Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network
Автоматическое обнаружение дефектов крепежных элементов устройств поддержки контактной сети с использованием глубоких сверточных нейронных сетей
2017-12-04
SCID: 54.1/2bbmuebc
Discuss with AI
catenary support devicescoarse-to-fine detectiondeep convolutional neural networksfastener defect detectionhigh-speed railway inspection
Figures from the paper
Abstract (AI)
The excitation and vibration triggered by the long-term operation of railway vehicles inevitably result in defective states of catenary support devices. With the massive construction of high-speed electrified railways, automatic defect detection of diverse and plentiful fasteners on the catenary support device is of great significance for operation safety and cost reduction. Nowadays, the catenary support devices are periodically captured by the cameras mounted on the inspection vehicles during the night, but the inspection still mostly relies on human visual interpretation. To reduce the human involvement, this paper proposes a novel vision-based method that applies the deep convolutional neural networks (DCNNs) in the defect detection of the fasteners. Our system cascades three DCNN-based detection stages in a coarse-to-fine manner, including two detectors to sequentially localize the cantilever joints and their fasteners and a classifier to diagnose the fasteners' defects. Extensive experiments and comparisons of the defect detection of catenary support devices along the Wuhan-Guangzhou high-speed railway line indicate that the system can achieve a high detection rate with good adaptation and robustness in complex environments.
Key Findings
1
Comparative evaluations indicate that the proposed system adapts well and remains robust in complex inspection environments.
2
Experiments on catenary support devices along the Wuhan–Guangzhou high-speed railway line demonstrate a high detection rate.
3
The approach aims to reduce reliance on human visual interpretation of nighttime railway inspection images, supporting safer and more cost-effective maintenance.
4
The paper introduces a vision-based deep convolutional neural network system for automatic defect detection of catenary support fasteners.
5
The system uses three cascaded DCNN stages in a coarse-to-fine pipeline: cantilever-joint localization, fastener localization, and defect classification.
Research Object
Fasteners on railway catenary support devices
Research Subject
Automatic vision-based detection and diagnosis of fastener defects, including localization, detection rate, adaptation, and robustness in complex environments
Publication Details
Publication Date
2017-12-04
Journal
Publisher
ISSN
Cited by
465
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest