Inbound Passenger Flow Prediction of Spatio-temporal Graph Convolutional Neural Network for Urban Rail Transit Based on Spatio-temporal Correlation
Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 9
Abstract
Objective Accurate short term passenger flow prediction is of great significance to improve the operation and management efficiency of the ultra-large scale of urban rail transit network. However, the current research on deep exploration of the spatio-temporal correlations is still insufficient. Therefore, according to the spatio-temporal law of short term passenger flow, a STGCN (spatio-temporal graph convolutional neural network) model based on spatio-temporal correlation characteristics of passenger flow is proposed. Method Firstly, the spatial correlation of ultra-large scale urban rail transit network is captured by ChebyNet （Chebyshev graph convolutional network）, and the temporal correlation of the passenger flow under multi-temporal correlation characteristics is explored with the help of GRU (gated recurrent unit). Secondly, the correlation of the historical passenger flow data of the station to be predicted and that of OD (origin-destination) passenger flow data are analyzed to extract the spatio-temporal correlation deeply. Finally, a STGCN model is established in combination with the spatio-temporal correlation characteristics of the passenger flow. Result & Conclusion Taking Jiangsu Road Station of Shanghai Metro Line as an example, a short-term inbound passenger flow prediction is conducted. The result shows that the prediction accuracy with spatio-temporal correlation characteristic parameters is 16% higher than that without the parameters, indicating a better prediction effect.
Authors and Affiliations
Runqi WANG, Yanxi HAO, Hua HU, Yong FANG, Zhigang LIU
Keywords
Related Articles
- EP ID EP744324
- DOI 10.16037/j.1007-869x.2024.09.016
- Views 69
- Downloads 0
Research on Energy Management Method of Fuel Cell Hybrid Power System Based on Improved Equivalent Hydrogen Consumption
Objective Equivalent hydrogen consumption, as a method for optimizing fuel economy, performs poorly in following the state of charge of energy storage systems. Therefore, it is necessary to improve it to achieve dynamic...
Fatigue Analysis of Urban Rail Transit Vehicles Bogies Based on Frequency Domain Features
Objective As a key structure for carrying the vehicle, the abnormal vibration of bogies has a direct impact on the service performance of rail transit trains. Therefore, it is necessary to conduct in-depth research on th...
Study on the Segment Damage Mechanism of Curved Shield Tunnels during Construction Stage
Objective Damage to shield tunnel segments will cause water seepage in the tunnel, affecting the structural bearing capacity and endanger the operational safety. Therefore, it is necessary to study the mechanism of segme...
Calculation Method of Crowd Density in the Local Area of Subway Station Platform
［Objective］ The calculation method of crowd density is the key to analyzing the risk of crowd gathering on subway station platforms. Usually, the internal density distribution is uneven when it is crowded, and there ar...
Influence of Wheel Flat Scars on High-speed Train Transmission Geer Dynamic Characteristics
Objective Wheel flat scars can exacerbate the vibration of train transmission gears. Therefore, it is necessary to study the impact of wheel flat scars on the vibrational dynamic characteristics of high-speed train trans...