Research on Railway Passenger Flow Prediction Method Based on GA Improved BP Neural Network

This paper chooses passenger flow data of some stations in China from January 2015 to March 2016, and the time series prediction model of BP neural network for railway passenger flow is established. But because of its slow convergence speed and easily falling into local optimal solution of the problem, we propose to improve the time series model of BP neural network by genetic algorithm to predict railway passenger flow. Experimental results show that the improved method has higher prediction accuracy and better nonlinear fitting ability.

Railway Passenger Flow Forecasting by Integrating Passenger Flow Relationship and Spatiotemporal Similarity

Railway passenger flow forecasting can help to develop sensible railway schedules,make full use of railway resources,and meet the travel demand of passengers.The structure of passenger flow in railway networks and the spatiotemporal relationship of passenger flow among stations are two distinctive features of railway passenger flow.Most of the previous studies used only a single feature for prediction and lacked correlations,resulting in suboptimal performance.To address the above-mentioned problem,we proposed the railway passenger flow prediction model called Flow-Similarity Attention Graph Convolutional Network(F-SAGCN).First,we constructed the passenger flow relations graph(RG)based on the Origin-Destination(OD).Second,the Passenger Flow Fluctuation Similarity(PFFS)algorithm is used to measure the similarity of passenger flow between stations,which helps construct the spatiotemporal similarity graph(SG).Then,we determine the weights of the mutual influence of different stations at different times through an attention mechanism and extract spatiotemporal features through graph convolution on the RG and SG.Finally,we fused the spatiotemporal features and the original temporal features of stations for prediction.The comparison experiments on a railway bureau’s accurate railway passenger flow data show that the proposed F-SAGCN method improved the prediction accuracy and reduced the mean absolute percentage error(MAPE)of 46 stations to 7.93%.

Medium-term forecast of daily passenger volume of high speed railway based on DLP-WNNMedium-term forecast of dailypassenger volume of high speedrailway based on DLP-WNN

Purpose – This paper aims to propose a medium-term forecast model for the daily passenger volume of HighSpeed Railway (HSR) systems to predict the daily the Origin-Destination (OD) daily volume formultiple consecutivedays (e.g. 120 days).Design/methodology/approach – By analyzing the characteristics of the historical data on daily passengervolume of HSR systems, the date and holiday labels were designed with determined value ranges.In accordance to the autoregressive characteristics of the daily passenger volume of HSR, the Double LayerParallel Wavelet Neural Network (DLP-WNN) model suitable for the medium-term (about 120 d) forecast of thedaily passenger volume of HSR was established. The DLP-WNN model obtains the daily forecast result byweighed summation of the daily output values of the two subnets. Subnet 1 reflects the overall trend of dailypassenger volumes in the recent period, and subnet 2 the daily fluctuation of the daily passenger volume toensure the accuracy of medium-term forecast.Findings – According to the example application, in which the DLP-WNN modelwas used for the medium-termforecast of the daily passenger volumes for 120 days for typical O-D pairs at 4 different distances, the averageabsolute percentage error is 7%-12%, obviously lower than the results measured by the Back Propagation (BP)neural network, the ELM (extreme learning machine), the ELMAN neural network, the GRNN (generalizedregression neural network) and the VMD-GA-BP. The DLP-WNN model was verified to be suitable for themedium-term forecast of the daily passenger volume of HSR.Originality/value – This study proposed a Double Layer Parallel structure forecast model for medium-termdaily passenger volume (about 120 days) of HSR systems by using the date and holiday labels and WaveletNeural Network. The predict results are important input data for supporting the line planning, scheduling andother decisions in operation and management in HSR systems.

Installation position determination of wind speed sensors on steel pole along a high-speed railway

In order to consider the influence of steel pole on the measurement of wind speed sensors and determinate the installation position of wind speed sensors, the flow field around wind speed sensors was investigated. Based on the three-dimensional steady Reynolds-averaged Navier-Stokes equations and k-ε double equations turbulent model, the field flow around the wind speed sensor and the steel pole along a high-speed railway was simulated on an unstructured grid. The grid-independent validation was conducted and the accuracy of the present numerical simulation method was validated by experiments and simulations carried out by previous researchers. Results show that the steel pole has a significant influence on the measurement results of wind speed sensors. As the distance between two wind speed sensors is varied from 0.3 to 1.0 m, the impact angles are less than ±20°, it is proposed that the distance between two wind speed sensors is 0.8 m at least, and the interval between wind speed sensors and the steel pole is more than 1.0 m with the sensors located on the upstream side.

New-concept Design Innovation of Passenger Station Construction for Qinghe Railway Station of the Beijing-Zhangjiakou HSR

Qinghe Railway Station is the largest passenger station along the Beijing-Zhangjiakou HSR and will serve as the originating station of this line during the A 2022 Winter Olympics.It is also one of the eight major passenger stations in.Beijing.During the construction of this station,all units involved in the construction have made their effors to learn and understand the new concept of building up a“well-connected,filly-integrated,environment-friendly,passenger-oriented,economically-efficient,culturally-rich,inelligent and convenient”passenger station in the new era.Qinghe Railway Station of the Beijing-Zhangjiakou HSR was completed and opened to traffic by the end of 2019 through exploration of new-concept design innovation for passenger station construction in the new era,which was widely praised by the general public.The paper summarizes how the new design concept of passenger station construction is innovated and implemented during the construction of Qinghe Railway Station,thus providing a reference for the future construction of passenger stations.

A two-layer optimization model for high-speed railway line planning

Line planning is the first important strategic element in the railway operation planning process,which will directly affect the successive planning to determine the efficiency of the whole railway system.A two-layer optimization model is proposed within a simulation framework to deal with the high-speed railway (HSR) line planning problem.In the model,the top layer aims at achieving an optimal stop-schedule set with the service frequencies,and is formulated as a nonlinear program,solved by genetic algorithm.The objective of top layer is tominimize the total operation cost and unserved passenger volume.Given a specific stop-schedule,the bottom layer focuses on weighted passenger flow assignment,formulated as a mixed integer program with the objective of maximizing the served passenger volume andminimizing the total travel time for all passengers.The case study on Taiwan HSR shows that the proposed two-layer model is better than the existing techniques.In addition,this model is also illustrated with the Beijing-Shanghai HSR in China.The result shows that the two-layer optimization model can reduce computation complexity and that an optimal set of stop-schedules can always be generated with less calculation time.

Wind tunnel test on the effect of metal net fences on sand flux in a Gobi Desert, China

The Lanzhou-Xinjiang High-speed Railway runs through an expansive windy area in a Gobi Desert, and sand-blocking fences were built to protect the railway from destruction by wind-blown sand. However, the shielding effect of the sand-blocking fence is below the expectation. In this study, effects of metal net fences with porosities of 0.5 and 0.7 were tested in a wind tunnel to determine the effectiveness of the employed two kinds of fences in reducing wind velocity and restraining wind-blown sand. Specifically, the horizontal wind velocities and sediment flux densities above the gravel surface were measured under different free-stream wind velocities for the following conditions： no fence at all, single fence with a porosity of 0.5, single fence with a porosity of 0.7, double fences with a porosity of 0.5, and double fences with a porosity of 0.7. Experimental results showed that the horizontal wind velocity was more significantly decreased by the fence with a porosity of 0.5, especially for the double fences. The horizontal wind velocity decreased approximately 65% at a distance of 3.25 m（i.e., 13 H, where H denotes the fence height） downwind the double fences, and no reverse flow or vortex was observed on the leeward side. The sediment flux density decreased exponentially with height above the gravel surface downwind in all tested fences. The reduction percentage of total sediment flux density was higher for the fence with a porosity of 0.5 than for the fence with a porosity of 0.7, especially for the double fences. Furthermore, the decreasing percentage of total sediment flux density decreased with increasing free-stream wind velocity. The results suggest that compared with metal net fence with a porosity of 0.7, the metal net fence with a porosity of 0.5 is more effective for controlling wind-blown sand in the expansive windy area where the Lanzhou-Xinjiang High-speed Railway runs through.