Research On The Early Warning Method Of Passenger Flow Dispersion In Large Railway Integrated Passenger Transport Hub

The large-scale railway comprehensive passenger transport hub is the connection point of urban transportation and the transformation center of intra-city transportation.It occupies a pivotal position in the layout of the transportation system at the national strategic level and the layout of the integrated transportation system at the city level.With the large-scale growth of railway passenger flow in recent years,it has also brought new problems and challenges to large-scale railway comprehensive passenger transportation hubs,such as passenger flow retention during peak hours,mismatch of multi-modal passenger flow relief,etc.,and management personnel cannot grasp the relief dynamics in time,Leading to lagging control measures,poor travel quality of railway passengers and poor travel experience.Most of the existing researches focus on the handling of unconventional passenger flows in emergencies.The important function and ultimate goal of large-scale railway comprehensive passenger transport hubs is to realize the rapid collection of passenger flows all-weather,so as to improve the efficiency of the railway hub and passengers.Travel quality.The relaxation time in the process of railway passenger flow is one of the key indicators to quantitatively evaluate the capacity of the railway hub.The psychological relaxation time is an important lever to quantitatively measure the mental state and experience of passengers in the process of passenger flow of the railway hub.Based on the above background,this paper takes the railway passenger transport hub as the research object,uses traffic behavior and traffic psychology as the basic theories,combined with multi-source big data and field surveys,and conducts the following three aspects of research.1.Construction of a hub passenger flow operating characteristic system based on multi-source data.Through the hub station video monitoring,mobile phone Bluetooth signaling detection,Auto Navi Urban Traffic Brain operation platform,railway operation management and control platform data,the hub passenger flow operation characteristic system has been constructed,which includes railway gathering and decentralization of passenger flow,passenger flow speed-density-flow relationship,The characteristic parameters of the selection probability data of passenger flow arrival rate,transfer traffic arrival rate,transfer traffic service rate and passenger flow relief method selection.Indepth correlation analysis of the acquired data is carried out through statistical methods,and the correlation between various parameters is summarized,which provides a model prototype for real-time update of various operating parameters in the later stage.2.The construction of a time prediction model for passenger flow relief mentality that considers the psychological state and relief experience of passengers.The process of passenger flow relief is separated into two parts: the outbound travel time and the transfer waiting time.Based on the classic unwinding time prediction model,the outbound travel time of each transfer passenger is studied;based on the stochastic service theory,the transfer waiting time of each transfer passenger is predicted,and the real-time queue number,transfer waiting time,and transfer waiting time of each transfer traffic waiting point are output.Key indicators such as average waiting time.The sum of the two parts of the time is the real time of dissolution.The theory of time perception is introduced to analyze the factors influencing the psychological time of distraction in the process of passenger flow distraction,and a predictive model of passenger flow dismantling psychological time is constructed by taking each influencing factor as a variable.3.Construction of an early warning model for passenger flow relief based on the psychological time of passenger flow relief.The State Anxiety Questionnaire(S-AI)of psychometrics is used to quantitatively describe the anxiety state of passengers under different psychological relief time,and compare with the domestic anxiety state norms.If it exceeds,it is judged that the passenger has anxiety.Introduce the high-efficiency team matching parameters and the Losada line to determine the proportion of passengers who have anxious emotions under different psychological relief times,and match them with the Losada ratio,thereby constructing a "blue(psychological relief time 22min)with the psychological relief time as an indicator),yellow(psychological relief time 34min),red(psychological relief time 48min)" early warning threshold.Then,the cloud model is introduced,and the maximum psychological relief time of arrival passengers per shift is used as the evaluation index to obtain a three-level early warning model for the relief time of arrival passengers per shift,and reasonable countermeasures are proposed for different warning levels.Finally,taking the Shapingba Railway Hub in Chongqing as an example,data collection and real-life verification are carried out.The model error rate of the real deconstruction time of each deconstruction method is all within 10%,and the error rate of the passenger flow deconstruction psychological time prediction model is within 8%,which is comparable.A good response to the decommissioning state of the railway hub.