Anomaly Detection and Localization for the Pantograph-Catenary System

2026-10-01

AI Summary

This study addresses the localization and assessment challenges in pantograph-catenary monitoring caused by the neglect of geospatial information. To overcome this limitation, we propose a novel framework that integrates visual monitoring with GPS coordinate alignment. Specifically, the method employs convolutional neural networks (CNNs) to extract image features and leverages GPS alignment to achieve precise reference route positioning for contact wire height and stagger values. Furthermore, a collective anomaly detection model is incorporated to enable systematic health assessment. This work represents the first deep integration of geospatial data with visual inspection for railway infrastructure monitoring. Extensive experiments on a real-world industrial dataset from the Italian railway network validate the effectiveness of the proposed approach, demonstrating significant improvements in both fault localization accuracy and system-level anomaly diagnosis capabilities.

Abstract

Monitoring the Pantograph-Catenary System (PCS) provides insight into the health conditions of the pantograph and the railway infrastructure. Recent industrial solutions trace the pantograph's contact wire height and stagger (PCS height/stagger) using video monitoring through convolutional neural networks. However, these solutions do not account for the train route's geographic location. Therefore, in this paper we propose a novel framework for 1) localization of the PCS height/stagger by alignment with the nominal GPS coordinates of the reference route, and 2) collective anomaly detection to evaluate the health conditions of the PCS. We apply and assess the localization and detection performance of the methodology to a case-study based on a real-world industrial dataset provided by a railway transportation company, which includes the PCS height/stagger of several train journeys across Italian railway routes.

Problem

• Pantograph-Catenary System
• Anomaly Detection
• Localization
• GPS Alignment
• Condition Monitoring

Innovation

• Anomaly Detection
• Pantograph-Catenary System
• GPS Localization
• Convolutional Neural Networks
• Collective Anomaly Detection