Application of Data Mining for Quick Root-Cause Identification and Automated Production Diagnostic of Gas Wells With Plunger Lift
- Ajay Singh (Halliburton)
- Document ID
- Society of Petroleum Engineers
- SPE Production & Operations
- Publication Date
- August 2017
- Document Type
- Journal Paper
- 279 - 293
- 2017.Society of Petroleum Engineers
- Data mining, regression tree analysis, plunger lift, production diagnostic, cross-validation
- 3 in the last 30 days
- 399 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 35.00|
The paper presents an application of the classification-and-regression-tree (CART) technique as a root-cause identification and production diagnostic tool, and presents case studies from real field data for gas wells using the plunger-lift system. Specifically, regression-tree analysis was performed on the basis of the available operation data. The regression-tree model is data-driven and easy to construct, and does not require all the parameters that a first-principles-based model often requires. Thus, these models are quite useful in cases where real-time data or the required data for a detailed analysis are unavailable. To improve prediction capability, a cross-validation technique was used to optimize tree size. A total of 8 to 10 variables that could potentially affect the gas-production rate was considered, with case studies conducted on actual field data. Questions, such as which group of wells is performing well or poorly, are quickly answered. Regression-tree analysis, when applied at the field level, can identify a group of wells that underperform compared with other wells. As a result, an asset team can prioritize wells identified as poor performers. Further, a statistical analysis helps to gain insight into understanding the causal relationship between the gas-production rate and various operational variables. On the basis of this analysis, recommendations are also provided to improve the gas-production rate of poorly performing wells. Individual-well models were also constructed to identify the root causes for high or low gas production on the basis of operational changes made during a certain period of time. Only a few of the variables were found to have a significant impact on gas production. The interpretation of the decision tree indicated that additional operational variables, such as production time and pressure-buildup time, should be included in the regression-tree analysis to improve the diagnostic process. This paper summarizes these conclusions and recommends future work to improve the prediction capability of the regression-tree analysis.
|File Size||1 MB||Number of Pages||15|
Breiman, L., Friedman, J. H., Olshen, R. A. et al. 1984. Classification and Regression Trees. Chapman & Hall.
Cashin, P. and Dattagupta, R. 2008. The Anatomy of Banking Crisis. In IMF Working Paper, 1–37.
Chen, L. S. and Su, C.-T. 2008. Using Granular Computing Model to Induce Scheduling Knowledge in Dynamic Manufacturing Environments. International Journal of Computer Integrated Manufacturing 21 (5): 569–583. https://doi.org/10.1080/09511920701381255.
Friedman, J. H. 1991. Multivariate Adaptive Regression Splines (with discussion). The Annals of Statistics 19 (1): 1–67.
Gasbarri, S. and Wiggins, M. L. 2001. A Dynamic Plunger Lift Model for Gas Wells. SPE Prod & Fac 16 (2): 89–96. SPE-72057-PA. https://doi.org/10.2118/72057-PA.
Hastie, T., Tibshirani, R., and Friedman, J. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, second edition. Springer.
Jekabsons, G. 2011. ARESLab: Adaptive Regression Splines Toolbox for Matlab/Octave http://www.cs.rtu.lv/jekabsons/.
Lea, J. F. 1982. Dynamic Analysis of Plunger Lift Operations. J Pet Technol 34 (11): 2617–2629. SPE-10253-PA. https://doi.org/10.2118/10253-PA.
Marshall, R. J. 2001. The Use of Classification and Regression Trees in Clinical Epidemiology. J. Clin. Epidemiol. 54 (6): 603–609.
Maucec, M., Singh, A., Bhattacharya, S. et al. 2015. Multivariate Analysis and Data Mining of Well-Stimulation Data by Use of Classification and Regression Tree With Enhanced Interpretation and Prediction Capabilities. SPE Econ & Mgmt 7 (2): 60–71. SPE-166472-PA. https://doi.org/10.2118/166472-PA.
McCoy, J., Rowlan, L., and Podio, A. L. 2001. Plunger-Lift Optimization by Monitoring and Analyzing Well High-Frequency Acoustic Signals, Tubing Pressure, and Casing Pressure. Presented at the Rocky Mountain Petroleum Technology Conference, Keystone, Colorado, USA, 21–23 May. SPE-71083-MS. https://doi.org/10.2118/71083-MS.
Morrow, S. J., Jr. and Rogers, J. R., Jr. 1992. Increasing Production Using Microprocessors and Tracking Plunger-Lift Velocity. Presented at the SPE Mid-Continent Gas Symposium, Amarillo, Texas, USA, 13–14 April. SPE-24296-MS. https://doi.org/10.2118/24296-MS.
Ozkan, E., Keefer, B., and Miller, M. G. 2003. Optimization of Plunger-Lift Performance in Liquid Loading Gas Wells. Presented at the Canadian International Petroleum Conference, Denver, 5–8 October. SPE-84135-MS. https://doi.org/10.2118/84135-MS.
Park, H. Y. 2008. Decision Matrix for Liquid Loading in Gas Wells for Cost/Benefit Analyses of Lifting Options. MS thesis, Texas A&M University, College Station, Texas.
Rowlan, O. L., McCoy, J. N., and Podio, A. L. 2007. Plunger Lift Analysis, Troubleshooting, and Optimization. Presented at the Canadian International Petroleum Conference, Calgary, 12–14 June. PETSOC-2007-159. https://doi.org/10.2118/2007-159.
Snousy, M. B. A., El-Deeb, H. M., Badran, K. et al. 2011. Suite of Decision Tree-Based Classification Algorithms on Cancer Gene Expression Data. Egyptian Informatics Journal 12 (2): 73–82. https://doi.org/10.1016/j.eij.2011.04.003.
Wiggins, M. L., Nguyen, S. H., and Gasbarri, S. 1999. Optimizing Plunger Lift Operations in Oil and Gas Wells. Presented at the SPE Mid-Continent Operations Symposium, Oklahoma City, Oklahoma, USA, 28–31 March. SPE-52119-MS. https://doi.org/10.2118/52119-MS.
Zhang, H. and Singer, B. H. 2010. Recursive Partitioning and Applications. Springer.