Learning Based Experimental Approach For Condition Monitoring Using Laser Cameras In Railway Tracks

Abstract

Detecting the rail surface faults is one of the most important components of railway inspection process which should be performed periodically. Today, the railway inspection process is commonly performed using computer vision. Performing railway inspection based on image processing can lead to false-positive results. The fact that the oil and dust residues occurring on railway surfaces can be detected as an error by the image processing software can lead to loss of time and additional costs in the railway maintenance process. In this study, a hardware and software architecture are presented to perform railway surface inspection using 3D laser cameras. The use of 3D laser cameras in railway inspection process provides high accuracy rates in real time. The reading rate of laser cameras to read up to 25.000 profiles per second is another important advantage provided in real time railway inspection.  Consequently, a computer vision-based approach in which 3D laser cameras that could allow for contactless and fast detection of the railway surface and lateral defects such as fracture, scouring and wear with high accuracy are used in the railway inspection process was proposed in the study. 

Keywords

• Railway Inspection,Anomaly Detect,Computer Vision,Laser Camera

References

1. [1] Y. Tai-shan, C. & Du-wu. The method of intelligent inspection of product quality based on computer vision, In 2006 7th International Conference on Computer-Aided Industrial Design and Conceptual Design , pp. 1-6, IEEE, 2006.
2. [2] S. Zheng, X. Chai, X. An, L. Li. Railway track gauge inspection method based on computer vision, In 2012 IEEE International Conference on Mechatronics and Automation, pp.1292-1296, IEEE, 2012.
3. [3] Q. Li, Z. Zhong, Z. Liang, Y. Liang. Rail Inspection Meets Big Data: Methods and Trends, In Network-Based Information Systems (NBiS), 2015 18th International Conference, pp.302-308, IEEE, 2015.
4. [4] D. F. Cannon, K. O. EDEL, S. L. Grassie, K. Sawley. Rail defects: an overview, Fatigue & Fracture of Engineering Materials & Structures, 26(10), 865-886, 2003.
5. [5] www.cater-eu.com/gallery, “C.A.T.E.R”. [Online]. 2016
6. [6] Y. Santur, M. Karaköse, İ. Aydın and E. Akın. IMU based adaptive blur removal approach using image processing for railway inspection, In 2016 International Conference on Systems, Signals and Image Processing (IWSSIP), pp.1-4, IEEE, May, 2016.
7. [7] E. Resendiz, L. F. Molina, J. M. Hart, J. R. Edwards, S. Sawadisavi, N. Ahuja and C. P. L. Barkan. Development of a machine-vision system for inspection of railway track components, In 12th World Conference on Transport Research, 12.WCTR, Lisbon, Portugal, 2010.
8. [8] R. Huber-Mörk, M. Nölle, A. Oberhauser, E. Fischmeister. Statistical Rail Surface Classification Based on 2D and 21/2D Image Analysis, In Advanced Concepts for Intelligent Vision Systems, pp.50-61, 2010

9. [9] T. Hackel, D. Stein, I. Maindorfer, M. Lauer and A. Reiterer. Track detection in 3-D laser scanning data of railway infrastructure, I2MTC, 2015 IEEE International (pp. 693-698), 2015.
10. [10] İ. Aydın, E. Karaköse, M. Karaköse, M.T. Gencoglu and E. Akın. A New Computer Vision Approach for Active Pantograph Control, IEEEInternational Symposium on Innovations in Intelligent Systems and Applications (IEEE INISTA 2013), Albena, Bulgaria, 2013.
11. [1] X. Peng, J Liang. 3D Detection Technique of Surface Defects for Steel Rails Based on Linear Lasers, Journal of Mech. Eng., 8, 003, 2010.
12. [2] M. Karakose and E. Akin., Type-2 fuzzy activation function for multilayer feedforward neural networks, In Systems, Man and Cybernetics, 2004 IEEE Int. Conf. on (Vol. 4, pp. 3762-3767), 2004.
13. [3] Y. Santur, M. Karakose, E. Akin. Random Forest Based Diagnosis Approach for Rail Fault Inspection in Railways, International Conference on Electrical and Electronics Engineering (Eleco 2015), 9.th, pp.714-719, 2015.
14. [4] H. Misawa, S. Juodkazis. 3D laser microfabrication: principles and applications, John Wiley & Sons, 2006.
15. [5] G. Zhang, Z. Wei, “A novel calibration approach to structured light 3D vision inspection”, Optics&Laser Technology, 34(5), pp.373-380, 2002.
16. [6] Santur Y., Karaköse M., Akın E. Condition Monitoring Approach Using 3d Modelling Of Railway Tracks With Laser Cameras, International Conference on Advanced Technology & Sciences (ICAT’16) pp. 132-135, 2016.
17. [7] M. Karaköse, Reinforcement Learning Based Artificial Immune Classifier, The Scientific World Journal-Computer Science, vol. 2013, Article ID 581846, 7 pages, 2013. doi:10.1155/2013/581846.
18. [8] M. Karaköse. Sensor Based Intelligent Systems for Detection and Diagnosis, Journal of Sensors, Editorial, vol 2016, Article ID 5269174, 1 pages, 2016. doi:10.1155/2016/5269174.
19. [9] AT sensor intelligence, ”3d Laser Cameras”, automationtechnology.de, 2016.
20. [10] P. Dubath, L. Rimoldini, M. Süveges, J. Blomme, M. López, L. M. Sarro, K. Nienartowicz, “Random forest automated supervised classification of Hipparcos periodic variable stars”, , 414(3), pp.2602-2617, 2011.