Advertisement

Development of a new rate of penetration model using self-adaptive differential evolution-artificial neural network

  • Salaheldin ElkatatnyEmail author
Original Paper
  • 45 Downloads

Abstract

The rate of penetration (ROP) is one of the key factors that affect the drilling costs. Optimizing the ROP is a big challenge as it depends on many factors such as revolutions per minute (RPM), weight on bit (WOB), torque (T), horsepower (HP), and uniaxial compressive strength (UCS) of the drilled rocks. In addition, drilling fluid properties have a major effect on ROP. The main goal of this study is to develop a new ROP model using an artificial neural network (ANN) combined with the self-adaptive differential evaluation (SaDE) technique. The model was built using different drilling mechanical parameters and drilling fluid properties. A new ROP empirical correlation was developed by extracting the weights and biases of the optimized SaDE-ANN model. The optimized ANN architecture based on SaDE is 5-30-1, where five input parameters were used in the input layers to predict the ROP which are drilling fluid density to plastic viscosity ratio, RPM, WOB/D, T/UCS, and HP. The optimized number of neurons was 30 and the output layer consists of one output parameter which is ROP. The data was divided into 60% training and 40% testing. The developed ROP model based on SaDE-ANN showed high accuracy where the correlation coefficient (R) was 0.98 and the average absolute percentage error (AAPE) was 5%. The new ROP empirical correlation outperformed the previous ROP models.

Keywords

Self-adaptive Artificial neural network Drilling fluid properties Drilling parameters, rate of penetration 

Nomenclature

ROP

rate of penetration, ft/h

UCS

uniaxial compressive strength, psi

D

mud density, pcf

PV

plastic viscosity, cP

d

bit diameter, in.

WOB

weight on bit, klbf

T

torque, klbf-ft

P

standpipe pressure, psi

Q

flow rate, gpm

RPM

revolutions per minute

HP

horsepower, HP

R

correlation coefficient

R2

coefficient of determination

AAPE

average absolute percentage error

TVD

true vertical depth, ft

SaDE

self-adaptive differential evolution

Notes

Compliance with ethical standards

Conflict of interest

The author declares that there is no conflict of interest.

References

  1. Aalst WMP, Rubin V, Verbeek HMW, Van Dongen BF, Kindler E, Günther CW (2010) Process mining: a two-step approach to balance between underfitting and overfitting. Softw Syst Model 9(1):87–111CrossRefGoogle Scholar
  2. Aguilar J, Prato F, Bravo C, Rivas F (2009) A multi-agent system for the management of abnormal situations in an artificially gas-lifted well. Appl Artif Intell 23(5):406–426.  https://doi.org/10.1080/08839510902872256 CrossRefGoogle Scholar
  3. Akcayol MA, Sagiroglu S (2007) Neuro-fuzzy controller implementation for an adaptive cathodic protection on Iraq-Turkey crude oil pipeline. Appl Artif Intell 21(3):241–256.  https://doi.org/10.1080/08839510701196345 CrossRefGoogle Scholar
  4. AlAjmi MD, Alarifi SA, Mahsoon AH (2015) Improving multiphase choke performance prediction and well production test validation using artificial intelligence: a new milestone. SPE-173394-MS, presented at the SPE Digital Energy Conference and Exhibition, held in The Woodlands, Texas, USA, 3-5 MarchGoogle Scholar
  5. Alarifi SA, AlNuaim S, Abdulraheem A (2015) Productivity index prediction for oil horizontal wells using different artificial intelligence techniques. SPE-172729-MS, presented at the SPE Middle East Oil & Gas Show and Conference, held in Manama, Bahrain, 8-11 MarchGoogle Scholar
  6. Ali JK (1994) Neural networks: a new tool for the petroleum industry. Paper SPE 27561presented in the European Petroleum Computer Conference, Aberdeen, U.K., 5-17 MarchGoogle Scholar
  7. Arabjamaloei, Shadizadeh S (2011) Modeling and optimizing rate of penetration using intelligent systems in an Iranian southern oil field (Ahwaz oil field). Pet Sci Technol 29(16):1637–1648.  https://doi.org/10.1080/10916460902882818 CrossRefGoogle Scholar
  8. Armenta M (2008) Identifying inefficient drilling conditions using drilling specific energy. Paper SPE 116667 presented at the Annual Technical Conference and Exhibition held in Denver, Colorado, USA, 21–24 SeptemberGoogle Scholar
  9. Bezminabadi S, Ramezanzadeh A, Esmaeil Jalali S, Tokhmenchi B, Roustaei A (2017) Effect of rock properties on ROP modeling using statistical and intelligent methods: a case study of an oil well in southwest of Iran. Arch Min Sci 62(1):131–144Google Scholar
  10. Bilgesu HI, Tetrick LT, Altmis U, Mohaghegh S, Ameri S (1997) A new approach for the prediction of rate of penetration (ROP) values. Paper SPE-39231 presented at the SPE Eastern Regional Meetingber, Lexington, Kentucky, 22–24 OctoberGoogle Scholar
  11. Bingham MG (1965) A new approach to interpreting rock drillability. Petroleum Pub. Co.Google Scholar
  12. Bourgoyne AT, Young FS (1974) A multiple regression approach to optimal drilling and abnormal pressure detection. J SPE 14(04):371–384Google Scholar
  13. Chen F, Duan Y, Zhang J, Wang K, Wang W (2015) Application of neural network and fuzzy mathematic theory in evaluating the adaptability of inflow control device in horizontal well. J Pet Sci Eng 134(2015):131–142Google Scholar
  14. Choubineh A, Helalizadeh A, Wood DA (2019) Estimation of minimum miscibility pressure of varied gas compositions and reservoir crude oil over a wide range of conditions using an artificial neural network model. Advances in Geo-Energy Research 3(1):52–66CrossRefGoogle Scholar
  15. Elkatatny SM (2017) New approach to optimize the rate of penetration using artificial neural network. Arab J Sci Eng 43:6297–6304.  https://doi.org/10.1007/s13369-017-3022-0 CrossRefGoogle Scholar
  16. Elkatatny S, Tariq Z, Mahmoud M (2016) Real time prediction of drilling fluid rheological properties using Artificial Neural Networks visible mathematical model (white box). J Pet Sci Eng 146:1202–1210CrossRefGoogle Scholar
  17. Elkatatny S, Mahmoud M, Tariq Z, Abdulraheem A (2017) New insights into the prediction of heterogeneous carbonate reservoir permeability from well logs using artificial intelligence network. Neural Comput & Applic 30:1–11.  https://doi.org/10.1007/s00521-017-2850-x CrossRefGoogle Scholar
  18. Elkatatny SM, Zeeshan T, Mahmoud MA, Abdulraheem A, Mohamed I (2018a) An integrated approach for estimating static Young’s modulus using artificial intelligence tools. Neural Comput ApplicGoogle Scholar
  19. Elkatatny SM, Mahmoud MA, Moahmed I, Abdulraheem A (2018b) Development of a new correlation to determine the static Young’s Modulus. J Pet Explor Prod Technol 8(1):17–30CrossRefGoogle Scholar
  20. Fear MJ (1999) How to improve rate of penetration in field operations? SPE Drill Complet 14(01):1064–6671CrossRefGoogle Scholar
  21. Galle EM and Woods HB (1963) Best constant weight and rotary speed for rotary rock bits. Paper API-63-048 presented at the drilling and production practice, New York, 1 JanuaryGoogle Scholar
  22. Hareland G, Wu A, Rashidi B and James JA (2010) A new drilling rate model for tricone bits and its application to predict rock compressive strength. Paper ARMA 10-206 presented at 44th U.S. Rock Mechanics Symposium and 5th U.S.-Canada Rock Mechanics Symposium, Salt Lake City, Utah, 27–30 JuneGoogle Scholar
  23. Haykin (1998) Neural networks, a comprehensive foundation. Prentice Hall PTR, Upper Saddle RiverGoogle Scholar
  24. He S (2009) Neural predictive force control for a hydraulic actuator: simulation and experiment. Appl Artif Intell 23(2):151–167.  https://doi.org/10.1080/08839510802631752 CrossRefGoogle Scholar
  25. Hossain ME, Al-Majed AA (2015) Fundamentals of sustainable drilling engineering. Scrivener Publishing LLC., 27 FebGoogle Scholar
  26. Isa D, Rajkumar R (2009) Pipeline defect prediction using support vector machines. Appl Artif Intell 23(8):758–771.  https://doi.org/10.1080/08839510903210589 CrossRefGoogle Scholar
  27. Jahanbakhshi R, Keshavarzi R and Jafarnezhad A (2012) Real-time prediction of rate of penetration during drilling operation in oil and gas wells. Paper ARMA-2012-244 presented at the 46th U.S. Rock Mechanics/Geomechanics Symposium, Chicago, Illinois, 24–27 JuneGoogle Scholar
  28. Jain AK, Mao J, Mohiuddin KM (1996) Artificial neural networks: a tutorial. Computer 29(3):31–44CrossRefGoogle Scholar
  29. Karakul H (2018) Effects of drilling fluids on the strength properties of clay-bearing rocks. Arab J Geosci 11:450.  https://doi.org/10.1007/s12517-018-3816-8 CrossRefGoogle Scholar
  30. Khandelwal M, Singh TN (2011) Predicting elastic properties of schistose rocks from unconfined strength using intelligent approach. Arab J Geosci 4(3–4):435–442.  https://doi.org/10.1007/s12517-009-0093-6 CrossRefGoogle Scholar
  31. Kowakwi I, Chen H, Hareland G, Rashidi B (2012) The two-term rollercone rate of penetration (ROP) model with integrated hydraulics function. Paper ARMA-2012-246 presented at the 46th U.S. Rock Mechanics/Geomechanics Symposium, Chicago, Illinois, 24–27 JuneGoogle Scholar
  32. Lippmann R (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4(2):4–22CrossRefGoogle Scholar
  33. Maurer WC (1962) The “perfect-cleaning” theory of rotary drilling. J Pet Technol 14(11):1270–1274CrossRefGoogle Scholar
  34. Moussa TM, Awotunde AA (2018) Self-adaptive differential evolution with a novel adaptation technique and its application to optimize ES-SAGD recovery process. Comput Chem Eng 118:64–76.  https://doi.org/10.1016/j.compchemeng.2018.07.018 CrossRefGoogle Scholar
  35. Pessier RC and Fear MJ (1992) Quantifying common drilling problems with mechanical specific energy and a bit-specific coefficient of sliding friction, Paper SPE-24584 presented at the SPE Annual Technical Conference and Exhibition, Washington, D.C., USA, 4-7 OctoberGoogle Scholar
  36. Qin AK, Huang VL, Suganthan PN (2009) Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans Evol Comput 13(2):398–417CrossRefGoogle Scholar
  37. Rumzan I and Schmitt DR (2001) The influence of well bore fluid pressure on drilling penetration rates and stress dependent strength. Paper ARMA-0100911 presented at 38th U.S. Rock Mechanics Symposium. Washington.Google Scholar
  38. Schalkoff R (1997) Artificial neural networks. The University of Michigan: McGraw-HillGoogle Scholar
  39. Storn R, Price K (1997) Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4):341–359CrossRefGoogle Scholar
  40. Su H, Ma H, Hu B, Qu C, Wang N (2018) An analysis of drilling fluid pumping pressure for the Maxi-HDD crossing project. Arab J Geosci 11:347.  https://doi.org/10.1007/s12517-018-3708-y CrossRefGoogle Scholar
  41. Teale R (1965) The concept of specific energy in rock drilling. Int J Rock Mech Min Sci 2(1):57–73CrossRefGoogle Scholar
  42. Van SL, Chon BH (2017a) Effective prediction and management of a CO2 flooding process for enhancing oil recovery using artificial neural networks. ASME J Energy Resour Technol 140:032906.  https://doi.org/10.1115/1.4038054 CrossRefGoogle Scholar
  43. Van SL, Chon BH (2017b) Evaluating the critical performances of a CO2–enhanced oil recovery process using artificial neural network models. J Pet Sci Eng 157:207–222CrossRefGoogle Scholar
  44. Walker BH, Black AD, Klauber WP, et al (1986) Roller-bit penetration rate response as a function of rock properties and well depth. Paper SPE 15620 presented at the 61st Annual Technical Conference and Exhibition of the Society of Petroleum Engineers. New Orleans, LA October 5e8Google Scholar
  45. Wang Q, Gao H, Jiang B, Yang J, LV Z (2018) Relationship model for the drilling parameters from a digital drilling rig versus the rock mechanical parameters and its application. Arab J Geosci 11:357.  https://doi.org/10.1007/s12517-018-3715-z CrossRefGoogle Scholar
  46. Warren TM (1987) Penetration-rate performance of roller–cone bits. SPE Drill Eng 2(1):9–18CrossRefGoogle Scholar
  47. Winters WJ, Warren TM, Onyia EC, (1987) Roller bit model with rock ductility and cone offset. Paper SPE 16696 presented at the SPE Annual Technical Conference. Dallas, September 27–30Google Scholar
  48. Wu A, Hareland G, Rashidi B (2010) The effect of different rock types and roller cone insert types and wear on ROP (rate of penetration). Paper ARMA-10-207 presented at the 44th U.S. Rock Mechanics Symposium and 5th U.S.-Canada Rock Mechanics Symposium, Salt Lake City, Utah, 27–30 JuneGoogle Scholar
  49. Zhang Z, Yin J, Cheng Liu C (2018) A modular real-time tidal prediction model based on Grey-GMDH neural network. Appl Artif Intell 32(2):165–185.  https://doi.org/10.1080/08839514.2018.1451220 CrossRefGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2019

Authors and Affiliations

  1. 1.Department of Petroleum EngineeringKing Fahd University of Petroleum & MineralsDhahranSaudi Arabia

Personalised recommendations