Rail Defect Recognition Based on Waveform Subtraction and Rule Base
Publication: Journal of Performance of Constructed Facilities
Volume 36, Issue 1
Abstract
Internal defects in rail may affect the safety of the train travel and deteriorate the infrastructure of rail transit. However, the existing manual defect detection mode has difficulty coping with the increasing mileage and defect detection data. To accomplish the comprehensive detection of internal defects in rail, we propose a waveform subtraction recognition method based on rail defect features in B-scan images. First, rail structure waveforms are detected based on the You Only Look Once (YOLO) v4 network. Then, after removing normal structure waveforms, abnormal waveforms of defect are located. Last, according to the law of B-scan imaging and relationships with structure waveforms, abnormal waveforms are screened and classified into specific types of defect by the rule base. The detection method was tested on a real-world data set, and the test results showed that the accuracy of normal waveform detection was 0.871 and the accuracy of defect detection was 0.755. Furthermore, previous defect detection methods were compared, and results showed that the proposed method is feasible for the comprehensive detection of rail defects.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This research is supported by the National Natural Science Foundation of China (Grant No. 61703308), the National Key R&D Program of China (2016YFB1200402), and Sichuan Province Science and Technology Program (2019YFG0040). The authors gratefully acknowledge the invaluable contribution of the reviewers.
References
Alahakoon, S., Y. Q. Sun, M. Spiryagin, and C. Cole. 2017. “Rail flaw detection technologies for safer, reliable transportation: A review.” J. Dyn. Syst. Meas. Control 140 (020801): 1–17. https://doi.org/10.1115/1.4037295.
Ananth, C., and K. Nagarajan. 2017. A smart approach for secure control of railway transportation systems. Rochester, NY: Social Science Research Network.
Baysari, M. T., A. S. McIntosh, and J. R. Wilson. 2008. “Understanding the human factors contribution to railway accidents and incidents in Australia.” Accid. Anal. Prev. 40 (5): 1750–1757. https://doi.org/10.1016/j.aap.2008.06.013.
Bazulin, E. G. 2010. “SAFT imaging of flaws in the rail base blade with consideration of multiple reflections of an ultrasonic pulse from the boundaries of a test object.” Russ. J. Nondestr. Test. 46 (2): 125–136. https://doi.org/10.1134/S1061830910020075.
Bochkovskiy, A., C.-Y. Wang, and H.-Y. M. Liao. 2020. “YOLOv4: Optimal speed and accuracy of object detection.” Preprint, submitted April 24, 2020. http://arxiv.org/abs/2004.10934.
Chen, W., W. Liu, K. Li, P. Wang, H. Zhu, Y. Zhang, and C. Hang. 2018. “Rail crack recognition based on adaptive weighting multi-classifier fusion decision.” Measurement 123 (Jul): 102–114. https://doi.org/10.1016/j.measurement.2018.03.059.
Chen, Z., Q. Wang, K. Yang, T. Yu, J. Yao, Y. Liu, P. Wang, and Q. He. 2021. “Deep learning for the detection and recognition of rail defects in ultrasound B-scan images.” Transp. Res. Rec. https://doi.org/10.1177/03611981211021547.
Clark, R. 2004. “Rail flaw detection: Overview and needs for future developments.” NDT&E Int. 37 (2): 111–118. https://doi.org/10.1016/j.ndteint.2003.06.002.
Du, S., P. Zhang, B. Zhang, and H. Xu. 2021. “Weak and occluded vehicle detection in complex infrared environment based on improved YOLOv4.” IEEE Access 9 (Feb): 25671–25680. https://doi.org/10.1109/ACCESS.2021.3057723.
Liu, X., A. Lovett, T. Dick, M. Rapik Saat, and C. P. L. Barkan. 2014. “Optimization of ultrasonic rail-defect inspection for improving railway transportation safety and efficiency.” J. Transp. Eng. 140 (1): 04014048. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000697.
Sadeghi, J., Y. Rahimizadeh, A. Khajehdezfuly, M. Rezaee, and E. Rajaei Najafabadi. 2020. “Development of rail-condition assessment model using ultrasonic technique.” J. Transp. Eng. 146 (8): 04020078. https://doi.org/10.1061/JTEPBS.0000390.
Sulimova, V., A. Zhukov, O. Krasotkina, V. Mottl, and A. Markov. 2018. “Automatic rail flaw localization and recognition by featureless ultrasound signal analysis.” In Vol. 10934 of Machine learning and data mining in pattern recognition. MLDM 2018: Lecture notes in computer science, edited by P. Perner. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-96136-1.
Sun, C., J. Liu, Y. Qin, and Y. Zhang. 2018. “Intelligent detection method for rail flaw based on deep learning.” Zhongguo Tiedao Kexue/China Railway Sci. 39 (5): 51–57. https://doi.org/10.3969/j.issn.1001-4632.2018.05.07.
Wang, P., L. Xiong, Y. Sun, H. Wang, and G. Tian. 2014. “Features extraction of sensor array based PMFL technology for detection of rail cracks.” Measurement 47 (Jan): 613–626. https://doi.org/10.1016/j.measurement.2013.09.047.
Wei, H. A. O., and L. I. Chengtong. 2009. “Automatic realtime SVM-based ultrasonic rail flaw detection and classification system.” [In Chinese.] J. Graduate Sch. Chin. Acad. Sci. 26 (4): 517–521.
Wu, D., S. Lv, M. Jiang, and H. Song. 2020a. “Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments.” Comput. Electron. Agric. 178 (4): 105742. https://doi.org/10.1016/j.compag.2020.105742.
Wu, F., Q. Li, S. Li, and T. Wu. 2020b. “Train rail defect classification detection and its parameters learning method.” Measurement 151 (2): 107246. https://doi.org/10.1016/j.measurement.2019.107246.
Xu, Q., Q. Zhao, L. Wang, and T. Shen. 2021. “Rail defect detection method based on BP neural network.” In Vol. 1274 of Proc., 10th Int. Conf. on Computer Engineering and Networks, 68–78. New York: Springer. https://doi.org/10.1007/978-981-15-8462-6_8.
Xu, Q., Q. Zhao, G. Yu, L. Wang, and T. Shen. 2020. “Rail defect detection method based on recurrent neural network.” In Proc., 39th Chinese Control Conf. (CCC), 6486–6490. New York: IEEE. https://doi.org/10.23919/CCC50068.2020.9188823.
Zhang, B., K. Mei, and N. Zheng. 2013. “Reconfigurable processor for binary image processing.” IEEE Trans. Circuits Syst. Video Technol. 23 (5): 823–831. https://doi.org/10.1109/TCSVT.2012.2223872.
Zhang, H., X. Jin, Q. M. J. Wu, Y. Wang, Z. He, and Y. Yang. 2018. “Automatic visual detection system of railway surface defects with curvature filter and improved Gaussian mixture model.” IEEE Trans. Instrum. Meas. 67 (7): 1593–1608. https://doi.org/10.1109/TIM.2018.2821998.
Zhang, J., W. Lu, X. Yin, W. Liu, and Y. Yeung. 2019. “Binary image steganography based on joint distortion measurement.” J. Visual Commun. Image Represent. 58 (Jan): 600–605. https://doi.org/10.1016/j.jvcir.2018.12.038.
Information & Authors
Information
Published In
Journal of Performance of Constructed Facilities
Volume 36 • Issue 1 • February 2022
Copyright
© 2021 American Society of Civil Engineers.
History
Received: May 30, 2021
Accepted: Sep 16, 2021
Published online: Oct 26, 2021
Published in print: Feb 1, 2022
Discussion open until: Mar 26, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Junfeng Li, Yuanxun Yang, HM-YOLOv5: A fast and accurate network for defect detection of hot-pressed light guide plates, Engineering Applications of Artificial Intelligence, 10.1016/j.engappai.2022.105529, 117, (105529), (2023).