Power Electronics & Motor Control

Advanced direct torque control of induction motors with quantum-inspired memetic neural swarm optimization (QIMNSO) for improved torque stability and energy efficiency

This paper introduces QIMNSO-DTC, a novel control strategy for induction motors that integrates quantum computing principles, memetic algorithms, neural networks, and swarm intelligence. It addresses the limitations of traditional Direct Torque Control (DTC) methods, such as high torque ripple, response lag, and energy inefficiency, particularly under dynamic load conditions. QIMNSO-DTC achieves prompt torque and flux adjustment, significantly smaller ripples, and reduced mechanical stress. Its neural network component enables real-time adaptation of parameters for optimal performance across various operating and load conditions. Simulation results demonstrate that QIMNSO-DTC outperforms classical control methods like FOC, SMC, and PID in terms of torque stability, response speed, energy efficiency, and self-adaptiveness, making it suitable for high-precision applications such as robotics and electric vehicles.