Identification of Downhole Conditions in Sucker Rod Pumped Wells Using Deep Neural Networks and Genetic Algorithms
- Ramez Abdalla (The American University in Cairo) | Mahmoud Abu El Ela (Cairo University) | Ahmed El-Banbi (The American University in Cairo)
- Document ID
- Society of Petroleum Engineers
- SPE Production & Operations
- Publication Date
- May 2020
- Document Type
- Journal Paper
- 435 - 447
- 2020.Society of Petroleum Engineers
- genetic algorithm, elliptical Fourier descriptors (EFD), deep artificial neural networks (ANN), dynamometer cards, sucker rod pump faults
- 18 in the last 30 days
- 137 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 35.00|
In this paper, deep learning artificial neural networks (ANNs) are used to analyze the features of downhole dynamometer cards and identify the sucker rod pumping system conditions. A description model for the dynamometer cards, using Fourier descriptors, was established for card feature extraction. Then, neural networks were trained to generate failure prediction models to recognize downhole faults of the rod pumping systems. The failure prediction models were validated and tested with a large database of previously interpreted cards. The proposed model is trained by using 4,467 dynamometer cards—29.2% of these cards represent sucker rod pumping systems of normal conditions, while the rest (70.8%) represent faulty sucker rod pumping systems. Genetic algorithms (GAs) were used to search for the best deep ANN structure that gives highest accuracy for the testing data. Accuracy of the proposed ANN model was measured with 1,915 cards that were not used in developing the ANN. The proposed model identified the sucker rod system failure successfully with very high accuracy (99.69%).
|File Size||2 MB||Number of Pages||13|
AlMaraghi, A. M. and El-Banbi, A. H. 2015. Automatic Reservoir Model Identification Using Artificial Neural Networks in Pressure Transient Analysis. Paper presented at the SPE North Africa Technical Conference and Exhibition, Cairo, Egypt, 14–16 September. SPE-175850-MS. https://doi.org/10.2118/175850-MS.
Anemangely, M., Ramezanzadeh, A., and Tokhmechi, B. 2017. Shear Wave Travel Time Estimation from Petrophysical Logs Using ANFIS-PSO Algorithm: A Case Study from Ab-Teymour Oilfield. J Nat Gas Sci Eng 38: 373–387. https://doi.org/10.1016/j.jngse.2017.01.003.
Demuth, H., Beale, M., and Hagan, M. 2007. Neural Network Toolbox 5 User’s Guide. Natick, Massachusetts, USA: The MathWorks, Inc.
Dickinson, R. and Jennings, J. 1990. Use of Pattern-Recognition Techniques in Analyzing Downhole Dynamometer Cards. SPE Prod Eng 5 (2): 187–192. SPE-17313-PA. https://doi.org/10.2118/17313-PA.
El-Banbi, A. H., Alzahaby, A., and Al-Maraghi, A. 2018. PVT Property Correlations, Selection and Estimation, Chap. 10. Burlington, Massachusetts, USA: Gulf Professional Publishing/Elsevier.
Gao, Q., Sun, S., and Liu, J. 2015. Working Condition Detection of Sucker Rod Pumping System via Extreme Learning Machine. Paper presented at the International Conference on Civil, Materials and Environmental Sciences. https://doi.org/10.2991/cmes-15.2015.120.
Gibbs, S. G. and Neely, A. B. 1966. Computer Diagnosis of Downhole Conditions in Sucker Rod Pumping Wells. J Pet Technol 18 (1): 91–98. SPE-1165-PA. https://doi.org/10.2118/1165-PA.
Karamizadeh, S., Abdullah, S. M., Zamani, M. et al. 2015. Pattern Recognition Techniques: Studies on Appropriate Classifications. In Advanced Computer and Communication Engineering Technology. Lecture Notes in Electrical Engineering, ed. H. Sulaiman, M. Othman, Y. Rahim, and N. Pee, Vol. 315, 791–799. Heidelberg, Germany: Springer-Verlag.
Kuhl, F. and Giardina, C. 1982. Elliptic Fourier Features of a Closed Contour. Dover, New Jersey, USA: US Army Armamenr Research and Development Command.
Li, K., Gao, X. W., Yang, W. B. et al. 2013. Multiple Fault Diagnosis of Down-Hole Conditions of Sucker-Rod Pumping Wells Based on Freeman Chain Code and DCA. Pet Sci 10 (3): 347–360. https://doi.org/10.1007/s12182-013-0283-4.
Lima, F. S., Guedes, L. A., and Silva, D. 2012. Comparison of Border Descriptors and Pattern Recognition Techniques Applied to Detection and Diagnosis of Faults on Sucker-Rod Pumping System. In Digital Image Processing. Rijeka, Croatia: InTechOpen.
Liu, S., Raghavendra, C. S., Liu, Y. et al. 2011. Automatic Early Fault Detection for Rod Pump Systems. Paper presented at the SPE Annual Technical Conference and Exhibition, Denver, Colorado, USA, 30 October–2 November. SPE-146038-MS. https://doi.org/10.2118/146038-MS.
Nazi, G. M., Ashenayi, K., Lea, J. F. et al. 1994. Application of Artificial Neural Network to Pump Card Diagnosis. SPE Comput Appl 6 (6): 9–14. SPE-25420-PA. https://doi.org/10.2118/25420-PA.
Oldham, W. B., Rogers, J. D., and Guey, C. G. 1990. Artificial Neural Networks for Identification of Beam Pump Dynamometer Load Cards. Paper presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, USA, 23–26 September. SPE-20651-MS. https://doi.org/10.2118/20651-MS.
Peng, X., Shijin, X., and Hongwei, Y. 2007. Application of Self-Organizing Competitive Neural Network in Fault Diagnosis of Sucker Rod Pumping System. J Pet Sci Eng 58: 43–48. https://doi.org/10.1016/j.petrol.2006.11.008.
Qian, G., Shaobo, S., and Jianchao, L. 2015. Fault Diagnosis of Suck Rod Pumping System via Extreme Learning Machines. Paper presented at the IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, China, 8–12 June. https://doi.org/10.1109/CYBER.2015.7287990.
Schnitman, L., Albuquerque, G. S., Corrêa, J. F. et al. 2003. Modeling and Implementation of a System for Sucker Rod Downhole Dynamometer Card Pattern Recognition. Paper presented at the SPE Annual Technical Conference and Exhibition, Denver, Colorado, USA, 5–8 October. SPE-84140-MS. https://doi.org/10.2118/84140-MS.
Schnitman, L., Bezerra, M. D., Filho, M. et al. 2009. Pattern Recognition for Downhole Dynamometer Card in Oil Rod Pump System Using Artificial Neural Networks. Paper presented at the ICEIS—Proceedings of the 11th International Conference on Enterprise Information Systems, Volume AIDSS, Milan, Italy, 6–10 May. https://doi.org/10.5220/0002000403510355.
Takacs, G. 2015. Production Engineering Fundamentals and Long-Stroke Rod Pumping. In Sucker-Rod Pumping Handbook. Burlington, Massachusetts, USA: Gulf Professional Publishing/Elsevier.
Tripp, H. A. 1989. A Review: Analyzing Beam-Pumped Wells. J Pet Technol 41 (5): 457–458. SPE-19031-PA. https://doi.org/10.2118/19031-PA.
Wu, Z., Huang, S., and Luo, Y. 2013. Research on Automatic Diagnosis Based on ANN Well Conditions Fault. Paper presented at the International Conference on Information Science and Computer Applications. https://doi.org/10.2991/ISCA-13.2013.6.
Yu, Y., Shi, H., and Mi, L. 2013. Research on Feature Extraction of Indicator Card Data for Sucker-Rod Pump Working Condition Diagnosis. J Control Sci Eng 2013: 6. https://doi.org/10.1155/2013/605749.