Detection of Symptoms for Revealing Causes Leading to Drilling Failures
- Pål Skalle (Norwegian University of Science and Technology) | Agnar Aamodt (Norwegian University of Science and Technology) | Odd Erik Gundersen (VerdandeTechnology A/S)
- Document ID
- Society of Petroleum Engineers
- SPE Drilling & Completion
- Publication Date
- May 2013
- Document Type
- Journal Paper
- 182 - 193
- 2013. Society of Petroleum Engineers
- 1.6 Drilling Operations, 1.12.6 Drilling Data Management and Standards
- 4 in the last 30 days
- 786 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 12.00|
|SPE Non-Member Price:||USD 35.00|
When a diagnosis of a problem is known, the problem can usually be solved efficiently. This paper presents a method that helps reveal the most probable cause of a drilling-process failure immediately after occurrence. Normally, it takes some time to investigate and evaluate all available information before the correct cause can be determined. The method presented is targeted at reducing this time and at the same time improving the quality of the interpretation. The method relies on input parameters from the ongoing drilling process, parameters that behave irregularly and are referred to as symptoms or errors when the irregularity is severe. Recognized symptoms are used as input parameters in a knowledge-modeling method that relates symptoms to failures. The method was verified on the basis of historical drilling data, and its ability to point out the correct causes with high probability was demonstrated. Field testing the method is yet to be performed.
|File Size||792 KB||Number of Pages||12|
Aamodt, A. 2004. Knowledge-Intensive Case-Based Reasoning in Creek. InAdvances in Case-Based Reasoning, 1-15, P. Funk and P.A. GonzalezCalero, ed. (Proceedings of the 7th European Conference, ECCBR 2004, Madrid,Spain, August/September 2004). Lecture Notes in Artificial Intelligence, LNAI3155: Springer.
Abdollahi, J., Carlsen, I.M., Randhol, P. et al. 2008. A Case-BasedApproach To Understand the Complexity of Causal Connections Related to WellIntegrity Problems. Paper SPE 11129 presented at the IADC/SPE DrillingConference, Orlando, Florida, 4-6 March. http://dx.doi.org/10.2118/11129-MS.
Bi, X., Yan, T., Zhang, S. et al. 2005. Knowledge Discovery in DrillingOptimization for Eliminating Surprise. Paper SPE 93187 presented at the SPEAsia Pacific Oil and Gas Conference and Exhibition, Jakarta, 5-7 April. http://dx.doi.org/10.2118/93187-MS.
Bourgoyne Jr., A.T., Chenevert, M.E., Millheim, K. et al. 1986.Applied Drilling Engineering, Richardson: SPE Textbook Series.
Chang, P.C., Liu, C.H., Lin, J.L. et al. 2009. A Neural NetworkWith a Case-Based Dynamic Window for Stock Trading Prediction, ExpertSystems with Applications, Vol. 36.
Connor, J.T., Martin, R.D., and Atlas, L.E. 1994. Recurrent Neural Networksand Robust Time Series Prediction. Neural Networks, IEEE Trans. 5 (2): 240-254.
Corti, M. 1992. Real-Time Expert Systems for Drilling Operations Support.Paper SPE 24 272 presented at the European Petroleum Computer Conference,Stavanger, 24-27 May. http://dx.doi.org/10.2118/24272-MS.
Cramer, R., Krebbers, J., van Oort, E. et al. 2012. Establishing a DigitalOil Field Data Architecture Suitable for Current and Foreseeable BusinessRequirements. Paper SPE 149959 presented at Intelligent Energy International,Utrecht, 27-29, March. http://dx.doi.org/10.2118/149959-MS.
Dashevskiy, D., Macpherson, J.D., Dubinsky, V. et al. 2007. Real-TimeDrilling Optimization Based on MWD Dynamic Measurements—Field Test Results.Paper presented at the AADE Technical Conference.
Fiatech. 2011. An Introduction to ISO 15926. Fiatech, 175 pp.
Giese, M. and Bratvold, R.B. 2010. Probabilistic Modeling for DecisionSupport in Integrated Operations. Paper SPE 127761 presented at the SPEIntelligent Energy Conference and Exhibition, Utrecht, 23-25 March. http://dx.doi.org/10.2118/127761-MS.
Gundersen, O.E., Sørmo, F., Aamodt, A. et al. 2012. A real-timedecision-support system for high cost oil well drilling operations. Associationfor the Advancement of Artificial Intelligence (www.aaai.org).
Halliburton Solving Challenge: http://www.halliburton.com/ps/default.aspx?pageid=3265&navid=1368(assessed 21 November 2012).
Hayatdavoudi, A. and Rahmatian, M. 2010. A Methodology of Root CauseAnalysis of Well Bore Failure and Lost Production Using the Well Information.In Proceedings of the 44th US Rock Mechanics Symposium and 5th USCanada Rock Mechanics Symposium, Salt Lake City, June.
He, H. and Garcia, E.A. 2009. Learning from Imbalanced Data. Knowledgeand Data Engineering, IEEE Trans. 21 (9): 1263-1284.
Hubbard, B.L., Shabib J.K., Crotinger, M.J. et al. 2010. NonproductiveTime (NPT) Reduction Delivered Through Effective Failure Investigations. PaperSPE 128425 presented at the IADC/SPE Drilling Conference and Exhibition, NewOrleans, Louisiana, 2-4 February. http://dx.doi.org/10.2118/128425-MS.
Irgens, M. 2008. The Impending Expertise Crisis: New Technology Comes to theRescue. Paper SPE 116634 presented at the SPE Annual Technical Conference andExhibition, Denver, Colorado, 21-24 September. http://dx.doi.org/10.2118/116634-MS.
Keogh, E. 2004. Data Mining and Machine Learning in Time SeriesDatabases. Tutorial in SIGKDD 2004, http://www.cs.uiuc.edu/class/fa05/cs591han/kdd04/docs/tutorial.htm(assessed 12 February 2012).
Keogh, E. 2011. Machine Learning in Time Series Databases (andEverything Is a Time Series!). Tutorial in AAAI 2011, http://www.cs.ucr.edu/~eamonn/tutorials.html(assessed 7 August 2011).
La Greca, G., Sofia, M., Sparatore, F. et al. 2008. Problem inDiagnosis and Intraoperative Treatment in Case of Rare Peripancreatic Tumors.JOPJ Pancreas (on-line) 9 (6 Suppl.): 821-822.
Rafatian, N., Miska, S., Ledgerwood III, L.W. et al. 2010.Experimental Study of MSE of a Single PDC Cutter Interacting With Rock UnderSimulated Pressurized Conditions. SPE Drill & Compl 25(1).
Rommetveit, R., Ødegård, S.I., Nordstrand, C. et al. 2010. Drilling aChallenging HPHT Well Utilizing an Advanced ECD Management System With DecisionSupport and Real Time Simulations. Paper IADC/SPE 128648 presented at the 2010IADC/SPE Drilling Conference and Exhibition. New Orleans, Louisiana, 2-4February. http://dx.doi.org/10.2118/128648-MS.
Salakhov, T.R., Yamaliev, V.U., and Dubinsky, V. 2010. An Expert SystemApproach to Real-Time Diagnosis of Drill Bit Condition and Preventing ItsDamage. Paper SPE 127371 presented at the SPE Oil and Gas India Conference andExhibition, Mumbai, India, 20-22 January. http://dx.doi.org/10.2118/127371-MS.
Shokouhi, S.V., Aamodt, A., Skalle, P. et al. 2009a. Determine Root Causeof Drilling Problems by Combining Cases and General Knowledge. ICCBR 2009, LNAI5650, 509-523. Berlin: Springer Verlag.
Shokouhi, S.V. and Skalle, P. 2009. Enhancing Decision Making in CriticalDrilling Operations. Paper SPE 120290 presented at the 2009 SPE Middle East Oiland Gas Show and Conference, Bahrain, 15-18 March. http://dx.doi.org/10.2118/120290-MS.
Shokouhi, S.V., Skalle, P., and Aamodt, A. 2009b. Integration of Real-TimeData and Past Experience for Reducing Operational Problems. Paper presented atthe IPTC, Doha, Qatar, 7-9 December.
Shokouhi, S. V., Skalle, P., Aamodt, A. et al. 2009c. DeterminingRoot Causes of Drilling Problems by Combining Cases and General Knowledge.Lecture Notes in Computer Science, 509-523. Berlin: Springer-Verlag,ICCBR2009 Seattle.
Skalle, P. and Aamodt, A. 2004. Knowledge-Based Decision Support in Oil WellDrilling. In Proceedings of the ICIIP 2004, International Conference onIntelligent Information Systems. Beijing, Z. Shi, ed., 21-23 October.
Staab, S. and Studer, R. 2009. Handbook of Ontologies.International Handbooks of Information Systems. Berlin: SpringerVerlag.
Stacey, M., McGregor, C., and Tracy, M. 2007. An Architecture forMulti-Dimensional Temporal Abstraction and Its Application To Support NeonatalIntensive Care. Proceedings of the 29th Annual InternationalConference of the IEEE EMBS, Cité Internationale, Lyon, 23-26 August.
VerdandeTechnology. 2009. Harvesting knowledge to improve drillingperformance in real time; A perspective on lowering NPT in difficult andcritical wells. White paper. (http://www.verdandetechnology.com/images/stories/Verdande/publications/vt_whitepaper.pdf)
Wei, L. and Keogh, E. 2006. Semi-Supervised Time Series Classification, KDD'06. Proceedings of the 12th ACM SIGKDD International Conference onKnowledge Discovery and Data Mining.