Brushless direct current motors (BLDCMs) are widely used in corporate oversight, computerized procedures, computer auxiliary devices, and residential appliances. Because of their advantages, which include an intuitive structure, high reliability, great efficiency, low electromagnetic disturbance, and a long operational life. Because of their wide range of applications, BLDC motors necessitate online condition monitoring and fault diagnosis to increase reliability and continuous functioning. Various problems can arise in BLDC motors, notably a grounding issue, which is lethal to the motor. Finding flaws in BLDC motors is a hot topic right now, and several approaches for doing so have been developed. Artificial intelligence (AI) based approaches are currently employed to accurately identify flaws. The study provides a brushless DC motor fault detection system based on (Recurrent Neural Networks) RNN. In a short amount of time, the RNN fault detection approach analyzes numerous fault scenarios and detects faulty signals. The rapidity of the BLDC motor is controlled by a PI controller, which enhances the drive. The simulation application MATLAB 2021a/Simulink was used to test the system that was proposed. The highest value comparison between the controller's efficiency and accuracy values are 92% and 91.5% © 2024 Elsevier B.V., All rights reserved.