit neural network[J]. Progress in Geophysics,2022,37(1): 357-366.
[21]
王俊,曹俊兴,周欣. 基于深度双向循环神经网络的储层孔隙度预测[J]. 地球物理学进展,2022,37(1): 267-274.WANG Jun,CAO Junxing,ZHOU Xin. Reservoir porosity prediction based on deep bidirectional recurrent neural network[J]. Progress in Geophysics,2022,37(1): 267-274.
[22]
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 Yuntian. Research on Well Log Completion and Generation Based on Machine Learning[D].Peking University,Beijing,2020.