4/6/2025, 1:35:37 PM 星期日
Integration of real-time intelligent stratigraphic identification and prediction model for geologically-guided field operation
CSTR:
Affiliation:

1.College of Environment and Civil Engineering, Chengdu University of Technology,Chengdu Sichuan 610059, China;2.State Key Laboratory of Geohazard Prevention and Geoenvironment Protection;(Chengdu University of Technology), Chengdu Sichuan 610059, China

Clc Number:

P634

  • Article
  • | |
  • Metrics
  • |
  • Reference [26]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    This paper employs deep learning algorithms based on actual wellbore trajectory parameter data and well logging data collected from the Weiyuan block in Sichuan. An algorithmic framework capable of real-time predicting encountered strata during drilling is established. Firstly, this framework utilizes a time-series prediction algorithm to forecast the subsequent wellbore trajectory. Subsequently, based on this prediction, it achieves the forecast of strata gamma values. Finally, the identification of encountered strata types is accomplished by utilizing the predicted strata gamma values. To enhance the predictive accuracy of the entire algorithmic framework, various algorithms are employed and compared at each stage. The results demonstrate that real-time prediction using recurrent neural networks, gamma value regression prediction through random forests, and strata classification prediction using support vector machines yield the best training outcomes. The predictive accuracies reach 0.81, 0.83 and 81.8%, respectively. The real-time anticipation of encountered strata during the geologically guided process provides on-site data support and auxiliary judgment means. This contributes to the more reliable and effective achievement of geological objectives in practical engineering.

    Reference
    [1] Jin Y, Wan Q, Wu X, et al. FPGA-accelerated deep neural network for real-time inversion of geosteering data[J]. Geoenergy Science and Engineering, 2023,224:211610.
    [2] Mohamed D, Jeremy C. Unconventional horizontal well placement challenges-LWD geosteering applications utilizing a unique spectral azimuthal gamma ray in real time[Z]. 2014.
    [3] Thwaites N, Suh A. Use of near bit azimuthal gamma ray and inclination tool improves geosteering in CBM wells, Airth Field, Scotland[Z]. EAGE Publications BV, 20141-12.
    [4] Qin Z, Pan H, Wang Z, et al. A fast forward algorithm for real-time geosteering of azimuthal gamma-ray logging[J]. Applied Radiation and Isotopes, 2017,123:114-120.
    [5] Moorkamp M, Lelièvre P G, Linde N, et al. Integrated Imaging of the Earth: Theory and Applications[M]. John Wiley & Sons, 2016.
    [6] Sun Q, Duan Y, Yan Y, et al. Forward Algorithm of LWD Azimuthal Gamma[J]. Journal of System Simulation, 2018,30(11):4268.
    [7] Qin Z, Tang B, Wu D, et al. A qualitative characteristic scheme and a fast distance prediction method of multi-probe azimuthal gamma-ray logging in geosteering[J]. Journal of Petroleum Science and Engineering, 2021,199:108244.
    [8] Lu H, Shen Q, Chen J, et al. Parallel multiple-chain DRAM MCMC for large-scale geosteering inversion and uncertainty quantification[J]. Journal of Petroleum Science and Engineering, 2019,174:189-200.
    [9] Kullawan K, Bratvold R B, Bickel J E. Sequential geosteering decisions for optimization of real-time well placement[J]. Journal of Petroleum Science and Engineering, 2018,165:90-104.
    [10] Zong C, Liu J, Liu Z, et al. A fast forward algorithm of azimuthal gamma imaging logging while drilling[J]. Applied Radiation and Isotopes, 2023,194:110659.
    [11] Dawoud A, El Mahdi A, Ayoub M, et al. Geosteering long horizontal holes in Abu Dhabi heterogeneous carbonate reservoirs[Z]. 2010128851.
    [12] Mahesh B. Machine learning algorithms—A review[J]. International Journal of Science and Research (IJSR) (Internet), 2020,9:381-386.
    [13] 奉国和.SVM分类核函数及参数选择比较[J].计算机工程与应用,2011,47(3):123-124.
    [14] Ron A E L G E. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow[M]. O’Reilly Media, Inc., 2022.
    [15] Altin F G, Budak 0, özcan F. Predicting the amount of medical waste using kernel-based SVM and deep learning methods for a private hospital in Turkey[J]. Sustainable Chemistry and Pharmacy, 2023,33:101060.
    [16] Raghavendra. N S, Deka P C. Support vector machine applications in the field of hydrology: A review[J]. Applied Soft Computing, 2014,19:372-386.
    [17] Hamad A, Houssein E H, Hassanien A E, et al. A hybrid EEG signals classification approach based on grey wolf optimizer enhanced SVMs for epileptic detection[C]//Cham: Springer International Publishing, 2018.
    [18] Houssein E H, Hamad A, Hassanien A E, et al. Epileptic detection based on whale optimization enhanced support vector machine[J]. Journal of Information and Optimization Sciences, 2019,40(3):699-723.
    [19] Tang W, Gong Y, Qiu G. Feature preserving 3D mesh denoising with a Dense Local Graph Neural Network[J]. Computer Vision and Image Understanding, 2023,233:103710.
    [20] 胡中源,薛羽,查加杰.演化循环神经网络研究综述[J].计算机科学,2023,50(3):254-265.
    [21] Qian K, Tian L. An embedded Hamiltonian dynamic evolutionary neural network model for high-dimensional data recognition[J]. Applied Soft Computing, 2023,141:110299.
    [22] Resende P A A, Drummond A E C. A survey of random forest based methods for intrusion detection systems[J]. ACM Computing Surveys (CSUR), 2018,51(3):1-36.
    [23] Mohapatra N, Shreya K, Chinmay A. Optimization of the Random Forest Algorithm[M]. Springer, 2020:201-208.
    [24] 王奕森,夏树涛.集成学习之随机森林算法综述[J].信息通信技术,2018,12(1):49-55.
    [25] Karabadji N E I, Amara Korba A, Assi A, et al. Accuracy and diversity-aware multi-objective approach for random forest construction[J]. Expert Systems with Applications, 2023,225:120138.
    [26] 吕红燕,冯倩.随机森林算法研究综述[J].河北省科学院学报,2019,36(3):37-41.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:222
  • PDF: 466
  • HTML: 102
  • Cited by: 0
History
  • Received:May 30,2023
  • Revised:August 09,2023
  • Adopted:August 10,2023
  • Online: October 21,2023
Article QR Code