Geomechanics and Geoenergy Journal

Geomechanics and Geoenergy Journal

Optimization of drilling rate of penetration considering geomechanical properties and operational drilling parameters in a well from a southern Iranian oil field

Document Type : Original Article

Authors
Ghasem Karimi Firouzjaei
Ahmad Ramezanzadeh
Mohammad Mehrad
Petroleum Geomechanics Group, Faculty of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology
10.22107/ggj.2025.482073.1241
Abstract
Optimization of the drilling rate of penetration (ROP), recognized as one of the key factors influencing the efficiency and productivity of drilling operations, plays a crucial role in the success of the process and directly impacts the reduction of drilling time and associated costs. In this study, conducted in one of the Persian Gulf fields, geomechanical parameters of the studied well were estimated based on petrophysical and rock mechanics data. Additionally, pore pressure variations, stresses, and wellbore stability conditions were simulated through one-dimensional geomechanical modeling using the Geolog software. After evaluating the geomechanical and drilling modeling, the parameters were used for ROP modeling using MATLAB software. ROP modeling and optimization were carried out using two databases (drilling data and drilling–geomechanical data). Initially, a correlation matrix between the geomechanical/petrophysical parameters and drilling ROP was generated, where eight parameters in the drilling–geomechanical database and six parameters in the drilling database yielded the lowest RMSE values between the actual and predicted ROP. These parameters were then applied to ROP modeling using two approaches, Multi-Layer Perceptron (MLP) and Random Forest (RF), with RF selected as the final modeling method. Following the ROP modeling, for the optimization stage, considering the characteristics of different algorithms, the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm was chosen. Accordingly, by optimizing the controllable parameters, the average drilling rate was enhanced to 14.1 m/hr using the drilling database and to 15.5 m/hr using the drilling–geomechanical database. Consequently, the drilling time for the studied depth interval (360 m) was reduced by 2.65 hours using the drilling database and by 4.9 hours using the drilling–geomechanical database, highlighting the significant effect of incorporating geomechanical data on optimizing drilling parameters.
Keywords
Rate of Penetration (ROP)
Geomechanical Parameters of Rock
One-Dimensional Wellbore Geomechanical Modeling
Drilling Rate of Penetration Modeling
Drilling Rate Optimization
[1] Cooper, G. A., Cooper, A. G., & Bihn, G. (1995). An interactive drilling simulator for teaching and research. SPE Petroleum Computer Conference.
[2] Bourgoyne, A. T., Millheim, K. K., Chenevert, M. E., & Young, F. S. (1986). Applied drilling engineering (Vol. 2). Society of Petroleum Engineers Richardson.
[3] Hasimi, A., et al. (2012). Optimization of Rate of Penetration with Mechanical Specific Energy. Geotechnical and Geological Engineering.
[4] Saeidi, H., et al. (2018). Effect of Rock Geomechanical Parameters On oil wells Drilling Rate of Penetration using Rock Engineering Systems Shahrood University of Technology].
[5] Sabah, M., Talebkeikhah, M., Wood, D. A., Khosravanian, R., Anemangely, M., & Younesi, A. (2019). A machine learning approach to predict drilling rate using petrophysical and mud logging data. Earth Science Informatics, 12, 319-339.
[6]  Anemangely, M., et al. (2017). Developing a New Rock Drillability Index for Oil and Gas Reservoirs Based on Drilling rate Shahrood University of Technology.
[7] Zhang, H., Ni, H., Wang, Z., Liu, S., & Liang, H. (2020). Optimization and application study on targeted formation ROP enhancement with impact drilling modes based on clustering characteristics of logging. Energy Reports, 6, 2903-2912.
[8]  Ahmed, A., Elkatatny, S., Ali, A., Mahmoud, M., & Abdulraheem, A. (2019). New model for pore pressure prediction while drilling using artificial neural networks. Arabian Journal for Science and Engineering, 44(6), 6079-6088.
[9]  Mehrad, M., Bajolvand, M., Ramezanzadeh, A., & Neycharan, J. G. (2020). Developing a new rigorous drilling rate prediction model using a machine learning technique. Journal of Petroleum Science and Engineering, 192, 107338.
[10]  Delavar, M. R., Ramezanzadeh, A., & Tokhmechi, B. (2021). An investigation into the effect of geomechanical properties of reservoir rock on drilling parameters—a case study. Arabian Journal of Geosciences, 14, 1-25.
[11] Bani Mustafa, A., Abbas, A. K., Alsaba, M., & Alameen, M. (2021). Improving drilling performance through optimizing controllable drilling parameters. Journal of Petroleum Exploration and Production, 11, 1223-1232.‏
[12] Bajolvand, M., Ramezanzadeh, A., Mehrad, M., & Roohi, A. (2022). Optimization of controllable drilling parameters using a novel geomechanics-based workflow. Journal of Petroleum Science and Engineering, 218, 111004.‏
[13] Delavar, M. R., Ramezanzadeh, A., Gholami, R., & Sanei, M. (2023). Optimization of drilling parameters using combined multi-objective method and presenting a practical factor. Computers & Geosciences, 175, 105359.
[14] Shaygan, K., & Jamshidi, S. (2023). Prediction of rate of penetration in directional drilling using data mining techniques. Geoenergy Science and Engineering, 221, 111293.
[15] Wang, Q., & Jia, X. (2020). Multi-objective optimization of CFRP drilling parameters with a hybrid method integrating the ANN, NSGA-II and fuzzy C-means. Composite Structures, 235, 111803.
[16] Kolmer, H. P., Cunningham, C. M., & Al-Dushaishi, M. F. (2022). ROP Optimization of Lateral Wells in SW Oklahoma: Artificial Neural Network Approach. International Conference on Offshore Mechanics and Arctic Engineering.
[17] Mantha, B., & Samuel, R. (2016). ROP optimization using artificial intelligence techniques with statistical regression coupling. SPE Annual Technical Conference and Exhibition.
[18]  Mehrad, M., Ramezanzadeh, A., Bajolvand, M., & Hajsaeedi, M. R. (2022). Estimating shear wave velocity in carbonate reservoirs from petrophysical logs using intelligent algorithms. Journal of petroleum science and engineering, 212, 110254.
[19]  Bizhani, M., & Kuru, E. (2022). Towards drilling rate of penetration prediction: Bayesian neural networks for uncertainty quantification. Journal of petroleum science and engineering, 219, 111068.
[20]  Osman, H., Ali, A., Mahmoud, A. A., & Elkatatny, S. (2021). Estimation of the rate of penetration while horizontally drilling carbonate formation using random forest. Journal of Energy Resources Technology, 143(9), 093003.
[21]  Sun, J., Zhang, R., Chen, M., Chen, B., Wang, X., Li, Q., & Ren, L. (2021). Identification of porosity and permeability while drilling based on machine learning. Arabian Journal for Science and Engineering, 46, 7031-7045.
[22] Ashena, R., Rabiei, M., Rasouli, V., Mohammadi, A. H., & Mishani, S. (2021). Drilling parameters optimization using an innovative artificial intelligence model. Journal of Energy Resources Technology, 143(5), 052110.
[23]  Anemangely, M., Ramezanzadeh, A., & Behboud, M. M. (2019). Geomechanical parameter estimation from mechanical specific energy using artificial intelligence. Journal of petroleum science and engineering, 175, 407-429.
Geomechanics and Geoenergy Journal
Volume 8, Issue 1
Spring 2025
Pages 19-31