Ebrahimi, Zahed (2025) Intelligent Control of Directional Drilling Using GRU Neural Networks. Masters thesis, Concordia University.
Preview |
Text (application/pdf)
12MBEbrahimi_MA_S2026.pdf - Accepted Version Available under License Spectrum Terms of Access. |
Abstract
Directional drilling requires precise trajectory control under highly nonlinear and time-varying downhole conditions. Conventional proportional–integral–derivative (PID) controllers are simple to implement but struggle to maintain performance when formation properties change. Model predictive control (MPC) can achieve improved accuracy and constraint handling, yet it remains computationally impractical for real-time downhole processors. To address these challenges, this thesis develops two intelligent control strategies based on gated recurrent unit (GRU) neural networks integrated with a finite-element model (FEM) of the drillstring and a nonlinear polycrystalline-diamond-compact (PDC) bit–rock.
The first approach introduces an adaptive GRU–PID controller that updates PID gains online using a trained GRU network to estimate the local input–output Jacobian of the drilling process. This strategy preserves the interpretability and low complexity of PID while significantly improving the transient response, robustness to uncertainties, and steady-state accuracy. The second approach presents a GRU-based MPC surrogate (GMPC) that learns the optimal MPC control policy offline from input–output data and adapts online through a GRU estimator. The resulting controller achieves MPC-level tracking performance with drastically reduced computation, enabling real-time feasibility.
Both controllers were evaluated using identical simulation scenarios derived from the FEM. The results demonstrate that GRU–PID offers low computational cost, while GMPC provides near-optimal accuracy and superior constraint compliance. Together, the proposed methods illustrate a practical path towards adaptive, high-performance, and computationally efficient directional drilling automation.
| Divisions: | Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering |
|---|---|
| Item Type: | Thesis (Masters) |
| Authors: | Ebrahimi, Zahed |
| Institution: | Concordia University |
| Degree Name: | M.A. Sc. |
| Program: | Electrical and Computer Engineering |
| Date: | 19 November 2025 |
| Thesis Supervisor(s): | Selmic, Rastko |
| Keywords: | Directional Drilling, Gated Recurrent Unit (GRU), Neural Network (NN), Model Predictive Control (MPC), Adaptive Control, Control Sensitivity |
| ID Code: | 996639 |
| Deposited By: | Zahed Ebrahimi |
| Deposited On: | 29 Jun 2026 14:40 |
| Last Modified: | 29 Jun 2026 14:40 |
References:
[1] T. Ma, P. Chen, and J. Zhao, “Overview on vertical and directional drilling technologies for the exploration and exploitation of deep petroleum resources,” Geomechanics and Geophysics for Geo-Energy and Geo-Resources, vol. 2, no. 4, pp. 365–395, 2016.[2] E. J. Bouki-Matondo, Miglioramento delle operazioni di perforazione con l’uso di un rivestimento di custodia da 7 pollici, economico e sicuro. Enhancement of drilling operations with the use of 7”casing liner, cost effective and safe. PhD thesis, Politecnico di Torino, 2023.
[3] S. Schaaf, D. Pafitis, and E. Guichemerre, “Application of a point the bit rotary steerable system in directional drilling prototype well-bore profiles,” SPE Western Regional Meeting, pp. SPE–62519, 2000.
[4] J. Kim, B. Park, J.-U. Shin, S. Jung, and H. Myung, “A novel steering sections of hybrid rotary steerable system for directional drilling,” 2014 14th International Conference on Control, Automation and Systems (ICCAS 2014), pp. 1617–1619, 2014.
[5] H. Wang, Z. C. Guan, and G. S. Zhao, “Dynamic characteristic analysis on the bit lateral
steering force of push-the-bit rotary steerable bottom hole assembly,” Mathematical Models in Engineering, vol. 4, no. 4, pp. 201–209, 2018.
[6] S. Bridges and L. Robinson, A practical handbook for drilling fluids processing. Gulf Professional Publishing, 2020.
[7] C. Ke and X. Song, “Control of down-hole drilling process using a computationally efficient dynamic programming method,” Journal of Dynamic Systems, Measurement, and Control, vol. 140, no. 10, p. 101010, 2018.
[8] C. Ke and X. Song, “Control design for directional down-hole drilling using dual-heuristic programming with a high-order dynamic model,” IEEE Transactions on Control Systems Technology, vol. 30, no. 3, pp. 1009–1020, 2021.
[9] J. Wu, C. Lu, H. Li, H. Wei, and M. Wu, “Trajectory tracking for directional drilling in underground coal mine using robust model predictive control,” 2025 IEEE International Conference on Industrial Technology (ICIT), pp. 1–6, 2025.
[10] J. Ding, M. Wu, and M. Xiao, “Nonlinear decoupling control with pi λ d μ neural network for mimo systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 6, pp. 8715–8722, 2022.
[11] Z. Ebrahimi and R. R. Selmic, “Intelligent control system for directional drilling: A gru neural network approach,” 2025 33rd Mediterranean Conference on Control and Automation (MED), pp. 257–262, 2025.
[12] Z. Ebrahimi and R. R. Selmic, “Adaptive gated recurrent unit-based predictive control for directional drilling operations,” Journal of Dynamic Systems, Measurement, and Control, 2025.
[13] Y. Gao, N. Wang, and Y. Ma, “L2-ssa-lstm prediction model of steering drilling wellbore trajectory,” IEEE Access, vol. 12, pp. 450–461, 2023.
[14] H. Tian, J. Tang, and W. Yu, “Lstm neural network-based on model predictive control for furnace temperature in mswi process,” 2025 37th Chinese Control and Decision Conference (CCDC), pp. 2151–2154, 2025.
[15] W. Li, M. Wu, K. YaO, Q. Li, C. Lu, and S. Du, “Design of an intelligent control system for underground directional drilling trajectory in coal mines,” 2022 41st Chinese Control Conference (CCC), pp. 2586–2590, 2022.
[16] E. I. Epelle and D. I. Gerogiorgis, “A review of technological advances and open challenges for oil and gas drilling systems engineering,” AIChE Journal, vol. 66, no. 4, p. e16842, 2020.
[17] B. Park, J. Kim, J. Park, J.-U. Shin, and H. Myung, “Hybrid 4-pad rotary steerable system for directional drilling of unconventional resources,” 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp. 659–660, 2013.
[18] J. Tian and L. Sheng, “Cubature kalman filtering for dynamic pointing rotary steerable system based on dynamic event-triggering mechanism,” 2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes (SAFEPROCESS), pp. 1–6, 2021.
[19] J. Park, J. Kim, B. Park, and H. Myung, “Design and analysis of a new hybrid rotary steerable system for directional drilling,” IEEE ISR 2013, pp. 1–3, 2013.
[20] J. Kim and H. Myung, “Development of a novel hybrid-type rotary steerable system for directional drilling,” IEEE access, vol. 5, pp. 24678–24687, 2017.
[21] K. Isaka, K. Tsumura, T.Watanabe,W. Toyama, M. Okui, H. Yoshida, and T. Nakamura, “Soil discharging mechanism utilizing water jetting to improve excavation depth for seabed drilling explorer,” IEEE Access, vol. 8, pp. 28560–28570, 2020.
[22] K. Gurney, An introduction to neural networks. CRC press, 2018.
[23] P. Kittisupakorn, P. Thitiyasook, M. A. Hussain, andW. Daosud, “Neural network based model predictive control for a steel pickling process,” Journal of process control, vol. 19, no. 4, pp. 579–590, 2009.
[24] J.-Y. Dieulot, “Model predictive control of fuel cells using a neural network based inverted model,” 2023 9th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 864–869, 2023.
[25] S. V. Feofilov and D. Khapkin, “Application of recurrent neural networks in closed loop tracking systems for controlling essentially nonlinear objects,” 2021 3rd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), pp. 467–472, 2021.
[26] E. Calle and J. Oliden, “Recurrent neural network based predictive control applied to 4 coupled-tank system,” 2021 IEEE International Conference on Automation/XXIV Congress of the Chilean Association of Automatic Control (ICA-ACCA), pp. 1–6, 2021.
[27] Y. Bu, W. Liao, W. Tian, J. Zhang, and L. Zhang, “Stiffness analysis and optimization in
robotic drilling application,” Precision Engineering, vol. 49, pp. 388–400, 2017.
[28] G. Downton, “Challenges of modeling drilling systems for the purposes of automation and control,” IFAC Proceedings Volumes, vol. 45, no. 8, pp. 201–210, 2012.
[29] E. Detournay and P. Defourny, “A phenomenological model for the drilling action of drag bits,”International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, vol. 29, no. 1, pp. 13–23, 1992.
[30] R. Ma, B. Zhang, Y. Zhou, Z. Li, and F. Lei, “Pid controller-guided attention neural network learning for fast and effective real photographs denoising,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 7, pp. 3010–3023, 2021.
[31] R. Ma, B. Zhang, Y. Zhou, Z. Li, and F. Lei, “Pid controller-guided attention neural network learning for fast and effective real photographs denoising,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 7, pp. 3010–3023, 2021.
[32] F. Lewis, S. Jagannathan, and A. Yesildirak, Neural network control of robot manipulators and non-linear systems. CRC press, 2020.
[33] Y. M. Ren, M. S. Alhajeri, J. Luo, S. Chen, F. Abdullah, Z.Wu, and P. D. Christofides, “A tutorial review of neural network modeling approaches for model predictive control,” Computers & Chemical Engineering, vol. 165, p. 107956, 2022.
[34] D.Wang, Z. J. Shen, X. Yin, S. Tang, X. Liu, C. Zhang, J.Wang, J. Rodriguez, and M. Norambuena,“Model predictive control using artificial neural network for power converters,” IEEE Transactions on Industrial Electronics, vol. 69, no. 4, pp. 3689–3699, 2021.
[35] Y. Liu, Y. Wang, Y. Feng, and Y. Wu, “Neural network-based adaptive boundary control of a flexible riser with input deadzone and output constraint,” IEEE transactions on cybernetics, vol. 52, no. 12, pp. 13120–13128, 2021.
[36] J. Yu, P. Shi, W. Dong, B. Chen, and C. Lin, “Neural network-based adaptive dynamic surface control for permanent magnet synchronous motors,” IEEE transactions on neural networks and learning systems, vol. 26, no. 3, pp. 640–645, 2014.
[37] S. Piche, B. Sayyar-Rodsari, D. Johnson, and M. Gerules, “Nonlinear model predictive control using neural networks,” IEEE Control Systems Magazine, vol. 20, no. 3, pp. 53–62, 2000.
[38] A. Theodorakopoulos and G. A. Rovithakis, “A simplified adaptive neural network prescribed performance controller for uncertain mimo feedback linearizable systems,” IEEE transactions on neural networks and learning systems, vol. 26, no. 3, pp. 589–600, 2014.
[39] M. B. Milovanovi´c, D. S. Anti´c, M. T. Milojkovi´c, and M. D. Spasi´c, “Adaptive control of nonlinear mimo system with orthogonal endocrine intelligent controller,” IEEE Transactions on Cybernetics, vol. 52, no. 2, pp. 1221–1232, 2020.
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.
Repository Staff Only: item control page
Download Statistics
Download Statistics