Integration of Building Information Modeling and Machine Learning for Railway Defect Localization

Sresakoolchai, Jessada; Kaewunruen, Sakdirat

doi:10.1109/access.2021.3135451

Cited by 20 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…8. The findings conform to previous studies stating that the integration of digital twin and machine learning will promote the overall efficiency of project life not only at a specific stage of the project [28][29][30] considering all risks and vulnerabilities [31][32][33] .…”

Section: Digital Twinsupporting

confidence: 89%

Railway infrastructure maintenance efficiency improvement using deep reinforcement learning integrated with digital twin based on track geometry and component defects

Sresakoolchai

Kaewunruen

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Railway maintenance is a complex and complicated task in the railway industry due to the number of its components and relationships. Ineffective railway maintenance results in excess cost, defective railway structure and components, longer possession time, poorer safety, and lower passenger comfort. Of the three main maintenance approaches, predictive maintenance is the trendy one, and is proven that it provides the highest efficiency. However, the implementation of predictive maintenance for the railway industry cannot be done without an efficient tool. Normally, railway maintenance is corrective when some things fail or preventive when maintenance is routine. A novel approach using an integration between deep reinforcement learning and digital twin is proposed in this study to improve the efficiency of railway maintenance which other techniques such as supervised and unsupervised learning cannot provide. In the study, Advantage Actor Critic (A2C) is used to develop a reinforcement learning model and agent to fulfill the need of the study. Real-world field data over four years and 30 km. is obtained and applied for developing the reinforcement learning model. Track geometry parameters, railway component defects, and maintenance activities are used as parameters to develop the reinforcement learning model. Rewards (or penalties) are calculated based on maintenance costs and occurring defects. The new breakthrough exhibits that using reinforcement learning integrated with digital twin can reduce maintenance activities by 21% and reduce the occurring defects by 68%. Novelties of the study are the use of A2C which is faster and provides better results than other traditional techniques such as Deep Q-learning (DQN), each track geometry parameter is considered without combining into a track quality index, filed data are used to develop the reinforcement learning model, and seven independent actions are included in the reinforcement learning model. This study is the world’s first to contribute a new guideline for applying reinforcement learning and digital twins to improve the efficiency of railway maintenance, reduce the number of defects, reduce the maintenance cost, reduce the possession time for railway maintenance, improve the overall safety of the railway operation, and improve the passenger comfort which can be seen from its results.

show abstract

Section: Digital Twinsupporting

confidence: 89%

Railway infrastructure maintenance efficiency improvement using deep reinforcement learning integrated with digital twin based on track geometry and component defects

Sresakoolchai

Kaewunruen

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…In several countries such as Italy, UK, Spain, and China, building information modeling (BIM) is implemented in railway infrastructure maintenance digital transformation [46][47][48][49][50][51]. Its implementation can improve the railway infrastructure maintenance planning with time saving, cost optimization [46], [47][48][49][50][51][52], and provide the internal requirement in terms of the safety of the users [52]. Building information modeling (BIM) facilitates all stakeholders, so they can keep the maintenance project scope in review if there is any changes [50].…”

Section: E-maintenance Implementation Trends In Railway Infrastructurementioning

confidence: 99%

Railway Infrastructures E-Maintenance Systems: A Literature Review

Wardahni,

Latief

2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

This paper aims to identify and summarise available literature on railway infrastructure e-maintenance system as a report of the state of the art of research in railway infrastructure e-maintenance system by systematically classifying the published literatures in the period of 2000-2023. The author identify the aspects and elements which influence the railway infrastructure e-maintenance system as well as various approaches to optimize the railway infrastructure e-maintenance system. This paper identify the current research gaps in order to conduct the future prospect of the research. As results, it is observed that based on the study of the published literatures, the implementation of e-maintenance in railway infrastructure sector mostly focus on the use of the information and communication technology (ICT) itself and there is no proper integration between the managerial aspects (i.e. regulation, work breakdown structure, risk, and safety) with information and communication technology (ICT) to optimize the e-maintenance system.

show abstract

“…Although the extant literature on the topic is limited, the findings suggest an emerging tendency for artificial intelligence (AI) and machine learning (ML) publications in the railway domain [290]. Currently, rail projects are utilizing AI and ML to optimize the effectiveness and performance of railway systems by different means, including resources and equipment planning during the construction stage [291], delving into the causation factors of highway-rail crossing crashes [292], categorizing fatality rates for accidents [293], improving safety measures [294,295], mitigating collision risks [296], and integrating building information modeling (BIM) and ML to enhance the operation and maintenance of railway networks [297].…”

Section: Citation Burst and Trend Analysismentioning

confidence: 99%

Minimizing Cost Overrun in Rail Projects through 5D-BIM: A Systematic Literature Review

et al. 2023

View full text Add to dashboard Cite

Mega projects delivering rail infrastructure are constantly seeking cost-effective and efficient technologies to sustain the growing population. Building information modeling (BIM) and BIM for cost management (5D-BIM) have shown great potential in the building industry and have been adopted widely. However, 5D-BIM implementation in rail infrastructure is still in its infancy. This paper presents a systematic literature review of 380 publications related to cost overrun, cost management and 5D-BIM for rail infrastructure, including rail projects. The review identified knowledge gaps and synthesized existing research on cost overrun in rail projects, cost estimation models, and the current use of 5D-BIM. The review revealed that there is no current study integrating 5D-BIM into the rail project lifecycle. This paper highlights the importance of integrating 5D-BIM systematically in the rail project life cycle to avoid/minimize cost overrun. The review provides researchers and practitioners with crucial information for deploying 5D-BIM to minimize cost overruns in rail projects.

show abstract

Integration of Building Information Modeling and Machine Learning for Railway Defect Localization

Cited by 20 publications

References 18 publications

Railway infrastructure maintenance efficiency improvement using deep reinforcement learning integrated with digital twin based on track geometry and component defects

Railway infrastructure maintenance efficiency improvement using deep reinforcement learning integrated with digital twin based on track geometry and component defects

Railway Infrastructures E-Maintenance Systems: A Literature Review

Minimizing Cost Overrun in Rail Projects through 5D-BIM: A Systematic Literature Review

Contact Info

Product

Resources

About