Analysis and Controlling of Uncertainty in BLDC Motor Using Optimal Hybrid Algorithm in State Space

Abstract

In this article, we present a novel approach for enhancing the performance of Brushless DC Motors (BLDC) by utilizing a Hybrid Controller that combines Proportional – Integral – Derivative (PID) and Artificial Neural Network (ANN) elements. We employ this innovative controller to assess the motor’s behavior under steady-state conditions and internal faults within a state space model. To evaluate the controller’s effectiveness, we compare it with traditional controllers in scenarios involving rapid load changes, and variations in speed, as well as open circuit faults and short circuit faults, which are known to induce disruptive states in the motor. Our study involves a comprehensive examination of the proposed controller’s steady-state stability using state-space representation and the Lyapunov Technique. We construct a prototype model to capture the Steady State and dynamic characteristic variables of a 300 W BLDC motor system. The suggested Hybrid PID-ANN Controller clearly outperforms the traditional PID controller, providing greater control capabilities for BLDC motor applications depending on the results from both simulations and data from experiments.