Well Production Real-Time Intelligent Monitoring Based on Convolutional Neural Network

  • Zhen Wang
  • X. WangEmail author
  • W. G. Duan
  • F. J. Li
  • F. Chen
Conference paper
Part of the Springer Series in Geomechanics and Geoengineering book series (SSGG)


Based on the theory of deep learning, this paper proposes the use of convolutional neural network (CNN) method to identify the working condition of pumping unit of an oil well by indicator diagram. The structure and principle of CNN are introduced, and the CNN-based indicator diagram identification model is established. Over 180,000 pieces of indicator diagram data from a real oilfield are collected, and the working conditions corresponding to each indicator diagram are manually labeled as the training set for CNN model. Using this training set, the CNN-based indicator diagram identification model is trained and tested. The training and test results show that the accuracy of the CNN-based indicator diagram identification model is more than 90%. Compared with the traditional neural network models, CNN model can learn from the image directly and avoid the complex process of artificial extraction of features, hence leads to a better performance. The CNN-based indicator diagram classification and recognition model can be combined with the real-time data acquisition system of the well to realize the real-time intelligent monitoring of the oil well working condition.


Indicator diagram Intelligent monitoring Deep learning Convolutional neural network 



We would like to thank Luming oil and gas exploration and development Co., Ltd, Shengli oilfield which provides experimental data. The authors acknowledge funding from the Natural Science Research Project of Higher Education of Jiangsu, China (No. 17KJB440001).


  1. 1.
    Wang ZW, Xue GZ, Jin ZQ, Wang JH (2001) Using human nerve network for indicator diagram identification. Petroleum Drill Tech 29(2):56–57Google Scholar
  2. 2.
    Wang Y (2006) Remote monitoring and fault diagnosis system of sucker road oil well. Master thesis, Wuhan University of TechnologyGoogle Scholar
  3. 3.
    Gong JC (2006) Fault diagnosis of sucker oil well based on expert system. Master thesis, China University of Petroleum (East China)Google Scholar
  4. 4.
    Xu GF, Yang SL (2013) Application of grey theory in fault diagnosis of rod-pumped well. J Hefei Univ Technol Natural Sci 36(10):1265–1268Google Scholar
  5. 5.
    Schirmer P, Gay JC, Toutain P (1991) Use of advanced pattern-recognition and knowledge-based system in analyzing dynamometer cards. SPE Comput Appl 3(6):21–24CrossRefGoogle Scholar
  6. 6.
    Nazi GM, Ashenayi K, Lea JF, Kemp F (1990) Application of artificial neural network to pump card diagnosis. SPE Comput Appl 6(6):9–14CrossRefGoogle Scholar
  7. 7.
    Martinez ER, Moreno WJ, Castillo VJ, Moreno JA (1993) “Rod pumping expert system” petroleum computer conference, New Orleans, United States, Jan 1993, pp 201–208Google Scholar
  8. 8.
    Pan ZJ, Ge JL (1996) An adaptive neural networks for identification of dynamometer card. Acta Petrolei Sinica 17(3):104–109Google Scholar
  9. 9.
    Yue JH, Zuo JJ, Li HW (1999) Distinguishing method to characteristics of dynamometer diagram moment of pumping wells. Oil-Gasfield Surf Eng 18(3):15–16Google Scholar
  10. 10.
    Li CS, Su XW, Wei J, Wang LL (2014) Research on diagrams identification of pumping unit based on support vector machine. Comput Technol Dev 24(8):215–222Google Scholar
  11. 11.
    Meng QP (2012) Theoretical research on recognition of rod pumped well working condition through dynamometer card based on cellular neural network theory. Master thesis, China University of Petroleum (East China)Google Scholar
  12. 12.
    Li PH (2015) Pump indicator diagram intelligent identification based on deep learning network. Master thesis, Henan University of Science and TechnologyGoogle Scholar
  13. 13.
  14. 14.
    Matsugu M, Mori K, Mitari Y, Kaneda Y (2003) Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Netw 16(5–6):555CrossRefGoogle Scholar
  15. 15.
    Aaron VDO, Dieleman S, Schrauwen B (2013) Deep content-based music recommendation. Adv Neural Inf Process Syst 26:2643–2651Google Scholar
  16. 16.
    Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: International conference on machine learning, New York, United States, July 2008, pp 160–167Google Scholar
  17. 17.
    Cun YL, Boser B, Denker JS, Howard RE, Habbard W, Jackel LD (1990) Handwritten digit recognition with a back-propagation network. Adv Neural Inf Process Syst 2(2):396–404Google Scholar
  18. 18.
    Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: International conference on document analysis and recognition, Edinburgh, UK, Aug 2003, pp 958–963Google Scholar
  19. 19.
    LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  20. 20.
    Jarrett K, Kavukcuoglu K, Ranzato M, Lecun Y (2010) What is the best multi-stage architecture for object recognition? In: IEEE international conference on computer vision, Kyoto, Japan, May 2010, pp 2146–2153Google Scholar
  21. 21.
    Elsawy A, Elbakry H, Loey M (2016) CNN for handwritten arabic digits recognition based on LeNet-5. In: International conference on advanced intelligent systems and informatics, Cairo, Egypt, Oct 2016Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Zhen Wang
    • 1
  • X. Wang
    • 2
    Email author
  • W. G. Duan
    • 1
  • F. J. Li
    • 1
  • F. Chen
    • 1
  1. 1.Luming Oil and Gas Exploration Development Co, LTD, Shengli OilfieldDongyingChina
  2. 2.School of Petroleum EngineeringChangzhou UniversityChangzhouChina

Personalised recommendations