Abstract
To ensure the safe operation of high-speed trains, catenary anomaly detection and alerting security have become an urgent problem to solve. In this paper, we propose a novel method for abnormal behavior localization of a pantograph-catenary for high-speed trains. First, a modified faster RCNN is proposed to detect the pantograph faults. By adjusting the parameters of the faster RCNN, the positional accuracy of the candidate box and accuracy of the algorithm are guaranteed. We perform the arc detection after detecting the pantograph head area. The detection accuracy is over 99%. The height of the pantograph center point is also obtained during detection. Then, the actual running mileage of the fault point is calculated. Experiments show that the method proposed in this paper is also applicable to various complex scenes and that this method can determine the fault localization in the shortest time, narrow the maintenance scope, and improve the overhaul efficiency.
Highlights
High-speed railways have the advantages of fast speed, less pollution, and large carrying capacity, and have been widely used all over the world [1]
The arc results in the following adverse effects: (1) when the bow becomes deformed, a highamplitude over-voltage is generated, which affects the safe operation of the train; (2) the pantograph strip and contact wire are ablated, shortening their lives and leading to
ENVIRONMENT CONFIGURATION AND DATASET The experiment in this thesis configures the py-faster RCNN with Caffe [46] as the deep-learning framework in the Ubuntu 16.04 environment, and the Caffe framework is used to construct the convolutional neural network (CNN)
Summary
High-speed railways have the advantages of fast speed, less pollution, and large carrying capacity, and have been widely used all over the world [1]. The pantograph-catenary system (PCS) was developed to provide continuous power to high-speed trains. Karakose et al [13] proposed a method based on edge extraction and the Hough transform for obtaining the contact points, and analyzed the number of contact points in each region of the pantograph to detect PCS faults. Barmada et al [19] used image processing to detect contact points between the pantograph strip and catenary contact wires to determine if a pantograph arc was present. Raghavendra et al [37] proposed an 18-layer CNN that effectively extracted powerful features from digital fundus images These CNN-based methods prove that CNN is a reasonable choice for pantograph arc detection. This paper concentrates on computer vision methods to detect faults in the high-speed train pantograph connected to the catenary wire.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
