Yinzhen Li

The conventional sequential planning of train timetables and maintenance windows cannot fully capture their interactions, particularly on plateau railways where infrastructure maintenance requirements are more demanding. This study develops a coordinated optimization model that jointly determines train arrival and departure times and the timing and duration of segmented rectangular maintenance windows. The model simultaneously minimizes total train travel time and maximizes maintenance-window duration while considering train departure and arrival time windows, section running times, dwell times, train headways, maintenance-window timing requirements, and safety separation between train operations and maintenance activities. A linear weighted-sum method is used to scalarize the bi-objective model, and a Benders-decomposition-based solution method is developed by separating discrete operating-sequence decisions from continuous timing decisions. The method incorporates optimality, feasibility, and conflict cuts to iteratively coordinate the master problem and subproblem. A case study of a certain plateau railway in China, involving 22 passenger trains and 25 section-based maintenance windows, demonstrates the applicability of the proposed approach. Sensitivity analysis reveals a clear trade-off between train operating efficiency and maintenance provision. With a weighting coefficient of λ = 0.8, the algorithm obtains a representative coordinated solution with a total train travel time of 8488.37 min and a maintenance-window duration of 200.64 min, illustrating the trade-off between transport efficiency and maintenance requirements. The proposed framework provides a practical modeling and solution approach for coordinated train timetabling and maintenance-window planning on plateau railways.

The purpose of this paper is to optimize the accuracy of airport express passenger flow prediction so as to meet the need for the optimal allocation of traffic resources against the background of accelerated urbanization and the rapid development of airport express services. A fusion intelligence network model (FINM) is proposed, which integrates the advantages of convolutional neural networks, bidirectional long short-term memory networks, and gated recurrent units. Firstly, by using the powerful feature extraction ability of convolutional neural networks, local features and detail information are captured from the input data to improve the data representation ability. Secondly, bidirectional long short-term memory networks are used to process the sequence data, capture the global information and its context relationship, and enhance the model’s understanding of the dependence of time series data. Finally, gated recurrent units are introduced to simplify the computational complexity while maintaining high prediction accuracy and training efficiency. Based on the actual passenger flow data for Tianjin Metro Line 2 on a 30 min time scale, the proposed FINM is verified. The experimental results show that the model achieves an excellent performance, with 0.0160, 0.0947, 0.0160, 0.1255, 18.40, and 0.7788 in key indicators such as loss value (Loss Value), mean absolute error (MAE), mean squared error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R-Squared). Compared with the comparison algorithm, this model shows significant advantages in all indicators, which proves its effectiveness in dealing with complex time series data.