Online Incremental Learning Algorithms for Real-time Fault Diagnosis in Charging Stations

The health status of electric vehicle charging piles is critical for the efficient operation of charging infrastructure and user satisfaction. Traditional fault diagnosis methods often rely on offline analysis and cannot adapt to real-time changes in the operational environment. In this paper, we propose an Online Incremental Learning algorithm for Charging Pile Health Assessment and Fault Diagnosis (OIL-CP). The algorithm employs an online Support Vector Machine for real-time model updating, incorporates concept drift detection using the ADWIN algorithm to adapt to changes in data distribution, and utilizes federated learning for collaborative model improvement without compromising data privacy. OIL-CP offers a practical and scalable solution for real-time health monitoring and fault diagnosis in charging piles, with the potential to enhance the reliability and efficiency of electric vehicle charging infrastructure. The proposed method contributes to the advancement of intelligent operation and maintenance strategies in the rapidly growing field of electric mobility.