Pantograph unsupervised anomaly detection network based on reverse distillation

The pantograph, as a crucial component for the transmission of electrical energy in trains, plays a pivotal role in ensuring the safety of train operations. In this study, we have developed an unsupervised anomaly detection network, denoted as Pantograph Anomaly Detection Network (PADN), specifically tailored for the anomaly detection of the pantograph. PADN leverages a reverse distillation architecture and incorporates structural characteristics of the pantograph through a two-phase training approach. Meanwhile, The approach utilizes a trainable dual-teacher architecture, facilitating the assimilation of a more comprehensive range of features specific to the pantograph dataset by the student network. Empirical results demonstrate that PADN surpasses the performance of the current state-of-the-art (SOTA) networks on the pantograph dataset, achieving an accuracy rate of 97.87% in the final identification of pantograph anomalies.