Random-Forest Machine Learning Approach for High-Speed Railway Track Slab Deformation Identification Using Track-Side Vibration Monitoring
Source abstract
Abstract
High-speed railways (HSRs) are established all over the world owing to their advantages of high speed, ride comfort, and low vibration and noise. A ballastless track slab is a crucial part of the HSR, and its working condition directly affects the safe operation of the train. With increasing train operation time, track slabs suffer from various defects such as track slab warping and arching as well as interlayer disengagement defect. These defects will eventually lead to the deformation of track slabs and thus jeopardize safe train operation. Therefore, it is important to monitor the condition of ballastless track slabs and identify their defects. This paper proposes a method for monitoring track slab deformation using fiber optic sensing technology and an intelligent method for identifying track slab deformation using the random-forest model. The results show that track-side monitoring can effectively capture the vibration signals caused by train vibration, track slab deformation, noise, and environmental vibration. The proposed intelligent algorithm can identify track slab deformation effectively, and the recognition rate can reach 96.09%. This paper provides new methods for track slab deformation monitoring and intelligent identification.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Railway Engineering and Dynamics · Structural Health Monitoring Techniques · Advanced Fiber Optic Sensors
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Civil Engineering, Wuhan University, Wuhan 430072, China
School of Civil Engineering, Beijing Jiaotong University, Beijing 100044, China
School of Computer Science and Engineering, Beihang University, Beijing 100191, China
References (64)
Show source-provided references
1. Measurement, analysis, and model updating based on the modal parameters of high-speed railway ballastless track10.1016/j.measurement.2020.107891 ↗
2. (2021, March 18). Statistical Bulletin 2020 of China Railway. Available online: http://baijiahao.baidu.com/s?id=1691683529166535242.
3. Effect of cement asphalt mortar debonding on dynamic properties of CRTS II slab ballastless track
4. Li, Z.W., Liu, X.Z., and He, Y.L. (2019). Identification of temperature-induced deformation for HSR Slab track using track geometry measurement data. Sensors, 19.10.3390/s19245446 ↗
5. Temperature warping deformation and modification of longitudinal slab-type ballastless track structure on bridge
6. Analysis of damage of joints in CRTS II slab track under temperature and vehicle loads10.1007/s12205-020-1799-y ↗
7. Influence of damage of wide and narrow joints on mechanical performance of CRTS II slab-type ballastless track CWR
8. Study on the mechanical performance and interface damage of CRTS II slab track with debonding repairment10.1016/j.conbuildmat.2020.119600 ↗
9. Recognition algorithm for the disengagement of cement asphalt mortar based on dynamic responses of vehicles10.1177/0954409718794018 ↗
10. Influence of slab arch imperfection of double-block ballastless track system on vibration response of high-speed train10.1007/s40430-018-0972-4 ↗
11. Ma, Z.R., Gao, L., Zhong, Y.L., Ma, S., and An, B.L. (2020). Arching detection method of slab track in high-speed railway based on track geometry data. Appl. Sci., 10.10.3390/app10196799 ↗
12. Arching mechanism of the slab joints in CRTS II slab track under high temperature conditions10.1016/j.engfailanal.2019.01.076 ↗
13. Zhao, L., Zhou, L.Y., Zhang, G.C., Wei, T.Y., Mahunon, A.D., Jiang, L.Q., and Zhang, Y.Y. (2020). Experimental study of the temperature distribution in CRTS II ballastless tracks on a high-speed railway bridge. Appl. Sci., 10.10.3390/app10061980 ↗
14. Interface damage and its effect on vibrations of slab track under temperature and vehicle dynamic loads10.1016/j.ijnonlinmec.2013.10.004 ↗
15. Singh, M., Singh, S., Jaiswa, J., and Hernpshall, J. (2006, January 16–17). Autonomous rail track inspection using vision based system. Proceedings of the IEEE International Conference on Computational Intelligence for Homeland Security & Personal Safety, Alexandria, VA, USA.10.1109/CIHSPS.2006.313313 ↗
16. Automated Visual Inspection of Railroad Tracks10.1109/TITS.2012.2236555 ↗
17. Research on detection method of gap caused by camber of CRTS II track slab
18. Ke, Y.T., Cheng, C.C., Lin, Y.C., Ni, Y.Q., Hsu, K.T., and Wai, T.T. (2020). Preliminary study on assessing delaminated cracks in cement asphalt mortar layer of high-speed rail track using traditional and normalized impact–echo methods. Sensors, 20.10.3390/s20113022 ↗
19. Damage detection of ballastless railway tracks by the impact-echo method
20. Pierre, A.B. (2019). Performance Evaluation of Impact Echo Method for Detection of Cavity Underneath a Concrete Slab Track Using Finite Element Method. [Master’s Thesis, Pai Chai University].
21. Curvelet transform-based identification of void diseases in ballastless track by ground penetrating radar10.1002/stc.2322 ↗
22. Detection of ballastless track diseases in high-speed railway based on ground penetrating radar
23. Zhang, J.X., Huang, W.Z., Zhang, W.T., Li, F., and Du, Y.L. (2021). Train-induced vibration monitoring of track slab under long-term temperature load using fiber-optic accelerometers. Sensors, 21.10.3390/s21030787 ↗
24. Application of optical-fiber Bragg grating sensors in monitoring the rail track deformations10.1520/GTJ20140123 ↗
25. Study of ballastless track structure monitoring by distributed optical fiber sensors on a real-scale mockup in laboratory10.1016/j.engstruct.2013.07.005 ↗
26. An analysis of railway track behaviour based on distributed optical fibre acoustic sensing10.1016/j.ymssp.2020.106769 ↗
27. Research on monitoring technology of track slab upwarp based on distributed optical fiber sensing
28. Gao, W.H. (2020). Study on Analytical Method of Track Geometrical Irregularities for High-Speed Railway. [Master’s Thesis, Beijing Jiaotong University].
29. Fault diagnosis for wind turbine transmission systems via demodulation analysis based on EEMD and energy separation
30. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis10.1098/rspa.1998.0193 ↗
31. He, Y.F. (2016). Research on the Rail Defect Detection and Identification of the Urban Rail Transit. [Master’s Thesis, Beijing Jiaotong Unviersity].
32. Ning, J. (2011). Study on the Time-Frequency Analysis by EMD and Cohen’s Kernel and Application in Track. [Ph.D. Thesis, Southwest Jiaotong University].
33. Chen, X.M. (2006). Time-Frequency Analysis and Prediction Study on Track Irregularities. [Ph.D. Thesis, Institute of Railway Science].
34. Study on identification of CA mortar layer void based on convolution neural network
35. The local mean decomposition and its application to EEG perception data10.1098/rsif.2005.0058 ↗
36. Fault diagnosis of rolling bearing based on improved LMD and comprehensive characteristic index
37. Research on signal feature extraction method of LMD-KICA rolling bearing
38. An improved local mean decomposition method based on improved composite interpolation envelope and its application in bearing fault feature extraction10.1016/j.isatra.2019.07.027 ↗
39. Kocbek, S., and Gabrys, B. (2019, January 8–11). Automated machine learning techniques in prognostics of railway track defects. Proceedings of the International Conference on Data Mining Workshops (ICDMW), Beijing, China.10.1109/ICDMW.2019.00115 ↗
40. Acoustic emission wave classification for rail crack monitoring based on synchrosqueezed wavelet transform and multi-branch convolutional neural network
41. Zhan, Y., Dai, X.X., Yang, E.H., and Wang, K.C.P. (2020). Convolutional neural network for detecting railway fastener defects using a developed 3D laser system. Int. J. Rail Transp., 1–21.10.1080/23248378.2020.1825128 ↗
42. Railway fastener fault diagnosis based on generative adversarial network and residual network model
43. Real-time inspection system for ballast railway fasteners based on point cloud deep learning10.1109/ACCESS.2019.2961686 ↗
44. Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study10.1016/j.engappai.2019.01.008 ↗
45. Prediction of mechanical properties of rail pads under in-service conditions through machine learning algorithms10.1016/j.advengsoft.2020.102927 ↗
46. Zhuang, Z., Zhang, G.H., Dong, W., Sun, X.Y., and Wang, C.J. (2018, January 11–14). Intelligent fault detection of high-speed railway turnout based on hybrid deep learning. Proceedings of the 31st Australasian Joint Conference on Artificial Intelligence, Wellington, New Zealand.10.1007/978-3-030-03991-2_10 ↗
47. Li, W.J., Shen, Z.H., and Li, P.G. (2019, January 14–15). Crack detection of track plate based on YOLO. Proceedings of the 12th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China.10.1109/ISCID.2019.10086 ↗
48. Automated crack severity level detection and classification for ballastless track slab using deep convolutional neural network10.1016/j.autcon.2020.103484 ↗
49. Damage identification of CA mortar layer of CRTS Ⅰ slab track based on BP neural network
50. Monitoring technology for deformation of key sections of CRTS Ⅱ slab ballastless track foundation
51. Zhou, Z.H. (2016). Machine Learning, Tsinghua University Press. [1st].
52. Zhang, L.H., Ni, Y.Q., Lai, S., and Wang, S.G. (2018, January 17–19). A novel machine learning technique for online health monitoring of high-speed trains. Proceedings of the 2nd International Workshop on Structural Health Monitoring for Railway System, Qingdao, China.
53. Chen, X.Y. (2015). Research and Application of Intrusion Detection Technology Based on Features Analysis and Support Vector Machines. [Master’s Thesis, Beijing University of Posts and Telecommunications].
54. Meng, D.M. (2012). Study on the Structural Damage Identification Based on the Free Response Signal and Neural Network. [Master’s Thesis, Qingdao Technological University].
55. Bagging predictors10.1007/BF00058655 ↗
56. All-metal optical fiber accelerometer with low transverse sensitivity for seismic monitoring10.1109/JSEN.2013.2270554 ↗
57. Comparison between the methods of local mean decomposition and empirical mode decomposition
58. Buda, A., and Jarynowski, A. (2010). Life Time of Correlations and its Applications, Wydawnictwo Niezalezne.
59. Wang, Y.M. (2019). Study on the Structural Damage Identification Based on the Response and PSO-SVM. [Master’s Thesis, Qingdao University of Technology].
60. Identifying the damage degree of structure based on empirical mode decomposition and parameters in time domain amplitude
61. Wu, S.S. (2018). Research on Void Detection Method of CRTS Ⅱ Slab Track Based on Transient Impulse Response. [Master’s Thesis, Shijiazhuang Tiedao University].
62. Zhou, T.L. (2016). Research on Structural Damage Identification Method Based on CEEMD. [Master’s Thesis, Changsha University of Technology].
63. Random forests10.1023/A:1010933404324 ↗
64. Machine learning-based decision tree classifier for the diagnosis of progressive supranuclear palsy and corticobasal degeneration