Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jul 29:2021:2565500.
doi: 10.1155/2021/2565500. eCollection 2021.

A Defect Detection Method for Rail Surface and Fasteners Based on Deep Convolutional Neural Network

Danyang Zheng  1 , Liming Li  1   2 , Shubin Zheng  1 , Xiaodong Chai  1 , Shuguang Zhao  2 , Qianqian Tong  1 , Ji Wang  1 , Lizheng Guo  3
Affiliations

A Defect Detection Method for Rail Surface and Fasteners Based on Deep Convolutional Neural Network

Danyang Zheng et al. Comput Intell Neurosci. .

Abstract

As a result of long-term pressure from train operations and direct exposure to the natural environment, rails, fasteners, and other components of railway track lines inevitably produce defects, which have a direct impact on the safety of train operations. In this study, a multiobject detection method based on deep convolutional neural network that can achieve nondestructive detection of rail surface and fastener defects is proposed. First, rails and fasteners on the railway track image are localized by the improved YOLOv5 framework. Then, the defect detection model based on Mask R-CNN is utilized to detect the surface defects of the rail and segment the defect area. Finally, the model based on ResNet framework is used to classify the state of the fasteners. To verify the robustness and effectiveness of our proposed method, we conduct experimental tests using the ballast and ballastless railway track images collected from Shijiazhuang-Taiyuan high-speed railway line. Through a variety of evaluation indexes to compare with other methods using deep learning algorithms, experimental results show that our method outperforms others in all stages and enables effective detection of rail surface and fasteners.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no conflicts of interest regarding the publication of this paper.

Figures

Figure 1
Figure 1
Railway track line.
Figure 2
Figure 2
Overall framework of rail surface and fastener defect detection method.
Figure 3
Figure 3
Improved YOLOv5 network.
Figure 4
Figure 4
Backbone before and after improvements.
Figure 5
Figure 5
Ghost bottleneck.
Figure 6
Figure 6
Rail surface defect detection model.
Figure 7
Figure 7
Different types of SFC fastener state. (a) Normal. (b) Loosening. (c) Broken.
Figure 8
Figure 8
Division of the fastener state judgment area.
Figure 9
Figure 9
Residual block.
Figure 10
Figure 10
Image acquisition. (a) Picture of image acquisition in Shijiazhuang-Taiyuan high-speed railway line. (b) Special rail inspection vehicle.
Figure 11
Figure 11
Overall training process.
Figure 12
Figure 12
Training loss curve of the rail and fastener localization model.
Figure 13
Figure 13
Training loss curve of the rail surface defect detection model.
Figure 14
Figure 14
Visualization results of rail and fastener localization. (a) Ballastless track image. (b) Ballast track image.
Figure 15
Figure 15
Comparison of detection results of rail surface defects with different methods: (a) original image, (b) ground truth, (c) PSPNet, (d) Deeplabv3+, and (e) Mask R-CNN.
Figure 16
Figure 16
Accuracy of different fastener state classification models.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Jin X., Wang Y., Zhang H., et al. DeepRail: automatic visual detection system for railway surface defect using bayesian CNN and attention network. Acta Automatica Sinica. 2019;45(12):2312–2327.
    1. Xiao L., Wu B., Hu Y. Surface defect detection using image pyramid. IEEE Sensors Journal. 2020;20(13):7181–7188. doi: 10.1109/jsen.2020.2977366. - DOI
    1. Huang D., Liao S., Sunny A. I., Yu S. A novel automatic surface scratch defect detection for fluid-conveying tube of Coriolis mass flow-meter based on 2D-direction filter. Measurement. 2018;126:332–341. doi: 10.1016/j.measurement.2018.05.060. - DOI
    1. Wang J., Luo L., Ye W., Zhu S. A defect-detection method of split pins in the catenary fastening devices of high-speed railway based on deep learning. IEEE Transactions on Instrumentation and Measurement. 2020;69(12):9517–9525. doi: 10.1109/tim.2020.3006324. - DOI
    1. Peng L., Zheng S., Li P., Wang Y., Zhong Q. A comprehensive detection system for track geometry using fused vision and inertia. IEEE Transactions on Instrumentation and Measurement. 2021;70 doi: 10.1109/tim.2020.3039301.5004615 - DOI