Page 58 - Read Online
P. 58

Ji et al. Intell Robot 2021;1(2):151-75                     Intelligence & Robotics
               DOI: 10.20517/ir.2021.14



               Review                                                                        Open Access



               Rail track condition monitoring: a review on deep

               learning approaches


                                   2
                                                          1
                      1
               Albert Ji , Wai Lok Woo , Eugene Wai Leong Wong , Yang Thee Quek 3
               1
                NewRIIS, Newcastle University, Singapore 609607, Singapore.
               2
                Department of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8ST, UK.
               3
                School of Engineering, Republic Polytechnic Singapore, Singapore 738964, Singapore.
               Correspondence to: Prof. Wai Lok Woo, Department of Computer and Information Sciences, Northumbria University, Ellison
               Place, Newcastle upon Tyne NE1 8ST, UK. E-mail: wailok.woo@northumbria.ac.uk
               How to cite this article: Ji A, Woo WL, Wong EWL, Quek YT. Rail track condition monitoring: a review on deep learning
               approaches. Intell Robot 2021;1(2):151-75. https://dx.doi.org/10.20517/ir.2021.14
               Received: 21 Oct 2021  First Decision: 23 Nov 2021  Revised: 12 Dec 2021  Accepted: 29 Dec 2021  Published: 31 Dec 2021

               Academic Editors: Simon X. Yang, Xin Xu  Copy Editor: Xi-Jun Chen  Production Editor: Xi-Jun Chen

               Abstract
               Rail track is a critical component of rail systems. Accidents or interruptions caused by rail track anomalies usually
               possess severe outcomes. Therefore, rail track condition monitoring is an important task. Over the past decade,
               deep learning techniques have been rapidly developed and deployed. In the paper, we review the existing literature
               on applying deep learning to rail track condition monitoring. Potential challenges and opportunities are discussed
               for the research community to decide on possible directions. Two application cases are presented to illustrate the
               implementation of deep learning to rail track condition monitoring in practice before we conclude the paper.

               Keywords: Rail track maintenance, condition monitoring, anomaly detection and classification, deep learning




               1. INTRODUCTION
               The rail industry plays an important role in a nation’s economy and development and directly affects the
               lifestyle of the residents. Hence, there is a low tolerance level by the public to any accidents or negative
               events happening to the rail operations as the economy, the livelihood, and the country’s reputation would
               be brought down and the social and political risk level will rise. The rail systems around the world operate
               under different environments with their most critical infrastructure, the steel rail track, including rails,
               sleepers, ballast, fastener, and subgrade. Undesirable consequences such as derailment, death, injury,







                           © The Author(s) 2021. Open Access This article is licensed under a Creative Commons Attribution 4.0
                           International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing,
                           adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as
               long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and
               indicate if changes were made.

                                                                                           www.intellrobot.com
   53   54   55   56   57   58   59   60   61   62   63