Improved Railway Track Geometry Degradation Modeling for Tamping Cycle Prediction

An, Ru; Sun, Qiang; Wang, Futian; Bai, Wenfei; Zhu, Xingyong; Liu, Rengkui

doi:10.1061/jtepbs.0000149

Cited by 14 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For statistical methods, the purpose is to estimate a small number of parameters from a large collection of samples. The basic assumption is that the data fit a specific hypothesis, like the Weibull distribution [31]. This is in contrast to machine learning, where a usually large set of model parameters is estimated from huge amounts of samples.…”

Section: Publication Distribution Among the Data-driven Methodsmentioning

confidence: 99%

Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering

et al. 2020

View full text Add to dashboard Cite

Conventional planning of maintenance and renewal work for railway track is based on heuristics and simple scheduling. The railway industry is now collecting a large amount of data with the fast-paced development of sensor technologies. These data sets carry information about the conditions of various components in railway track. Since just before the beginning of the 21st century, data-driven models have been used in the predictive maintenance of railway track. This study presents a systematic literature review of data-driven models applied in the predictive maintenance of railway track. A taxonomy to classify the existing literature based on types of models and types of applications is provided. It is found that applying the deep learning methods, unsupervised methods, and ensemble methods are the new trends for predictive maintenance of railway track. Rail geometry irregularity, rail head defect, and missing rail components detection were the top three most commonly considered issues within the application of data-driven models. Prediction of rail breaks has received increasing attention in the last four years. Among these data-driven model applications, the collected data types are the most critical factors which affect selecting suitable models. Finally, this study discusses upcoming challenges in the predictive maintenance of railway track.

show abstract

Section: Publication Distribution Among the Data-driven Methodsmentioning

confidence: 99%

Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering

et al. 2020

View full text Add to dashboard Cite

show abstract

“…According to the characteristics of railways, such as long lines, many points, wide areas, and clear land boundaries, the RCSRIG should be divided according to the length of the mileage. According to the characteristics of railway construction and previous studies [30], the RCSRIG uses a line section of 200 m as the basic mileage length unit.…”

Section: Safety Risk Management Grid Of Railway Constructionmentioning

confidence: 99%

Safety Risk Identification Method for Railway Construction in Complex and Dangerous Areas

et al. 2022

View full text Add to dashboard Cite

Safety risk identification is the premise and foundation of safety risk management for railway construction. However, due to some characteristics of railway projects, which include large volumes of work, complex construction environments, and long construction cycles, etc., the risk factors of railway projects are often hidden in all stages of engineering construction. It results in the comprehensive identification of safety risks of railway projects being usually difficult, and this problem is more serious when the railway is constructed in complex and dangerous areas. Therefore, to identify the safety risks comprehensively, this paper constructs a safety risk identification method applicable to railway construction in complex and dangerous areas. This method studies the spatial and temporal distribution of risks and their relationship with subprojects by using a work breakdown structure (WBS), a risk breakdown structure (RBS), grid-based management, and forming a safety risk identification matrix, which can help researchers analyze the characteristics of risks. In order to verify the effectiveness of the method, the CZ Railway, which is located in the Sichuan and Tibet provinces of China, crossing the Hengduan Mountains with a total length of 1838 km, was selected as a case study, and risk identification for its civil engineering was carried out. The research results show that in the construction process of the CZ Railway, the main types of safety risks suffered by various branch projects were different. In addition, some risk factors only appeared at specific times in space, and there is a strong interaction between these risk factors. Based on this method, safety risk identification can intuitively discover the spatial and temporal distribution of risk factors and analyze the interaction between risk factors, which can provide help for the formulation of targeted risk control measures.

show abstract

“…the Weibull and q-Weibull reliability models-in the electrical power sector; they use the maximum likelihood method for parameter estimation. An et al (2018) also use the maximum likelihood method to estimate Weibull parameters for their model, which aims to estimate railway track geometry conditions. Ramos et al (2018) present a study about five generalisations of the standard Weibull distribution to describe the lifetime of two important components of sugarcane harvesting machines, using maximum likelihood for parameter estimation.…”

Section: Literature Reviewmentioning

confidence: 99%

Age replacement policy in the case of no data: the effect of Weibull parameter estimation

Sgarbossa

Zennaro

Florian

et al. 2019

International Journal of Production Research

View full text Add to dashboard Cite

Age replacement is a common maintenance policy when wear-out failures occur, and it is characterised by periodic replacement of components. Data on time to failure (TTF), often modelled with the Weibull function, are necessary for estimating optimal replacement intervals to minimise the total maintenance costs. In many cases, such as new components, new machines or new installations, no TTF data are available, so the Weibull parameters and optimal replacement interval cannot be estimated. To overcome this problem, these parameters can be assessed from the experience of the maintenance engineers and technicians. The aim of this study is investigating the relationship between the error in parameter estimation and additional maintenance costs related to this error. Analysis of variance (ANOVA) and multifactorial analysis are carried out for investigating the influence of these estimations on the final costs. Economic decision maps are introduced for supporting maintenance engineering in defining the maintenance policy with minimal additional cost in the case of no data being available. The analysis shows that, when no data are available, the application of the age replacement policy can result in a global savings of more than 50% compared with corrective maintenance.

show abstract

Improved Railway Track Geometry Degradation Modeling for Tamping Cycle Prediction

Cited by 14 publications

References 2 publications

Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering

Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering

Safety Risk Identification Method for Railway Construction in Complex and Dangerous Areas

Age replacement policy in the case of no data: the effect of Weibull parameter estimation

Contact Info

Product

Resources

About