Developing ultrasonic soft sensors to measure rheological properties of non-Newtonian drilling fluids
-
Morten Hansen Jondahl
Morten Hansen Jondahl received the M.Sc. degree in Earth Sciences and Petroleum Engineering from Norwegian University of Science and Technology, Trondheim, Norway, in 2011. Part of this degree was completed as an exchange program at Colorado School of Mines, Golden, CO, USA. He was a graduate well engineer at Statoil, Stavanger, Norway from 2011 to 2012. He then joined Halliburton, Stavanger, Norway as an M/LWD Field engineer from 2012 till 2015. After a short tenure as substitute teacher at Skien high school from 2015 to 2016, he started pursuing his Ph.D. degree at University of South-Eastern Norway, Porsgrunn, Norway. His current research field includes drilling operations, sensor systems, sensor data fusion, machine learning and ultrasonic sensor applications.
and
Håkon Viumdal
Håkon received his B.S in optometry from Buskerud University College (Norway) in 1999, and his M.Sc. in cybernetics from Telemark University College in 2007. In his master thesis system identification methods where utilized to estimate water level in oil-water-gas separators. Level estimation using empirical models was also the main topic in his PhD-work carried out in collaboration between Tel-Tek, Telemark University College, Norwegian University of Science and Technology and Hydro Aluminium, Årdal. In addition to level estimation in aluminium electrolysis cells, his R&D work focused on measuring the same level using ultrasonic measurement in combination with wave guiding buffer rods. He finished his PhD in 2015. Since 2011 he has given lectures in physics, mathematics and sensor technology at Telemark University College. Currently he is an Associate Professor at The University of South-Eastern Norway, where he is program administrator for the M.Sc programme “Industrial IT and Automation” as well as an assistant project leader for a project with the topic “Sensors and models for improved kick/loss detection in drilling (Semi-kidd, Project No. 255348/E30)”. The project involved four PhD-students, supported by National R esearch Council of Norway and Equinor.
Abstract
Surveillance of the rheological properties of drilling fluids is crucial when drilling oil wells. The prevailing standard is lab analysis. The need for automated real-time measurements is, however, clear.
Ultrasonic measurements in non-Newtonian fluids have been shown to exhibit a non-linear relationship between the acoustic attenuation and rheological properties of the fluids. In this paper, three different fluid systems are examined. They are diluted to give a total of 33 fluid sets and their ultrasonic and rheological properties are measured. Machine learning models are applied to develop soft sensors that are capable of estimating the rheological properties based on the ultrasonic measurements. This study explores three different machine learning model types and, extensive training and tuning of the models is carried out. The best model types that show good results and the potential to develop a real-time sensor system suitable for use in oil & gas drilling process automation are selected.
Zusammenfassung
Die Überwachung der rheologischen Eigenschaften von Bohrflüssigkeiten ist bei der Erdölexploration von entscheidender Bedeutung. Der derzeit vorherrschende Standard ist die chemische Laboranalyse. Es besteht aber der Bedarf nach einer automatisierter Echtzeitmessung. In nicht-newtonschen Flüssigkeiten besteht eine nicht-lineare Beziehung zwischen der Schallabsorption und den rheologischen Eigenschaften der Flüssigkeit. In dieser Arbeit werden drei verschiedene Systeme von Bohrflüssigkeiten, aus denen 33 unterschiedlich zusammengesetzte Mischungen hergestellt wurden, hinsichtlich ihrer Ultraschall- und rheologischen Eigenschaften untersucht. Mithilfe von Modellen für maschinelles Lernen werden virtuelle Sensoren entwickelt, mit denen die rheologischen Eigenschaften auf der Grundlage von Ultraschallmessungen abgeschätzt werden können. Diese Studie vergleicht drei verschiedene Methoden des maschinellen Lernens hinsichtlich ihrer Eignung, in einem Echtzeit-Sensorsystem bei der Automatisierung von Öl- und Gasbohrprozessen eingesetzt zu werden.
Funding source: Norges Forskningsråd
Award Identifier / Grant number: 255348/E30
Funding statement: Economic support from Research Council of Norway and Equinor ASA through project no. 255348/E30 “Sensors and models for improved kick/loss detection in drilling (Semi-kidd)” is gratefully acknowledged.
About the authors
Morten Hansen Jondahl received the M.Sc. degree in Earth Sciences and Petroleum Engineering from Norwegian University of Science and Technology, Trondheim, Norway, in 2011. Part of this degree was completed as an exchange program at Colorado School of Mines, Golden, CO, USA. He was a graduate well engineer at Statoil, Stavanger, Norway from 2011 to 2012. He then joined Halliburton, Stavanger, Norway as an M/LWD Field engineer from 2012 till 2015. After a short tenure as substitute teacher at Skien high school from 2015 to 2016, he started pursuing his Ph.D. degree at University of South-Eastern Norway, Porsgrunn, Norway. His current research field includes drilling operations, sensor systems, sensor data fusion, machine learning and ultrasonic sensor applications.
Håkon received his B.S in optometry from Buskerud University College (Norway) in 1999, and his M.Sc. in cybernetics from Telemark University College in 2007. In his master thesis system identification methods where utilized to estimate water level in oil-water-gas separators. Level estimation using empirical models was also the main topic in his PhD-work carried out in collaboration between Tel-Tek, Telemark University College, Norwegian University of Science and Technology and Hydro Aluminium, Årdal. In addition to level estimation in aluminium electrolysis cells, his R&D work focused on measuring the same level using ultrasonic measurement in combination with wave guiding buffer rods. He finished his PhD in 2015. Since 2011 he has given lectures in physics, mathematics and sensor technology at Telemark University College. Currently he is an Associate Professor at The University of South-Eastern Norway, where he is program administrator for the M.Sc programme “Industrial IT and Automation” as well as an assistant project leader for a project with the topic “Sensors and models for improved kick/loss detection in drilling (Semi-kidd, Project No. 255348/E30)”. The project involved four PhD-students, supported by National R esearch Council of Norway and Equinor.
Acknowledgment
The authors would like to thank MSc students K. Mozie and M. Hafredal for their experimental planning and execution. Cooperation with Equinor’s multiphase test facility personell has been invaluable.
References
1. A. S. Dukhin and P. J. Goetz, Characterization of Liquids, Nano- and Microparticulates, and Porous Bodies using Ultrasound. Elsevier, 2002.Search in Google Scholar
2. A. T. Bourgoyne, K. K. Millheim, M. E. Chenevert, and F. S. Young, Jr., Applied Drilling Engineering, 1st ed., vol. 2. Richardson, TX, USA: Society of Petroleum Engineers, 1985.10.2118/9781555630010Search in Google Scholar
3. “Deep water: the Gulf oil disaster and the future of offshore drilling: report to the President,” National Commission on the BP Deepwater Horizon Oil Spill and Offshore Drilling, Washington, D.C., Report to the President, 2011.Search in Google Scholar
4. J. J. Orban, K. J. Zanner, and A. E. Orban, “New Flowmeters for Kick and Loss Detection During Drilling,” presented at the SPE Annual Technical Conference and Exhibition, 1987.10.2118/16665-MSSearch in Google Scholar
5. J. M. Speers and G. F. Gehrig, “Delta Flow: An Accurate, Reliable System for Detecting Kicks and Loss of Circulation During Drilling,” SPE Drilling Engineering, vol. 2, no. 04, pp. 359–363, Dec. 1987.10.2118/13496-PASearch in Google Scholar
6. D. M. Schafer, G. E. Loeppke, D. A. Glowka, D. D. Scott, and E. K. Wright, “An Evaluation of Flowmeters for the Detection of Kicks and Lost Circulation During Drilling,” presented at the SPE/IADC Drilling Conference, 18–21 February, SPE, 1992.10.2118/23935-MSSearch in Google Scholar
7. J. D. Brakel, B. A. Tarr, W. Cox, F. Jørgensen, and H. V. Straume, “SMART Kick Detection; First Step on the Well Control Automation Journey,” presented at the SPE/IADC Drilling Conference and Exhibition, 2015.10.2118/173052-MSSearch in Google Scholar
8. K. Chhantyal, M. H. Jondahl, H. Viumdal, and S. Mylvaganam, “Upstream Ultrasonic Level Based Soft Sensing of Volumetric Flow of Non-Newtonian Fluids in Open Venturi Channels,” IEEE Sensors Journal, vol. 18, no. 12, pp. 5002–5013, Jun. 2018.10.1109/JSEN.2018.2831445Search in Google Scholar
9. A. L. Podio and R. L. Gregory, “Ultrasonic Velocity and Attenuation Measurements in Water-Based Drilling Muds,” in Drilling Technology Symposium 1990: presented at the Thirteenth Annual Energy-Sources Technology Conference and Exhibition, New Orleans, Louisiana, January 14–18, 1990, New York, N.Y: American Society of Mechanical Engineers, 1990, vol. 27.Search in Google Scholar
10. N. G. Pope, D. K. Veirs, T. N. Claytor, and M. B. Histand, “Fluid density and concentration measurement using noninvasive in situ ultrasonic resonance interferometry,” in IEEE 1992 Ultrasonics Symposium Proceedings, 1992, pp. 855–858, vol. 2.10.1109/ULTSYM.1992.275863Search in Google Scholar
11. R. A. Pappas, J. A. Bamberger, L. J. Bond, M. S. Greenwood, P. D. Panetta, and D. M. Pfund, “Ultrasonic methods for characterization of liquids and slurries,” in 2001 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No. 01CH37263), 2001, pp. 563–566, vol. 1.10.1109/ULTSYM.2001.991685Search in Google Scholar
12. M. S. Greenwood and J. A. Bamberger, “Ultrasonic sensor to measure the density of a liquid or slurry during pipeline transport,” Ultrasonics, vol. 40, no. 1, pp. 413–417, May 2002.10.1016/S0041-624X(02)00153-1Search in Google Scholar PubMed
13. M. S. Greenwood and J. A. Bamberger, “Measurement of viscosity and shear wave velocity of a liquid or slurry for on-line process control,” Ultrasonics, vol. 39, no. 9, pp. 623–630, Aug. 2002.10.1016/S0041-624X(02)00372-4Search in Google Scholar PubMed
14. A. H. Harker and J. A. G. Temple, “Velocity and attenuation of ultrasound in suspensions of particles in fluids,” J. Phys. D: Appl. Phys., vol. 21, no. 11, p. 1576, 1988.10.1088/0022-3727/21/11/006Search in Google Scholar
15. A. J. Hayman, “Ultrasonic properties of oil-well drilling muds,” in Proceedings., IEEE Ultrasonics Symposium, 1989, pp. 327–332 vol. 1.10.1109/ULTSYM.1989.67003Search in Google Scholar
16. K. N. Mozie, “Characterization of Ultrasonic Waves in Various Drilling Fluids,” M.S., University College of Southeast Norway, Porsgrunn, Norway, 2017.Search in Google Scholar
17. M. H. Jondahl, H. Viumdal, K. N. Mozie, and S. Mylvaganam, “Rheological characterization of non-Newtonian drilling fluids with non-invasive ultrasonic interrogation,” in 2017 IEEE International Ultrasonics Symposium (IUS), 2017, pp. 1–4.10.1109/ULTSYM.2017.8092555Search in Google Scholar
18. “Immersion Transducers.” [Online]. Available: https://www.olympus-ims.com/en/ultrasonic-transducers/immersion/#%21cms%5Btab%5D=%2Fpanametrics-ndt-ultrasonic%2Fimmersion%2Flarge-diameter. [Accessed: 02-May-2019].Search in Google Scholar
19. “EPOCH 1000 Ultrasonic Flaw Detector.” [Online]. Available: https://www.olympus-ims.com/en/ut-flaw/epoch1000/#%21cms%5Btab%5D=%2Fut-flaw%2Fepoch1000%2Fresources. [Accessed: 03-May-2019].Search in Google Scholar
20. R. Caenn, H. C. H. Darley, and G. R. Gray, Composition and Properties of Drilling and Completion Fluids. Saint Louis, United States: Elsevier Science & Technology, 2011.Search in Google Scholar
21. API, “API RP 13B-2 Recommended Practice for Field Testing of Oil-based Drilling Fluids.” API, 2014.Search in Google Scholar
22. M. H. Jondahl and H. Viumdal, “Estimating Rheological Properties of Non-Newtonian Drilling Fluids using Ultrasonic-Through-Transmission combined with Machine Learning Methods,” in 2018 IEEE International Ultrasonics Symposium (IUS), 2018, pp. 1–4.10.1109/ULTSYM.2018.8579796Search in Google Scholar
23. M. Hafredal, “Characterization of rheological properties of drilling fluids using ultrasonic waves,” M.S., University of South-Eastern Norway, Porsgrunn, Norway, 2018.Search in Google Scholar
24. NORSOK Standard, “Drilling facilities. Edition 3, December 2012.” NORSOK, Dec-2012.Search in Google Scholar
25. S. Haykin, Neural networks and learning machines, 3rd ed. Upper Saddle River, N.J: Pearson, 2009.Search in Google Scholar
26. Nazmul Siddique, Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing. Hoboken: Wiley, 2013.10.1002/9781118534823Search in Google Scholar
27. “Process matrices by mapping row minimum and maximum values to [−1 1] – MATLAB mapminmax – MathWorks Nordic.” [Online]. Available: https://se.mathworks.com/help/deeplearning/ref/mapminmax.html?searchHighlight=mapminmax&s_tid=doc_srchtitle. [Accessed: 14-Dec-2018].Search in Google Scholar
28. “Choose a Multilayer Neural Network Training Function – MATLAB & Simulink – MathWorks Nordic.” [Online]. Available: https://se.mathworks.com/help/deeplearning/ug/choose-a-multilayer-neural-network-training-function.html. [Accessed: 14-Dec-2018].Search in Google Scholar
29. W. S. Noble, “What is a support vector machine?,” Nature Biotechnology, vol. 24, no. 12, pp. 1565–1567, Dec. 2006.10.1038/nbt1206-1565Search in Google Scholar PubMed
30. “Understanding Support Vector Machine Regression – MATLAB & Simulink – MathWorks Nordic.” [Online]. Available: https://se.mathworks.com/help/stats/understanding-support-vector-machine-regression.html. [Accessed: 18-Oct-2018].Search in Google Scholar
31. “Fit a support vector machine regression model – MATLAB fitrsvm – MathWorks Nordic.” [Online]. Available: https://se.mathworks.com/help/stats/fitrsvm.html. [Accessed: 14-Dec-2018].Search in Google Scholar
32. J.-R. Jang and C.-T. Sun, “Neuro-fuzzy modeling and control,” Proceedings of the IEEE, vol. 83, no. 3, pp. 378–406, Mar. 1995.10.1109/5.364486Search in Google Scholar
33. “Neuro-Adaptive Learning and ANFIS – MATLAB & Simulink – MathWorks Nordic.” [Online]. Available: https://se.mathworks.com/help/fuzzy/neuro-adaptive-learning-and-anfis.html. [Accessed: 05-Nov-2018].Search in Google Scholar
34. Wikimedia Commons (2008). Figure 1. Taken from: https://commons.wikimedia.org/wiki/File:Oil_Rig_NT8.jpg.Search in Google Scholar
© 2019 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Beiträge
- Konzeptionierung einer Totlastanlage zur Darstellung der Kraft auf Basis der Messunsicherheitsbetrachtung
- Developing ultrasonic soft sensors to measure rheological properties of non-Newtonian drilling fluids
- Reconstruction of multispectral images from spectrally coded light fields of flat scenes
- Herausforderungen der Temperaturmessung während des Rührreibschweißprozesses
- Testing normality
Articles in the same Issue
- Frontmatter
- Beiträge
- Konzeptionierung einer Totlastanlage zur Darstellung der Kraft auf Basis der Messunsicherheitsbetrachtung
- Developing ultrasonic soft sensors to measure rheological properties of non-Newtonian drilling fluids
- Reconstruction of multispectral images from spectrally coded light fields of flat scenes
- Herausforderungen der Temperaturmessung während des Rührreibschweißprozesses
- Testing normality
