Fault Detection and Torque Control in BLDC Motor using AI

Due to its longevity, bldc turbines are currently used in many different applications and they are in great demand. In the case of a challenging situation in an aircraft, the powerplant must be securely stopped. In this example, a novel flaw detecting technique is designed to control the frequency of the BLDC motor. LRGF is a synthetic neural network methodology that uses the pole working method to develop systems while taking into account the challenges of dynamically integrating the management system of BLDC motors with analytical problem-solving. All through fault analysis approach, LRGFNN s was used to segregate the fault signal. The adjustable lifting method and otsu thresholding strategy are used to find defects using segregated problem signals with in context of imperfections like both mechanical and electrical mistakes. Reliability of the fault detection system is assessed in a machine that has both a technical and an electromagnetic simulated defect. Additionally, load and resonance problems have been identified.