Optimizing BLDC Motor Performance: A Study of PID, Artificial Neural Network and Fuzzy Logic Controllers

This paper compares the dynamic performance of Brushless DC (BLDC) motor control using three different methodologies: Proportional-Integral-Derivative (PID) control, Artificial Neural Network (ANN) control, and Fuzzy Logic Control (FLC). BLDC motors are widely used in various applications due to their high efficiency, reliability, and compactness. However, achieving optimal dynamic performance is challenging due to the non-linear characteristics of BLDC motors. PID controllers are conventional but often struggle with non-linearities and parameter variations. ANN and FLC offer advanced control techniques capable of adapting to these complexities. The research involves designing and implementing ANN, FLC, and PID controllers for a BLDC motor, followed by an extensive performance evaluation based on key transient parameters: rise time, settling time, and peak overshoot. Simulation results indicate that ANN and FLC outperform the PID controller in handling non-linearities and achieving faster response times with reduced overshoot.