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
. 2023 Nov 29;23(23):9501.
doi: 10.3390/s23239501.

A Study on Wheel Member Condition Recognition Using 1D-CNN

Jin-Han Lee  1 , Jun-Hee Lee  2 , Chang-Jae Lee  1 , Seung-Lok Lee  1 , Jin-Pyung Kim  3 , Jae-Hoon Jeong  2
Affiliations

A Study on Wheel Member Condition Recognition Using 1D-CNN

Jin-Han Lee et al. Sensors (Basel). .

Abstract

The condition of a railway vehicle's wheels is an essential factor for safe operation. However, the current inspection of railway vehicle wheels is limited to periodic major and minor maintenance, where physical anomalies such as vibrations and noise are visually checked by maintenance personnel and addressed after detection. As a result, there is a need for predictive technology concerning wheel conditions to prevent railway vehicle damage and potential accidents due to wheel defects. Insufficient predictive technology for railway vehicle's wheel conditions forms the background for this study. In this research, a real-time tire wear classification system for light-rail rubber tires was proposed to reduce operational costs, enhance safety, and prevent service delays. To perform real-time condition classification of rubber tires, operational data from railway vehicles, including temperature, pressure, and acceleration, were collected. These data were processed and analyzed to generate training data. A 1D-CNN model was employed to classify tire conditions, and it demonstrated exceptionally high performance with a 99.4% accuracy rate.

Keywords: deep learning; machine learning; recognizing condition algorithm; tire; wheel.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
(a) Uniform wear, (b) Tire bead crack.
Figure 2
Figure 2
Tire structure of railway vehicle wheels.
Figure 3
Figure 3
Measuring equipment installation signal diagram for railway vehicle wheels.
Figure 4
Figure 4
Installation of measuring equipment inside railway vehicles: (a) Temperature/pressure sensor installation (No.1,2), (b) Installation of acceleration sensor transmitter inside tire (No.7), (c) Installing acceleration sensor inside tire (No.3), (d) Installation of tire internal temperature/pressure sensor receiver (No.1,2), (e) Installing the acceleration sensor receiver inside the tire, (f) Axial acceleration sensor installation (No.4), (g) Speed sensor installation (No.5), (h) Data acquisition device installation (No.8), (i) Location of sensors installed on railway vehicles
Figure 4
Figure 4
Installation of measuring equipment inside railway vehicles: (a) Temperature/pressure sensor installation (No.1,2), (b) Installation of acceleration sensor transmitter inside tire (No.7), (c) Installing acceleration sensor inside tire (No.3), (d) Installation of tire internal temperature/pressure sensor receiver (No.1,2), (e) Installing the acceleration sensor receiver inside the tire, (f) Axial acceleration sensor installation (No.4), (g) Speed sensor installation (No.5), (h) Data acquisition device installation (No.8), (i) Location of sensors installed on railway vehicles
Figure 5
Figure 5
Tire temperature/pressure/acceleration correlation analysis: (a) T1 point correlation coefficient analysis heatmap, (b) T2 point correlation coefficient analysis heatmap, (c) T9 point correlation coefficient analysis Heatmap, (d) T10 point correlation coefficient analysis heatmap, (e) T15 point correlation coefficient analysis heatmap, (f) T16 point correlation coefficient analysis heatmap.
Figure 5
Figure 5
Tire temperature/pressure/acceleration correlation analysis: (a) T1 point correlation coefficient analysis heatmap, (b) T2 point correlation coefficient analysis heatmap, (c) T9 point correlation coefficient analysis Heatmap, (d) T10 point correlation coefficient analysis heatmap, (e) T15 point correlation coefficient analysis heatmap, (f) T16 point correlation coefficient analysis heatmap.
Figure 6
Figure 6
(a) Linearity relationship based on tire temperature, (b) Linearity relationship based on tire pressure.
Figure 7
Figure 7
Scatter plot of classification analysis of tire temperature/pressure/acceleration and tire condition at point T10.
Figure 8
Figure 8
1D–CNN-based tire condition classification using light-rail driving measurement data.
Figure 9
Figure 9
Tire condition classification model learning: (a) Loss graph, (b) Accuracy graph.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Shim J., Koo J., Park Y., Kim J. Anomaly Detection Method in Railway Using Signal Processing and Deep Learning. Appl. Sci. 2022;12:12901. doi: 10.3390/app122412901. - DOI
    1. Hou M.R., Wang W.D., Chang C., Li L. A study of rail wear on sharp curves in EMU maintenance depot. J. China Railw. Soc. 2018;40:45–50.
    1. Li T., Burdisso R., Sandu C. An Artificial Neural Network Model to Predict Tread Pattern–Related Tire Noise. SAE International; Warrendale, PA, USA: 2017. SAE Technical Paper. - DOI
    1. Ye Y., Zhu B., Huang P., Peng B. OORNet: A deep learning model for on–board condition monitoring and fault diagnosis of out–of–round wheels of high–speed trains. Measurement. 2022;199:111268. doi: 10.1016/j.measurement.2022.111268. - DOI
    1. Arastounia M. Automated recognition of railroad infrastructure in rural areas from LiDAR data. Remote Sens. 2015;7:14916–14938. doi: 10.3390/rs71114916. - DOI