<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Ensuring the safety of railway transport operation requires constant monitoring of the technical condition of individual elements of railway infrastructure. The necessary activities that contribute to maintaining good operational condition of the railway transport line also include the diagnostics of track length. Diagnostics of railway tracks is most often performed by means of regular visual inspection (in the conditions of the infrastructure manager – ŽSR). The objective of the article is to provide information on the application of a new approach to diagnostics of the technical condition of railway infrastructure. The new approach to defect identification on railway infrastructure uses non-invasive diagnostic methods based on the latest knowledge in the field of information and communication technologies. These facts resulted in investigating the possibilities of automatic detection of the technical condition of the track length using neural networks. The article is part of the following scientific research task: ‘Research into new knowledge and observational experience of a new generation of diagnostic systems in industrial production and transport industry – research into the physical nature of an automated track length video inspection system’, supported by the Ministry of Education, Science, Research and Sport of the Slovak Republic.</p>
</abstract>

Ensuring the safety of railway transport operation requires constant monitoring of the technical condition of individual elements of railway infrastructure. The necessary activities that contribute to maintaining good operational condition of the railway transport line also include the diagnostics of track length. Diagnostics of railway tracks is most often performed by means of regular visual inspection (in the conditions of the infrastructure manager – ŽSR). The objective of the article is to provide information on the application of a new approach to diagnostics of the technical condition of railway infrastructure. The new approach to defect identification on railway infrastructure uses non-invasive diagnostic methods based on the latest knowledge in the field of information and communication technologies. These facts resulted in investigating the possibilities of automatic detection of the technical condition of the track length using neural networks. The article is part of the following scientific research task: ‘Research into new knowledge and observational experience of a new generation of diagnostic systems in industrial production and transport industry – research into the physical nature of an automated track length video inspection system’, supported by the Ministry of Education, Science, Research and Sport of the Slovak Republic.

Automatic Detection of Track Length Defects

LOGI – Scientific Journal on Transport and Logistics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Automatic Detection of Track Length Defects"}

Ensuring the safety of railway transport operation requires constant monitoring of the technical condition of individual elements of railway infrastructure....

Automatic Detection of Track Length Defects

Publié en ligne: 12 mai 2022

Pages: 13 - 24

Reçu: 18 oct. 2021

Accepté: 14 févr. 2022

DOI: https://doi.org/10.2478/logi-2022-0002

Mots clés
Railway transport, diagnostics, track length, neural networks

© 2022 Juaraj Kanis et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Automatic Detection of Track Length Defects

Publié en ligne: 12 mai 2022

Pages: 13 - 24

Reçu: 18 oct. 2021

Accepté: 14 févr. 2022

DOI: https://doi.org/10.2478/logi-2022-0002

Mots clésRailway transport, diagnostics, track length, neural networks

© 2022 Juaraj Kanis et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
Railway transport, diagnostics, track length, neural networks