Journal Home > Volume 5 , Issue 4
Advances in Geo-Energy Research 2021, 5(4): 386-406 https://doi.org/10.46690/ager.2021.04.05
Original Article | Open Access | Issue | Published: 17 October 2021

Application of mathematical and machine learning models to predict differential pressure of autonomous downhole inflow control devices

Show Author's Information Hossein Yavari1,  Rasool Khosravanian2,  David A. Wood3 ( ),  Bernt Sigve Aadnoy2
Department of Petroleum Engineering, Amirkabir University of Technology, Tehran, Iran
Department of Energy and Petroleum Engineering, University of Stavanger, Stavanger, Norway
DWA Energy Limited, Lincoln, United Kingdom
Keywords:
machine learning, multiple regression, Autonomous inflow control, downhole differential pressure, intelligent non-linear models, optimum viscosity
Cite this article:
Yavari H, Khosravanian R, Wood DA, et al. Application of mathematical and machine learning models to predict differential pressure of autonomous downhole inflow control devices. Advances in Geo-Energy Research, 2021, 5(4): 386-406. https://doi.org/10.46690/ager.2021.04.05
Download citation
EndNote(RIS)
BibTeX

1190

Views

202

Downloads

Citations

11

Crossref

11

WoS

12

Scopus

N/A

CSCD

Abstract Full text Electronic supplementary material About this article

Controlling reservoir fluid flow is important for maximizing petroleum production through wellbores. A major challenge that reduces the production of oil is early breakthrough of secondary fluids to the wellbore perforations. This occurs due to the low viscosity of gas and water relative to oil, and the heterogeneity of reservoir permeability. Autonomous inflow control devices represent a new self-regulating technology that helps to increase petroleum production, particularly oil, by restricting the production of unwanted fluids like gas and water into the wellbores. This study develops smart systems based on machine learning models to predict the performance of autonomous inflow control devices. Several machine learning models are evaluated including adaptive neuro fuzzy inference system, hybrid adaptive neuro-fuzzy inference system genetic algorithm, artificial neural network and support vector machine and their prediction performance is compared to that of linear regression, full quadratic regression model and the mathematical autonomous inflow control device performance model. Each model is developed to estimate the differential pressure of Equiflow autonomous inflow control devices based on ninety experimentally recorded data records. The range of equiflow autonomous inflow control device, viscosity, density and flow rate are the input variables and differential pressure is the output dependent variable of each model. The prediction accuracy of the models is assessed in terms of several standard statistical accuracy performance measures. These performance indicators confirm that the machine-learning models provide superior prediction accuracy for autonomous inflow control device differential pressure. Overall, the support vector machine achieves the most accurate predictions of all the models evaluated recording root mean square error of 0.14 Mpa and coefficient of determination of 0.98. On the other hand, the linear regression model records the lowest prediction performance, highlighting the non-linearity of the autonomous inflow control device processes.


menu
Abstract
Full text
Outline
Electronic supplementary material
About this article

Application of mathematical and machine learning models to predict differential pressure of autonomous downhole inflow control devices

Show Author's information Hossein Yavari1, Rasool Khosravanian2, David A. Wood3 ( ), Bernt Sigve Aadnoy2
Department of Petroleum Engineering, Amirkabir University of Technology, Tehran, Iran
Department of Energy and Petroleum Engineering, University of Stavanger, Stavanger, Norway
DWA Energy Limited, Lincoln, United Kingdom

Abstract

Controlling reservoir fluid flow is important for maximizing petroleum production through wellbores. A major challenge that reduces the production of oil is early breakthrough of secondary fluids to the wellbore perforations. This occurs due to the low viscosity of gas and water relative to oil, and the heterogeneity of reservoir permeability. Autonomous inflow control devices represent a new self-regulating technology that helps to increase petroleum production, particularly oil, by restricting the production of unwanted fluids like gas and water into the wellbores. This study develops smart systems based on machine learning models to predict the performance of autonomous inflow control devices. Several machine learning models are evaluated including adaptive neuro fuzzy inference system, hybrid adaptive neuro-fuzzy inference system genetic algorithm, artificial neural network and support vector machine and their prediction performance is compared to that of linear regression, full quadratic regression model and the mathematical autonomous inflow control device performance model. Each model is developed to estimate the differential pressure of Equiflow autonomous inflow control devices based on ninety experimentally recorded data records. The range of equiflow autonomous inflow control device, viscosity, density and flow rate are the input variables and differential pressure is the output dependent variable of each model. The prediction accuracy of the models is assessed in terms of several standard statistical accuracy performance measures. These performance indicators confirm that the machine-learning models provide superior prediction accuracy for autonomous inflow control device differential pressure. Overall, the support vector machine achieves the most accurate predictions of all the models evaluated recording root mean square error of 0.14 Mpa and coefficient of determination of 0.98. On the other hand, the linear regression model records the lowest prediction performance, highlighting the non-linearity of the autonomous inflow control device processes.

Keywords: machine learning, multiple regression, Autonomous inflow control, downhole differential pressure, intelligent non-linear models, optimum viscosity

References(84)

Aakre, H., Halvorsen, B., Werswick, B., et al. Smart well with autonomous inflow control valve technology. Paper SPE 164348 Presented at Middle East Oil and Gas Show and Conference, Manama, Bahrain, 10-13 March, 2013.
DOI
Aakre, H., Halvorsen, B., Werswick, B., et al. Autonomous inflow control valve for heavy and extra-heavy oil. Paper SPE 71141 Presented at Heavy and Extra Heavy Oil Conference, Latin America, Medellín, Colombia, 24-26 September, 2014.
DOI
Abad, A. R. B., Mousavi, S., Mohamadian, N., et al. Hybrid machine learning algorithms to predict condensate viscosity in the near wellbore regions of gas condensate reservoirs. Journal of Natural Gas Science and Engineering, 2021, 95: 104210.
DOI Google Scholar
Aiken, L. S., West, S. G., Pitts, S. C., et al. Multiple linear regression, in Handbook of Psychology, edited by , J. A. Schinka and W. F. Velicer, Second Edition, John Wiley & Sons, Inc, New York, 2012.
DOI
Al Amrani, Y., Lazaar, M., El Kadiri, K. E. Random forest and support vector machine based hybrid approach to sentiment analysis. Procedia Computer Science, 2018, 127: 511-520.
DOI Google Scholar
Al-Khelaiwi, F. T., Davies, D. R. Inflow control devices: Application and value quantification of a developing technology. Paper SPE 108700 Presented at International Oil Conference and Exhibition in Mexico, Veracruz, Mexico, 27-30 June, 2007.
DOI
Andreas, L., Midttveit, O., Gyllensten, A. J., et al. AICD implementation on oseberg H vestflanken 2. Paper SPE 195617 Presented at SPE One Day Seminar, Bergen, Norway, 14 May, 2019.
Ashrafi, S. B., Anemangely, M., Sabah, M., et al. Application of hybrid artificial neural networks for predicting rate of penetration (ROP): A case study from Marun oil field. Journal of Petroleum Science and Engineering, 2019, 175: 604-623.
DOI Google Scholar
Bao, H., Wang, J., Li, J., et al. Effects of corn straw on dissipation of polycyclic aromatic hydrocarbons and potential application of backpropagation artificial neural network prediction model for PAHs bioremediation. Ecotoxicology and Environmental Safety, 2019, 186: 109745.
DOI Google Scholar
Barbosa, L. F. F., Nascimento, A., Mathias, M. H., et al. Machine learning methods applied to drilling rate of penetration prediction and optimization-A review. Journal of Petroleum Science and Engineering, 2019, 183: 106332.
DOI Google Scholar
Bui, X-N., Muazu, M. A., Nguyen, H. Optimizing Levenberg-Marquardt backpropagation technique in predicting factor of safety of slopes after two-dimensional OptumG2 analysis. Engineering with Computers, 2019, 36: 941-952.
DOI Google Scholar
Burges, C. J. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 1998, 2(2): 121-167.
DOI Google Scholar
Chen, W., Panahi, M., Khosravi, K., et al. Spatial prediction of groundwater potentiality using ANFIS ensembled with teaching-learning-based and biogeography-based optimization. Journal of Hydrology, 2019, 572: 435-448.
DOI Google Scholar
Cheng, L., Wang, D., Cao, R., et al. The influence of hydraulic fractures on oil recovery by water flooding processes in tight oil reservoirs: an experimental and numerical approach. Journal of Petroleum Science and Engineering, 2020, 185: 106572.
DOI Google Scholar
Chochua, G., Rudic, A., Kumar, A., et al. Cyclone type autonomous inflow control device for water and gas control: Simulation-driven design. Paper SPE 192723 Presented at Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, 12-15 November, 2018.
DOI
Ciulla, G., D’Amico, A. Building energy performance forecasting: A multiple linear regression approach. Applied Energy, 2019, 253: 113500.
DOI Google Scholar
Colkesen, I., Sahin, E. K., Kavzoglu, T. Susceptibility mapping of shallow landslides using kernel-based Gaussian process, support vector machines and logistic regression. Journal of African Earth Sciences, 2016, 118: 53-64.
DOI Google Scholar
Deshwal, S., Kumar, A., Chhabra, D. Exercising hybrid statistical tools GA-RSM, GA-ANN and GA-ANFIS to optimize FDM process parameters for tensile strength improvement. CIRP Journal of Manufacturing Science and Technology, 2020, 31: 189-199.
DOI Google Scholar
Ebrahim, S., Mesbah, M., Hajilari, N., et al. ANFIS modeling for prediction of CO2 solubility in potassium and sodium based amino acid salt solutions. Journal of Environmental Chemical Engineering, 2019, 7(1): 102925.
DOI Google Scholar
Ehsanollah, H., Salehi, M., Yadegarfar, G., et al. Optimization of the ANFIS using a genetic algorithm for physical work rate classification. International Journal of Occupational Safety and Ergonomics, 2020, 26(3): 436-443.
DOI Google Scholar
Elkatatny S. Real-time prediction of rate of penetration while drilling complex lithologies using artificial intelligence techniques. Ain Shams Engineering Journal, 2021, 12(1): 917-926.
DOI Google Scholar
Eltaher, E. M. K. Modelling and applications of autonomous flow control devices. Edinburgh, Heriot-Watt University, 2017.
Eltaher, E. Muradov, K., Davies, D., et al. Autonomous flow control device modelling and completion optimization. Journal of Petroleum Science and Engineering, 2019, 17: 995-1009.
DOI Google Scholar
Fripp, M., Zhao, L., Least, B. The theory of a fluidic diode autonomous inflow control device. Paper SPE 167415 Presented at SPE Middle East Intelligent Energy Conference and Exhibition, 28-30 October, 2013.
DOI
Gamal, H., Elkatatny, S., Abdulraheem, A. Rock drillability intelligent prediction for a complex lithology using artificial neural network. Paper SPE 202767 Presented at Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, 9-12 November, 2020.
DOI
Gao, C. H., Rajeswaran, R. T., Nakagawa, E. Y. A literature review on smart well technology. Paper SPE 106011 Presented at Production and Operations Symposium, Oklahoma City, Oklahoma, USA, 31 March-3 April, 2007.
DOI
Ghorbani, H., Wood, D. A., Choubineh, A., et al. Performance comparison of bubble point pressure from oil PVT data: Several neurocomputing techniques compared. Experimental and Computational Multiphase Flow, 2020, 2: 225-246.
DOI Google Scholar
Gimre, J. Efficiency of ICV/ICD systems. Stavanger, University of Stavanger, 2012.
Glandt, C. A. Reservoir management employing smart wells: A review. SPE Drilling & Completion, 2005, 20(4): 281-288.
DOI Google Scholar
Goldberg, D. E., Holland, J. H. Genetic algorithms and machine learning. Machine Learning, 1988, 3: 95-99.
DOI Google Scholar
Gurses, S., Chochua, G., Rudic, A., et al. Dynamic modeling and design optimization of cyclonic autonomous inflow control devices. Paper SPE 193824 Presented at SPE Reservoir Simulation Conference, Galverston, Texas, USA, 10-11 April, 2019.
DOI
Habibi, E., Salehi, M., Yadegarfar, G., et al. Optimization of the ANFIS using a genetic algorithm for physical work rate classification. International Journal of Occupational Safety and Ergonomics, 2020, 26(3): 436-443.
DOI Google Scholar
Halvorsen, M., Elseth, G., Nævdal, O. M. Increased oil production at Troll by autonomous inflow control with RCP valves. Paper SPE 159634 Presented at SPE Annual Technical Conference and Exhibition, San Antonio, Texas, USA, 8-10 October, 2012.
DOI
Hazbeh, O., Aghdam, S. K. Y., Ghorbani, H., et al. Comparison of accuracy and computational performance between the machine learning algorithms for rate of penetration in directional drilling well, Petroleum Research, 2021, 6(3): 271-282.
DOI Google Scholar
Holland, J. H. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. Cambridge, Massachusetts, USA, The MIT Press, 1992b.
DOI
Holland, J. H. Genetic algorithms. Scientific American, 1992a, 267(1): 44-50.
DOI Google Scholar
Huang, Y., Zhao, L. Review on landslide susceptibility mapping using support vector machines. Catena, 2018, 165: 520-529.
DOI Google Scholar
Iqbal, F., Iskandar, R., Radwan, E., et al. Autonomous inflow control device-a case study of first successful field trial in GCC for water conformance. Paper SPE 177927 Presented at Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, UAE, 9-12 November, 2015.
DOI
Javad, G., Narges, T. Application of artificial neural networks to the prediction of tunnel boring machine penetration rate. Mining Science and Technology, 2010, 20(5): 727-733.
DOI Google Scholar
Jia, C. Breakthrough and significance of unconventional oil and gas to classical petroleum geology theory. Petroleum Exploration and Development, 2017, 44(1): 1-10.
DOI Google Scholar
Jovanov, I. Performance of autonomous inflow control systems. Stavanger, University of Stavanger, 2016.
Jovic, S., Anicic, O., Pejovic, B. Management of the wind speed data using adaptive neuro-fuzzy methodology. Flow Measurement and Instrumentation, 2016, 50: 201-208.
DOI Google Scholar
Khademi, F., Akbari, M., Jamal, S. M., et al. Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28 days compressive strength of concrete. Frontiers of Structural and Civil Engineering, 2017 11(1): 90-99.
DOI Google Scholar
Kumar, R., Hynes, N. R. J. Prediction and optimization of surface roughness in thermal drilling using integrated ANFIS and GA approach. Engineering Science and Technology, 2020, 23(1): 30-41.
DOI Google Scholar
Kumar, V., Kumar, A., Chhabra, D., et al. Improved biobleaching of mixed hardwood pulp and process optimization using novel GA-ANN and GA-ANFIS hybrid statistical tools. Bioresource technology, 2019, 271: 274-282.
DOI Google Scholar
Lauritzen, J. E., Martiniussen, I. B. Single and multi-phase flow loop testing results for industry standard inflow control devices. Paper SPE 146347 Presented at SPE Offshore Europe Oil and Gas Conference and Exhibition, Aberdeen, UK, 6-8 September, 2011.
DOI
Least, B., Greci, S., Burkey, R. C., et al. Autonomous ICD single phase testing. Paper SPE 160165 Presented st SPE Annual Technical Conference and Exhibition, San Antonio, Texas, USA, 8-10 October, 2012.
DOI
Lei, Q., Jackson, M. D., Muggeridge, A. H., et al. Modelling the reservoir-to-tubing pressure drop imposed by multiple autonomous inflow control devices installed in a single completion joint in a horizontal well. Journal of Petroleum Science and Engineering, 2020, 189: 106991.
DOI Google Scholar
Mardanirad, S., Wood, D. A., Zakeri, H. The application of deep learning algorithms to classify subsurface drilling lost circulation severity in large oil field datasets. SN Applied Sciences, 2021, 3: 785.
DOI Google Scholar
Mathiesen, V., Werswick, B., Aakre, H., et al. The Autonomous RCP valve - new technology for inflow control in horizontal wells autonomous valve. Paper SPE 145737 Presented at SPE Offshore Europe Oil and Gas Conference and Exhibition, Aberdeen, UK, September 6-8, 2011.
DOI
Mathur, N., Glesk, I., Buis, A. Comparison of adaptive neuro-fuzzy inference system (ANFIS) and Gaussian processes for machine learning (GPML) algorithms for the prediction of skin temperature in lower limb prostheses. Medical Engineering & Physics, 2016, 38(10): 1083-1089.
DOI Google Scholar
Mehrotra, K., Mohan, C. K., Ranka, S. Elements of Artificial Neural Networks, Cambridge, Massachusetts, USA, The MIT Press, 1997.
DOI
Mehrad, M., Bajolvand, M., Ramezanzadeh, A., et al. Developing a new rigorous drilling rate prediction model using a machine learning technique. Journal of Petroleum Science and Engineering, 2020, 192: 107338.
DOI Google Scholar
Mikkelsen, J. K., Norheim, T., Sagatun, S. The Troll story. Paper SPE 171108 Presented at the Offshore Technology Conference, Houston, Texas, 2-5 May, 2005.
DOI
Mitchell, M. An Introduction to Genetic Algorithms. Cambridge, Massachusetts, USA, The MIT Press, 1996.
Moazzeni, A. R., Khamehchi, E. Rain optimization algorithm (ROA): A new metaheuristic method for drilling optimization solutions. Journal of Petroleum Science and Engineering, 2020, 195: 107512.
DOI Google Scholar
Mohamadian, N., Ghorbani, H., Wood, D. A., et al. A geomechanical approach to casing collapse prediction in oil and gas wells aided by machine learning. Journal of Petroleum Science and Engineering, 2021, 196: 107811.
DOI Google Scholar
Moraveji, M. K., Naderi, M. Drilling rate of penetration prediction and optimization using response surface methodology and bat algorithm. Journal of Natural Gas Science and Engineering, 2016, 31: 829-841.
DOI Google Scholar
Nathans, L. L., Oswald, F. L., Nimon, K. Interpreting multiple linear regression: A guidebook of variable importance. Practical Assessment, Research, and Evaluation, 2012, 17(9): 1-19.
Google Scholar
Ossai, C. I., Duru, U. I. Applications and theoretical perspectives of artificial intelligence in the rate of penetration. Petroleum, 2020, in Press, .
DOI Google Scholar
Pedroso, C. A., Latini, C., Araujo, Z., et al. First open-hole gravel pack with aicd in ultra deep water, (2020). Paper SPE 199325 Presented at SPE International Conference and Exhibition on Formation Damage Control, Lafayette, Louisiana, USA, 19-21 February, 2020.
DOI
Pham, B. T., Bui, D. T., Prakash, I. Bagging based support vector machines for spatial prediction of landslides. Environmental Earth Sciences, 2018, 77(4): 146.
DOI Google Scholar
Porturas, F. Enhanced production with ICD and AICD completions in oil wells: Case studies from Latin America. Paper SPE 181204 Presented at SPE Latin America and Caribbean Heavy and Extra Heavy Oil Conference, Lima, Peru, 19-20 October, 2016.
DOI
Rabiei, A., Sayyad, H., Riazi, M., et al. Determination of dew point pressure in gas condensate reservoirs based on a hybrid neural genetic algorithm. Fluid Phase Equilibria, 2015, 387: 38-49.
DOI Google Scholar
Rahul, M., Narinder, S., Yaduvir, S. Genetic Algorithms: Concepts, design for optimization of process controller. Computer and Information Science, 2011, 4(2): 39-54.
DOI Google Scholar
Rashid, S., Ghamartale, A., Abbasi, J., et al. Prediction of critical multiphase flow through chokes by using A rigorous artificial neural network method. Flow Measurement and Instrumentation, 2019, 69: 101579.
DOI Google Scholar
Sabah, M., Talebkeikhah, M., Wood, D. A., et al. A machine learning approach to predict drilling rate using petrophysical and mud logging data. Earth Science Informatics, 2019, 12: 319-339.
DOI Google Scholar
Sadrmomtazi, A., Sobhani, J., Mirgozar, M. A. Modeling compressive strength of EPS lightweight concrete using regression, neural network and ANFIS. Construction and Building Materials, 2013, 42: 205-216.
DOI Google Scholar
Sekki, T., Airaksinen, M., Saari, A. Impact of building usage and occupancy on energy consumption in Finnish daycare and school buildings. Energy and Buildings, 2015, 105: 247-257.
DOI Google Scholar
Shahin, M. A., Jaksa, M. B., Maier, H. R. Artificial neural network applications in geotechnical engineering. Australian Geomechanics, 2020, 36(1): 49-62.
Google Scholar
Somehsaraei, H. N., Hölle, M., Hönen H. A novel approach based on artificial neural network for calibration of multi-hole pressure probes. Flow Measurement and Instrumentation, 2020, 73: 101739.
DOI Google Scholar
Soroush, E., Mesbah, M., Hajilary, N., et al. ANFIS modeling for prediction of CO2 solubility in potassium and sodium based amino acid Salt solutions. Journal of Environmental Chemical Engineering, 2019, 7(1): 102925.
DOI Google Scholar
Sugeno, M., Kang, G. T. Structure identification of fuzzy model. Fuzzy Sets and Systems, 1988, 28(1): 15-33.
DOI Google Scholar
Sun, W., Huang, C. A carbon price prediction model based on secondary decomposition algorithm and optimized back propagation neural network. Journal of Cleaner Production, 2020, 243: 118671.
DOI Google Scholar
Tang, J-S. R. ANFIS: adaptive network based fuzzy inference systems. IEEE Transactions on Systems, Man, and Cybernetics, 1993, 23: 515-520.
DOI Google Scholar
Vapnik, V. N. The Nature of Statistical Learning Theory. Springer-Verlag, New York, USA, 1995.
DOI
Velez-Langs, O. Genetic algorithms in oil industry: An overview. Journal of petroleum Science and Engineering, 2005, 47(1-2): 15-22.
DOI Google Scholar
Vickers, N. J. Animal communication: When i’m calling you, will you answer too? Current Biology, 2017, 27(14): R713-R715.
DOI Google Scholar
Wood, D. A. A transparent open-box learning network provides insight to complex systems and a performance benchmark for more-opaque machine learning algorithms. Advances in Geo-Energy Research, 2018, 2(2): 148-162.
DOI Google Scholar
Yavari, Y., Sabah, M., Khosravanian, R., et al. Application of an adaptive neuro-fuzzy inference system and mathematical rate of penetration models to predicting drilling rate. Iranian Journal of Oil and Gas Science and Technology, 2018, 7(3): 73-100.
Google Scholar
Yilmaz, I., Kaynar, O. Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Expert Systems with Applications, 2011, 38(5): 5958-5966.
DOI Google Scholar
Zhang, N., Li, H., Liu, Y., et al. A new autonomous inflow control device designed for a loose sand oil reservoir with bottom water. Journal of Petroleum Science and Engineering, 2019, 178: 334-355.
DOI Google Scholar
Zhao, L., Least, B., Greci, S., et al. Fluidic diode autonomous ICD range 2A single-phase testing. Paper SPE 170993 Presented as SPE Oilfield Water Management Conference and Exhibition, Kuwait City, Kuwait, 21-22 April, 2014.
DOI
Zhao, X., Zhou, L., Pu, X., et al. Exploration breakthroughs and geological characteristics of continental shale oil: A case study of the Kongdian Formation in the Cangdong Sag, China. Marine and Petroleum Geology, 2019, 102: 544-556.
DOI Google Scholar
File
2207-9963-2021-4-386-S001.pdf (31.7 KB)
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 25 September 2021
Revised: 15 October 2021
Accepted: 15 October 2021
Published: 17 October 2021
Issue date: December 2021

Copyright

© The Author(s) 2021.

Acknowledgements

The authors thank their respective institutions for supporting this research.

Rights and permissions

This article is distributed under the terms and conditions of the Creative Commons Attribution (CC BY-NC-ND) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Return