Performance Comparison of FOC, DTC and ANN-Assisted DTC for a Solar PV-Battery Powered PMSM Drive under Variable Load Conditions

Abstract

Renewable energy-based motor drive systems require control techniques that can deliver stable operation under changing load conditions while maintaining high efficiency. This study investigates the performance of three control methods, namely Field-Oriented Control (FOC), Direct Torque Control (DTC), and Artificial Neural Network-assisted Direct Torque Control (ANN-DTC), for a solar photovoltaic and battery powered Permanent Magnet Synchronous Motor (PMSM) drive. A MATLAB/Simulink model is developed in which the motor operates at a constant reference speed while the applied load torque is varied. The three controllers are assessed using identical operating conditions to ensure a fair comparison. Performance is evaluated through transient and steady-state indices, including rise time, settling time, peak overshoot, speed deviation, torque ripple, and RMS speed error. The obtained results show that FOC provides smooth steady-state operation, DTC offers a rapid dynamic response, and the ANN-assisted DTC approach improves overall drive performance by achieving better speed regulation with reduced torque oscillations during load variations. The proposed comparison demonstrates that ANN-assisted DTC is an effective control strategy for enhancing the performance of solar PV-battery powered PMSM drive systems.

Introduction

This study presents a solar PV–battery powered Permanent Magnet Synchronous Motor (PMSM) drive and compares three motor control strategies: Field-Oriented Control (FOC), Direct Torque Control (DTC), and Artificial Neural Network (ANN)-assisted DTC. The objective is to identify the most effective control method for maintaining constant motor speed under varying load conditions in renewable energy-powered applications.

A solar photovoltaic (PV) system, combined with a lithium-ion battery, provides a stable power supply despite fluctuations in solar irradiance and temperature. The PMSM is selected because of its high efficiency, compact size, fast dynamic response, and wide operating speed range, making it suitable for applications such as water pumping, electric vehicles, and industrial drives.

The study reviews existing research on renewable energy-powered motor drives and highlights that:

• FOC offers smooth operation, accurate speed regulation, and low torque ripple but has a slower dynamic response.
• DTC provides faster torque response and better transient performance but produces higher torque ripple and speed fluctuations.
• ANN-assisted DTC enhances conventional DTC by using machine learning to adapt to changing operating conditions, reducing torque ripple while maintaining fast response.

The research identifies a gap in the literature, as few studies compare these three control techniques under identical conditions using a solar PV-battery power source with constant-speed, variable-load operation.

The proposed system consists of:

• A 6.394 kW solar PV array with Maximum Power Point Tracking (MPPT) using the Perturb and Observe (P&O) algorithm.
• A boost converter that increases the PV voltage from approximately 290 V to an 800 V DC bus.
• A lithium-ion battery for energy storage and voltage stabilization.
• A 5.12 kW, 3000 rpm PMSM driving a water pumping system.
• Three alternative control strategies (FOC, DTC, and ANN-assisted DTC) implemented and analyzed in MATLAB/Simulink.

The controllers are evaluated using transient and steady-state performance metrics, including:

• Rise time
• Settling time
• Peak overshoot
• Speed deviation
• Torque ripple
• RMS speed error
• Load disturbance recovery

Conclusion

This work presented a comparative analysis of Field-Oriented Control (FOC), Direct Torque Control (DTC), and the proposed ANN-assisted DTC for a solar PV-battery powered PMSM drive operating under constant speed and variable load conditions. The simulation results indicate that each control strategy offers distinct advantages. FOC provides smooth motor operation with low torque ripple and excellent steady-state accuracy, making it well suited for precision applications such as CNC machines, robotic manipulators, servo drives, and medical equipment, where accurate speed regulation and smooth operation are essential. In contrast, conventional DTC delivers a faster dynamic response due to its direct control of torque and flux, making it suitable for electric traction systems, conveyor drives, elevators, and rolling mills, where rapid torque response is more important than waveform quality. To overcome the limitations of conventional DTC, an Artificial Neural Network (ANN) was integrated into the DTC control loop by replacing the conventional PI-based torque reference generator. The trained ANN adapts to varying operating conditions and generates a more accurate torque reference, resulting in improved speed regulation, reduced torque ripple, and faster stabilization while preserving the rapid response characteristics of DTC. These features make the proposed ANN-assisted DTC particularly suitable for electric vehicles, solar-powered water pumping systems, renewable energy-based industrial drives, agricultural pumping applications, and intelligent industrial automation, where both dynamic performance and steady-state stability are equally important. Overall, the proposed ANN-assisted DTC combines the smooth operating characteristics of FOC with the fast dynamic response of conventional DTC, making it a promising control strategy for next-generation solar PV-battery integrated PMSM drive systems

References

[1] A. Rezkallah, A. Chandra, B. Singh, and S. Singh, \"Microgrid: Configurations, control and applications,\" IEEE Transactions on Smart Grid, vol. 10, no. 2, pp. 1290–1302, 2019, doi: 10.1109/TSG.2017.2762365. [2] R. Kumar and B. Singh, \"Solar photovoltaic array fed water pumping system using BLDC motor drive,\" IEEE Transactions on Industry Applications, vol. 56, no. 4, pp. 3980–3990, 2020. [3] M. A. Hannan, M. M. Hoque, P. J. Ker, A. Mohamed, and A. Ayob, \"Battery energy storage systems for renewable energy integration: A review,\" Renewable and Sustainable Energy Reviews, vol. 120, 2020, Art. no. 109599, doi: 10.1016/j.rser.2019.109599. [4] P. Pillay and R. Krishnan, \"Modeling of permanent magnet motor drives,\" IEEE Transactions on Industrial Electronics, vol. 35, no. 4, pp. 537–541, Nov. 1988, doi: 10.1109/41.9176. [5] T. M. Jahns and W. L. Soong, \"Pulsating torque minimization techniques for permanent magnet AC motor drives—A review,\" IEEE Transactions on Industrial Electronics, vol. 43, no. 2, pp. 321–330, Apr. 1996, doi: 10.1109/41.491350. [6] F. Blaschke, \"The principle of field orientation as applied to the new TRANSVECTOR closed-loop control system for rotating-field machines,\" Siemens Review, vol. 39, no. 5, pp. 217–220, 1972. [7] I. Takahashi and T. Noguchi, \"A new quick-response and high-efficiency control strategy of an induction motor,\" IEEE Transactions on Industry Applications, vol. IA-22, no. 5, pp. 820–827, Sept. 1986, doi: 10.1109/TIA.1986.4504799. [8] K. Harsh, K. Pandey, R. Kumar, and A. K. Jangir, \"BLDC Motor Driven Water Pump Fed by Solar Photovoltaic Array using Boost Converter,\" International Journal of Engineering Research & Technology, vol. 9, no. 6, 2020, doi: 10.17577/IJERTV9IS060478. [9] M. Thahir et al., \"Energy-efficient solar powered PMSM water pumping system with battery storage,\" International Journal of Renewable Energy Research, 2021. [10] S. Peer and K. B. Mohanty, \"Performance enhancement of direct torque controlled PMSM drive for solar water pumping applications,\" IET Electric Power Applications, 2021. [11] F. Korkmaz, I. Topaloglu, M. F. Cakir, and R. Gurbuz, \"Comparative performance evaluation of FOC and DTC controlled PMSM drives,\" Proc. IEEE POWERENG 2013, pp. 1–6, doi: 10.1109/PowerEng.2013.6635696. [12] N. Maleki, M. R. A. Pahlavani, and I. Soltani, \"A Detailed Comparison Between FOC and DTC Methods of a Permanent Magnet Synchronous Motor Drive,\" Journal of Electrical and Electronic Engineering, vol. 3, no. 2-1, pp. 1–7, 2015, doi: 10.11648/j.jeee.s.2015030201.30. [13] F. Korkmaz, I. Topaloglu, M. F. Cakir, and Y. Korkmaz, \"Comparison of vector control methods for motor drives under dynamic load conditions,\" International Conference on Power Electronics and Motion Control, pp. 1–6. [14] M. N. Uddin, M. A. Rahman, and M. A. Chy, \"Artificial Neural Network-Based Direct Torque Control of Permanent Magnet Synchronous Motor Drive,\" IEEE Transactions on Industry Applications, vol. 57, no. 3, pp. 2576–2586, 2021. [15] Y. Zhang, H. Li, J. Wang, and X. Liu, \"Neural Network Assisted Direct Torque Control for Permanent Magnet Synchronous Motor Drives,\" IEEE Access, vol. 10, pp. 45871–45882, 2022. [16] S. K. Sahoo, B. Singh, and A. Chandra, \"Artificial Intelligence-Based Torque Ripple Reduction in Direct Torque Controlled PMSM Drives,\" IET Electric Power Applications, vol. 16, no. 8, pp. 1054–1066, 2022.

Copyright

Copyright © 2026 Battula Surya Teja, Dr. D. VenkataBrahmaNaidu. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.