Submit

Login Login

Register Register

Home / Journals / SDHM / Online First / doi:10.32604/sdhm.2026.088908
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

Open Access

ARTICLE

HPCLIP-AD: Hybrid Prompt Adaptation of CLIP for Anomaly Detection in Electrified Railway Catenary Support Components

Fanhao Zhou1, Hui Wang1,*, Wenqiang Liu2, Haonan Yang1, Hongrui Wang1,3, Xinlong Liu4, Zhigang Liu1
1 School of Electrical Engineering, Southwest Jiaotong University, Chengdu, China
2 National Rail Transit Electrification and Automation Engineering Technology Research Center (Hong Kong Branch), The Hong Kong Polytechnic University, Hong Kong, China
3 Department of Engineering Structures, Delft University of Technology, Delft, The Netherlands
4 School of Mechatronics and Vehicle Engineering, East China Jiaotong University, Nanchang, China
* Corresponding Author: Hui Wang. Email: email

Structural Durability & Health Monitoring https://doi.org/10.32604/sdhm.2026.088908

Received 11 July 2026; Accepted 03 September 2026; Published online 20 September 2026

Abstract

Reliable inspection of catenary support components is challenging because defective samples are scarce, defect regions are often small, and outdoor railway scenes contain complex background interference. To address these challenges, this paper proposes a hybrid prompt adaptation framework based on Contrastive Language-Image Pre-training (CLIP), termed Hybrid Prompting CLIP for Anomaly Detection (HPCLIP-AD), for joint image-level defect identification and pixel-level defect localization. The framework combines static prompts learned from auxiliary industrial anomaly data with image-conditioned dynamic prompts to strengthen defect-related semantics, and introduces an anomaly feature enhancement module that groups patch embeddings into semantic clusters and selectively aggregates the most suspicious cluster, thereby suppressing irrelevant background responses. Experiments on a real-world catenary inspection dataset show that HPCLIP-AD achieves image-level area under the receiver operating characteristic curve (AUROC), average precision (AP), and F1 scores of 98.9%/97.7%/96.0% and pixel-level AUROC, AP, and F1 scores of 99.3%/72.4%/67.5%, respectively, outperforming representative anomaly detection baselines. These results indicate that the proposed framework can provide both reliable component-level defect alarms and localized defect cues for practical catenary inspection and maintenance.

Keywords

Electrified railways; catenary support components; anomaly detection; intelligent inspection; condition assessment

  • 6

    View

  • 0

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link