SHI, Jing (Beijing National Railway Research & Design Institute of Signal &), Wang, Jiye (School of Transportation & Logistics Southwest Jiaotong Universi), Cui, Junfeng (Beijing National Railway Research and Design Institute of Signal), Jia, Yunguang (Beijing National Railway Research and Design Institute of Signal), Yao, Wenhua (Beijing National Railway Research and Design Institute of Signal), Yu, Tianyao (School of Automation and Electrical Engineering, Lanzhou Jiaoton)

Multi-Objective Train Timetable Rescheduling Via Speed Optimization under Interruptions

Scheduled for presentation during the Regular Session "S33b-Intelligent Control for Next-Generation Railway Systems" (FR-EA-T33), Friday, November 21, 2025, 13:30−13:50, Southport 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Train operations are easily subject to interruptions, leading to complex train delay propagation on the railway network. To address the problem, a multi-objective optimization model is constructed to reschedule the train timetable under delay conditions through train speed curve optimization. The speeds of train cruising and braking points were addressed as decision variables, and train operation safety and passengers’ comfort were considered as constraints. A dynamic interval elastic adjustment strategy was proposed to simulate a virtual spring-damping system between trains. To solve the model, the non-dominated sorting genetic algorithm (NSGA-II) was designed to obtain the Pareto front and search for the optimal solution. The simulation results show that the number of affected/delayed trains and total train delays by the proposed model and algorithm have significantly decreased (by approximately 40%). The experimental results show that the optimization scheme achieves a synergistic improvement in safety, efficiency, and comfort by dynamically adjusting the tracking interval and speed curve, verifying the applicability of the model in complex delay scenarios.