Abstract
A multi-robot-based fault detection system for railway tracks is proposed to eliminate manual human visual inspection. A hardware prototype is designed to implement a master–slave robot mechanism capable of detecting rail surface defects, which include cracks, squats, corrugations, and rust. The system incorporates ultrasonic sensor inputs coupled with image processing using OpenCV and deep learning algorithms to classify the surface faults detected. The proposed Convolutional Neural Network (CNN) model fared better compared to the Artificial Neural Network (ANN), random forest, and Support Vector Machine (SVM) algorithms based on accuracy, R-squared value, F1 score, and Mean-Squared Error (MSE). To eliminate manual inspection, the location and status of the fault can be conveyed to a central location enabling immediate attention by utilizing GSM, GPS, and cloud storage-based technologies. The system is extended to a multi-robot framework designed to optimize energy utilization, increase the lifetime of individual robots, and improve the overall network throughput. Thus, the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol is simulated using 100 robot nodes, and the corresponding performance metrics are obtained.
Similar content being viewed by others
References
ARTC (Australian Rail Track Corporation) (2006) Rail defects handbook some rail defects, their characteristics, causes and control. Eng Pract Manual, (A):1–68
Singh M, Singh S, Jaiswal J, Hempshall J (2006) Autonomous rail track inspection using vision based system. In: 2006 IEEE International conference on computational intelligence for homeland security and personal safety, Alexandria, VA, pp 56–59
Zhan Dong, Yu L, Xiao Jian, Chen T-L (2014) Study on track wear cross-section measurement utilizing laser-photogrammetric technique. J China Railw Soc 36:32–37
Gao Y, Wang P, Wang H, Shi Y (2016) Review of railway rail defect non-destructive testing and monitoring. Yi Qi Yi Biao Xue Bao/Chin J Sci Instrument 37:1763–1780
Xing L (2008) Research on defect characteristics and classification of higher speed rails. China Academy of Railway Sciences, Beijing
Singh AK et al (2019) Vision based rail track extraction and monitoring through drone imagery. ICT Express. 5(4):250–255
Min Y, Xiao B, Dang J et al (2018) Real time detection system for rail surface defects based on machine vision. J Image Video Proc. 2018:3
Shah AA et al (2020) Real time identification of railway track surface faults using canny edge detector and 2D discrete wavelet transform. Ann Emerging Technol Comput (AETiC) 4(2):53–60
Malekjafarian A et al (2019) Railway track monitoring using train measurements: an experimental case study. Appl Sci 9(22):4859
Kostryzhev AG, Davis CL, Roberts C (2013) Detection of crack growth in rail steel using acoustic emission. Ironmak Steelmak 40(2):98–102
Liu X-Z, Ni Y-Q, Wu W-L, Pei Y-F, Hou YH, Qin D-Y (2015) AET-based Pattern Recognition Technique for Rail Defect Detection. https://doi.org/10.12783/shm2015/252
Feng N, Zhang X, Zou Z, Wang Y, Yi S (2015) Rail health monitoring using acoustic emission technique based on NMF and RVM. In: 2015 IEEE international instrumentation and measurement technology conference (I2MTC) proceedings, Pisa, pp 699–704
Li Qingyong, Ren Shengwei (2012) A real-time visual inspection system for discrete surface defects of rail heads. IEEE Trans Instrument Meas 61(8):2189–2199
Li Q, Ren S (2012) A visual detection system for rail surface defects. IEEE Trans Syst Man Cybern Part C (Appl Rev) 42(6):1531–1542
Liu Scarlett, Wang Quandong, Luo Yiping (2019) A review of applications of visual inspection technology based on image processing in the railway industry. Transp Safety Environ 1(3):185–204
Mariani S, Nguyen T, Phillips RR, Kijanka P, LanzadiScalea F, Staszewski WJ, Fateh M, Carr G, Mariani S (2013) Noncontact ultrasonic guided wave inspection of rails. Struct Health Monitoring 12(5–6):539–548
Molodova Maria, Li Zili, Núñez Alfredo, Dollevoet Rolf (2014) Automatic detection of squats in railway infrastructure. IEEE Trans Intell Transp Syst 15(5):1980–1990
Wei X et al (2020) Multi-target defect identification for railway track line based on image processing and improved YOLOv3 Model. IEEE Access 8:61973–61988
Pahwa RS et al (2019) FaultNet: faulty rail-valves detection using deep learning and computer vision. In: 2019 IEEE intelligent transportation systems conference (ITSC). IEEE
James A et al (2018) Tracknet-a deep learning based fault detection for railway track inspection. In: 2018 International conference on intelligent rail transportation (ICIRT). IEEE
Yanan S, Hui Z, Li L, Hang Z (2018) Rail surface defect detection method based on YOLOv3 deep learning networks. In: 2018 Chinese Automation Congress (CAC), Xi’an, China, pp 1563–1568, https://doi.org/10.1109/CAC.2018.8623082
Cao Xiaohui, Xie Wen, Ahmed Siddiqui, Li Cunrong (2020) Defect detection method for rail surface based on line-structured light. Measurement 159:107771. https://doi.org/10.1016/j.measurement.2020.107771
Heinzelman WR, Chandrakasan A, Balakrishnan H (2000) Energy-efficient communication protocol for wireless sensor networks. In: Proceedings of the 33rd Annual Hawaii International Conference on System Sciences, Maui, HI, USA, pp. 10 pp. vol 2, pp 1–10
Budes Antoni, Coll Bartomeu, Morel Jean-Michel (2011) Non-local means denoising. Image Process Line 1:208–212
Bay H, Tuytelaars T, Van Gool L (2006) SURF: speeded up robust features. In: Leonardis A, Bischof H, Pinz A (eds) Computer Vision—ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3951. Springer, Berlin. https://doi.org/10.1007/11744023_32
Perrig A, Szewczyk R, Tygar JD, Wen V, Culler DE (2002) SPINS: security protocols for sensor networks. Wireless Netw 8(5):521–534, Kluwer Academic Publishers, MA, USA
Karlof C, Sastry N, Wagner D (2004) TinySec: a link layer security architecture for wireless sensor networks. In: SenSys ‘04: proceedings of the 2nd international conference on Embedded Networked Sensor Systems, pp 162–175, ACM, NY, USA
Li T, Wu H, Wang X, Bao F (2005) SenSec: sensor security framework for TinyOS. In: Proceedings of the second international workshop on networked sensing systems, pp 145–150. San Diego, USA
Luk M, Mezzour G, Perrig A, Gligor V (2007) MiniSec: a secure sensor network communication architecture. In: Proceedigns of the ACM international conference on information processing in sensor networks, pp 479–488, ACM, NY
Jinwala D, Patel D, Dasgupta K (2012). FlexiSec: a configurable link layer security architecture for wireless sensor networks. J Inf Assurance Secur Special Issue Inf Assurance Data Security 4
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Iyer, S., Velmurugan, T., Gandomi, A.H. et al. Structural health monitoring of railway tracks using IoT-based multi-robot system. Neural Comput & Applic 33, 5897–5915 (2021). https://doi.org/10.1007/s00521-020-05366-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05366-9