Actual Train Operation Research Articles

Decentralized learning control for high-speed trains with unknown time-varying speed delays

Treating the multi-point-mass dynamic model of high-speed trains as an interconnected system, this study proposes a decentralized iterative learning control scheme for high-speed trains to achieve the trajectory tracking goal. By making reasonable estimates of the interaction term and compensating for it, the proposed control scheme utilizes only local information from each carriage and does not need any inter-carriage information exchange. The zero-error tracking of the desired trajectory is guaranteed even in a restricted communication environment. Considering unknown time-varying speed delays in the actual high-speed train operations, a modified decentralized iterative learning control scheme is also provided to address the negative impact of speed delays. The convergence of tracking errors is strictly proven by constructing appropriate composite energy functions. Numerical simulations further verify the theoretical results.

IGBT Gate Boost Drive Technology for Promoting the Overload Capacity of Traction Converter.

Under certain circumstances, a high-speed railway may require constant acceleration or emergency braking, in which case the inverter may experience short-term overload conditions and the current passing through the IGBT will go beyond the rated design tolerance. Under overload conditions, the IGBT loss will increase instantly, raising the power semiconductor device's junction temperature in the process. This research examines the boosting-gate-voltage-driven IGBT control technology. It increases the gate drive voltage and the IGBT current capacity and decreases the conduction voltage drop of IGBT under short-term overload conditions, reducing the instantaneous loss and temperature rise undulation of IGBT. The working characteristics of IGBT devices are studied, and the influence of gate drive voltage on device loss and temperature rise fluctuations is analyzed. Based on the emergency acceleration and brake conditions of the actual train operation, the short-term overload characteristics of the inverter are analyzed. The optimization analysis of the boosting gate voltage under emergency conditions is carried out, and the IGBT drive circuit with gate voltage pumping function is designed. The effectiveness of the driving circuit is verified through PSpice simulation and actual switching characteristic test. According to the analysis of experimental data, it can be verified that increasing the gate voltage technology can reduce IGBT losses.

An improved energy‐efficient driving strategy for routes with various gradients and speed limits

AbstractWith the increasing concerns about railway energy efficiency, two typical driving strategies have been used in actual train operation. One includes a sequence of full power traction, cruising, coasting, and full braking (CC). The other uses coasting–remotoring (CR) to replace cruising in CC. However, energy‐saving performance by CC and CR, which can be affected by route parameters of gradients and speed limits, has not been fully compared and studied. This paper analyses the energy distribution of CC and CR considering various route parameters and proposes an improved strategy for different gradients and speed limits. The detailed energy flow of CC and CR is analysed by Cauchy–Bunyakovsky–Schwarz inequality and the generalised Hölder's inequality, and then, a novel driving strategy CC_CR is designed. To verify the theoretical results and the effectiveness of the proposed strategy, three simulators with CC, CR, and CC_CR driving modes have been developed and implemented into case studies of four scenarios as well as a real‐world metro line. Simulation results demonstrate that CR can only outperform CC on routes with steep downhill and CC_CR is always the best strategy. The energy savings of CC_CR can be as much as 15% more than CR and 42% greater than CC.

Control strategy and capacity optimization of energy-storage-based railway power conditioner

Electrified railroad has the characteristics of high safety factors, high comfort, large transportation capacity, and less time-consuming, which is an effective means to solve traffic congestion. However, with the rapid development of China’s electrified railroad, harmonic, negative sequence and other power quality problems have also been widely concerned, while more and more regenerative braking energy in the traction power supply system can not be effectively utilized. The input of railroad power regulators makes the power quality problem be solved effectively, this paper studies the control strategy of traditional railroad power regulators. Combined with the actual working conditions of railroad vehicles, the simulation model of traction network, vehicles, and railroad power conditioner is established, and the load characteristics of traction substation are simulated by this model. Secondly, for a domestic substation field collection data processing to obtain the actual train operation load changes, to the battery energy storage device life within the maximum economic returns as the optimization goal, for the peak load reduction judgment threshold and the capacity of the battery energy storage device through the genetic algorithm to process the data of previous years to optimize the design.

Field study on the through-draught characteristics and its influencing factors in subway carriages

The through-draught effect inside a subway significantly impacts the flow field profile, thus causing a potential threat to pollutant dispersion and human health. This study conducted multiple field measurements to systematically analyze the through-draught characteristics during actual train operation. The results show that the total variation of airflow velocity has a high consistency with train operation parameters, which reaches its peak value at the end of the acceleration period (EAP). And the airflow direction reverses as the running speed falls to nearly 0.45 times the maximum of that. For the whole subway train, the air velocity grows continuously in the first four carriages and then drops from the fifth carriage, with a maximum speed of 2.37 ± 0.12 m/s. Moreover, the airflow velocity distribution in a carriage exhibits an approximate “W-shape”, and the profile of the maximum airflow velocity is equivalent to a “parabolic surface”, with a velocity difference of less than 0.45 m/s. Finally, the through-draught effect is comprehensively affected by train acceleration and station spacing which further impact the air inertia forces and internal pressure difference, respectively; the wind speed peak positively correlates with train acceleration and subjects to an inverse exponential function with the station spacing. The research outcome can provide a valid basis for airflow control and air quality improvement in subway carriages operating in the underground tunnel.

A small sample diagnosis method driven by simulation and test data: applied to axle box bearings of high-speed train

Abstract Fault diagnosis of axle box bearings is an important technology to improve the service safety and economy of high-speed trains. However, it is difficult to obtain sufficient fault samples in actual train operation, which limits the application of deep learning methods in the field of high-speed train fault diagnosis. Therefore, in this paper, a simulation and test data fusion-driven fault diagnosis method for axle box bearings with few samples is proposed. In this method, a bearing dynamics model is constructed to obtain simulation data for fault bearings, and the accuracy of the constructed dynamics model is verified by experimental data. Data fusion methods are proposed which use massive simulated fault samples and only normal test samples to construct new samples for the pre-training of deep learning diagnostic models. The parameter transfer strategy is used to fine-tune the diagnostic model with a small amount of test fault samples. A real train experiment is carried out for validating the proposed methods which use the real fault bearings that fail during operation. The results show that the proposed method via the fusion of simulation and test data has higher generalization ability and diagnostic accuracy in small sample situations.

Parallel Kalman filter group integrated particle filter method for the train nonlinear operational status high-precision estimation under non-Gaussian environment

For the problem of multi-mode state estimation in actual train operation, this paper proposes a nonlinear non-gaussian high-precision parallel Kalman filter group (NN-HEKFG) integrated Particle Filter. A multi-model Gaussian decomposition of the probability density function for state equations and measurement equations is performed, and each local state model is represented by a multi-dimensional high-order polynomial to establish the expanded dimensional state model. Then, by updating the mean and variance of the local state expanded dimensional model and in turn solving the particle filtering posterior probability density distribution function, the global estimation results are obtained. In reducing the number of Gaussian terms, a new parameter reduction criterion is established, which can effectively carry out the re-identification of parameters such as weights and means, so as to avoid the problem of parameter explosion. The superiority of NN-HEKFG over particle filters and Gaussian sum filters and its effectiveness for train running state estimation are verified by simulating the multi-model running state of trains.

A Learning Based Intelligent Train Regulation Method With Dynamic Prediction for the Metro Passenger Flow

With the acceleration of urbanization, the dynamic passenger flow has an ever-growing impact on the actual train operation. In this paper, we propose a learning based intelligent train regulation method with dynamic passenger flow prediction. To capture the characteristics of the dynamic metro passenger flow, a convolutional neural network is established to predict the real-time passenger flow from two dimensions including space and time. As the prediction accuracy is restricted by the insufficiency of the practical passenger flow data, a deep convolutional generative adversarial network is constructed to generate data that have the same distribution as the original passenger flow dataset. Then, by considering the effects of the dynamic passenger flow on the train operation and the train capacity constraints, the dynamic train regulation is formulated as a multi-stage optimal control problem with the objective function of minimizing the train traction energy consumption and the total traveling time of passengers. To efficiently obtain the optimal regulation strategy at each decision step, a deep Q-network algorithm is proposed to solve the formulated problem such the dimensionality curse caused by the excessive state space is avoided. The numerical experiments demonstrate the high efficiency and effectiveness of our proposed algorithm and model.

The Dynamic Programming Model for Calculating the Maximum Number of Gathering Passengers in High-Speed Railway Station Based on Gaussian distribution

in this paper, based on the actual train operation plan and evacuation plan of the high-speed railway station, taking the train capacity and occupancy rate as the basic data, the Gaussian function is used to describe the passenger arrival law and the uniform distribution is used to describe the passenger evacuation law. Also, the calculation model of the number of gathering passengers at the high-speed railway station is established by MATLAB. Taking Guangzhou South Railway Station as an actual case, the maximum number of gathering passengers in the whole day and the change curve of the number of gathering passengers with time are obtained. The calculation results are consistent with the actual situation, which can provide a reference for the passenger flow organization and management of the high-speed railway station and the new construction and reconstruction of the high-speed railway station.

Dynamic hybrid mechanism-based differential evolution algorithm and its application

In order to effectively schedule railway train delay, an adaptive cooperative co-evolutionary differential evolution with dynamic hybrid mechanism of the quantum evolutionary algorithm and genetic algorithm, named QGDECC is designed in this paper. In the QGDECC, the quantum variable decomposition strategy is designed by utilizing qubit string to decompose variables adaptively according to the coevolution performance. Then the increment mutation method is proposed to improve the convergence speed which make full use of searched evolution information. Besides, the parameter adaptive strategy is deeply explored for strengthening the robust of the algorithm. The QGDECC with global search capability is employed to realize a railway train delay scheduling method for effectively eliminating the impact of train delay. Finally, several benchmark functions and actual train operation data are selected to verify the optimization performance of QGDECC. The experimental results show that QGDECC has higher adaptability, faster convergence speed and accuracy. The train delay scheduling method can effectively eliminate the impact of delay on the railway network, and minimize the gap between the rescheduled train schedule and the original train schedule.

태풍과 고속열차 운행에 의한 지상역사 승강장 스크린도어의 풍압 수치해석 연구

In the present study, the wind pressure acting on the platform screen door is investigated numerically by a train-induced wind and a typhoon. The dual island platform on a ground-level station was considered as a computational domain. To make a stable simulation, detailed buildings and station structures were modeled in a 2 km long, 1 km wide and 200 m hight computational domain. The high-speed train and station were modeled as detail as possible, and the actual train operation was considered to build similar analysis conditions. The overset mesh method was adopted to consider the high-speed train

Long Short-Term Memory-Based Model Predictive Control for Virtual Coupling in Railways

The increasing need for capacity has led the railway industry to explore new train control systems based on a concept called virtual coupling. Inspired by the platooning of autonomous vehicles, the safe operation of virtual coupling is guaranteed by a relative brake distance-based train separation method. This paper proposes a novel long short-term memory (LSTM)-based model predictive control (MPC) method for train operations. An MPC-based control design for virtual coupled train operations is presented. The LSTM is introduced to model the dynamics of the preceding train to approximate the actual train operations. With the train dynamics models, the operation trajectories of the preceding train are predicted based on planned control inputs. A study of a metro line in Chengdu was chosen to analyze the proposed control approach. The simulation results of different scenarios show that compared with the conventional MPC methods, the proposed LSTM-based MPC can reduce the speed differences and position differences of tracking trains by up to 35 % and 25 % , respectively.

ОПРЕДЕЛЕНИЕ ПАРАМЕТРОВ ПОЕЗДА В ПУТИ СЛЕДОВАНИЯ ПО ДАННЫМ БОРТОВЫХ ИЗМЕРИТЕЛЬНЫХ СИСТЕМ ГРУЗОВЫХ ЭЛЕКТРОВОЗОВ

The paper suggests an approach to determination of actual train operation parameters according to data from on-board measurement systems in order to increase efficiency of application of automatic electric motive power operation systems. The authors have analysed scientific works in the sphere of improvement of automatic electric locomotive operation. The paper also presents results of comparison of grade computations in KORTES and real data from on-board measurement systems on 2ES6 electric locomotives that operate on a section of the West-Siberian Railway. As a result, the authors have substantiated a possibility to apply data gained from on-board measurement systems in real-time mode for determination of such train parameters as tractive effort torque of traction motors, electric locomotive traction effort, external forces of train tractive resistance, reduced gross load hauled and etc. The approach to determination of train parameters according to data of current measurements allows increasing peculiarity of transmission of control actions and efficiency of an automatic train operation system.

Using the gradient boosting decision tree (GBDT) algorithm for a train delay prediction model considering the delay propagation feature

Accurate prediction of train delay is an important basis for the intelligent adjustment of train operation plans. This paper proposes a train delay prediction model that considers the delay propagation feature. The model consists of two parts. The first part is the extraction of delay propagation feature. The best delay classification scheme is determined through the clustering method of delay types for historical data based on the density-based spatial clustering of applications with noise algorithm (DBSCAN), and combining the best delay classification scheme and the k-nearest neighbor (KNN) algorithm to design the classification method of delay type for online data. The delay propagation factor is used to quantify the delay propagation relationship, and on this basis, the horizontal and vertical delay propagation feature are constructed. The second part is the delay prediction, which takes the train operation status feature and delay propagation feature as input feature, and use the gradient boosting decision tree (GBDT) algorithm to complete the prediction. The model was tested and simulated using the actual train operation data, and compared with random forest (RF), support vector regression (SVR) and multilayer perceptron (MLP). The results show that considering the delay propagation feature in the train delay prediction model can further improve the accuracy of train delay prediction. The delay prediction model proposed in this paper can provide a theoretical basis for the intelligentization of railway dispatching, enabling dispatchers to control delays more reasonably, and improve the quality of railway transportation services.

Research on High-Speed Train Load Spectrum and Bridge Load Effect Spectrum

Based on ANSYS finite element analysis software, a dynamic model of the Beijing-Tianjin intercity railway car-track-bridge system is established to analyze the dynamic response of the bridge under the normal high-speed double-track traffic conditions. Combined with the statistics of actual train operation, the bridge load spectrum represented by wheel/rail force is obtained. With the aid of the rain-flow counting method, the stress data of the weak part of the bridge span is equivalently converted into variable amplitude stress amplitude and the corresponding cycle times are obtained. In this way, the stress spectrum of the Beijing-Tianjin intercity railway bridge in the use reference period is estimated, which provides a certain reference basis for the life assessment of the in-service bridge and the reinforcement of weak parts in the future.

Modelling on Novel Cable Traction Power Supply System and Power Distribution Analysis

Novel cable traction power supply system (NCTPSS) is a kind of long distance co-phase traction power supply system (TPSS), it can effectively solve problems caused by train's passing through electrical phase separation and improve utilization rate of regenerative energy in system, which is an ideal traction power supply mode. However, its structure is relatively complex due to cable power supply pattern, and internal power flow distribution mechanism still needs further study. In order to establish train-network coupling power flow calculation model, in this paper, two-port network model of each system component is established at first, then equivalent solid circuit model of the system is built by external cascade strategy and tearing nodal method. Then, power flow, the change of traction transformer power output and network voltage are analyzed under the condition that trains work in traction and regenerative braking condition, based on actual train operation schedule. The research shows that the proposed model can accurately calculate and detailed reflect electrical characteristics of NCTPSS, traction transformer capacity is effectively decreased compared with that needed in existing TPSS; Regenerative power can feed back to entire cable traction network and be reused by traction trains with high utilization rate inside NCTPSS.

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.

Fitting Method of Optimal Energy-Running Time Curve Based on Train Operation Data of an Urban Rail Section

Due to the complexity of the operation control of urban rail transit and diversity requirements for section running time standards, based on actual train operation data, this paper proposes a curve fitting method to find the interrelation between running time and energy consumption. According to features of the energy consumption-running time curve, the discriminant criterion of outliers is constructed to select the candidate fitting data set from the original data set. To fit the energy consumption-running time curve from two-dimensional scatter points, we propose a B-spline curve fitting method based on a genetic algorithm and the fitting method is proven to have high fitting accuracy and convergence speed. Furthermore, we propose an optimization method for the fitting curve based on dynamic adjustment of the fitting data set which is selected from the candidate fitting data set to obtain the optimal energy-running time curve. The validation of Guangzhou Metro's actual operation data shows that the energy-running time curve fitted and optimized by our method has lower energy and better continuity and smoothness and could be used for evaluation of train drivers’ performance and energy consumption of train operation diagram.

Multistation coordinated and dynamic passenger inflow control for a metro line

Passenger inflow control is an efficient way to relieve peak passenger flow and reduce security risks in metro networks. However, station operators develop passenger inflow control strategies independently, thus ignore the interactions among stations and lines in the actual operation. Subsequently, the single-fixed control intensity usually fails to satisfy dynamic temporal passenger demand, resulting in great stranded passengers. To address this problem, a coordinated and dynamic inflow control method is proposed to generate an optimal demand-driven control pattern in metro systems. First, a mixed integer programming model with the concept of the equivalent time interval is formulated to minimise the total number of stranded passengers on one line. Second, special consideration is paid to the transfer passengers with the aim of ensuring the safety of transfer stations. Finally, an actual passenger flow and train operation data in Beijing Batong line is conducted to test the performance of the approach. Compared with the non-coordinated and dynamic inflow control method, results show that the proposed model can balance the utilisation of transportation capacity and reduce the total number of stranded passengers by 20.6%. Sensitivity analysis results indicate that both transportation capacity and transfer capability are the main factors affecting the inflow control.

Deformation characteristics of fine-grained soil under cyclic loading with intermittence

Since there is an interval time between two trains traveling in the same direction on an automatically blocked line, the dynamic loading on the railway subgrade is composed of periodic vibration when the train passes and an intermittent stage after a train has passed. Take into account this characteristic, a series of continuous-stopping repeated load triaxial tests were conducted to study deformation characteristics such as plastic strain and elastic strain of fine-grained soil under intermittent loading. Compared to continuous loading, it is found that the intermittent stage has a significant effect on the deformation characteristics of subgrade. The excess pore water pressure accumulated during the loading stage dissipated during the intermittent stage. The development of plastic strain in subsequent loading stages slowed down significantly, and the axial strain of the sample rebounded in the intermittent stage, so cumulative plastic strain was reduced. The intermittent effect on reducing elastic strain was, however, limited. An increase in intermittent time can also improve the resistance of the sample to subsequent cyclic loading. An alternating continuous-stopping loading mode can better simulate intermittent loading of trains in actual train operation and produce more practical results, providing a theoretical basis and guidance for further understanding of deformation characteristics of railway subgrade.