arXiv：cs.LG（机器学习，全量分类）· Francesco Vitale, Hangli Ge, Francesco Flammini·· 14 小时前AI 评分27
面向受电弓-接触网系统的异常检测与定位框架
Anomaly Detection and Localization for the Pantograph-Catenary System
AI 导读
研究提出一套受电弓-接触网系统（PCS）异常检测与定位框架，通过与参考线路的标称 GPS 坐标对齐实现 PCS 高度/拉出值定位，并进行集体异常检测以评估 PCS 健康状态。该方法在意大利铁路线路真实工业数据集上完成验证，数据涵盖多趟列车的 PCS 高度/拉出值，成果已被 IEEE ITSC 2026 工业轨道接收。
正文
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.
| Comments: | Accepted and presented at the Industry Track of the IEEE International Conference on Intelligent Transportation Systems 2026 (IEEE ITSC 2026) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01721 [cs.LG] |
| (or arXiv:2610.01721v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01721 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Francesco Vitale Dr. [view email]
[v1]
Thu, 1 Oct 2026 13:58:21 UTC (753 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org