A Quick and Effective Current-based Approach for BLDC Motor Interturn Fault Identification Using Artificial Neural Network

Brushless DC motors (BLDC) motor fault detection has recently attracted a lot of interest.Asymmetrical conditions result from the three-phase current waveforms being distorted by interturn failures in BLDC motors.This paper presents an Artificial Neural Network (ANN)-based fault classification approach to locate faults in Brushless Direct Current (DC) Motors and introduces a straightforward and effective way to identify inter-turn problems.Hall effect sensors are used to orient the rotor and measure the motor's current and speed.The PWM generator (ANN fault classification technique) analyses various fault instances and quickly diagnoses defective signals.The proportional integral (PI) controller is utilized to execute the BLDC motor speed management, improving drive.The proposed FFD approach can be easily applied in conventional drive systems because of the diagnostic algorithm's compactness.The project is carried out using simulation in Matlab.The outcomes support the proposed method's superior precision and rapidity of fault identification.