Development Of Urban Rail Transit Research Articles

Passenger Flow Prediction of Urban Rail Transit Based on Deep Learning Methods

The rapid development of urban rail transit brings high efficiency and convenience. At the same time, the increasing passenger flow also remarkably increases the risk of emergencies such as passenger stampedes. The accurate and real-time prediction of dynamic passenger flow is of great significance to the daily operation safety management, emergency prevention, and dispatch of urban rail transit systems. Two deep learning neural networks, a long short-term memory neural network (LSTM NN) and a convolutional neural network (CNN), were used to predict an urban rail transit passenger flow time series and spatiotemporal series, respectively. The experiments were carried out through the passenger flow of Beijing metro stations and lines, and the prediction results of the deep learning methods were compared with several traditional linear models including autoregressive integrated moving average (ARIMA), seasonal autoregressive integrated moving average (SARIMA), and space–time autoregressive integrated moving average (STARIMA). It was shown that the LSTM NN and CNN could better capture the time or spatiotemporal features of the urban rail transit passenger flow and obtain accurate results for the long-term and short-term prediction of passenger flow. The deep learning methods also have strong data adaptability and robustness, and they are more ideal for predicting the passenger flow of stations during peaks and the passenger flow of lines during holidays.

Vibration characteristics of damping pad floating slab on the long-span steel truss cable-stayed bridge in urban rail transit

With the development of urban rail transit, long-span steel truss cable-stayed bridges have become increasingly favored. Therefore, train-induced bridge-borne vibration and noise are occurring more often. The damping pad floating slab (DPFS) has been widely used as an effective vibration damping track structure; however, there is a lack of research on the vibration mechanism and effects of the DPFS for long-span steel truss cable-stayed bridges. This study focuses on the steel truss cable-stayed bridge in urban rail transit. First, the theoretical model of the train-track-bridge coupling interaction is established in the frequency-domain (the track structure is DPFS, and the interaction of multiple wheels is considered). Using this model, the wheel–rail dynamic force, force transmission rate of the track, and the force transmitted to the bridge are calculated. Then, the vibration prediction model of the long-span steel truss cable-stayed bridge is established using the plate-beam finite element (FE) method and statistical energy method. The force transmitted to the bridge is applied to the vibration prediction model to obtain the vibration transmission characteristics of the typical plate of the bridge. The prediction model is verified by comparing the obtained results with the field test of a long-span steel truss cable-stayed bridge, and the damping mechanism of DPFS track is discussed. Finally, the force transmitted to the bridge is calculated based on the embedded-sleeper (ES) track structure (the ES has no vibration damping facilities). The values of the overall vibration level are calculated from the prediction models using ES and DPFS, and the vibration reduction effect of DPFS is studied by comparison with the ES.

Simulation Study on Emergency Evacuation of Metro Stations in Fire Degradation Mode

With the rapid development of urban rail transit, the safety hazards of subway stations are increasing, and the safe evacuation of fires inside the station has become the focus of research. This paper analyzes the situation of platform fire and station hall fire emergency treatment, establishes an evaluation system on the analysis of passenger evacuation bottleneck factors, and proposes a risk evaluation method. Taking Wenze Road Station of Hangzhou Metro as an example, combined with Anylogic simulation to evaluate and analyze different situations, the overall risk level of Wenze Road Station fire is higher, and the evaluation results are consistent with the actual situation. According to the results, corresponding improvement measures are proposed to provide reference for station emergency evacuation.

Resilience Assessment and Optimization for Urban Rail Transit Networks: A Case Study of Beijing Subway Network

With the rapid development of urban rail transit, huge subway systems have been built, which is the best choice for people due to the efficiency, safety, and punctuality. Therefore, the ability of subway systems to resist failures especially interruptions has attracted the attention of operators. In the paper, based on the graph theory, a resilience assessment method is proposed to quantitatively measure the performance and recovery rapidity within unifying metrics and models. We represent the subway network with an undirected graph where the subway stations are described using the nodes whereas tracks are demonstrated with the edges. The performance evaluation of a subway network is implemented based on the assessment of passenger flow and topological structure of the network, where weighted degrees and the weighted sum of the reasonable passageway to the other nodes are considered. The resilience of a subway network can be associated to the network performance loss triangle over the relevant timeline from the occurrence of a random or intentional disruption to full recovery. The Beijing Subway is taken as the example to perform the proposed approach which is verified through the numerical results in the paper. Following the resilience evaluation, a structure optimization model with a computational algorithm is proposed. Based on the genetic algorithm, we achieved the solution results of the simplified network of the Beijing Subway. Several interesting conclusions are drawn from the results.

Subway Passenger Flow Forecasting With Multi-Station and External Factors

With the rapid development of urban rail transit, more and more people choose to travel by subway. Therefore, accurate passenger flow forecasting is of great significance for passengers and municipal construction and contributes to smart city services. In this paper, we propose a multi-type attention-based network to forecast the subway passenger flow with multi-station and external factors. The proposed network has different types of attention mechanisms to adaptively extract relevant features, including multi-station, external factors, and historical data. In addition, the hierarchical attention mechanism is used to model the hierarchical relationship between subway lines and stations. In addition, the embedding method is applied to better combine the different kinds of data. The experiments on real subway passenger flow data in a city in China demonstrate that our method outperforms five baseline methods. Moreover, our method can visualize the impact of different stations and other factors on traffic, which plays an important role in passenger travel and subway dispatch.

3DCNN-Based Real-Time Driver Fatigue Behavior Detection in Urban Rail Transit

With the rapid development of urban rail transit, traffic safety has become the focus of attention and people are paying increasing attention to the prevention of fatigue driving. “Gesture and oral instructions of urban rail traffic drivers” is operational actions of drivers written in the Chinese metro operation specification. It is a method to prevent drivers from fatigue driving and ensure safety. However, there is a lack of scientific detection methods. We combine the standard traffic operational actions with fatigue action to construct a fatigue detection system that is suitable for the urban rail transit industry. The system includes a dynamic tracking model for the large-scale operation of rail transit drivers and a dual-input action discrimination model based on a three-dimensional convolutional neural network (3DCNN). The model sets the skipping frame and continuous frame as two inputs of the model, and extracts five channels of information from the two inputs. Dual-input multi-channel information enables the model to learn not only the spatial and temporal information of the entire action, but also the subtle changes of the action. First, we trained and validated the dual-input model based on a 3DCNN using the open dataset KTH, which contains several variations. Then, the model trained on KTH was migrated to our data using the transfer learning method, which saved training time and achieves an accuracy of 98.41%. This transfer learning scheme can also be applied when new categories are encountered in practice. Finally, we discussed and envisaged the future optimization of the system.

Cluster-Based LSTM Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit

Short-term passenger flow forecasting is an essential component for the operation of urban rail transit (URT). Therefore, it is necessary to obtain a higher prediction precision with the development of URT. As artificial intelligence becomes increasingly prevalent, many prediction methods including the long short-term memory network (LSTM) in the deep learning field have been applied in road transportation systems, which can give critical insights for URT. First, we propose a novel two-step K-Means clustering model to capture not only the passenger flow variation trends but also the ridership volume characteristics. Then, a predictability assessment model is developed to recommend a reasonable time granularity interval to aggregate passenger flows. Based on the clustering results and the recommended time granularity interval, the LSTM model, which is called CB-LSTM model, is proposed to conduct short-term passenger flow forecasting. Results show that the prediction based on subway station clusters can not only avoid the complication of developing numerous models for each of the hundreds of stations, but also improve the prediction performance, which make it possible to predict short-term passenger flow on a network scale using limited dataset. The results provide critical insights for subway operators and transportation policymakers.

Research on Quantitative Demand of Underground Space Development for Urban Rail Transit Station Areas: A Case Study of Metro Line 1 in Xuzhou, China

Under the background of the rapid development of urban rail transit in China, the development demand of urban underground space has also greatly increased especially in the rail transit station areas. In this paper, taking the high-speed railway station area of Xuzhou Metro Line 1 as an example, the underground space development demand evaluation is conducted by considering the principle of urban underground space stock planning, the local underground space development conditions, as well as the special planning of the local urban constructions. Using the Analytic Hierarchy Process (AHP), a specific weight indicator scale is employed after the rationality of different weight indicator scales being compared. And then the weight indicator of different function types, i.e., commercial, parking, road, etc., are calculated and laterly utilized to forecast the recent development demand of underground space in the station area. Moreover, the steps to forecast the underground space development demand in rail transit station area are proposed, which can provide a reference for the forecasting of underground space development demand in the urban rail transit station areas.

Impact of a New Metro Line: Analysis of Metro Passenger Flow and Travel Time Based on Smart Card Data

Over the past few decades, massive volumes of smart card data from metro systems have been used to investigate passengers’ mobility patterns and assess the performance of metro network. With the rapid development of urban rail transit in densely populated areas, new metro lines are constantly designed and operated in recent years. The appearance of new metro lines may significantly affect passenger flow and travel time in the metro network. In this study, smart card data of metro system from Nanjing, China, are used to study the changes of metro passenger flow and travel time due to the operation of a new metro line (i.e., Line 4, opened on 18 January 2017). The impact of the new metro line on passenger flow distribution and travel time in the metro network is first analysed. As commuting is one of the major purposes of metro trips, the impact of the new metro line on commuters’ trips is then explicitly investigated. The results show that the new metro line influences passenger flow, travel time, and travel time reliability in the metro network and has different impacts on different categories of commuters.

Research of Urban Rail Transit Vehicle Aluminum Alloy Bolster FSW Welding Technology Based on Thermal-Mechanical Coupling

With the rapid development of urban rail transit and the increasing level of research and development, aluminum alloy materials feature excellent physical and mechanical properties, and thus an urban rail transit vehicle adopts aluminum alloy materials. Friction Stir Welding (FSW) technology is adopted in the production process of a bolster in this article and research of stress strain of friction stir welding parts plays an important role for engineering application of friction stir welding technology.

An Energy Efficient Train Dispatch and Control Integrated Method in Urban Rail Transit

With the rapid development of urban rail transit, the energy consumption of trains is increasing dramatically. The shortage of electrical energy is becoming more and more serious. In this paper, a novel method is proposed to better use regenerative braking energy for energy saving. A ‘time slot and energy grid’ model is set up to analyze the utilization of regenerative energy among trains. Based on this model, an energy efficient strategy that integrates train dispatch with train control is designed. The running time of trains in sections, the dwell time of trains at stations and the headway can be adjusted to find the global optimal solution for energy saving. The operational data of Beijing Changping subway line and Beijing Yizhuang subway line are used in simulation to illustrate the effectiveness of the proposed method in different scenarios. Simulation results show that our approach can significantly improve the utilization of regenerative braking energy and minimize the energy consumption in different scenarios when compared with the existing method.

Integrated optimization method of operational subsidy with fare for urban rail transit

For the sustainable development of urban rail transit, an operational subsidy is a way to increase operators’ profits and can balance profits among government, operators, and passengers. A method of efficiency-oriented subsidy optimization is proposed. With the aim of maximizing the efficiency of the subsidy, that is, minimizing the average subsidy of passengers, the optimization model is constructed considering elastic demand and congestion, with fares and train operating headway and the passenger demand as the decision variables. A solution algorithm is designed to solve the model, including two sub-algorithms for calculating the headway and passenger volume in the main iteration. Taking metro line 2 in Changsha, China, as an example, the optimization result is analysed and compared with that of the reality. The sensitivity analysis of the proposed model and algorithm is also examined.

GROUND SUBSIDENCE ALONG SHANGHAI METRO LINE 6 BY PS-InSAR METHOD

Abstract. With the rapid development of urban economy, convenient, safe, and efficient urban rail transit has become the preferred method for people to travel. In order to ensure the safety and sustainable development of urban rail transit, the PS-InSAR technology with millimeter deformation measurement accuracy has been widely applied to monitor the deformation of urban rail transit. In this paper, 32 scenes of COSMO-SkyMed descending images and 23 scenes of Envisat ASAR images covering the Shanghai Metro Line 6 acquired from 2008 to 2010 are used to estimate the average deformation rate along line-of-sight (LOS) direction by PS-InSAR method. The experimental results show that there are two main subsidence areas along the Shanghai Metro Line 6, which are located between Wuzhou Avenue Station to Wulian Road Station and West Gaoke Road Station to Gaoqing Road Station. Between Wuzhou Avenue Station and Wulian Road Station, the maximum displacement rate in the vertical direction of COSMO-SkyMed images is −9.92 mm/year, and the maximum displacement rate in the vertical direction of Envisat ASAR images is −8.53 mm/year. From the West Gaoke Road Station to the Gaoqing Road Station, the maximum displacement rate in the vertical direction of COSMO-SkyMed images is −15.53 mm/year, and the maximum displacement rate in the vertical direction of Envisat ASAR images is −17.9 mm/year. The results show that the ground deformation rates obtained by two SAR platforms with different wavelengths, different sensors and different incident angles have good consistence with each other, and also that of spirit leveling.

A synergistic energy-efficient planning approach for urban rail transit operations

Large-scale development of urban rail transit has attracted attention owing to its sizable energy consumption. Energy-efficient planning can enhance the distribution and utilization of limited energy resources. This study proposes a two-stage urban rail transit operation planning approach comprising running time allocation and regenerative energy utilization to save energy consumption. The proposed models and algorithms holistically deal with inter-station running time synergy which utilizes surplus running time to achieve minimum energy consumption. They also implement the hauling and braking synergy of multiple trains in multiple trips, with adjustments to departure intervals and dwelling times, to maximize the regenerative energy real-time utilization rate. The algorithms utilize chromosomes in genetic algorithm to represent possible operation stage combinations, conduct feasible direction iterations to facilitate surplus-time effective allocations, and maximize the derived overlap time for operation synergy of trains under the precondition of energy-efficient train movements between stations. A case study of the metro line demonstrates that considerable energy saving is achievable through the proposed planning approach.

Design of a Simulation Software to Optimize the Train Driving Strategy for Urban Rail Transit

The surge of the operational energy consumption has become a major challenge for the sustainable development with the rapid development of urban rail transit. Traction energy used to provide kinetic energy for the train during operation is about 50% in the total energy consumption of the urban rail transit, so the energy saving potential is considerable. Traction energy between train stations is determined by the driving strategy of the train, therefore, studying energy-efficient train driving strategy to reduce traction energy consumption has a great significance to achieve an environmentally friendly transport system. This paper designs a simulation software of energy-efficient train driving strategy based on the numerical algorithm to optimize energy-efficient train driving strategy with energy allocation. The simulation software can calculate energy-efficient train driving strategy according to any input line data, vehicle condition, and running time. The performance of simulation software is verified through the simulation of the actual data of Yizhuang line in Beijing.

Urban rail transit PPPs: Lessons from East Asian cities

Private sector participation in urban rail transit has proliferated in the past two decades. The large metropolises of East Asia have had decades of experience with private sector participation in the provision of heavy metro services. The design of these public–private partnerships (PPP) are varied. The diverse experiences of Tokyo, Hong Kong, Singapore and Beijing contain valuable lessons for other cities. Using a case study approach, this paper discusses three features of urban rail transit developments in the context of East Asian cities, viz., farebox recovery, land value capture mechanisms, and vertical structure of the industry. Super vertical integration between rail transit and real estate development as land value capture strategy to finance urban rail transit has proven to be successful in Japanese cities and Hong Kong. Singapore’s experience illustrates that vertically unbundled PPPs could cut off avenues for cross-subsidisation, reduce information flows as well as economies of scale and scope, introduce principal agent problems, and result in underinvestment in capital stock and maintenance. We conclude that (i) a combination of high farebox recovery ratios and successful land value capture contributed significantly to the development of urban rail transit in East Asia cities; (ii) given the complexities and high costs of heavy metros, the optimal structure is a vertically integrated public-owned and driven system, with the public sector entering into selective partnerships with the private sector where risk sharing is clearly defined and allocated.

Research on the Training of Computer Application Ability of Rail Transit Operators

With the rapid development of urban rail transit, it is the cultivation of operational personnel of rail transit with information management technology that has become the central issue. Although university is the major base to cultivate operational management personnel, there are many problems in the process of their cultivation since the professional direction is set for not long enough over there. In response to the lack of computer application ability among operational personnel of rail transit, the planning method of curriculum setting based on the engineering certification training standards is proposed to optimize the personnel training in university. Through the construction of matrix among rail transit professional (rail transit operation management) graduation requirements, required knowledge, ability and quality, and their realization way, the reason why students are not good at computer operation is analyzed before the corresponding countermeasure is formulated. The personnel training program is revised by re-setting the curriculum and adjusting the syllabus of the relevant courses. It is worth mentioning that the desired teaching effect is achieved after a year of operation.

Development of a Vibration Attenuation Track at Low Frequencies for Urban Rail Transit

AbstractRailway‐induced vibrations at low frequencies have become an important environmental issue with the rapid development of urban rail transit. In this study, a new vibration attenuation track (VAT) capable of passively mitigating vibrations at low frequencies is developed based on an integrated theoretical and experimental study. The full‐scale VAT is built which incorporates a floating slab track (FST) and the attached dynamic vibration absorbers (DVAs) with key parameters determined by the fixed‐point theory and modal analysis technique. The vibration attenuation performance of the VAT is investigated under train dynamic loads by establishing a three‐dimensional coupled dynamic model of a metro vehicle‐VAT‐subgrade system, and is further elucidated and validated by carrying out full‐scale dynamic tests under different harmonic loadings. Computational and experimental results both show that vibrations of the track are effectively absorbed by the attached DVAs leading to a significant reduction of the subgrade vibrations at the low frequency of 9–16 Hz.

Research on Dynamic Characteristics of Mechanical Fast Loading Trolley Bridge in the Urban Rail Construction

With the rapid development of urban rail transit, more and more rail projects such as light railway and subway have been constructed in recent years. Rail constructions often locate in the main roads and always occupy a part of road, so the traffic capacity of the original road declines drastically and traffic jams occur. For the car playing a remarkable role in the traffic jams, this paper puts forward two types of structure, steel trussed girder-bridge and steel trussed cable-stayed bridge, as the car overpass, which is a special path only for cars. Presented and analyzed the model of the structures by the finite element program of ANSYS, the results of model analysis show that the strength and safety of the two structures can both meet the relevant specifications. Making further efforts on comparison of mechanics and construction features, the steel trussed cable-stayed bridge has been presented, for its advantages of quickly assembled with standard unit of steel truss cable-stayed, light weighted, self-balanced, rapid construction, and less damage to the road surface

基坑开挖对地铁隧道及高架基桩的影响分析

随着城市轨道交通的发展，使得大量基坑工程与地铁结构相邻，由此引起的环境岩土问题日益突出，地铁结构对变形控制要求极其严格，为此，需采取有效措施使基坑施工对地铁结构的影响减小。论文针对广州南沙某邻近地铁四号线由高架转入地下隧道过渡段的基坑设计及施工，应用有限元方法，研究了基坑施工对既有地铁结构的影响，其分析结果可为优化设计和施工提供有益参考，为以后类似的工程实践提供积累经验。 With the development of urban rail transit, which makes lots of foundation pit engineering and metro adjacent structures, the resulting environmental and geotechnical problems have become increasingly prominent, and subway station structure of deformation is extremely strict. Thus, it is necessary to take effective measures to make the foundation pit construction reduce the influence of metro structure. This research in this paper, by means of the field monitoring of a foundation pit construction near changeover portion from elevated structure to underground tunnel of Guangzhou Metro Line 4, using finite element analysis method, researched the foundation pit construction on the influence of metro structure. The result provides valuable reference for design and construction. It is helpful to other similar projects.