Authors: Akash Baghel, Professor Amit kumar Asthana
Abstract: The control of Brushless DC (BLDC) motors plays a vital role in various high-performance applications such as electric vehicles, robotics, aerospace, and industrial automation. Traditional control techniques like Proportional-Integral (PI) or Proportional-Integral-Derivative (PID) controllers often struggle to maintain optimal performance under nonlinear conditions, parameter variations, and dynamic load changes. To address these limitations, this study proposes an Artificial Neural Network (ANN)-based control method for BLDC motor operation. The proposed ANN controller is designed to learn the nonlinear dynamics of the motor and generate optimal control signals in real-time. Trained using supervised learning techniques, the ANN effectively predicts the appropriate voltage or PWM duty cycle required for desired speed and torque control. The controller adapts to disturbances and uncertainties, resulting in improved transient response, reduced steady-state error, and better disturbance rejection compared to conventional controllers. Simulation and experimental results demonstrate the superior performance of the ANN-based controller in terms of dynamic response, accuracy, and robustness. This approach enhances the efficiency and reliability of BLDC motor drives, making it highly suitable for intelligent motion control systems in modern applications