Development of an Adaptive Control System for Synchronous Electric Motors Using Neural Networks to Improve Industrial Energy Efficiency
DOI:
https://doi.org/10.70062/jeci.v1i2.221Keywords:
Adaptive Control, Deep Neural Network, MATLAB, PI Controller, PMSMAbstract
This study presents the development and performance evaluation of a Deep Neural Network (DNN)-based adaptive control system for a Permanent Magnet Synchronous Motor (PMSM). The main objective is to enhance the dynamic response, steady-state accuracy, and energy efficiency of the PMSM drive compared to a conventional Proportional–Integral (PI) controller. The proposed control architecture integrates a DNN within the speed and torque control loop, enabling online adaptation to system nonlinearities and varying load conditions. The neural network structure utilizes speed error, current, and torque feedback as inputs, while training data are obtained from motor dynamics in MATLAB/Simulink simulations. Both the DNN and PI controllers are implemented and tested under multiple scenarios with different load torques (0%, 50%, and 100% rated load) and reference speeds (500–1500 rpm). Simulation results demonstrate that the DNN-based adaptive controller significantly improves performance metrics. The settling time is reduced by over 50%, maximum overshoot by 72%, and steady-state error by 83% compared to the PI controller. Additionally, torque ripple and energy consumption are decreased by approximately 60% and 19%, respectively, showing enhanced smoothness and efficiency. The findings confirm that the DNN controller provides robust adaptability, precise tracking, and lower energy use, making it a promising alternative for intelligent PMSM drive applications in industrial and electric vehicle systems.
References
[1] G. Seggewiss, J. Dai, and M. Fanslow, “Evaluation of synchronous motors on grinding mills,” in Proc. IEEE Cement Industry Technical Conf., 2014, art. no. 6820109. [Online]. Available: https://doi.org/10.1109/CITCon.2014.6820109.
[2] A. Ganapathy Ram and K. R. Santha, “Review of sliding mode observers for sensorless control of permanent magnet synchronous motor drives,” Int. J. Power Electron. Drive Syst., vol. 9, no. 1, pp. 46–54, 2018. [Online]. Available: https://doi.org/10.11591/ijpeds.v9.i1.pp46-54.
[3] J. Parrish, S. Moll, and R. C. Schaefer, “Synchronous versus induction motors,” IEEE Ind. Appl. Mag., vol. 12, no. 2, pp. 61–70, 2006. [Online]. Available: https://doi.org/10.1109/MIA.2006.1598028.
[4] B. P. Ganthia, S. R. Sahu, S. Biswal, A. Abhisekh, and S. K. Barik, “Genetic algorithm based direct torque control of VSI fed induction motor drive using MATLAB simulation,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 8, no. 5, pp. 2359–2369, 2019. [Online]. Available: https://doi.org/10.30534/ijatcse/2019/76852019.
[5] F. Du Plessis, S. Pastellides, and R.-J. Wang, “Design and comparison of three surface-mounted PM motors for a light electric vehicle,” in Proc. SAUPEC/RobMech/PRASA 2021, 2021, art. no. 9377239. [Online]. Available: https://doi.org/10.1109/SAUPEC/RobMech/PRASA52254.2021.9377239.
[6] X. Fu and K. Xia, “sDFT based IRP detection of the electrical excited synchronous machine,” in Lecture Notes in Electrical Engineering, vol. 1060, pp. 269–278, 2023. [Online]. Available: https://doi.org/10.1007/978-981-99-4334-0_34.
[7] D. K. Patel and R. P. Mehta, “Modeling and implementation of efficient control for permanent magnet synchronous motor: A review,” in Lecture Notes in Electrical Engineering, vol. 1304, pp. 109–134, 2025. [Online]. Available: https://doi.org/10.1007/978-981-96-0104-2_9.
[8] A. Gonzalez-Prieto, I. Gonzalez-Prieto, J. J. Aciego, M. Bermudez, and M. J. Duran, “Permanent magnet synchronous machines,” in Encyclopedia of Electrical and Electronic Power Engineering, vol. 1, pp. V1-329–V1-336, 2022. [Online]. Available: https://doi.org/10.1016/B978-0-12-821204-2.00021-0.
[9] A. R. Raut and S. V. Jadhav, “Model predictive speed control of permanent magnet synchronous motor,” in Proc. 10th IEEE Int. Conf. Power Electron., Drives and Energy Syst. (PEDES), 2022. [Online]. Available: https://doi.org/10.1109/PEDES56012.2022.10080344.
[10] “High starting performance synchronous motor: Topic number T2,” in Proc. SPEEDAM 2010 – Int. Symp. Power Electron., Electr. Drives, Autom. Motion, 2010, pp. 293–297. [Online]. Available: https://doi.org/10.1109/SPEEDAM.2010.5545097.
[11] G. Foo, X. Zhang, and M. F. Rahman, “Sensorless control of PMSM drives,” in Modeling, Simulation and Control of Electrical Drives, pp. 513–544, 2019. [Online]. Available: https://doi.org/10.1049/pbce118e_ch14.
[12] A. R. Harkat, L. Barazane, A. Larabi, A. Loukriz, and A. Bendib, “Advanced adaptive nonlinear control with deadbeat observer for permanent magnet synchronous motor drives,” J. Eur. Syst. Automatises, vol. 58, no. 3, pp. 479–491, 2025. [Online]. Available: https://doi.org/10.18280/jesa.580306.
[13] V. Sládeček, P. Palacký, D. Slivka, and P. Hudeček, “Operating mode of permanent magnet synchronous generator,” in Proc. 11th Int. Sci. Conf. Electric Power Engineering (EPE 2010), pp. 249–252, 2010.
[14] M. Habibullah, K. N. Bhumkittipich, N. Mithulananthan, R. Sharma, and F. Zare, “Damping oscillation and removing resonance in a RE based DC microgrids,” IEEE Access, vol. 9, pp. 163516–163525, 2021. [Online]. Available: https://doi.org/10.1109/ACCESS.2021.3135033.
[15] S. Rajkumar, R. Gopalakrishnan, V. Shreemitha, R. Parkavi, and S. Sankaranarayanan, “NeuroCluster: Neural networks for intelligent energy-aware clustering in IIoT,” in Proc. 2nd Int. Conf. Emerging Trends Inf. Technol. Eng. (ic-ETITE), 2024. [Online]. Available: https://doi.org/10.1109/ic-ETITE58242.2024.10493335.
[16] Y. Ouaomar, S. Benkechcha, and M. Kaddiri, “ANN-enhanced energy reference models for industrial buildings: Multinational company case study,” Model. Simul. Eng., vol. 2024, art. no. 1179795, 2024. [Online]. Available: https://doi.org/10.1155/2024/1179795.
[17] V. Sumathi, S. Ramesh, C. C. S. Basavaraddi, J. Visumathi, M. V. Ishwarya, and S. Srinivasan, “Advanced process control in manufacturing using IoT devices and artificial neural networks,” in Proc. 4th Int. Conf. Sustainable Expert Systems (ICSES 2024), pp. 321–326, 2024. [Online]. Available: https://doi.org/10.1109/ICSES63445.2024.10763299.
[18] A. Aghmadi, O. Ali, H. Hussein, and O. A. Mohammed, “Dynamic pulsed load mitigation in PV-battery-supercapacitor systems: A hybrid PI-NN controller approach,” in Proc. IEEE Design Methodologies Conf. (DMC 2023), 2023. [Online]. Available: https://doi.org/10.1109/DMC58182.2023.10412563.
[19] L. Kong, Q. Yang, R. Chen, Z. Zhang, Y. Li, and Y. Shi, “Improved proportional integral (PI) controller for water level control in open channel systems: A case study of the Middle Route Project for South-to-North Water Transfer,” J. Hydrol.: Reg. Stud., vol. 51, art. no. 101646, 2024. [Online]. Available: https://doi.org/10.1016/j.ejrh.2023.101646.
[20] E. R. Gallup, J. Tuttle, and K. M. Powell, “Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems,” Comput. Chem. Eng., vol. 189, art. no. 108787, 2024. [Online]. Available: https://doi.org/10.1016/j.compchemeng.2024.108787.
[21] R. Tabakh, H. Tiryaki, and N. Bayhan, “Active power control of a natural gas/fuel oil turbine power plant with adaptive neuro-fuzzy inference system-based on modern controllers,” in Lecture Notes in Networks and Systems, vol. 504, pp. 735–743, 2022. [Online]. Available: https://doi.org/10.1007/978-3-031-09173-5_84.
[22] R. Errouissi, A. Al-Durra, and S. M. Muyeen, “Experimental validation of a novel PI speed controller for AC motor drives with improved transient performances,” IEEE Trans. Control Syst. Technol., vol. 26, no. 4, pp. 1414–1421, 2018. [Online]. Available: https://doi.org/10.1109/TCST.2017.2707404.
[23] A. K. Singh, R. Raja, T. Sebastian, and A. Ali, “Limitations of the PI control with respect to parameter variation in PMSM motor drive systems,” in Proc. IEEE Int. Electr. Machines and Drives Conf. (IEMDC), 2019, pp. 1688–1693. [Online]. Available: https://doi.org/10.1109/IEMDC.2019.8785406.
[24] V. A. Davydov and R. I. Zhiligotov, “Electrical drive efficiency improving using an adaptive neural network controller,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 643, no. 1, p. 012110, 2019. [Online]. Available: https://doi.org/10.1088/1757-899X/643/1/012110.
[25] S. Basyal, J. Ting, K. Mishra, and B. C. Allen, “Augmentation of a Lyapunov-Based Deep Neural Network Controller with Concurrent Learning for Control-Affine Nonlinear Systems,” in Proc. Amer. Control Conf., 2024, pp. 2885–2890. [Online]. Available: https://doi.org/10.23919/ACC60939.2024.10644820.
[26] E. Sabouni, B. Merah, and I. K. Bousserhane, “Adaptive backstepping controller design based on neural network for PMSM speed control,” Int. J. Power Electron. Drive Syst., vol. 12, no. 3, pp. 1940–1952, 2021. [Online]. Available: https://doi.org/10.11591/ijpeds.v12.i3.pp1940-1952.
[27] O. S. Patil, D. M. Le, E. J. Griffis, and W. E. Dixon, “Deep Residual Neural Network (ResNet)-Based Adaptive Control: A Lyapunov-Based Approach,” in Proc. IEEE Conf. Decision and Control, 2022. [Online]. Available: https://doi.org/10.1109/CDC51059.2022.9992881.
[28] R. Sun, M. L. Greene, D. M. Le, Z. I. Bell, G. Chowdhary, and W. E. Dixon, “Lyapunov-Based Real-Time and Iterative Adjustment of Deep Neural Networks,” IEEE Control Syst. Lett., vol. 6, pp. 193–198, 2022. [Online]. Available: https://doi.org/10.1109/LCSYS.2021.3055454.
[29] L. Zhaona, W. Chuanxing, W. Junlong, and W. Yan, “Adaptive Control of Multimodal Permanent Magnet Synchronous Motor Based on Embedded Neural Network,” Int. J. High Speed Electron. Syst., 2024, Art. no. 2540122. [Online]. Available: https://doi.org/10.1142/S0129156425401226.
[30] J. G. Ziegler and N. B. Nichols, “Optimum settings for automatic controllers,” Trans. ASME, vol. 64, no. 11, pp. 759–768, 1942.
[31] K. J. Åström and T. Hägglund, PID Controllers: Theory, Design, and Tuning, 2nd ed. Research Triangle Park, NC: ISA, 1995.
[32] G. F. Franklin, J. D. Powell, and A. Emami-Naeini, Feedback Control of Dynamic Systems, 8th ed. Pearson, 2021.
[33] H. Shayeghi and A. Jalili, “Modified PID control design for nonlinear systems using Lyapunov theory,” ISA Trans., vol. 92, pp. 56–67, 2019. [Online]. Available: https://doi.org/10.1016/j.isatra.2019.02.016.
[34] M. R. Khosravi, “Dynamic load compensation in PID-based synchronous drive systems,” IEEE Trans. Ind. Electron., vol. 68, no. 7, pp. 6551–6560, 2021. [Online]. Available: https://doi.org/10.1109/TIE.2020.3012789.
[35] C. A. Monje, Y. Q. Chen, B. M. Vinagre, D. Xue, and V. Feliu, Fractional-Order Systems and Controls: Fundamentals and Applications. Springer, 2010. [Online]. Available: https://doi.org/10.1007/978-1-84996-335-0.
[36] M. E. H. Benbouzid and D. Diallo, “Nonlinear PID control optimized by PSO for variable load systems,” Energies, vol. 13, no. 8, pp. 1987–1998, 2020. [Online]. Available: https://doi.org/10.3390/en13081987.
[37] E. J. Griffis, O. S. Patil, W. A. Makumi, and W. E. Dixon, “Deep Recurrent Neural Network-Based Observer for Uncertain Nonlinear Systems,” IFAC-PapersOnLine, vol. 56, no. 2, pp. 6851–6856, 2023. [Online]. Available: https://doi.org/10.1016/j.ifacol.2023.10.475.
[38] S. Lin, H. Wu, S. Liu, X. Wang, and Z. Zhao, “Adaptive neural network control for permanent magnet synchronous motor with input nonlinearity,” Asian J. Control, vol. 27, no. 1, pp. 311–321, 2025. [Online]. Available: https://doi.org/10.1002/asjc.3423.
[39] T. Fei, Y. Yang, C. Zheng, H. Zhang, and G. Yuan, “Adaptive neural design for permanent magnet synchronous motor with asymmetric constraints and input dead-zone,” Neurocomputing, vol. 640, 2025. [Online]. Available: https://doi.org/10.1016/j.neucom.2025.130294.
[40] Y. Liu, J. Li, Z.-Y. Sun, and C.-C. Chen, “A New Adaptive Control Design of Permanent Magnet Synchronous Motor Systems with Uncertainties,” Symmetry, vol. 17, no. 1, Art. no. 2, 2025. [Online]. Available: https://doi.org/10.3390/sym17010002.
[41] W. Li, Y. Ma, J. Yu, X. Wang, and L. Liu, “Neural network-based adaptive tracking control for permanent magnet synchronous motors with iron loss,” ICIC Express Lett., vol. 10, no. 4, pp. 929–934, 2016.
[42] H. Xu, J. G. Lai, J. Y. Liu, N. Cao, and J. Zhao, “Neural network pattern recognition and its application,” Adv. Mater. Res., vol. 756–759, pp. 2438–2442, 2013. [Online]. Available: https://doi.org/10.4028/www.scientific.net/AMR.756-759.2438.
[43] R. K. Sahu, P. Dash, and S. Panda, “Intelligent backstepping control of nonlinear systems using adaptive neural networks,” ISA Trans., vol. 135, pp. 126–135, 2023. [Online]. Available: https://doi.org/10.1016/j.isatra.2022.11.024.
[44] M. Hu and F. Zhang, “Adaptive neural backstepping control for PMSM with uncertainties,” IEEE Access, vol. 11, pp. 24412–24423, 2023. [Online]. Available: https://doi.org/10.1109/ACCESS.2023.3256784.
[45] Z. Wang, L. Chen, X. Qian, and Y. Zhang, “Embedded neural network-based multimodal control for PMSM under complex conditions,” IEEE Trans. Ind. Appl., vol. 61, no. 3, pp. 2890–2901, 2025. [Online]. Available: https://doi.org/10.1109/TIA.2025.3475610.
