Data-driven optimization of railway maintenance for track geometry

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.     

Position synchronization for track geometry inspection data via big-data fusion and incremental learning

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.     

Improving rail network velocity: A machine learning approach to predictive maintenance

Rail network velocity is defined as system-wide average speed of line-haul movement between terminals. To accommodate increased service demand and load on rail networks, increase in network velocity, without compromising safety, is required. Among many determinants of overall network velocity, a key driver is service interruption, including lowered operating speed due to track/train condition and delays caused by derailments. Railroads have put significant infrastructure and inspection programs in place to avoid service interruptions. One of the key measures is an extensive network of wayside mechanical condition detectors (temperature, strain, vision, infrared, weight, impact, etc.) that monitor the rolling-stock as it passes by. The detectors are designed to alert for conditions that either violate regulations set by governmental rail safety agencies or deteriorating rolling-stock conditions as determined by the railroad.Using huge volumes of historical detector data, in combination with failure data, maintenance action data, inspection schedule data, train type data and weather data, we are exploring several analytical approaches including, correlation analysis, causal analysis, time series analysis and machine learning techniques to automatically learn rules and build failure prediction models. These models will be applied against both historical and real-time data to predict conditions leading to failure in the future, thus avoiding service interruptions and increasing network velocity. Additionally, the analytics and models can also be used for detecting root cause of several failure modes and wear rate of components, which, while do not directly address network velocity, can be proactively used by maintenance organizations to optimize trade-offs related to maintenance schedule, costs and shop capacity. As part of our effort, we explore several avenues to machine learning techniques including distributed learning and hierarchical analytical approaches.     

An autonomous system for maintenance scheduling data-rich complex infrastructure: Fusing the railways’ condition,planning and cost

National railways are typically large and complex systems. Their network infrastructure usually includes extended track sections, bridges, stations and other supporting assets. In recent years, railways have also become a data-rich environment.Railway infrastructure assets have a very long life, but inherently degrade. Interventions are necessary but they can cause lateness, damage and hazards. Every day, thousands of discrete maintenance jobs are scheduled according to time and urgency. Service disruption has a direct economic impact. Planning for maintenance can be complex, expensive and uncertain.Autonomous scheduling of maintenance jobs is essential. The design strategy of a novel integrated system for automatic job scheduling is presented; from concept formulation to the examination of the data to information transitional level interface, and at the decision making level. The underlying architecture configures high-level fusion of technical and business drivers; scheduling optimized intervention plans that factor-in cost impact and added value.A proof of concept demonstrator was developed to validate the system principle and to test algorithm functionality. It employs a dashboard for visualization of the system response and to present key information. Real track incident and inspection datasets were analyzed to raise degradation alarms that initiate the automatic scheduling of maintenance tasks. Optimum scheduling was realized through data analytics and job sequencing heuristic and genetic algorithms, taking into account specific cost & value inputs from comprehensive task cost modelling. Formal face validation was conducted with railway infrastructure specialists and stakeholders. The demonstrator structure was found fit for purpose with logical component relationships, offering further scope for research and commercial exploitation.     

Evaluation of CO2 emissions from railway resurfacing maintenance activities

This paper is the world first to investigate the CO₂ impact of railway resurfacing in ballasted track bed maintenance. Railway resurfacing is an important routine maintenance activity that restores track geometry to ensure safety, reliability and utility of the asset. This study consisted of an extensive field data collection from resurfacing machineries (diesel-engine tamping machines, ballast regulators and ballast stabilisers) including travel distances, working distances, fuel consumption and construction methodologies. Fuel consumption was converted to a kg CO₂/m using the embodied energies of diesel. Analyses showed that tamping machines emitted the highest CO₂ emissions of the resurfacing machineries, followed by ballast regulators and ballast stabilisers respectively. Tamping machines processed 4.25 m of track per litre of diesel, ballast regulators processed 6.51 m of track per litre of diesel and ballast stabilisers processed 10.61 m of track per litre of diesel. The results were then compared to previous studies and a rigorous parametric study was carried out to consider long-term resurfacing CO₂ emissions on Australian railway track. The outcome of this study is unprecedented and it enables track engineers and construction managers to critically plan strategic rail maintenance and to develop environmental-friendly policies for track geometry and alignment restoration.     

Estimating the marginal cost of railway track renewals using corner solution models

Economic theory advocates marginal cost pricing for efficient utilisation of transport infrastructure. A growing body of literature has emerged on the issue of rail marginal infrastructure wear and tear costs, but the majority of the work is focused on costs for infrastructure maintenance. Railway track renewals are a substantial part of an infrastructure manager’s budget, but in disaggregated statistical analyses they cause problems for traditional regression models since there is a piling up of values of the dependent variable at zero. Previous econometric work has sought to circumvent the problem by aggregation in some way. In this paper we instead apply corner solution models to disaggregate (track-section) data, including the zero observations. We derive track renewal cost elasticities with respect to traffic volumes and in turn marginal renewal costs using Swedish railway renewal data over the period 1999–2009. This paper is the first attempt in the literature to apply corner solution models, and in particular the two-part model, to disaggregate renewal cost data in railways. It is also the first paper that we are aware of to report usage elasticities specifically for renewal costs and therefore adds important new evidence to the previous literature where there is a paucity of studies on renewals and considerable uncertainty over the effects of rail traffic on renewal costs. In the Swedish context, we find that the inclusion of marginal track renewal costs in the track access pricing regime, which currently only reflects marginal maintenance costs, would add substantially to the existing track access charge. EU legislation requires that access charges reflect the ‘costs directly incurred as a result of operating the train service’, which should include a marginal renewal cost component. This change would also increase the cost recovery ratio of the Swedish infrastructure manager, thus meeting a policy objective of the national government.     

High-Speed Rail Operations on an Existing Network: An Assessment Model for China

High-speed rail operations have the potential to reduce the long-term decline in rail passenger travel demand for the medium to long distance inter-urban markets. Such decline has been evident through most of the industrialized countries where air and road transport tend to be the dominant modes. In China, the operations of long distance high-speed rail on fully dedicated track is not very easy to implement, due to the high proportion of passengers who travel between high-speed and conventional railways. An alternative approach would be to allow for mixed operations with trains of various speeds on the same track. This article puts forward a simulation model designed to allow an evaluation of the most efficient distance for high-speed rail operations under mixed train speed scenarios. The model takes into account the main operating parameters such as passenger volumes, train speeds, capital and maintenance costs, train operating costs and energy consumption. The distance of high-speed train running on conventional rail that will yield the most economic benefit can be estimated using the model. The article includes the results of using the model for a specific example. It is concluded that large-scale high-speed trains have the potential to be successfully operated on conventional rail networks.     

Analysis of peak and non‐peak traffic forecasts using combined models

Accurate and timely traffic forecasting is crucial to effective management of intelligent transportation systems (ITS). To predict travel time index (TTI) data, we select six baseline individual predictors as basic combination components. Applying the one‐step‐ahead out‐of‐sample forecasts, the paper proposes several linear combined forecasting techniques. States of traffic situations are classified into peak and non‐peak periods. Based on detailed data analyses, some practical guidance and comments are given in what situation a combined model is better than an individual model or other types of combined models. Indicating which model is more appropriate in each state, persuasive comparisons demonstrate that the combined procedures can significantly reduce forecast error rates. It reveals that the approaches are practically promising in the field. To the best of our knowledge, it is the first time to systematically investigate these approaches in peak and non‐peak traffic forecasts. The studies can provide a reference for optimal forecasting model selection in each period. Copyright © 2010 John Wiley & Sons, Ltd.     

Analysis of air traffic control operational impact on aircraft vertical profiles supported by machine learning

The Air Traffic Management system is under a paradigm shift led by NextGen and SESAR. The new trajectory-based Concept of Operations is supported by performance-based trajectory predictors as major enablers. Currently, the performance of ground-based trajectory predictors is affected by diverse factors such as weather, lack of integration of operational information or aircraft performance uncertainty.Trajectory predictors could be enhanced by learning from historical data. Nowadays, data from the Air Traffic Management system may be exploited to understand to what extent Air Traffic Control actions impact on the vertical profile of flight trajectories.This paper analyses the impact of diverse operational factors on the vertical profile of flight trajectories. Firstly, Multilevel Linear Models are adopted to conduct a prior identification of these factors. Then, the information is exploited by trajectory predictors, where two types are used: point-mass trajectory predictors enhanced by learning the thrust law depending on those factors; and trajectory predictors based on Artificial Neural Networks.Air Traffic Control vertical operational procedures do not constitute a main factor impacting on the vertical profile of flight trajectories, once the top of descent is established. Additionally, airspace flows and the flight level at the trajectory top of descent are relevant features to be considered when learning from historical data, enhancing the overall performance of the trajectory predictors for the descent phase.     

Very-high-speed tests on the french railway track

The campaigns conducted by SNCF at very high speeds allowed improvement in the knowledge of the actual TGV vehicle/track system and, in particular of the dynamical behavior of numerous components, which were obtained under very hard working conditions, for instance:

• — mechanical components (axle boxes, transmissions, etc.)
• — suspensions, damper particularly,
• — bogies,
• — pantograph,
• — electrical traction equipments (transformer of power, electric motors, power electronics, cooling systems),
• — signalling equipment.

Made with a TGV Atlantic series train set equipped with series components, it allowed demonstration to our passengers the very large safety margin of the whole system, track and vehicle as well, for revenue speeds of 300 km/h. At last, the tests allowed dramatically to raise the limit of the wheel and rail system, up to the mythic figure of 500 km/h, thus demonstrating that railways will reamin the first guided transport system during the 21st century.     

Infrastructure maintenance,regeneration and service quality economics: A rail example

This paper proposes a formalized framework for the joint economic optimization of continuous maintenance and periodic regeneration of rail transport infrastructure taking into account output consisting not only in traffic levels but also in track service quality. In contrast with much optimization work pertaining to spatially contiguous maintenance works, its principal economic emphasis and objective focus are centered on the optimal allocation of current maintenance and periodic renewal expenses, on their yearly distribution among large network partitions, and on infrastructure pricing. The model equations are based on very simple assumptions of infrastructure degradation laws and on a manager's objective function optimized through optimal control procedures. Equations are tested on national French rail track segment databases using Box–Cox transformations and match rail regeneration and maintenance practices prevailing in France. More generally, the paper makes a broad contribution to capital theory, on the optimal maintenance and renewal of equipment, and defines a method applicable not only to other transport infrastructure but to a wide range of capital goods, including housing, cars and industrial machines.     

基于AIGA-WLSSVM的埋地管道腐蚀速率预测方法

为了降低埋地管道腐蚀影响因素之间的复杂相关性,提高腐蚀预测精度,文中提出一种基于自适应免疫遗传算法-加权最小二乘支持向量机(AIGA-WLSSVM)的埋地管道腐蚀速率预测建模方法,并采用AIGA优化模型参数,进一步提高模型的学习能力和稳定性。最后通过实例分析验证了AIGA-WLSSVM建模方法在埋地管道腐蚀速率预测中的可行性和有效性,为埋地管道的检修与更换提供参考。     

An integrated sea–land transportation system model and its theory

To enhance the efficiency of intermodal transportation for large quantities of goods, the current sea–land transportation system has been reviewed and systematically analyzed, and a bottleneck is pinpointed in the linkage or goods transfer between the waterway and railway. The bottleneck impacts the efficiency of the goods through transportation combining the two modes. To eliminate the existing bottleneck and inefficiency towards intermodality, a new type of flexible double-rail track has recently been invented together with innovations both in trestle bridges and in train ferries. The outcomes of the research in progress show that the flexible double-rail track is feasible from the viewpoints of both geometry and engineering mechanics, it can be used to improve the compatibility of a trestle bridge with various types of train ferries and hence it can support the development of train ferries on a large scale. Based on the innovations, an integrated sea–land transportation system model is proposed as a systematic solution, which is expected to effectively overcome the existing bottleneck and to enhance the efficiency of the whole sea–land combined transportation. Further research on this system model and its major components is also addressed in the paper.     

Field investigation and parametric study of greenhouse gas emissions from railway plain-line renewals

Railway transportation is becoming increasingly important in many parts of the world for mass transport of passengers and freight. This study was prompted by the industry’s need to systemically estimate greenhouse gas emissions from railway construction and maintenance activities. In this paper, the emphasis is placed on plain-line railway maintenance and renewal projects. The objective of this study was to reduce the uncertainties and assumptions of previous studies based on ballasted track maintenance and renewal projects. A field-based data collection was carried out on plain-line ballasted track renewals. The results reveal that the emissions from the materials contribute more than nine times the CO₂-e emissions than the machines used in the renewal projects. The results show that extending the lifespan of rail infrastructure assets through maintenance is beneficial in terms of reducing CO₂-e emissions. Analysis was then carried out using the field data. Then the results were compared to two ballastless track alternatives. The results show that CO₂-e emissions per metre from ballasted track were the least overall, however, the maintenance CO₂-e emissions are greater than those of ballastless tracks over the infrastructure lifespan, with ballasted track maintenance emitting more CO₂-e emissions at the 30 and 60 year intervals and the end of life when compared to the ballastless track types. The outcome of the study can provide decision makers, construction schedulers, environmental planners and project planners with reasonably accurate GHG emission estimates that can be used to plan, forecast and reduce emissions for plain-line renewal projects.     

Birds using tram tracks in Poznań (Poland): Species,infrastructure use and behaviour

Transport infrastructures, mainly roads and railways, influence many aspects of bird life. The use of trams in urban areas for mass transit has been suggested as having a lower impact on the environment. However, to date, the impact of tram tracks and the surrounding infrastructure on birds has not been directly tested. Therefore, we posed two questions during a study of tramways in Poznań (western Poland): (1) which bird species use tram tracks and their infrastructure; and (2) how does their behaviour respond to moving trams. Tram tracks were recorded as used by 11 species, with four corvids (jackdaw Corvus monedula, rook Corvus frugilegus, magpie Pica pica and hooded crow Corvus cornix) totalling 66% of records and feral pigeon Columba livia contributing a further 24%. Species showed different usage patterns of the tram infrastructure. In the case of rook during winter, significantly more birds were observed further from a tram stop. In summer, a higher density of jackdaws occurred where track surroundings were vegetated, and both hooded crows in winter and magpies in winter were more abundant where track geometry was more complex. During our field work only two dead birds on tram tracks were observed. The results of this study, and a literature survey of other transport options, suggest that tram tracks are not very dangerous for birds, and at least from this point of view, can be recommended as an environmentally friendly transport system in urban areas.     

Influence of vehicle driving parameters on the noise caused by passenger cars in urban traffic

In this work, a sample of vehicles has been instrumented to measure of variables that influence vehicle noise emissions in Madrid. A circuit reproducing a normal travel pattern in large city is traveled by a fleet of vehicle models representing the fleets of cars in a European city. A sample of drivers covers the test track under different traffic conditions. Driving parameters and noise emitted have been recorded in each test and average values have been extracted. These data have been analyzed to define the noise emissions produced by a vehicle in real driving conditions and to identify the noisiest driving behaviors.     

A hybrid machine learning model for short-term estimated time of arrival prediction in terminal manoeuvring area

4D trajectory prediction is the core element of future air transportation system, which is intended to improve the operational ability and the predictability of air traffic. In this paper, we introduce a novel hybrid model to address the short-term trajectory prediction problem in Terminal Manoeuvring Area (TMA) by application of machine learning methods. The proposed model consists of two parts: clustering-based preprocessing and Multi-Cells Neural Network (MCNN)-based prediction. Firstly, in the preprocessing part, after data cleaning, filtering and data re-sampling, we applied principal Component Analysis (PCA) to reduce the dimension of trajectory vector variable. Then, the trajectories are clustered into several patterns by clustering algorithm. Using nested cross validation, MCNN model is trained to find out the appropriate prediction model of Estimated Time of Arrival (ETA) for each individual cluster cell. Finally, the predicted ETA for each new flight is generated in different cluster cells classified by decision trees. To assess the performance of MCNN model, the Multiple Linear Regression (MLR) model is proposed as the comparison learning model, and K-means++ and DBSCAN are proposed as two comparison clustering models in preprocessing part. With real 4D trajectory data in Beijing TMA, experimental results demonstrate that our proposed model MCNN with DBSCAN in preprocessing is the most effective and robust hybrid machine learning model, both in trajectory clustering and short-term 4D trajectory prediction. In addition, it can make an accurate trajectory prediction in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) with regards to comparison models.     

Analysis of travel activity determinants using robust statistics

This study investigates travel behavior determinants based on a multiday travel survey conducted in the region of Ghent, Belgium. Due to the limited data reliability of the data sample and the influence of outliers exerted on classical principal component analysis, robust principal component analysis (ROBPCA) is employed in order to reveal the explanatory variables responsible for most of the variability. Interpretation of the results is eased by utilizing ROSPCA. The application of ROSPCA reveals six distinct principal components where each is determined by a few variables. Among others, our results suggest a key role of variable categories such as journey purpose-related impedance and journey inherent constraints. Surprisingly, the variables associated with journey timing turn out to be less important. Finally, our findings reveal the critical role of outliers in travel behavior analysis. This suggests that a systematic understanding of how outliers contribute to observed mobility behavior patterns, as derived from travel surveys, is needed. In this regard, the proposed methods serve for processing raw data typically used in activity-based modelling.     

Financial relations between European railways for their international services

The operations of European railway companies are generally confined to the territory of one country. Each company incurs the cost of operations on its network. For international trains there are systems of physical compensation for vehicles and staff operating outside their home network. Revenues either go direct to each company involved, or, in the case of through international rates, are apportioned according to distance. This situation implies that for any decision on price and services agreement of all operators involved is necessary. Also, the apportionment of costs between operators is not in line with real cost structure. With further integration in the European community, and freer movement between Eastern and Western Europe, international transport will become more important, and railways will be at a disadvantage compared with other modes that can operate international services throughout. An organisation is proposed and illustrated with some examples, wherein separate commercial units are formed responsible for running and marketing an international rail service. Track, vehicles, and staff of national railway companiew may be used as now, but at a price to be agreed, and without the need for physical compensation.     

Prediction of ground vibration amplitudes due to urban railway traffic using quantitative and qualitative field data

The growth of railway transport in urban areas has lead to an increase in ground vibrations enhancing their negative environmental impact. Therefore is mandatory to predict and control ground vibrations. This work presents a methodology for the determination of prediction models of ground vibration amplitudes due to railway train circulation in urban environments. Using quantitative predictors (train speed and distance) and qualitative predictors (railway track type, dominant geology and building type), being the use of the latter predictors justified by the fact that, most frequently, quantitative parameters are very difficult to obtain in the urban environment due to their characterization. Thus, a detailed statistical study based on the proposal and validation of multiple linear regression models, is successfully applied in order to predict vibration amplitudes produced by railway train circulation, in the considered domain, as function of quantitative and qualitative predictors, easily obtained in field work. A multiple linear regression model for ground vibration prediction due to underground railway traffic has been presented for the Lisbon area.