Action-driven Reinforcement Learning for Improving Localization of Brace Sleeve in Railway Catenary

Action-driven Reinforcement Learning for Improving Localization of Brace Sleeve in Railway Catenary

Zhong, J. (Southwest Jiaotong University)
Liu, Zhigang (Southwest Jiaotong University)
Wang, H. (TU Delft Railway Engineering)
Liu, W. (Southwest Jiaotong University)
Yang, Cheng (Southwest Jiaotong University)
Nunez, Alfredo (TU Delft Railway Engineering)

2020

Brace Sleeve (BS) plays an essential role in connecting and fixing cantilevers of railway catenary systems. It needs to be monitored to ensure the safety of railway operations. In the literature, image processing techniques that can localize BSs from inspection images are proposed. However, the boxes produced by existing methods can contain incomplete and/or irrelevant information of the localized BS. This reduces the accuracy of BS condition diagnosis in further analyses. To address this issue, this paper proposes the use of an action-driven reinforcement learning method that adopts the coarse-localized box provided by existing methods, and finds the movements needed for the box to approach to the true BS position automatically and accurately. In contrast to the existing methods that predict one position of the box containing a BS, the proposed action-driven method sees the localization problem as a dynamic position searching process. The localization of BS is achieved by following a sequence of actions, which in this paper are position-moving (up, down, left or right), scale-changing (scale up or scale down) and shape-changing (fatter or taller). The policy of selecting dynamic actions is obtained by reinforcement learning. In the experiment, the proposed method is tested with real-life images taken from a high-speed line in China. The results show that our method can effectively improve the localization accuracy for 81.8% of the analyzed images. We also analyze cases where the method did not improve the localization and suggest further research lines.

action-driven learning
brace sleeve
localization
railway catenary
reinforcement learning

http://resolver.tudelft.nl/uuid:8cbba7af-7c18-4576-a18b-c58dbfebeb61

https://doi.org/10.1109/ICSMD50554.2020.9261697

IEEE

2021-05-24

978-1-7281-9278-9

International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2020 - Proceedings: Proceedings

ICSMD 2020, 2020-10-15 → 2020-10-17, Xi'an, China

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2020 J. Zhong, Zhigang Liu, H. Wang, W. Liu, Cheng Yang, Alfredo Nunez