Intelligent Prediction of Differential Pipe Sticking by Support Vector Machine Compared With Conventional Artificial Neural Networks: An Example of Iranian Offshore Oil Fields
- Reza Jahanbakhshi (Islamic Azad University) | Reza Keshavarzi (Islamic Azad University) | Mahdi Aliyari Shoorehdeli (K.N.Toosi University of Technology) | Abolqasem Emamzadeh (Islamic Azad University)
- Document ID
- Society of Petroleum Engineers
- SPE Drilling & Completion
- Publication Date
- December 2012
- Document Type
- Journal Paper
- 586 - 595
- 2012. Society of Petroleum Engineers
- 1.11 Drilling Fluids and Materials, 1.6 Drilling Operations, 1.10.1 Drill string components and drilling tools (tubulars, jars, subs, stabilisers, reamers, etc), 1.11.2 Drilling Fluid Selection and Formulation (Chemistry, Properties), 1.6.1 Drilling Operation Management, 4.1.2 Separation and Treating
- 4 in the last 30 days
- 621 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 10.00|
|SPE Non-Member Price:||USD 30.00|
Differential pipe sticking (DPS) is one of the most conventional and serious problems in drilling operations that imposes some extra costs to companies. This phenomenon originates mainly from improper mud properties, bottomhole assembly (BHA) (contacting area), still pipe time, and differential pressure between the formation and the drilling mud. Investigation on various conditions that lead to DPS makes it possible to develop some preventive treatments to avoid this problem's occurrence. In the past, statistical methods were applied in this area, but recently artificial neural network (ANN) approaches are frequently being used. ANNs have some priorities over conventional statistical methods such as the model-free form of predictions, tolerance to data errors, data-driven nature, and fast computation. On the other hand, the designed ANNs have some shortcomings and restrictions as they are developed to predict problems. In this paper, to solve most of the existing disadvantages of ANNs, a novel support-vector machine (SVM) approach has been developed to predict a DPS occurrence in horizontal and sidetracked wells in Iranian offshore oil fields. The results from the analysis have shown the potential of the SVM and ANNs to predict DPS, with the SVM results being more promising.
|File Size||403 KB||Number of Pages||10|
Ali, J. K. 1994. Neural Networks: A New Tool for the Petroleum Industry?Paper SPE 27561 presented at the European Petroleum Computer Conference,Aberdeen, U.K., 15-17 March. http://dx.doi.org/10.2118/27561-MS.
Batyrshin, I., Sheremetov, L., Markov, M. et al 2005. Hybrid Method forPorosity Classification in Carbonate Formations. J. Pet. Sci. & Eng. 47 (1-2): 35-50. http://dx.doi.org/10.1016/j.petrol.2004.11.005.
Centilmen, A., Ertekin, T., and Grader, A. S. 1999. Applications ofNeural-Networks in Multi-well Field Development. Paper SPE 56433 presented atthe SPE Annual Technical Conference and Exhibition, Houston, Texas, 3-6October. http://dx.doi.org/10.2118/56433-MS.
Cortes, C. and Vapnik, V. 1995. Support Vector Networks. MachineLearning 20: 273-297.
Demuth, H. and Beale, M. 1998. Neural network toolbox for use with MATLAB.In User's Guide, Fifth Printing, Version 3. Natick, Massachusetts:Mathworks, Inc.
El-Sebakhy, E. A. 2009. Forecasting PVT Properties of Crude Oil SystemsBased on Support Vector Machines Modeling Scheme. J. Pet. Sci. &Eng. 64 (1-4): 25-34. http://dx.doi.org/10.1016/j.petrol.2008.12.006.
Fawcett, T. 2006. An Introduction to ROC Analysis. Pattern RecognitionLetters J. 27 (8): 861-874. http://dx.doi.org./10.1016/j.patrec.2005.10.010.
Hagan, M.T., Demuth, H.B., and M. H., Beale. 1995. Neural NetworkDesign. Boston, Massachusetts: PWS Publishing Company.
Haykin, S. 1998. Neural Networks, a Comprehensive Foundation. UpperSaddle River, New Jersey: Prentice Hall.
Jahanbakhshi, R., Keshavarzi, R., and Azinfar, M. J. 2011. IntelligentPrediction of Uniaxial Compressive Strength for Sandstone. Paper ARMA 11-189presented at the 45th U.S. Rock Mechanics/Geomechanics Symposium, SanFrancisco, California, 26-29 June.
Konyuhov, A.I., and Maleki, B. 2006. The Persian Gulf Basin: GeologicalHistory, Sedimentary Formations, and Petroleum Potential. Lithology andMineral Resources 41 (4): 344-361. http://dx.doi.org/10.1134/S0024490206040055.
Malallah, A., and Nashawi, I. S. 2005. Estimating the Fracture GradientCoefficient Using Neural Networks for a Field in the Middle East. J. Pet.Sci. & Eng. 49 (3-4): 193-211. http://dx.doi.org/10.1016/j.petrol.2005.05.006.
Miri, R., Sampaio, J., Afshar, M. et al. 2007. Development of ArtificialNeural Networks To Predict Differential Pipe Sticking In Iranian Offshore OilFields. Paper SPE 108500 presented at the International Oil Conference andExhibition in Mexico, Veracruz, Mexico, 27-30 June. http://dx.doi.org/10.2118/108500-MS.
Minoux, M. 1986. Mathematical Programming: Theory and Algorithms. NewYork, New York: John Wiley and Sons.
Murillo, A., Neuman, J., and Samuel, R. 2009. Pipe Sticking Prediction andAvoidance Using Adaptive Fuzzy Logic Modeling. Paper SPE 120128 presented atthe SPE Production and Operations Symposium, Oklahoma City, Oklahoma, 4-8April. http://dx.doi.org./10.2118/120128-MS.
Rabia, H. 1985. Oilwell Drilling Engineering: Principles andPractice. Gaithersburg, Maryland: Graham & Trotman.
Reid, P.I., Meeten, G.H., Way, P.W. et al. 2000. Differential-StickingMechanisms and a Simple Wellsite Test for Monitoring and Optimizing DrillingMud Properties. SPE Drill & Compl 15 (2): 97-104. http://dx.doi.org./10.2118/64114-PA.
Rychetsky, M. 2001. Algorithms and Architectures for Machine LearningBased on Regularized Neural Networks and Support Vector Approaches. Berlin,Germany: Shaker Verlag Gmbh.
Salehi, S., Hareland, G., Dehkordi, K. H. et al. 2009. Casing Collapse RiskAssessment and Depth Prediction with a Neural Network System Approach. J.Pet. Sci. & Eng 69 (1-2): 156-162. http://dx.doi.org/10.1016/j.petrol.2009.08.011.
Santos, H. 2000. Differentially Stuck Pipe: Early Diagnostic and Solution.Paper SPE 59127 presented at the IADC/SPE Drilling Conference, New Orleans,Louisiana, 23-25 February. http://dx.doi.org/10.2118/59127-MS.
Siruvuri, C., Nagarakanti, S., and Samuel, R.. 2006. Stuck Pipe Predictionand Avoidance: A Convolution Neural Network Approach. Paper SPE 98378 presentedat the IADC/SPE Drilling Conference, Miami, Florida, 21-23 February. http://dx.doi.org/10.2118/98378.
Smola, A.J., and Schölkopf, B.. 1998. On a Kernel-Based Method for PatternRecognition, Regression, Approximation, and Operator Inversion.Algorithmica 22: 211-231.
Taylor, J.R. 1999. An Introduction to Error Analysis: The Study ofUncertainties in Physical Measurements, 128-129. Sausalito, California:University Science Books.
Vapnik, V. 1999. The Nature of Statistical Learning Theory. New York,New York: Springer-Verlag.
Vapnik, V. 1998. Statistical Learning Theory. New York, New York:John Wiley & Sons.
Velez-Langs, O. 2005. Genetic Algorithms in Oil Industry: An Overview. J.Pet. Sci. & Eng. 47 (1-2): 15-22. http://dx.doi.org/10.1016/j.petrol.2004.11.006.
Wang, W. J., Men, C. Q., and Lu, W. Z. 2008. Online Prediction Model Basedon Support Vector Machine. NeuroComputing 71 (4-6): 550-558. http://dx.doi.org/10.1016/j.neucom.2007.07.020.