Fault detection and diagnosis of electric vehicles using artificial intelligence

Abstract

Electric vehicle (EV) performance is greatly influenced by the motor drive system's stability, efficiency, and safety. With the increased usage of electric vehicles, fault detection and diagnostics (FDD) of the motor drive system has become an important topic of research. In recent years, there has been a lot of interest in artificial intelligence (AI) approaches employed in FDD. This paper provides an overview of the application of AI in defect detection for electric vehicles. The FDD method is divided into two steps: feature extraction and fault classification. Feature extraction involves identifying relevant parameters or characteristics from the EV's sensors and signals, enabling the AI system to capture meaningful patterns. Subsequently, fault classification employs AI algorithms to categorize and identify specific faults based on the extracted features, facilitating efficient diagnosis and maintenance of EVs. In the realm of EVs, the combination of AI techniques and FDD has the potential to improve performance, reliability, and safety while enabling proactive maintenance and reducing downtime. Using machine learning and deep learning, we can detect the fault in the system before it starts damaging our EV.