A Global Transport Capacity Risk Prediction Method for Rail Transit Based on Gaussian Bayesian Network

TL;DR

This paper introduces an explainable, Gaussian Bayesian network-based method for predicting transport capacity risks in rail transit systems, addressing passenger demand mismatches with simulation-validated results.

Contribution

It develops a novel Bayesian network structure based on rail network topology and applies MLE for parameter learning, enhancing risk prediction accuracy.

Findings

Effective risk prediction demonstrated through simulation examples.

The method accurately captures the relationship between passenger flow and transport capacity.

Provides an explainable model for rail transit capacity risk assessment.

Abstract

Aiming at the prediction problem of transport capacity risk caused by the mismatch between the carrying capacity of rail transit network and passenger flow demand, this paper proposes an explainable prediction method of rail transit network transport capacity risk based on linear Gaussian Bayesian network. This method obtains the training data of the prediction model based on the simulation model of the rail transit system with a three-layer structure including rail transit network, train flow and passenger flow. A Bayesian network structure construction method based on the topology of the rail transit network is proposed, and the MLE (Maximum Likelihood Estimation) method is used to realize the parameter learning of the Bayesian network. Finally, the effectiveness of the proposed method is verified by simulation examples.