A parallel method for assessing track segment quality in railway maintenance

Izadi Yazdan Abadi E., Khadem Sameni M., Yaghini M.

Maintaining railway tracks is capital intensive, time consuming and safety-critical. Novel maintenance methods can decrease these costs and improve efficiency by analysis of collected data from tracks. Twist is one of the common track failures, which poses the risk of derailment, fatalities, injuries and financial loss. In this paper, track parameters are studied for part of a major railway route in Iran. Polynomial regression and association rules, which are popular data mining approaches are used to discover relationship between twist failure with failures of other track parameters for the period between 2018 and 2020. The results show that alignment and super elevation have the highest impact on twist and most of the times these failures occur simultaneously. By adopting this approach twist failure can be identified in order to avoid chain failure and move toward condition-based maintenance.

Elbeh H., Elkawkagy M.

Falamarzi A., Moridpour S., Nazem M.

Track quality indices can be used as an indicator of rail condition concerning the risk of damage or failure. Previous studies have mainly focused on conventional rail track quality indices and lig...

Palese J.W., Zarembski A.M., Attoh-Okine N.O.

Railroads have long used track inspection vehicles that capture data on a defined interval as the vehicle travels longitudinally down the track. These data can be captured on a constant interval, near-constant interval, or temporally. The data are normally evaluated in real time against exception thresholds, which define locations of safety or maintenance concern. In addition, railways evaluate multiple inspection runs of the same track over time to determine the rates of degradation. Since most inspection vehicles rely on the operator input of location events (mile posts, signals, switches, etc.) and tachometer-based distance measurement, the resulting inspection data are often longitudinally misaligned, on occasion by as much as several hundred feet. This paper presents an application of classical and advanced time-series methods for aligning data longitudinally. It also presents a novel methodology for aligning data with a nonconstant sampling interval, utilizing a combination of classical techniques.

Wang Y., Wang P., Wang X., Liu X.

Track geometry inspection data is important for managing railway infrastructure integrity and operational safety. In order to use track geometry inspection data, having accurate and reliable position information is a prerequisite. Due to various issues identified in this research, the positions of different track geometry inspections need to be aligned and synchronized to the same location before being used for track degradation modeling and maintenance planning. This is referred to as “position synchronization”, a long-standing important research problem in the area of track data analytics. With the aim of advancing the state of the art in research on this subject, we propose a novel approach to more accurately and expediently synchronize track geometry inspection positions via big-data fusion and incremental learning algorithms. Distinguishing it from other relevant studies in the literature, our proposed approach can simultaneously address data exceptions, channel offsets and local position offsets between any two inspections. To solve the Position Synchronization Model (PS-Model), an Incremental Learning Algorithm (IL-Algorithm) is developed to handle the “lack of memory” challenge for the fast computation of massive data. A case study is developed based on a dataset with data size of 18 GB, including 58 inspections between February 2014 and July 2016 over 323 km (200 miles) of tracks belonging to China High Speed Railways. The results show that our proposed model performs robustly against data exceptions via the use of multi-channel information fusion. Also, the position synchronization error using our proposed approach is within 0.15 meters (0.5 feet). Our proposed data-driven, incremental learning algorithm can quickly solve the complex, data-extensive, position synchronization problem, using an average of 0.1 s for processing one additional kilometer of track. In general, the data analysis methodology and algorithm presented in this paper are also suitable to address other relevant position synchronization problems in transportation engineering, especially when the dataset contains multiple channels of sensors and abnormal data outliers.

TSUBOKAWA Y., ISHIKAWA T.

Sharma S., Cui Y., He Q., Mohammadi R., Li Z.

Railway big data technologies are transforming the existing track inspection and maintenance policy deployed for railroads in North America. This paper develops a data-driven condition-based policy for the inspection and maintenance of track geometry. Both preventive maintenance and spot corrective maintenance are taken into account in the investigation of a 33-month inspection dataset that contains a variety of geometry measurements for every foot of track. First, this study separates the data based on the time interval of the inspection run, calculates the aggregate track quality index (TQI) for each track section, and predicts the track spot geo-defect occurrence probability using random forests. Then, a Markov chain is built to model aggregated track deterioration, and the spot geo-defects are modeled by a Bernoulli process. Finally, a Markov decision process (MDP) is developed for track maintenance decision making, and it is optimized by using a value iteration algorithm. Compared with the existing maintenance policy using Markov chain Monte Carlo (MCMC) simulation, the maintenance policy developed in this paper results in an approximately 10% savings in the total maintenance costs for every 1 mile of track.

Higgins C., Liu X.

In a railroad track, the inherent and small geometrical deviations in the position of rails from their ideal design states constitute imperfections that can have a significant impact on the safety and the rate of degradation of the rail system. These deviations are measured by various technologies and further assessed using various algorithms and statistical techniques to quantify the condition of the system. This paper reviews the existing research regarding the collection of track geometry data, analysis of degradation, and the associated safety and maintenance decisions. The knowledge gaps in the existing literature are identified and possible future research directions are suggested. The review can be used as a reference by practitioners and researchers to determine optimal practices for assuring the safety of tracks.

Soleimanmeigouni I., Ahmadi A., Kumar U.

Increased demand for railway transportation is creating a need for higher train speeds and axle loads. These, in turn, increase the likelihood of track degradation and failures. Modelling the degradation behaviour of track geometry and development of applicable and effective maintenance strategies has become a challenging concern for railway infrastructure managers. During the last three decades, a number of track geometry degradation and maintenance modelling approaches have been developed to predict and improve the railway track geometry condition. In this paper, existing track geometry measures are identified and discussed. Available models for track geometry degradation are reviewed and classified. Tamping recovery models are also reviewed and discussed to identify the issues and challenges of different available methodologies and models. Existing track geometry maintenance models are reviewed and critical observations on each contribution are provided. The most important track maintenance scheduling models are identified and discussed. Finally, the paper provides directions for further research.

Armbrust M., Bateman D., Xin R., Zaharia M.

Originally started as an academic research project at UC Berkeley, Apache Spark is one of the most popular open source projects for big data analytics. Over 1000 volunteers have contributed code to the project; it is supported by virtually every commercial vendor; many universities are now offering courses on Spark. Spark has evolved significantly since the 2010 research paper: its foundational APIs are becoming more relational and structural with the introduction of the Catalyst relational optimizer, and its execution engine is developing quickly to adopt the latest research advances in database systems such as whole-stage code generation.

Sadeghi J., Askarinejad H.

Track geometry, consisting of several parameters, is the main factor influencing the ride quality and track performance. Railway authorities are spending considerably to maintain track geometry conditions within acceptable tolerance. Optimization of this expenditure requires a thorough investigation into the track structural factors influencing the conditions of track geometry. The current methods of track inspection are based on automated inspection of track geometry conditions, using track-recording cars. These methods have their limitations in identifying track structural defects, and in turn, lack the recognition of the causes of track geometry problems. There is a need to develop a track structural inspection and to investigate the relationship between track structural defects and track geometry problems. This research is an attempt to response to this need. The most dominant observable track structural distresses were studied, a track structural inspection method was proposed, and track structural conditions were quantified. A technique was developed to correlate track structural defects to track geometry problems. This technique was applied to tracks with various conditions, carrying out a comprehensive field investigation. The results obtained were analysed to identify the role of each track component on track geometry deviations, and in turn, develop correlations between track structural quality and track geometry conditions.

Fazio A.E., Corbin J.L.

Railroads have long faced the problem of formulating an objective measure of track quality, termed a Track Quality Index TQI. However, the industry has yet to formulate a standardized TQI. The Fede...

Uzarski D., McNeil S.

Rail continues to be an important transportation mode. Like other transportation infrastructure, maintenance and replacement are critical to ensure safe, efficient operation. Research and developme...