Petroleum Exploration and Development >

2021 , Vol. 48 >Issue 4: 978 - 986

DOI: https://doi.org/10.1016/S1876-3804(21)60082-4

RESEARCH PAPER

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

  • Qifeng SUN ,
  • Na LI ,
  • Youxiang DUAN ,
  • Hongqiang LI ,
  • Haiquan TANG
Expand
  • 1. College of Computer Science and Technology in China University of Petroleum, Qingdao 266580, China
    2. Drilling Technology Research Institute of Shengli Petroleum Engineering Corporation Limited, Sinopec, Dongying 257000, China
    3. Measurement and Control Technology Research Institute of Shengli Petroleum Engineering Corporation Limited, Dongying 257000, China

Received date: 2020-12-10

  Revised date: 2021-04-29

  Online published: 2021-08-25

Supported by

PetroChina Major Scientific and Technological Project(ZD2019-183-006);Fundamental Scientific Research Fund of Central Universities(20CX05017A);China National Science and Technology Major Project(2016ZX05021-001)

Fold

Abstract

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.

Key words： logging while drilling; azimuth gamma; stratigraphic identification; artificial intelligence; long short-term memory; wavelet transform

Cite this article

Qifeng SUN , Na LI , Youxiang DUAN , Hongqiang LI , Haiquan TANG . Logging-while-drilling formation dip interpretation based on long short-term memory[J]. Petroleum Exploration and Development, 2021 , 48(4) : 978 -986 . DOI: 10.1016/S1876-3804(21)60082-4

References

[1] NYE R, DI TOMMASO D. Well optimization using a LWD spectral azimuthal gamma ray tool in unconventional reservoirs. OMC 2013-137, 2013.
[2] CARRILERO S G, HOLMES A, HINZ D, et al. A method for calculating more accurate stratigraphic positioning of horizontal wells using continuous inclination and azimuthal gamma ray images even while sliding. SPE 191740-MS, 2018.
[3] LI K, GAO J, ZHAO X. Tool design of look-ahead electromagnetic resistivity LWD for boundary identification in anisotropic formation. Journal of Petroleum Science and Engineering, 2020, 184:106537.
[4] CHEN G, CHEN L, LI Q. Comparison and application of neural networks in LWD lithology identification. IOP Conference Series: Earth and Environmental Science, 2020, 526:012146.
[5] VIENS C, CLARK T, LIGHTFOOT J, et al. Real-time downhole data resolves lithology related drilling behavior. SPE 189697-MS, 2018.
[6] BOOTLE R, WAUGH M, BITTAR M, et al. Laminated sand shale formation evaluation using azimuthal LWD resistivity. SPE 123890-MS, 2009.
[7] SUN Dongzheng, YANG Jin, YANG Xiangqian, et al. Application of formation pressure prediction while drilling technology in HTHP wells. Oil Drilling & Production Technology, 2016, 38(6):746-751.
[8] POZO M, TORRES F, BEDOYA J, et al. Enhancing performance and operational safety of Argentinean Vaca Muerta shale wells by drilling high pressure formations using managed pressure drilling. SPE 187142-MS, 2017.
[9] LUTFALLAH M, HIBLER A P, MISHRA A, et al. Optimizing a unique new generation LWD technology for petrophysical evaluation, well-placement, geological mapping and completion design: Carbonate reservoir case study. SPE 181289-MS, 2016.
[10] MARTIN S J, THOMAS M G, HAMMONS S D, et al. Real-time azimuthal gamma and resistivity LWD data used to navigate complex unconventional reservoir: Western US Land. SPE 165923-MS, 2013.
[11] GUPTA K D, VALLEGA V, MANIAR H, et al. A deep- learning approach for borehole image interpretation. The Woodlands, Texas, USA: 2019 SPWLA 60th Annual Symposium, 2019.
[12] POPA A, CONNEL S. Optimizing horizontal well placement through stratigraphic performance prediction using artificial intelligence. Calgary: SPE Annual Technical Conference and Exhibition, 2019.
[13] MOHAMED I M, MOHAMED S, MAZHER I, et al. Formation lithology classification: Insights into machine learning methods. Calgary: SPE Annual Technical Conference and Exhibition, 2019.
[14] LI Xinran, WANG Lide, LI Peiqiang. The study on composite load model structure of artificial neural network. Nanjing: 2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies, 2008.
[15] XUE Bo, YANG Qing, ZHANG Chaohong. Automatic slicing method of logging curves based on morphological filtering and wavelet transform. Progress in Geophysics, 2020, 35(1):203-210.
[16] YUAN Mei, WU Yuting, LI Lin. Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network. Beijing: 2016 IEEE International Conference on Aircraft Utility Systems, 2016.
[17] LI Hongqiang, DING Jingli, LIN Nan, et al. Research and application of data processing method of gamma ray measurement while drilling. Petroleum Drilling Technology, 2008, 36(4):12-14.
[18] ZHOU Xuan, ZHOU Shudao, HUANG Feng, et al. A new image enhancement algorithm based on wavelet transform. Computer Applications, 2005, 25(3):606-608.
[19] DONG Ze, XIE Hua, HAN Pu, et al. Research on wavelet transform modulus maximum denoising algorithm. Power Science and Engineering, 2005(3):12-16.
[20] DIAO Yanhua, WANG Yutian, CHEN Guotong. Signal singularity detection based on modulus maxima of wavelet transform. Hebei Industrial Science and Technology, 2004, 21(1):1-3.
[21] COLE T J, GREEN P J. Smoothing reference centile curves: The LMS method and penalized likelihood. Statistics in Medicine, 1992, 11(10):1305-1319.
[22] WANG J, HUISZOON C, XU L, et al. Quantitative study of natural gamma ray depth of image and dip angle calculations. New Orleans, Louisiana: the SPWLA 54th Annual Logging Symposium, 2013.
[23] GRAVES A. Long short-term memory. Berlin: Springer, 2012: 1735-1780.
[24] LI D, ZHANG Y, GONG D, et al. Gas data prediction based on LSTM neural network. IOP Conference Series: Earth and Environmental Science, 2020, 750(1):012175.
[25] LIU J, WANG G, DUAN L Y, et al. Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Transactions on Image Processing, 2018, 27(99):1586-1599.
[26] QUAN Bo, YANG Bochen, HU Keqi, et al. Ship track prediction model based on LSTM. Computer Science, 2018, 45(S2):126-131.
[27] WANG Xin, WU Ji, LIU Chao, et al. Fault time series prediction based on LSTM recurrent neural network. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(4):772-784.
Options
Outlines

/

〈 〉

Copyright © Petroleum Exploration and Development
Address:P. O. Box 910, No.20 Xueyuan Road, Haidian District, Beijing 100083, China
Powered by Beijing Magtech Co. Ltd.