Predicting short-term passenger flow accurately is of great significance for daily management and for a timely emergency response of rail transit networks. In this paper, we propose an attention-based Graph–Temporal Fused Neural Network (GTFNN) that can make online predictions of origin–destination (OD) flows in a large-scale urban transit network. In order to solve the key issue of the passenger hysteresis in online flow forecasting, the proposed GTFNN takes finished OD flow and a series of features, which are known or observable, as the input and performs multi-step prediction. The model is constructed from capturing both spatial and temporal characteristics. For learning spatial characteristics, a multi-layer graph neural network is proposed based on hidden relationships in the rail transit network. Then, we embedded the graph convolution into a Gated Recurrent Unit to learn spatial–temporal features. For learning temporal characteristics, a sequence-to-sequence structure embedded with the attention mechanism is proposed to enhance its ability to capture both local and global dependencies. Experiments based on real-world data collected from Chongqing’s rail transit system show that the metrics of GTFNN are better than other methods, e.g., the SMAPE (Symmetric Mean Absolute Percentage Error) score is about 14.16%, with a range from 5% to 20% higher compared to other methods.
China’s coal industry has long faced challenges due to imbalance between supply and demand divisions and the discrepancies between supply and demand prices. Research on optimizing coal transfer amid fluctuating coal prices is crucial for enhancing coal resource allocation, ensuring a balanced and stable supply of coal resources, and promoting the sustainable development of the coal industry. This paper focuses on optimizing coal transfer schemes within a comprehensive transportation system, considering fixed transportation routes and opening times of railroad transportation and waterway transportation, with road transportation serving as a supplementary network. A three-dimensional spatio-temporal network model is established to represent the spatial and temporal paths and transportation modes of coal logistics. The study uses the coal transportation network from Inner Mongolia and Shaanxi to East China as a case study, analyzing factors such as coal price fluctuation, transportation rates, and the ratio of self-produced to purchased coal at the production end via sensitivity analysis. The findings indicate that the proposed model can effectively guide transportation practices under the integrated production, transportation, and sales framework in the energy industry. Additionally, it shows that enterprises can achieve higher profits and maintain revenue and supply stability despite coal price fluctuations, aligning with the coal industry’s transformation and development in the current context.
1 January 2024 in Journal of Advanced Transportation
Accurately predicting origin‐destination (OD) passenger flows serves as the basis for implementing efficient plans, including line planning and timetabling. However, due to the complexity and variety of OD passenger flows types, general prediction models have difficulty in capturing the features of different OD passenger flows, which in turn leads to poor prediction performance. To address this issue, we propose an integrated framework that combines clustering and prediction methods. First, an unsupervised deep learning model is devised to automatically cluster OD flow types by capturing shape characteristics. Second, three types of features are created to enhance training efficiency, including static features, time‐dependent observed features, and time‐dependent known features. Based on the clustering of OD passenger flow, a weighted adaptive passenger flow prediction model is developed. The study employs a temporal fusion transformers model to enable multitype OD passenger flow prediction. In the numerical experiments, the model was applied to the urban rail transit in South China, and the model clustered 15,168 OD pairs into 4 types for prediction. The findings show that this approach enhanced the prediction accuracy by 2.0%–9.6% compared to the LSTM model and by 1.6%–4.3% compared to the Graph WaveNet. Moreover, the model can accurately assess the various features for diverse types of OD flows.
1 January 2025 in IET Intelligent Transport Systems
Scheduling plans catering to dynamic and complex passenger demands have drawn recent attention. Given dynamic demand, there is an urgent need to explore methods for extracting valid data from vast amounts of information and achieving flexible, robust parametric control of scheduling to boost transportation resource utilization efficiency. This paper proposes a deep learning technique to construct uncertainty sets using first‐ and second‐order moment information of passenger demand. Based on previous research under deterministic demands, a distributional robust optimization model for integrated line plan and timetable scheduling is established. Unlike other robust optimization models, the distributional robust one can better utilize the information in uncertain data. To handle the ensuing mixed integer semidefinite programming problem, a generalized benders decomposition algorithm post‐linearization is presented, which decomposes the model for iterative solving. Notably, the proposed model attains an average demand satisfaction rate 10.19% higher than the deterministic demand model, reduces train usage by 9, and lifts the average full load rate by 19.05% compared to the strongly robust model. It can flexibly select parameters for diverse demand scenarios and decision‐making objectives, offering theoretical support for planning under uncertain passenger demands.
Rail expresses play a vital role in intracity and intercity transportations. For accommodating multi-source passenger traffic with different travel demand, while optimizing the energy consumption, we propose a multi-cycle train timetable optimization model and a decomposition algorithm. A periodized spatial-temporal network that can support the integrated optimization of passenger service satisfaction and energy consumption considering multi-cycles is studied as the basis of the modeling. Based on this, an integrated optimization model taking the planning of the train spatial-temporal path, cycle length and active lines as variables is proposed. Then, for solving the issues caused by the complex relationships among the cycle length, line and train spatial-temporal path in large-scale cases, a hybrid heuristic Lagrangian decomposition method is investigated. Numerical experiments under different passenger flow demand scenarios are performed. The results show that the more fluctuating the passenger flow is, the more obvious the advantage of a multi-cycle timetable is. For the scenario with two passenger flow peaks, compared to a single-cycle timetable, the demand satisfaction ratio of the multi-cycle timetable is 4.44% higher and the train vacancy rate is 11.49% lower. A multi-cycle timetable also saves 3.24 h running time and 15,553.6 kwh energy consumption compared to a single-cycle timetable. Large-scale real cases show that this advantage still exists in practice.
Transportation scheduling and inventory coordination for coal maritime supply assurance under demand dynamics are studied in an integrated railway-port-shipping-plant supply chain. Within a maritime inventory routing setting, a discrete-time transportation-inventory model is formulated to jointly capture loading-port inventory evolution, plant safety-inventory boundary control, port operation constraints, and vessel state transitions in a state-space-time network. A rolling-horizon solution framework with state inheritance, staged commitment, and soft boundary-inventory control is developed, and the model is further strengthened by structured valid inequalities for time reachability, prefix-demand coverage, and fractional state-network paths. Computational results show that the rolling-horizon framework substantially improves tractability while maintaining good final-gap performance, and that the additional valid inequalities further enhance solution efficiency and convergence quality. The proposed approach provides effective decision support for large-scale coal maritime supply assurance by coordinating transportation timing and inventory protection in dynamic operating environments.