Artificial Intelligence-Enhanced Field Oriented Control for Optimized Speed Control of BLDC Traction Motors in Railway

Brushless Direct Current (BLDC) motors are widely employed in electric railway traction systems due to their high efficiency and smooth operation. However, complex speed control and the occurrence of torque ripple-arising from speed instability under excessive load-prevent BLDC motors from operating at optimal performance. This study proposes an optimization approach based on Field-Oriented Control (FOC) using Proportional Integral (PI) controllers tuned through Hand Tuning (HT), Artificial Bee Colony (ABC), and Particle Swarm Optimization (PSO). The optimization process utilizes the Integral Time Multiplied by Absolute Error (ITAE) criterion. Simulation results indicate that PSO delivers the most optimal overall performance. PSO achieves the highest electromagnetic torque output (26.3937 Nm during start-up and 4.92347 Nm under load), provides the fastest speed recovery, and demonstrates superior resilience to load disturbances such as cornering effects. Therefore, PSO emerges as the most effective tuning strategy for BLDC motor control.