DC Motor Control using Deep Reinforcement Learning for Enhanced Robustness and Precision

Year : 2025 | Volume : 03 | Issue : 02 | Page : 22 29
    By

    N. N. Shaikh,

  • I.R Kazi Kutubuddin Sayyad Liyakat,

  1. Assistant Professor, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India
  2. Professor and Head, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India

Abstract

DC motors remain the workhorse of industrial automation and mobile robotics, but achieving simultaneous high-speed transient response and negligible steady-state error under variable load conditions continues to challenge classical Proportional-Integral-Derivative (PID) controllers. These model-dependent systems often require extensive tuning and struggle to maintain optimal performance when confronted with parametric uncertainties, non-linear friction, or sudden voltage fluctuations. This study presents a novel, model-free control paradigm utilizing Deep Reinforcement Learning (DRL)—specifically, a Proximal Policy Optimization (PPO) agent—to govern the speed and torque of a brushed DC motor. The PPO agent interacts directly with a high-fidelity motor simulation environment, learning optimal control policies by maximizing a custom reward function that penalizes overshoot, settling time, and steady-state error. The resulting AI controller demonstrates exceptional adaptation and robustness. Experimental validation shows that the DRL-based system achieves a 60% reduction in peak overshoot and a 45% faster settling time compared to a meticulously fine-tuned cascaded PID controller, particularly during abrupt load application and removal. By bypassing the need for explicit mathematical modeling, this approach provides a scalable, intelligent solution that mitigates common control challenges, paving the way for truly autonomous, highly resilient electromechanical systems.

Keywords: Deep Learning, DC motor, Deep Reinforced Learning, Proximal Policy Optimization

[This article belongs to International Journal of Electrical Machine Analysis and Design ]

How to cite this article:
N. N. Shaikh, I.R Kazi Kutubuddin Sayyad Liyakat. DC Motor Control using Deep Reinforcement Learning for Enhanced Robustness and Precision. International Journal of Electrical Machine Analysis and Design. 2025; 03(02):22-29.
How to cite this URL:
N. N. Shaikh, I.R Kazi Kutubuddin Sayyad Liyakat. DC Motor Control using Deep Reinforcement Learning for Enhanced Robustness and Precision. International Journal of Electrical Machine Analysis and Design. 2025; 03(02):22-29. Available from: https://journals.stmjournals.com/ijemad/article=2025/view=235519


References

  1.  Ahmed S, Tariq U, Hasan A, Rehman H. A Deep Reinforcement Learning Paradigm for DC Motor Speed Control. In2025 IEEE International Electric Machines Drives Conference (IEMDC) 2025 May 18 (pp. 709-714). IEEE.
  2. Saravanan G, Pazhanimuthu C, Naveen P. Performance improvement of DC motor control system using PID controller with Kookaburra and Red Panda optimization algorithm. Scientific Reports. 2025 Jun 6;15(1):20021.
  3. Youssef O, Wafa M, Shalaby R. Reinforcement learning-enhanced adaptive sliding mode control for nonlinear systems. Complex & Intelligent Systems. 2025 Aug;11(8):351.
  4. Lu P, Huang W, Xiao J. Speed tracking of Brushless DC motor based on deep reinforcement learning and PID. In2021 7th International Conference on Condition Monitoring of Machinery in Non-Stationary Operations (CMMNO) 2021 Jun 11 (pp. 130-134). IEEE.
  5. Alejandro-Sanjines U, Maisincho-Jivaja A, Asanza V, Lorente-Leyva LL, Peluffo- Ordóñez DH. Adaptive PI controller based on a reinforcement learning algorithm for speed control of a DC motor. Biomimetics. 2023 Sep 19;8(5):434.
  6. Jin X, Lv H, Tao Y, Lu J, Lv J, Opinat Ikiela NV. Deep Reinforcement Learning-Based Active Disturbance Rejection Control for Trajectory Tracking of Autonomous Ground Electric Vehicles. Machines. 2025 Jun 16;13(6):523.
  7. Gaikwad A, Chendke A, Mulani N, Sarika M. Submersible Pump Theft Indicator. IEJRD-International Multidisciplinary Journal. 2020 May;5(4):5.
  8. Raut MA, Mali MM. Miss. Trupti Mashale, Prof. Kazi KS (2018). Bagasse Level Monitoring System. International Journal of Trend in Scientific Research and Development (ijtsrd).;2:1657-9.
  9. Sunil PP, Tulshidas DU, Prakash GY, KS K. AI-Powered Motorcycle Anti-Theft and Safety System Volume 5, Issue 1, October 2025. pp. 445- 454.
  10. Streitz NA, Konomi SI, editors. Distributed, Ambient and Pervasive Interactions: 13th International Conference, DAPI 2025, Held as Part of the 27th HCI International Conference, HCII 2025, Gothenburg, Sweden, June 22–27, 2025, Proceedings, Part II. Springer Nature; 2025 May 30.
Regular Issue Subscription Original Research
Volume 03
Issue 02
Received 17/11/2025
Accepted 19/11/2025
Published 31/12/2025
Publication Time 44 Days
163

Login


My IP

PlumX Metrics