AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers

Sakdirat Kaewunruen; Abdullah Abimbola  Adesope; Junhui Huang; Ruilin You; Dan Li

doi:10.1007/s42452-024-05880-8

AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers

Sakdirat Kaewunruen^*, Abdullah Abimbola Adesope, Junhui Huang, Ruilin You, Dan Li

^*Corresponding author for this work

Civil Engineering

Research output: Contribution to journal › Article › peer-review

9 Downloads (Pure)

Abstract

Railway concrete sleepers are key safety-critical components in ballasted railway tracks. Due to frequent high-intensity impact loadings from train-track interaction over irregularities together with hostile environmental conditions, complicated characteristics of various crack patterns can incur on railway concrete sleepers, which will decrease their durability and service life overtime. Early warning of those cracks can help railway engineers to plan and schedule for renewal and maintenance timely and effectively. This study thus explores the artificial intelligence application of YOLOv5OBB (YOLOv5 with Oriented Bounding Box output) in the identification and classification of cracks in railway sleepers into three distinct types: longitudinal, transverse, and inclined, based on their specific crack angles, which have not been investigated in the past. The identification of crack angles is the novelty of this study. Recognising the various types of cracks is critical, given their varying causes and degrees of severity. Current corrective maintenance methods pose considerable safety risks to workers and exhibit low efficiency, underscoring the need for a more autonomous and efficient solution. This study marks a significant stride towards revolutionising railway maintenance, evidenced by an impressive mAP (Mean Average Precision) of 0.72 for crack detection and a 92% accuracy rate for angle detection. These promising results substantiate our study's potential to pioneer advancements in railway infrastructure maintenance.

Original language	English
Article number	217
Number of pages	16
Journal	Discover Applied Sciences
Volume	6
Issue number	5
DOIs	https://doi.org/10.1007/s42452-024-05880-8
Publication status	Published - 19 Apr 2024

Bibliographical note

Acknowledgements:
The authors wish to gratefully acknowledge the Japan Society for Promotion of Science (JSPS) for JSPS Invitation Research Fellowship (long-term), Grant No. L15701, at the Track Dynamics Laboratory, Railway Technical Research Institute and at Concrete Laboratory, the University of Tokyo, Tokyo, Japan. The JSPS financially supported this work as part of the research project entitled “Smart and reliable railway infra-structure”. Special thanks are given to the European Commission for H2020-MSCA-RISE Project No. 691135 “RISEN: Rail Infrastructure Systems Engineering Network”. Partial support from and by European Commission and UKRI Engineering and Physical Science Research Council (EPSRC) for the financial sponsorship of Re4Rail project (Grant No. EP/ Y015401/1) is acknowledged. In addition, the sponsorships and assistance from PCAT, Transport for London (TfL), China Academy of Railway Science, and RSSB (Rail Safety and Standard Board, UK) are highly appreciated.

Funding:
This research was funded by H2020 Marie Curie Action, grant number 691135; and by European Commission and UKRI Engineering and Physical Science Research Council (EPSRC) for the financial sponsorship of Re4Rail project (Grant No. EP/ Y015401/1). The APC has been kindly sponsored by the University of Birmingham’s Open Access Fund.

Keywords

Track maintenance
Cracks
Machine learning
Railway concrete sleepers
Damage detection
YOLO

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s42452-024-05880-8Licence: Creative Commons: Attribution (CC BY)

KaewunruenS2024AIbasedFinal published version, 1.53 MBLicence: Creative Commons: Attribution (CC BY)

https://link.springer.com/article/10.1007/s42452-024-05880-8Licence: Creative Commons: Attribution (CC BY)

1 Finished
1 Active

Re4Rail - AI and digital twin-based atomated technology to real-time repair, reuse, recycle and repurpose railway granular media
Kaewunruen, S.
UKRI Horizon Europe Underwriting â€“ EPSRC
1/04/24 → 31/03/26
Project: Research
H2020_RISE_RISEN
Kaewunruen, S.
European Commission - Management Costs, European Commission
1/04/16 → 30/09/21
Project: Research

Cite this

@article{bc65ad516f4449f8a444a5293a20f019,

title = "AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers",

abstract = "Railway concrete sleepers are key safety-critical components in ballasted railway tracks. Due to frequent high-intensity impact loadings from train-track interaction over irregularities together with hostile environmental conditions, complicated characteristics of various crack patterns can incur on railway concrete sleepers, which will decrease their durability and service life overtime. Early warning of those cracks can help railway engineers to plan and schedule for renewal and maintenance timely and effectively. This study thus explores the artificial intelligence application of YOLOv5OBB (YOLOv5 with Oriented Bounding Box output) in the identification and classification of cracks in railway sleepers into three distinct types: longitudinal, transverse, and inclined, based on their specific crack angles, which have not been investigated in the past. The identification of crack angles is the novelty of this study. Recognising the various types of cracks is critical, given their varying causes and degrees of severity. Current corrective maintenance methods pose considerable safety risks to workers and exhibit low efficiency, underscoring the need for a more autonomous and efficient solution. This study marks a significant stride towards revolutionising railway maintenance, evidenced by an impressive mAP (Mean Average Precision) of 0.72 for crack detection and a 92% accuracy rate for angle detection. These promising results substantiate our study's potential to pioneer advancements in railway infrastructure maintenance.",

keywords = "Track maintenance, Cracks, Machine learning, Railway concrete sleepers, Damage detection, YOLO",

author = "Sakdirat Kaewunruen and Adesope, {Abdullah Abimbola} and Junhui Huang and Ruilin You and Dan Li",

note = "Acknowledgements: The authors wish to gratefully acknowledge the Japan Society for Promotion of Science (JSPS) for JSPS Invitation Research Fellowship (long-term), Grant No. L15701, at the Track Dynamics Laboratory, Railway Technical Research Institute and at Concrete Laboratory, the University of Tokyo, Tokyo, Japan. The JSPS financially supported this work as part of the research project entitled “Smart and reliable railway infra-structure”. Special thanks are given to the European Commission for H2020-MSCA-RISE Project No. 691135 “RISEN: Rail Infrastructure Systems Engineering Network”. Partial support from and by European Commission and UKRI Engineering and Physical Science Research Council (EPSRC) for the financial sponsorship of Re4Rail project (Grant No. EP/ Y015401/1) is acknowledged. In addition, the sponsorships and assistance from PCAT, Transport for London (TfL), China Academy of Railway Science, and RSSB (Rail Safety and Standard Board, UK) are highly appreciated. Funding: This research was funded by H2020 Marie Curie Action, grant number 691135; and by European Commission and UKRI Engineering and Physical Science Research Council (EPSRC) for the financial sponsorship of Re4Rail project (Grant No. EP/ Y015401/1). The APC has been kindly sponsored by the University of Birmingham{\textquoteright}s Open Access Fund.",

year = "2024",

month = apr,

day = "19",

doi = "10.1007/s42452-024-05880-8",

language = "English",

volume = "6",

journal = "Discover Applied Sciences",

issn = "3004-9261",

publisher = "Springer Nature",

number = "5",

}

TY - JOUR

T1 - AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers

AU - Kaewunruen, Sakdirat

AU - Adesope, Abdullah Abimbola

AU - Huang, Junhui

AU - You, Ruilin

AU - Li, Dan

N1 - Acknowledgements: The authors wish to gratefully acknowledge the Japan Society for Promotion of Science (JSPS) for JSPS Invitation Research Fellowship (long-term), Grant No. L15701, at the Track Dynamics Laboratory, Railway Technical Research Institute and at Concrete Laboratory, the University of Tokyo, Tokyo, Japan. The JSPS financially supported this work as part of the research project entitled “Smart and reliable railway infra-structure”. Special thanks are given to the European Commission for H2020-MSCA-RISE Project No. 691135 “RISEN: Rail Infrastructure Systems Engineering Network”. Partial support from and by European Commission and UKRI Engineering and Physical Science Research Council (EPSRC) for the financial sponsorship of Re4Rail project (Grant No. EP/ Y015401/1) is acknowledged. In addition, the sponsorships and assistance from PCAT, Transport for London (TfL), China Academy of Railway Science, and RSSB (Rail Safety and Standard Board, UK) are highly appreciated. Funding: This research was funded by H2020 Marie Curie Action, grant number 691135; and by European Commission and UKRI Engineering and Physical Science Research Council (EPSRC) for the financial sponsorship of Re4Rail project (Grant No. EP/ Y015401/1). The APC has been kindly sponsored by the University of Birmingham’s Open Access Fund.

PY - 2024/4/19

Y1 - 2024/4/19

N2 - Railway concrete sleepers are key safety-critical components in ballasted railway tracks. Due to frequent high-intensity impact loadings from train-track interaction over irregularities together with hostile environmental conditions, complicated characteristics of various crack patterns can incur on railway concrete sleepers, which will decrease their durability and service life overtime. Early warning of those cracks can help railway engineers to plan and schedule for renewal and maintenance timely and effectively. This study thus explores the artificial intelligence application of YOLOv5OBB (YOLOv5 with Oriented Bounding Box output) in the identification and classification of cracks in railway sleepers into three distinct types: longitudinal, transverse, and inclined, based on their specific crack angles, which have not been investigated in the past. The identification of crack angles is the novelty of this study. Recognising the various types of cracks is critical, given their varying causes and degrees of severity. Current corrective maintenance methods pose considerable safety risks to workers and exhibit low efficiency, underscoring the need for a more autonomous and efficient solution. This study marks a significant stride towards revolutionising railway maintenance, evidenced by an impressive mAP (Mean Average Precision) of 0.72 for crack detection and a 92% accuracy rate for angle detection. These promising results substantiate our study's potential to pioneer advancements in railway infrastructure maintenance.

AB - Railway concrete sleepers are key safety-critical components in ballasted railway tracks. Due to frequent high-intensity impact loadings from train-track interaction over irregularities together with hostile environmental conditions, complicated characteristics of various crack patterns can incur on railway concrete sleepers, which will decrease their durability and service life overtime. Early warning of those cracks can help railway engineers to plan and schedule for renewal and maintenance timely and effectively. This study thus explores the artificial intelligence application of YOLOv5OBB (YOLOv5 with Oriented Bounding Box output) in the identification and classification of cracks in railway sleepers into three distinct types: longitudinal, transverse, and inclined, based on their specific crack angles, which have not been investigated in the past. The identification of crack angles is the novelty of this study. Recognising the various types of cracks is critical, given their varying causes and degrees of severity. Current corrective maintenance methods pose considerable safety risks to workers and exhibit low efficiency, underscoring the need for a more autonomous and efficient solution. This study marks a significant stride towards revolutionising railway maintenance, evidenced by an impressive mAP (Mean Average Precision) of 0.72 for crack detection and a 92% accuracy rate for angle detection. These promising results substantiate our study's potential to pioneer advancements in railway infrastructure maintenance.

KW - Track maintenance

KW - Cracks

KW - Machine learning

KW - Railway concrete sleepers

KW - Damage detection

KW - YOLO

U2 - 10.1007/s42452-024-05880-8

DO - 10.1007/s42452-024-05880-8

M3 - Article

SN - 3004-9261

VL - 6

JO - Discover Applied Sciences

JF - Discover Applied Sciences

IS - 5

M1 - 217

ER -

AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Fingerprint

Projects

Re4Rail - AI and digital twin-based atomated technology to real-time repair, reuse, recycle and repurpose railway granular media

H2020_RISE_RISEN

Cite this