An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks

The integrity and stability of railway fasteners are of vital importance to railway safety. To address the challenges of limited anomaly samples, irregular defect geometries, and complex operational conditions in rail fastener anomaly detection, this paper proposes an unsupervised anomaly detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongyan Chen, Zhiwei Li, Xinjie Xiao
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5933
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850130816891355136
author Hongyan Chen
Zhiwei Li
Xinjie Xiao
author_facet Hongyan Chen
Zhiwei Li
Xinjie Xiao
author_sort Hongyan Chen
collection DOAJ
description The integrity and stability of railway fasteners are of vital importance to railway safety. To address the challenges of limited anomaly samples, irregular defect geometries, and complex operational conditions in rail fastener anomaly detection, this paper proposes an unsupervised anomaly detection method using a knowledge-distilled generative adversarial network. First, the proposed method employs collaborative teacher–student learning to model normal sample distributions, where the student network reconstructs input images as normal outputs while a discriminator identifies anomalies by comparing input and reconstructed images. Second, a multi-scale attention-coupling feature-enhancement mechanism is proposed, effectively integrating hierarchical semantic information with spatial-channel attention to achieve both precise target localization and robust background suppression in the teacher network. Third, an enhanced anomaly discriminator is designed to incorporate an enhanced pyramid upsampling module, through which fine-grained details are preserved via multi-level feature map aggregation, resulting in significantly improved sensitivity for small-sized anomaly detection. Finally, the proposed method achieved an AUC of 94.0%, an ACC of 92.5%, and an F1 score of 91.6% on the MNIST dataset, and an AUC of 94.7%, an ACC of 90.1%, and an F1 score of 87.8% on the railway fastener dataset, which proves the superior anomaly detection ability of this method.
format Article
id doaj-art-721fbefabddf40ff947292faf83ec788
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-721fbefabddf40ff947292faf83ec7882025-08-20T02:32:34ZengMDPI AGApplied Sciences2076-34172025-05-011511593310.3390/app15115933An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial NetworksHongyan Chen0Zhiwei Li1Xinjie Xiao2School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaCollege of Information Science and Technology, Donghua University, Shanghai 201620, ChinaThe integrity and stability of railway fasteners are of vital importance to railway safety. To address the challenges of limited anomaly samples, irregular defect geometries, and complex operational conditions in rail fastener anomaly detection, this paper proposes an unsupervised anomaly detection method using a knowledge-distilled generative adversarial network. First, the proposed method employs collaborative teacher–student learning to model normal sample distributions, where the student network reconstructs input images as normal outputs while a discriminator identifies anomalies by comparing input and reconstructed images. Second, a multi-scale attention-coupling feature-enhancement mechanism is proposed, effectively integrating hierarchical semantic information with spatial-channel attention to achieve both precise target localization and robust background suppression in the teacher network. Third, an enhanced anomaly discriminator is designed to incorporate an enhanced pyramid upsampling module, through which fine-grained details are preserved via multi-level feature map aggregation, resulting in significantly improved sensitivity for small-sized anomaly detection. Finally, the proposed method achieved an AUC of 94.0%, an ACC of 92.5%, and an F1 score of 91.6% on the MNIST dataset, and an AUC of 94.7%, an ACC of 90.1%, and an F1 score of 87.8% on the railway fastener dataset, which proves the superior anomaly detection ability of this method.https://www.mdpi.com/2076-3417/15/11/5933rail fasteneranomaly detectionknowledge-distilled generative adversarial networkmulti-scale attention couplingmulti-level feature map aggregation
spellingShingle Hongyan Chen
Zhiwei Li
Xinjie Xiao
An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks
Applied Sciences
rail fastener
anomaly detection
knowledge-distilled generative adversarial network
multi-scale attention coupling
multi-level feature map aggregation
title An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks
title_full An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks
title_fullStr An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks
title_full_unstemmed An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks
title_short An Unsupervised Anomaly Detection Method for Railway Fasteners Based on Knowledge-Distilled Generative Adversarial Networks
title_sort unsupervised anomaly detection method for railway fasteners based on knowledge distilled generative adversarial networks
topic rail fastener
anomaly detection
knowledge-distilled generative adversarial network
multi-scale attention coupling
multi-level feature map aggregation
url https://www.mdpi.com/2076-3417/15/11/5933
work_keys_str_mv AT hongyanchen anunsupervisedanomalydetectionmethodforrailwayfastenersbasedonknowledgedistilledgenerativeadversarialnetworks
AT zhiweili anunsupervisedanomalydetectionmethodforrailwayfastenersbasedonknowledgedistilledgenerativeadversarialnetworks
AT xinjiexiao anunsupervisedanomalydetectionmethodforrailwayfastenersbasedonknowledgedistilledgenerativeadversarialnetworks
AT hongyanchen unsupervisedanomalydetectionmethodforrailwayfastenersbasedonknowledgedistilledgenerativeadversarialnetworks
AT zhiweili unsupervisedanomalydetectionmethodforrailwayfastenersbasedonknowledgedistilledgenerativeadversarialnetworks
AT xinjiexiao unsupervisedanomalydetectionmethodforrailwayfastenersbasedonknowledgedistilledgenerativeadversarialnetworks