Artificial Neural Network Based Fault Identification and Monitoring for Brushless Direct Current Motors

As the electric vehicle (EV) industry advances, guaranteeing the dependability and security of crucial components like inverters, brushless DC (BLDC) motors, and battery packs is essential to avoid malfunctions and safeguard passengers. This research focuses on enhancing the safety and dependability of electric vehicles by continuously monitoring their operational conditions and detecting failures early. Given the complexity of early failure detection, which involves navigating through intricate processes and addressing unpredictability, our study leverages artificial neural networks (ANNs) to facilitate effective real-time problem detection and implement fault-tolerant controls. Our work in this field involves a comprehensive examination of problems that could impact motors in electric vehicles, along with the creation of an effective fault detection system to address these issues. This paper introduces novel fault identification and diagnostic methods tailored for EV motors, tackling problems such as open and short circuit faults, sensor malfunctions, and fluctuations in temperature. Utilizing Artificial Neural Networks (ANNs), our methodology provides a rapid, accurate, sensitive, and cost-effective solution for ensuring the reliable operation of electric vehicles.