RAME Logo

RAME PUBLISHERS

A better space for Quality Research
International Journal of Computational and Electronics Aspects in Engineering (IJCEAE)
Volume 7 · Issue 4 · September 2026 · pp. 466–478
Research Article · Peer Reviewed
Received: July 30, 2026 · Accepted: September 16, 2026 · Published: September 27, 2026
DOI: 10.26706/ijceae.7.4.20260813
Open Access · CC BY 4.0

Improving Transient Performance of Hall-Commutated BLDC Drives via a Compact ANN Controller Trained from PID-Tuned Data

Omar Gheyath Ibrahim*
Department of Medical Instrumentation Techniques Engineering, Polytechnic College Mosul, Northern Technical University, Mosul, Iraq.
ORCID: 0009-0008-0917-2454
*Corresponding author: mti.lec17.omar@ntu.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 4

Abstract

Speed requirement are high speed tracking and well damped torque transients of brushless DC (BLDC) drives during starting and load disturbances. This paper introduces a Model of Simulink for Hall-effect sensor BLDC drive with six-step commutation, and compares the performance of a classical discrete-time PID speed controller to that of an ANN controller as a plug-and-play alternative. Where the PID gains are obtained through MATLAB PID Tuner (based on frequency response), supervised data to train a feedforward regression ANN with one input, and one hidden layer containing 20 neurons and an accelerated output.

At the rated condition (750 rpm, 50 N·m), compared to PID, ANN exhibits faster speed transient response and less electromagnetic torque overshoot. Validation at 500, 750, and 1000 rpm confirms the improvement with a significant reduction in rise time and settling time together with suppression of torque peaks. The disturbance rejection is evaluated by a step load test showing that the ANN yields smaller speed deviations and smoother torque transitions. These results demonstrate that an appropriately trained ANN can provide better transient performance than a tuned PID controller in BLDC drives without altering the inverter or commutation scheme.

Keywords

BLDC motor drive Hall-effect sensors neural network controller feedforward regression ANN torque overshoot reduction

References

  1. M. Şen and M. Mutluer, “A review of BLDC motors: Types, application, failure modes and detection,” Energies, vol. 18, no. 24, Art. no. 6402, 2025, doi: 10.3390/en18246402.
  2. N. Prabhu, R. Thirumalaivasan, and B. Ashok, “Critical review on torque ripple sources and mitigation control strategies of BLDC motors in electric vehicle applications,” IEEE Access, vol. 11, pp. 115699–115739, 2023, doi: 10.1109/ACCESS.2023.3324419.
  3. F. S. Ahmed, O. G. Ibrahim, and M. N. Allawi, “PV-integrated wireless power transfer system for high-efficiency electric vehicle charging applications,” Diagnostyka, vol. 27, no. 1, pp. 1–8, 2026, doi: 10.29354/diag/218930.
  4. J. Shi, Q. Mi, W. Cao, and L. Zhou, “Optimizing BLDC motor drive performance using particle swarm algorithm-tuned fuzzy logic controller,” SN Appl. Sci., vol. 4, Art. no. 293, 2022, doi: 10.1007/s42452-022-05179-6.
  5. A. Venkatesh, S. Nalinakshan, S. Phani Kumar, S. S. Kiran, and K. Akash, “Optimized control strategies for BLDC motor in sustainable energy systems: Enhancing stability and performance through intelligent controllers, filtering techniques and internal model control,” Global Energy Interconnection, early access, Dec. 31, 2025, doi: 10.1016/j.gloei.2025.09.004.
  6. K. Kroičs and A. Būmanis, “BLDC motor speed control with digital adaptive PID-fuzzy controller and reduced harmonic content,” Energies, vol. 17, no. 6, Art. no. 1311, 2024, doi: 10.3390/en17061311.
  7. H. Yin, W. Yi, J. Wu, K. Wang, and J. Guan, “Adaptive fuzzy neural network PID algorithm for BLDCM speed control system,” Mathematics, vol. 10, no. 1, Art. no. 118, 2022, doi: 10.3390/math10010118.
  8. M. H. Mahmood, O. F. Ali, M. J. Mnati, B. M. Sabbar, and A. Van Den Bossche, “Intelligent PID parameter tuning for BLDC motors by using genetic algorithms,” J. Européen des Systèmes Automatisés, vol. 58, no. 7, pp. 1463–1476, 2025, doi: 10.18280/jesa.580714.
  9. A. A. Hadi, “The Impact of Artificial Neural Network (ANN) on the Solar Energy Cells: A Review,” International Journal of Computational and Electronics Aspects in Engineering, vol. 5, no. 1, pp. 30–41, 2024, doi: 10.26706/ijceae.5.1.20240505.
  10. H. A. Mutar, I. J. Mohammed, and I. R. N. ALRubeei, “AI for Solar PV Forecasting, MPPT, and Energy Management: A Comprehensive Review,” International Journal of Computational and Electronics Aspects in Engineering, vol. 7, no. 1, pp. 100–114, 2026, doi: 10.26706/ijceae.7.1.20260111.
  11. F. H. Faris, “Physics-Informed Neural Network Framework for Dynamic Thermal Modeling of Power Transformers Under Extreme Climate Conditions,” International Journal of Computational and Electronics Aspects in Engineering, vol. 7, no. 2, pp. 244–254, 2026, doi: 10.26706/ijceae.7.2.20260313.
  12. E. H. Al-Zaidi, “Supervised learning for adaptive BLDC motor control: Integrating classical PID with neural networks,” The Eurasia Proceedings of Science, Technology, Engineering & Mathematics, vol. 37, pp. 180–193, 2025, doi: 10.55549/epstem.1195.
  13. S. Ghamari and A. Aziz, “A novel deep transfer learning-based adaptive cascade PI controller enhanced by reinforcement learning algorithm and snake optimization for robust speed regulation of brushless DC motors,” IET Power Electronics, vol. 19, no. 1, Art. no. e70157, 2026, doi: 10.1049/pel2.70157.
  14. A. Hasni, H. El Fadil, A. Lassioui, M. El Ancary, Y. El Asri, A. Hamed, and S. EL Jeilani, “Optimized speed regulation of BLDC motors: A comparative performance study of artificial neural networks and super-twisting sliding mode controllers,” Int. J. Robot. Control Syst., vol. 5, no. 4, pp. 2360–2378, 2025, doi: 10.31763/ijrcs.v5i4.2046.
  15. M. Megrini, A. Gaga, and Y. Mehdaoui, “Processor in the loop implementation of artificial neural network controller for BLDC motor speed control,” Results Eng., vol. 23, p. 102422, Sep. 2024, doi: 10.1016/j.rineng.2024.102422.
  16. Chandrarupa and M. Silas, “A Concise Review on Modelling and Performance Characteristics of Multistage Buck Converters for Deep Step-Down Applications,” International Journal of Computational and Electronics Aspects in Engineering, vol. 7, no. 2, pp. 115–121, 2026, doi: 10.26706/ijceae.7.1.20260107.
  17. M. Kadhim, “Improving Power Quality with Active Filtering and Energy Storage Technologies in Grid-Connected Hybrid Solar-Wind Renewable Energy Systems,” International Journal of Computational and Electronics Aspects in Engineering, vol. 7, no. 2, pp. 291–304, 2026, doi: 10.26706/ijceae.7.2.20260317.
  18. R. Shenbagalakshmi, S. K. Mittal, J. Subramaniyan, V. Vengatesan, D. Manikandan, and K. Ramaswamy, “Adaptive speed control of BLDC motors for enhanced electric vehicle performance using fuzzy logic,” Sci. Rep., vol. 15, Art. no. 12579, 2025, doi: 10.1038/s41598-025-90957-6.
  19. J. Ouakrim, A. Bodian, D. Ouardani, and A. Cardenas, “FPGA implementation and performance evaluation of classic PID, IMC and DTC for BLDC motor control,” Vehicles, vol. 8, no. 2, Art. no. 42, 2026, doi: 10.3390/vehicles8020042.
  20. V. Busher, V. Kuznetsov, V. Kovalenko, M. Babyak, V. Druzhinin, V. Tytiuk, A. Rojek, K. Klochko, I. Gurin, and Y. Shramko, “Fractional PI-PIμD controllers with neural network adaptation in control system of BLDC motor electric drives,” Energies, vol. 18, no. 23, Art. no. 6132, 2025, doi: 10.3390/en18236132.
  21. G. Yao, J. Feng, G. Wang, and S. Han, “BLDC motors sensorless control based on MLP topology neural network,” Energies, vol. 16, no. 10, Art. no. 4027, 2023, doi: 10.3390/en16104027.
  22. N. Prabhu, T. Rajaram, and B. Ashok, “Design of sliding mode model predictive dual-loop control through self-learning strategy to mitigate the torque ripple in BLDC motor for electric vehicles,” Scientific Reports, vol. 15, Art. no. 45617, 2025, doi: 10.1038/s41598-025-29445-w.
  23. R. Inan, “An improved model predictive current control of BLDC motor with a novel adaptive extended Kalman filter-based back EMF estimator and a new commutation duration approach for electrical vehicle,” Int. J. Circuit Theory Appl., vol. 53, no. 2, pp. 1135–1150, 2025, doi: 10.1002/cta.4407.
  24. S. T. Nguyen, T. M. Pham, A. Hoang, and T. T. Cao, “Optimal tuning of digital PID controllers for commercial BLDC motors using the Nelder–Mead method,” Power Electron. Drives, vol. 10, no. 1, pp. 210–226, 2025, doi: 10.2478/pead-2025-0015.
  25. M. A. Taleb and G. Husi, “Dynamic modeling of a three-phase BLDC motor using bond graph methodology,” Actuators, vol. 14, no. 11, Art. no. 523, 2025, doi: 10.3390/act14110523.
  26. R. Ristiana, S. Kaleg, A. C. Budiman, S. Sudirja, A. Hapid, A. Muharam, and Amin, “Novel hybrid-MPCC approach to generate switching sequence for six-step commutation of BLDC motor using Hall effect sensor,” Alexandria Eng. J., vol. 82, pp. 43–54, 2023, doi: 10.1016/j.aej.2023.09.052.
  27. Y. I. Son, H. Cho, and J. Kang, “Design and experimental validation of an ISMC-based position controller with supervisory RBF neural network and PIO for BLDC motor systems,” Electronics, vol. 15, no. 15, Art. no. 3373, 2026, doi: 10.3390/electronics15153373.
  28. S. Solgi, A. Stadler, K. Pourhossein, A. Jahic, M. Plenz, and D. Schulz, “Modeling, simulation, and performance evaluation of a commercial electric scooter,” World Electr. Veh. J., vol. 16, no. 9, Art. no. 529, 2025, doi: 10.3390/wevj16090529.