Abstract
High-speed railway is a comprehensive carrier of high-technology. As an important infrastructure of high - speed rail tracks, rail breakage and derailment accidents caused by rail rolling contact fatigue crack damage are quite common. Considering that a single eddy current pulsed thermography cannot directly and very accurately make a quantitative estimate of the geometric parameters of Rolling Contact Fatigue (RCF), this paper proposes a rail contact fatigue crack damage identification system and method based on the fusion of 2D optical images and eddy current thermography. A mathematical - physical model of Poisson reconstruction degree for the fusion of 2D optical images and eddy current thermography is proposed to quantitatively characterize the geometric parameters of rail cracks, such as length and depth. A rail contact fatigue crack damage identification robot system based on the fusion of 2D optical images and eddy current thermography is designed and built. Experiments are carried out to compare the detection accuracy of crack geometric parameter identification in static and dynamic (different motion states) modes, as well as to study the impact on the quantification of crack geometric parameters. The experimental results show that the proposed Poisson reconstruction degree based on the fusion of 2D optical images and eddy current thermography has good robustness in quantifying crack geometric parameters in the slow - speed mode, verifying the effectiveness of the system and method.
Data availability
The datasets generated and/or analysed during the current study are not publicly available due [This research project is a major ongoing scientific research project, which involves key enterprises in the relevant industry and is protected by technical confidentiality agreements signed with partner enterprises. It is precisely these agreements that restrict the public sharing of data to safeguard the intellectual property rights and business interests of the partnering enterprises. We have obtained all the necessary permissions for using these data within the scope of this thesis publication. However, unfortunately, we are unable to make these data publicly available.] but are available from the corresponding author on reasonable request.
References
Zhijun, Chen, Jianqing, Xuan & Ping, Wang. Identification of inclined cracks in steel rails based on leakage magnetic signals [J]. Non Destr. Test. 32(11), 842–846 (2023).
Lianqing, Zhu, Junhua, Sun & Mingli, Dong. Research on high speed rail flaw detection system [J]. Instrumen. Rep. 23(3), 119–121 (2023).
Peng, Hu., Haitao, Wang & Guiyun, Tian. Research on the identification method of rail cracks based on ultrasonic guided waves [J]. J. Railway 44(10), 105–112 (2022).
Hongbing, Zhang, Yanan, Song & Yaru, Chen. A method for detecting surface defects of steel rails based on convolutional neural networks [J]. China Railway Sci. 43(4), 141–148 (2022).
Clark, R. Rail flaw detection: overview and needs for future developments [J]. NDT & E Int. 37(2), 111–8 (2004).
Lu Chao, Tu Zhankuan, Cheng Jianjun, et al. Research progress on RCF damage characteristics and NDT of high-speed railway rails [J]. Failure Analysis and Prevention, 2009, 01): 51-7Hesse D, Cawley P. Defect detection in rails using ultrasonic surface waves J].Insight, 49(6): 318-26. (2007)
Edwards R S, Fan Y, Papaelias M, et al. ultrasonic detection of surface breaking railhead defects [J]. AIP Conference Proceedings 975(1): 602-9. (2008)
Lau, S. K., Almond, D. P. & Milne, J. M. A quantitative analysis of pulsed video thermography[J]. NDT E Int. 24, 195–202 (1991).
Luchao, Tu ZhanKuan, chengjianjun, etal. research progress on RCF damage characteristics and NDT of high speed railway rail [J].Failure analysis and prevention, 01: 51-7 (2009)
Papaelias M, Kerkyras S, Papaelias F, et al.The future of rail inspection technology and the INTERAIL FP7 project[C].51st Annual Conference of the British Institute of Non-Destructive Testing 2012 148-156. (2012)
Nafiah, F. et al. Quantitative evaluation of crack depths and angles for pulsed eddy current non-destructive testing[J]. NDT E Int. 102(3), 180–8 (2019).
Tian, G. Y. & Sophian, A. Defect classification using a new feature for pulsed eddy current sensors[J]. Ndt & E. Int. 38(1), 77–82 (2005).
He, Y. Z. et al. Defect edge identification with rectangular pulsed eddy current sensor based on transient response signals[J]. NDT E Int. 43(5), 409–15 (2010).
Wilson, J. et al. PEC thermography for imaging multiple cracks from rolling contact fatigue[J]. NDT E Int. 44(6), 505–12 (2011).
Cannon, D. F. et al. Rail defects: an overview [J]. Fatigue Fract. Eng. Mater. Struct. 26(10), 865–86 (2003).
Sadeghi, F. et al. A review of rolling contact fatigue. J. Tribol. 131(4), 220 (2009).
Machikhin, A. et al. Combined acoustic emission and digital image correlation for early detection and measurement of fatigue cracks in rails and train parts under dynamic loading[J]. Sensors 22(23), 9256 (2022).
Allen D H, Dorsett G, Kim Y R. Development of a computational model for predicting fracture in rails subjected to long-term cyclic fatigue loading[R]. University Transportation Center for Railway Safety (UTCRS) Tier-1 University Transportation Center (UTC) (2024).
Rowshandel, H. et al. Characterisation of clustered cracks using an ACFM sensor and application of an artificial neural network[J]. NDT E Int. 98, 80–8 (2018).
Ahmad, M. et al. Crack detection in railway track using the ai based image recognition techniques. Int. J. Softw. Hardware Res. Eng. 10(8), 80–87 (2022).
Tuschl, C., Oswald-Tranta, B. & Eck, S. Inductive thermography as non-destructive testing for railway rails. Appl. Sci. 11(15), 7156 (2021).
Jiang, Y., Wang, R. Y., Han, L. & Wang, Z. X. Quantitative detection of rail head oblique cracks by laser ultrasonic surface wave. Russian J. Nondestruct. Testing 59, 1151–1164 (2023).
Yang, H. F. et al. Deep learning and machine vision-based inspection of rail surface defects. IEEE Trans. Instrum. Meas. 71, 1–14 (2022).
Zhang, H. et al. MRSDI-CNN: multi-model rail surface defect inspection system based on convolutional neural networks. IEEE Trans. Intell. Transp. Syst. 23, 11162 (2021).
Ge, H. et al. Guided wave-based rail flaw detection technologies: state-of-the-art review. Struct. Health Monit. 21, 1287–1308 (2022).
Xu, Q. et al. Total focusing method approach of ultrasonic phased array based on compressed sensing. Russian J. Nondestruct. Testing 58, 355–368 (2022).
Chen, C., Sun, A., Ju, B. F. & Wang, C. Width and depth gauging of rectangular subsurface defects based on all-optical laser-ultrasonic technology. Appl. Acoust. 191, 108684 (2022).
Ying, K. N. et al. Multi-mode laser-ultrasound imaging using time-domain synthetic aperture focusing technique (t-saft). Photoacoustics 27, 100370 (2022).
Hu, P. et al. Wireless localization of spallings in switch-rails with guided waves based on a time-frequency method. IEEE Sens. Jour. 19, 11050–11062 (2019).
Hu, P. et al. Multifunctional flexible sensor array-based damage monitoring for switch rail μsing passive and active sensing. Smart Mater. Struct. 9, 95013 (2020).
Gao, Y. et al. Electromagnetic pulsed thermography for natural cracks inspection. Sci. Rep. 7, 1–9 (2017).
Fu, S., & Jiang, Z. Research on image-based detection and recognition technologies for cracks on rail surface. 2019 International Conference on Robots & Intelligent Systems (ICRIS). (2019)
Bai, R., Men, D., Yu, L. & Wang, D. Research on surface crack detection based on computer image recognition. J. Phys.: Conf. Series 1992, 032029 (2021).
Wang, Qiang et al. Performance evaluation of austenitic stainless steel weld by ultrasonic phased array inspection based on probability of detection. Russian J. Nondestruct. Testing 56(7), 566–573 (2020).
Acknowledgements
This research is financially supported by National Natural Science Foundation of China [51775456], the KeyR&D projects in Sichuan Province [2023YFG0197], the Self-developed Research Project of theState Key Laboratory of Traction Power [2023TPL_T08], and the Basic Scientific ResearchBusiness Expenses of Central Universities - Special Research Project [2682022ZTPY007].
Funding
This research is financially supported by National Natural Science Foundation of China, 51775456, 51775456, 51775456, 51775456, the KeyR& D projects in Sichuan Province, 2023YFG0197, 2023YFG0197, 2023YFG0197, 2023YFG0197, he Self-developed Research Project of theState Key Laboratory of Traction Power,2023TPL_T08,2023TPL_T08,2023TPL_T08,2023TPL_T08, and the Basic Scientific ResearchBusiness Expenses of Central Universities - Special Research Project, 2682022ZTPY007, 2682022ZTPY007, 2682022ZTPY007, 2682022ZTPY007.
Author information
Authors and Affiliations
Contributions
The contributions of each author are presented as follows: 1) Yu Wang – This author is responsible for the subject investigation, further development and manuscript writing and editing. 2) Bingrong Miao –This author is the original inventor of ECPT, supervised the study and assisted in reviewing, edited the manuscript, and is in charge of project administration and funding acquisition. 3) Ying Zhang – This author assisted on the scientific supervision, reviewing and editing the manuscript. 4) Zhong Huang – This author assisted on designing the artificial cracks on the rail surface.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Wang, Y., Miao, B., Zhang, Y. et al. Research on geometric parameter quantification of rail rolling contact fatigue crack damage based on 2D optical image. Sci Rep (2026). https://doi.org/10.1038/s41598-026-36276-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-36276-w
