Abstract
As the key components of electrified railway power supply, pantograph has complex electrical and mechanical effects while working, resulting in a high fault ratio. It is important to detect the defects timely to guarantee the safety of the railway system. Manual detection is the most common detection at present, which is high in accuracy but low in efficiency. Another automatic detection system is limited in function or poor in accuracy. In this paper, deep learning method is used for defects recognition of pantograph slide plate to the identification and classification of different types of defects. Through a large number of experiments and parameters optimizing, the innovated proposed in this paper can reach an accuracy rate of 90.625% used to identify a variety of different defects. This provides an alternative for pantograph slide plate defect identification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Han Z-W, Liu Z-G, Zhang G-N (2013) Overview of non-contact image detection technology for pantograph-catenary monitoring. J China Railway Soc 35(6):40–47 (in Chinese)
Kuen LK, Lee TKY, Ho SL, Cheng EW (2006) A novel intelligent train condition monitoring system coupling laser beam into image processing algorithm. HKIE Trans 13(1):27–34
NBao-lai YI, Bo-ming W (2008) Application of ultrasonic ranging principle in monitoring abrasion of pantograph slider. Electr Drive Locomotives 5:021
Boffi P, Cattaneo G, Amoriello L, Barberis A, Bucca G, Bocciolone MF, Collina A, Martinelli M (2009) Optical fiber sensors to measure collector performance in the pantograph-catenary interaction. IEEE Sens J 9(6):635–640
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Krizhevsky A, Sutskever I, Hinton GE (2012) Image net classification with deep convolutional neural networks advances in neural information processing systems. 1097–1105
Pantograph (transport) [Internet]. En.wikipedia.org. (2017). Available from: http://en.wikipedia.org/wiki/Pantograph_(rail)
Zhu J, Liao S, Lei Z, Li SZ (2017) Multi-label convolutional neural network based pedestrian attribute classification. Image Vis Comput 58:224–229
Ma J, Wu F, Zhu J, Xu D, Kong D (2017) A pre-trained convolutional neural network based method for thyroid nodule diagnosis. Ultrasonics 73:221–230
Acknowledgements
This work is partly supported by Chinese National Key Project of Research and Development (Contract No. 2016YFB1200400-2) and State Key Lab of Rail Traffic Control and Safety (Contract No. RCS2016ZT006), Beijing Jiaotong University, Beijing, China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, Y., Wei, X. (2018). Pantograph Slide Plate Abrasion Detection Based on Deep Learning Network. In: Jia, L., Qin, Y., Suo, J., Feng, J., Diao, L., An, M. (eds) Proceedings of the 3rd International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2017. EITRT 2017. Lecture Notes in Electrical Engineering, vol 483. Springer, Singapore. https://doi.org/10.1007/978-981-10-7989-4_22
Download citation
DOI: https://doi.org/10.1007/978-981-10-7989-4_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7988-7
Online ISBN: 978-981-10-7989-4
eBook Packages: EnergyEnergy (R0)