Real-time Train Research Articles

Robust Control for Dynamic Train Regulation in Fully Automatic Operation System Under Uncertain Wireless Transmissions

For enhancing the operation efficiency of the fully automatic operation (FAO) system in the urban rail transit (URT), this paper investigates the robust dynamic train regulation problem with respect to frequent disruptions and imperfect wireless transmissions. To better express the characteristic of the arriving passengers, the fuzzy passenger arrival rate is adopted to address the uncertainty of the passenger flow, and a T-S fuzzy state-space model is established to express the periodical movement of the train traffic in an URT loop line. By considering the possible packet dropout phenomenon during the wireless data transmissions, which may lead to the instability of the train traffic system and degrade the performance of the regulation strategy, a robust real-time train regulation strategy is developed based on the fuzzy predictive control theory, which distinguishes existing studies in that the uncertainty dropout rate is contemplated to address the complexity of the actual operation environment. A sufficient condition for the proposed control law is presented to guarantee that the nominal train schedule is recovered from disturbed situations with a given attenuation level by means of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$H_{\infty }$ </tex-math></inline-formula> performance index, and meanwhile the optimization of the upper bound on the objective function balancing the service efficiency and control cost is achieved. Numerical simulations based on the Beijing subway loop line 2 are presented for demonstration of the effectiveness of the introduced strategy.

PLC and SCADA based Real Time Monitoring and Train Control System for the Metro Railways Infrastructure

PLC and SCADA based Real Time Monitoring and Train Control System for the Metro Railways Infrastructure

Distributed model predictive control for real-time train regulation of metro line based on Dantzig-Wolfe decomposition

This paper aims to propose a novel distributed model predictive control (MPC) scheme for real-time train regulation in urban metro transportation. Particularly, a nonlinear real-time train regulation model is put forward to minimize the timetable deviations and the control strategies for each trainunder the uncertain disturbances, which is then reformulated into a linear optimization model for easy to solve. By regarding each train as a subsystem, we design the distributed MPC algorithm based on the Dantzig-Wolfe decomposition for the train regulation problem, which decomposes the original optimization problem into numerous smaller and less complicated optimization control problems that can be solved independently. Under the distributed mechanism, we regard each train as a local subsystem, which only interacts with the coordinator, ensuring the flexibility and modularity of the control structure. Numerical cases are provided to demonstrate the effectiveness and robustness of the proposed distributed MPC method.

Cooperative Tracking Control of the Multiple-High-Speed Trains System Using a Tunable Artificial Potential Function

It is a challenge to maintain a safe and efficient tracking for multiple high-speed trains under the moving block operational mode. In this paper, a novel cooperative tracking control based on a consensus algorithm and artificial potential field theory is proposed to realize the train tracking within a distance range. A tunable artificial potential function is first designed to dynamically adjust the distance between adjacent high-speed trains with real-time train states. By regulating the parameters of the artificial potential function, the safety distance can be adjusted according to the required tolerance deviation of the actual distance. Under the proposed strategy, each high-speed train operates with the desired speed and tracks the preceding one with an adjustable distance range. Numerical train operational cases are investigated to illustrate the effectiveness of the proposed methods.

Real-time train regulation method for metro lines with substation peak power reduction

In high-frequency metro lines, train delays and substation peak power often occur, affecting safe and efficient train operation. In this paper, we propose real-time train regulation methods considering substation peak power reduction, in which runtimes and dwelltimes are adjusted to minimize the timetable and headway deviations and avoid multiple train accelerating. Firstly, we proposed two indirect indicators, i.e. overlapping time between accelerating phases and overlapping quantity between accelerating phases, which are minimized to suppress substation peak power in joint optimal train regulation models. The joint optimal train regulation models are based on the traditional real-time train regulation model considering the train traffic dynamics and control constraints. For the real-time requirement of train regulation, model predictive control (MPC) algorithms are designed to solve the formulated joint optimal control models, which generate the optimal train regulation strategies at each control cycle based on the real-time updated feedback system states. Finally, numerical examples based on one of the Guangzhou metro lines are implemented to verify the effectiveness and robustness of the proposed methods. The results show that the train regulation strategy with minimizing the overlapping quantity can not only suppress train delays and substation peak power, but also meet the real-time computation requirement.

Research on the Applicability of Vibration Signals for Real-Time Train and Track Condition Monitoring.

The purpose of this research was to analyze the possibilities for the application of vibration signals in real-time train and track control. Proper experiments must be performed for the validation of the methods. Research on vibration in the context of transport must entail many of the different nonlinear dynamic forces that may occur while driving. Therefore, the paper addresses two research cases. The developed application contains the identification of movement and dynamics and the evaluation of the technical state of the rail track. The statistics and resultant vector methods are presented. The paper presents other useful metrics to describe the dynamical properties of the driving train. The angle of the resultant horizontal and vertical accelerations is defined for the evaluation of the current position of cabin. It is calculated as an inverse tangent function of current longitudinal and transverse, longitudinal and vertical, transverse, and vertical accelerations. Additionally, the resultant vectors of accelerations are calculated.

Real-time optimization for train regulation and stop-skipping adjustment strategy of urban rail transit lines

This paper addresses the real-time train regulation problem by taking the stop-skipping strategy into account in high-frequency urban rail transit lines. During rush hours, if the train regulation is not adopted properly and rapidly to deal with the frequent disturbances, the delays may further spread and result in a large number of passengers stranded in the stations. The purpose of this paper is to explore the possibility of dynamic train regulation and stop-skipping adjustment strategy to cope with the disturbance management in a real-time manner. By considering the impact of dynamic passenger flows, a nonlinear programming model for train regulation problem is proposed with the objective of minimizing the total train deviation and enhancing the passenger service quality, which is further converted into a mixed-integer quadratic programming model for ease to solve. In addition, the constraints related to the train rolling-stock plan are taken into account to provide a feasible scheme. Based on a customized model predictive control (MPC) method, the proposed model can be solved in a real-time manner, laying a theoretical groundwork for implementation of the train regulation strategy. Computational results based on the real-world data of Beijing Yizhuang metro line illustrate the superiority of the train regulation strategy in comparison with the practical strategy. The robustness of the method is examined through various scenarios of uncertain passenger demands, and the adjustment performance with different prediction horizons is explored to illustrate the added value brought by the updated information of the proposed MPC method.

A simulation-optimization framework for traffic disturbance recovery in metro systems

This paper analyses how train delays propagate in a metro network due to disturbances and disruptions when different recovery strategies are implemented. Metro regulators use traffic management policies to recover from delays as fast as possible, return to a predefined schedule, or achieve an expected regularity of train arrivals and departures. We use as a metro traffic simulator SIMSTORS, which is based on a Stochastic Petri Net variant and simulates a physical system controlled by traffic management algorithms. To model existing metro networks, SIMSTORS has been mainly used with rule-based traffic management algorithms. In this work, we enhance traffic management strategies. We integrate SIMSTORS and the AGLIBRARY optimization solver in a closed-loop framework. AGLIBRARY is a deterministic solver for managing complex scheduling and routing problems. We formulate the real-time train rescheduling problem by means of alternative graphs, and use the decision procedures of AGLIBRARY to obtain rescheduling solutions. Several operational issues have been investigated throughout the use of the proposed simulation–optimization framework, among which how to design suitable periodic or event-based rescheduling strategies, how to setup the traffic prediction horizon, how to decide the frequency and the length of the optimization process. The Santiago Metro Line 1, in Chile, is used as a practical case study. Experiments with this framework in various settings show that integrating the optimization algorithms provided by AGLIBRARY to the rule-based traffic management embedded in SIMSTORS optimizes performance of the network, both in terms of train delay minimization and service regularity.

Energy-Saving Driving Based on the Prediction of Block Clearing Times During Real-Time Train Rescheduling

Energy-Saving Driving Based on the Prediction of Block Clearing Times During Real-Time Train Rescheduling

A Mixed-integer Linear Program for Real-time Train Platforming Management

Unexpected events may perturb operations and generate conflicts that must be addressed promptly to limit delay propagation and other negative impacts on the network. The real-time railway traffic management problem deals with disruptions in railway networks, including tracks, junctions and stations. When they happen in station areas, new decisions involving train platforming, rerouting, ordering and timing must be made in real time. This paper explores a mesoscopic approach to deal with disruptions at rail stations. A mathematical programming-based model is proposed to determine re-routing and re-scheduling decisions for railway traffic in a station area. The key steps of the approach, which simulate what happens in real-time traffic management, are: i) an initial off-line preprocessing stage of the set of feasible routes originally planned, ii) a second preprocessing stage which analyses the disruption and sets the necessary parameters for the last step iii), which consists of an integer programming model that seeks solutions which minimise deviations from planned train schedules and assigns new and appropriate platforms (if necessary). Computational experiments show that realistic instances can be solved near to optimality using CPLEX in very short times. This allows to consider this methodology for solving real time traffic management problems.

Two-Step Optimization of Urban Rail Transit Marshalling and Real-Time Station Control at a Comprehensive Transportation Hub

Urban rail transit connecting with a comprehensive transportation hub should meet passenger demands not only within the urban area, but also from outer areas through high-speed railways or planes, which leads to different characteristics of passenger demands. This paper discusses two strategies to deal with these complex passenger demands from two aspects: transit train formation and real-time holding control. First, we establish a model to optimize the multi-marshalling problem by minimizing the trains’ vacant capacities to cope with the fluctuation of demand in different periods. Then, we establish another model to control the multi-marshalling trains in real time to minimize the passengers’ total waiting time. A genetic algorithm (GA) is designed to solve the integrated two-step model of optimizing the number, timetable and real-time holding control of the multi-marshalling trains. The numerical results show that the combined two-step model of multi-marshalling operation and holding control at stations can better deal with the demand fluctuation of urban rail transit connecting with the comprehensive transportation hub. This method can efficiently reduce the number of passengers detained at the hub station as well as the waiting time without increasing the passengers’ on-train time even with highly fluctuating passenger flow.

Research on Risk Prediction of Train Derailment based on Relative Wheel-rail Displacement

Derailment safety is the basis for safe train operation, and the derailment coefficient is an important indicator for judging whether a train is derailed. Traditional derailment coefficient prediction methods have problems such as high cost, low prediction accuracy, and the inability to monitor the contact status between wheels and rails of running trains in real time. This paper proposes a train derailment coefficient prediction method based on image processing. Firstly, use the generative adversarial network to extract the edge curve of the wheel-rail contact area. Secondly, determine the wheel-rail lateral relative displacement based on the positional relationship between the rail and the centerline of the wheelset. Use the speed and acceleration sensors to obtain the train speed, lateral acceleration, and longitudinal acceleration, and finally use improvements. The BP neural network integrates wheel-rail lateral displacement, speed, lateral acceleration, and longitudinal acceleration data to obtain the train derailment coefficient at the next moment. The field test results show that the derailment coefficient prediction model in this paper can achieve accurate prediction of the derailment coefficient and has good robustness.

Risk of delay evaluation in real-time train scheduling with uncertain dwell times

While trains travel in a railway network, disturbances may arise and corrective decisions to minimize delay propagation may be necessary to solve conflicting track requests. This problem is known in the literature as the real-time Railway Traffic Management Problem (rtRTMP) and its solutions represent plans of operations that minimize delay propagation due to unexpected disturbances. However, uncertainty may still affect such plans and their expected quality in terms of level of service or risk containment. This article proposes a new approach for the assessment of the risk of onset or worsening of delays associated to an rtRTMP solution when dwell times are uncertain and only an interval representation of them is known to the scheduler. To this aim, the Conditional-Value-at-Risk of the maximum train delay is adopted as risk index. In this study we address both modeling and computational issues, developing and testing a graph-based model to use with an innovative numerical method to obtain a real-time risk evaluation for rtRTMP solutions. The proposed approach is applied on a real case study analyzing the effects of uncertainties of different severity. Promising computational results enable to use the methodology to deal with the rtRTMP taking into account the uncertainty on the involved activities and the risk attitude of the decision-makers at the operational level.

Prediction and analysis of train arrival delay based on XGBoost and Bayesian optimization

Accurate train arrival delay prediction is critical for real-time train dispatching and for the improvement of the transportation service. This study proposes a data-driven method that combines eXtreme Gradient Boosting (XGBoost) and a Bayesian optimization (BO) algorithm to predict train arrival delays. First, eleven characteristics that may affect the train arrival time at the next scheduled station are identified as independent variables. Second, an XGBoost prediction model that captures the relation between the train arrival delays and various railway system characteristics is established. Third, the BO algorithm is applied to the hyperparameter optimization of the XGBoost model to improve the prediction accuracy. Subsequently, case studies using data from two high-speed railway (HSR) lines in China are performed to analyze the prediction efficiency and accuracy of the proposed model for different delay bins and at different stations. The results on two HSR lines demonstrate that the proposed method outperforms other benchmark models regarding the performance metrics of the determination coefficient (0.9889/0.9905), root-mean-squared error (2.686/1.887), and mean absolute error (0.896/ 0.802). In addition, the statistical test is carried out using Friedman Test (FT) and Wilcoxon Signed Rank Test (WSRT) to validate the efficacy of the proposed method. Furthermore, the train arrival delays at different abnormal events can also be accurately forecasted using the proposed method; the results indicate that the proposed method outperforms other benchmark methods, especially in the prediction of long delays caused by specific abnormal events.

Integrated train dwell time regulation and train speed profile generation for automatic train operations on high-density metro lines: A distributed optimal control method

The wide-spread application of automatic train operation (ATO) system on metro lines allows short service headways, high-density operations and high operation efficiency. This paper addresses real-time train control for ATO when faced with disturbances or disruptions in its operations. More specifically, the paper focuses on the design of integrated train dwell time regulation and speed profile generation in real-time and in response to dynamic changes in the operation environment. A nonlinear optimal control model is formulated in a rolling horizon scheme that incorporates three key operating elements: train timetable, passenger load and train speed profile. The objective is to simultaneously improve headway regularity and reduce the total energy consumptions. To satisfy the real-time control requirement for ATO system, a decomposition method based on the alternating direction method of multipliers (ADMM) is designed to divide the original optimization problem into many sub-problems, one for each train, which can then be computed in a distributed manner. Moreover, to address the non-convexity issue, a relax-round-polish process is developed to deal with the formulated nonlinear optimal control problem with convex objective over non-convex constraints in order to find the approximate solutions quickly for the embedded applications. The combined result is an ADMM-based heuristic algorithm. The effectiveness of the proposed model and solution algorithm is demonstrated using real-world data from the Changping Line of Beijing Metro. The results show that the proposed distributed and embedded optimization algorithm is able to significantly enhance the robustness and reliability of real-time train control in automated high-density metro lines.

Fitting Knock-on Delay Duration Distributions using High-Speed Train Operation Records

Delay distribution models are helpful in real-time train dispatching. These models can aid dispatchers to estimate the probability of delay duration and better manage train delays in practice. In this paper, based on the actual train operation records at Xiamen-Shenzhen high-speed railway (HSR) from April 2015 to October 2016, the number of knock-on delay (KD) trains and the number of arrival trains were counted. The statistical result demonstrated the train frequency affected the KD train frequency to some extent. The statistical method was used to establish the knock-on delay duration distribution (KDDD) model. The five common distribution models fitted KDDDs at peak hours and off-peak hours at four stations. The maximum likelihood estimate obtained the parameters of the five theoretical distributions. The log-normal distribution fitted the KDDDs best at both periods and four stations according to the Kolmogorov–Smirnov (K-S) test result. The probability of knock-on delay duration was calculated, and the result indicated the probability of knock-on delay duration in (1,5) min were the maximum, and those at peak hours were more than those at off-peak hours at Huizhou South and Houmen.

Using Real-Time Data to Detect Delays and Improve Customer Communications at New York City Transit

New York City Transit operates one of the world’s largest transit systems, and it can be difficult for the agency’s communications team to keep track of the numerous service disruptions that need to be communicated to customers. This paper introduces the Transit Visualization tool, which processes real-time train location data to automatically identify areas of the system where service may not be living up to customers’ expectations. Specifically, the Transit Visualization is set up to identify areas of the system where trains are operating at lower-than-normal speeds and areas of the system where there are atypically long gaps between trains. Any occurrence of slow speeds or long gaps is assigned a severity level (Moderate, Severe, or Very Severe) to indicate the magnitude of the problem. An overview of any problems the application identifies is shown on an interactive web map, as well as on several easy-to-digest summary tables. The map also displays real-time locations of trains and buses throughout the transit system. The Transit Visualization has been successfully rolled out to the subways communications team and has become a mission-critical tool for communicating delays to customers, especially during the course of the COVID-19 pandemic.

Train rescheduling in a major disruption on a high-speed railway network with seat reservation

ABSTRACT In this paper, we develop a method of real-time train rescheduling on double-track high-speed railway lines undergoing major disruption. As a result, trains approaching the disrupted area cannot use the blocked tracks and must be efficiently rescheduled. As most tracks in a high-speed railway station can be shared by trains arriving from both directions, we reschedule both inbound and outbound trains simultaneously by allowing them to share sidings. Based on a space-time network, an integer linear programming (ILP) model is formulated to minimize the train-deviation cost. As the ILP model is difficult to solve for real-world problems, we decompose it into many easy-to-solve subproblems by the alternating direction method of multipliers (ADMM) algorithm. Our model is tested on an abstract representation of the Chinese high-speed railway system to illustrate both the benefit of rescheduling trains in both directions simultaneously and the efficiency of the ADMM algorithm in train rescheduling.

A real-time train routing and platforming problem in complex railway stations

This paper studies the real-time trains routing and platforming problem (RT-TRPP) in railway stations that arises from the unreliable arrival times of freight trains, flexible shunting operations and dynamic station layout caused by equipment failure. The feasibility of station timetable is checked before preparing a route for a train or after updating the station layout. If the station timetable is infeasible, the reassignment of trains is triggered. After introducing a problem formulation for the RT-TRPP, we propose an Integer Linear Program (ILP) that strives to minimize the number of conflicting trains. In resulting timetable, directions, arrival and leaving time remain the same with networks timetable to prevent traffic disturbance of neighboring territories. If the resulting timetable is still infeasible, conflicting trains are pointed out with the cause analysis. The method is tested on real-world complex station which receives always the overload of trains’ activities. The optimal full-day solution of 249 trains is obtained within 2 seconds. The efficiency of this method meets the time-critical nature of RT-TRPP.

A Real-Time Train Timetable Rescheduling Method Based on Deep Learning for Metro Systems Energy Optimization under Random Disturbances

Considering that uncertain dwell disturbances often occur at metro stations, researchers have proposed many methods for solving the train timetable rescheduling (TTR) problem. This paper proposes a Modified Genetic Algorithm-Gate Recurrent Unit (MGA-GRU) method, which is a real-time TTR method based on deep learning. The proposed method takes the Gate Recurrent Unit (GRU) network as the decision network and uses the results produced by the Modified Genetic Algorithm (MGA) as the training set of the decision network. A well-trained decision network can provide effective solutions in real time after random disturbances occur, in order to optimize the net traction energy consumption of trains in metro systems. Based on the Shanghai Metro Line One (SML1) pilot network, this paper establishes a comprehensive model of the metro system as a training and testing environment to verify the energy-saving effect and real-time performance of the proposed method in solving the TTR problem. The experimental results show that in the two-train metro system, the three-train metro system, and the five-train metro system, the MGA-GRU method can save an average of energy by 4.45%, 6.16%, and 7.19%, while the average decision time is only 0.15 s, 0.27 s, and 0.33 s, respectively.