Computational Technology Resources - CCC

X. Tang¹, X. Cai¹, Y. Wang¹, H. Peng¹ and Y. Hou²

¹School of Civil Engineering, Beijing Jiaotong University, China
²Department of Civil Engineering, Swansea University, United Kingdom

doi:10.4203/ccc.7.8.2

X. Tang, X. Cai, Y. Wang, H. Peng, Y. Hou, "Intelligent and Convenient Detection of Micrometer-Scale Rail Corrugation", in J. Pombo, (Editor), "Proceedings of the Sixth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 7, Paper 8.2, 2024, doi:10.4203/ccc.7.8.2

Keywords: rail corrugation, wavelet packet decomposition, dilated convolution, residual connection, car body acceleration, vehicle-track coupling dynamics.

Abstract

In the process of long-term operation of the railway, rail corrugation seriously affects the safe operation of vehicles and greatly increases the maintenance costs, so it is very necessary to know the degree of rail corrugation in advance. A wavelet packet time-convolutional neural network (WPTCN) is proposed to detect micrometer-scale rail corrugation by using car body acceleration, which is a low-cost and fast detection method. By taking the car body acceleration as input, the recognition accuracy of WPTCN for micron-scale rail corrugation at different wavelengths and amplitudes is compared. The results show that there is strong robustness, superiority of WPTCN. The recognition accuracy of WPTCN is 96.60% ~ 99.10% at different wavelengths and 95.40% ~ 100% at different amplitudes, which is a great improvement compared with the traditional model.

download the full-text of this paper (PDF, 13 pages, 1434 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 7 PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 8.2 Intelligent and Convenient Detection of Micrometer-Scale Rail Corrugation X. Tang¹, X. Cai¹, Y. Wang¹, H. Peng¹ and Y. Hou² ¹School of Civil Engineering, Beijing Jiaotong University, China ²Department of Civil Engineering, Swansea University, United Kingdom doi:10.4203/ccc.7.8.2 Full Bibliographic Reference for this paper X. Tang, X. Cai, Y. Wang, H. Peng, Y. Hou, "Intelligent and Convenient Detection of Micrometer-Scale Rail Corrugation", in J. Pombo, (Editor), "Proceedings of the Sixth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 7, Paper 8.2, 2024, doi:10.4203/ccc.7.8.2 Keywords: rail corrugation, wavelet packet decomposition, dilated convolution, residual connection, car body acceleration, vehicle-track coupling dynamics. Abstract In the process of long-term operation of the railway, rail corrugation seriously affects the safe operation of vehicles and greatly increases the maintenance costs, so it is very necessary to know the degree of rail corrugation in advance. A wavelet packet time-convolutional neural network (WPTCN) is proposed to detect micrometer-scale rail corrugation by using car body acceleration, which is a low-cost and fast detection method. By taking the car body acceleration as input, the recognition accuracy of WPTCN for micron-scale rail corrugation at different wavelengths and amplitudes is compared. The results show that there is strong robustness, superiority of WPTCN. The recognition accuracy of WPTCN is 96.60% ~ 99.10% at different wavelengths and 95.40% ~ 100% at different amplitudes, which is a great improvement compared with the traditional model. download the full-text of this paper (PDF, 13 pages, 1434 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions