To lighten the workload of train drivers and enhance railway transportation safety, a novel and intelligent method for railway turnout identification is investigated based on semantic segmentation. More specifically, a railway turnout scene perception (RTSP) dataset is constructed and annotated manually in this paper, wherein the innovative concept of side rails is introduced as part of the labeling process. After that, based on the work of Deeplabv3+, combined with a lightweight design and an attention mechanism, a railway turnout identification network (RTINet) is proposed. Firstly, in consideration of the need for rapid response in the deployment of the identification model on high-speed trains, this paper selects the MobileNetV2 network, renowned for its suitability for lightweight deployment, as the backbone of the RTINet model. Secondly, to reduce the computational load of the model while ensuring accuracy, depth-separable convolutions are employed to replace the standard convolutions within the network architecture. Thirdly, the bottleneck attention module (BAM) is integrated into the model to enhance position and feature information perception, bolster the robustness and quality of the segmentation masks generated, and ensure that the outcomes are characterized by precision and reliability. Finally, to address the issue of foreground and background imbalance in turnout recognition, the Dice loss function is incorporated into the network training procedure. Both the quantitative and qualitative experimental results demonstrate that the proposed method is feasible for railway turnout identification, and it outperformed the compared baseline models. In particular, the RTINet was able to achieve a remarkable mIoU of 85.94%, coupled with an inference speed of 78 fps on the customized dataset. Furthermore, the effectiveness of each optimized component of the proposed RTINet is verified by an additional ablation study.

This study aims to elucidate the implications of carbon peak and carbon neutrality targets on corridor logistics, with a focus on the burgeoning high-speed rail express sector. Acknowledging carbon emissions taxation as an integral component of transportation costs, it examines the competitive dynamics among four cargo transport modes: high-speed rail (HSR), conventional rail, aviation, and road transport. Within a strategic game framework, carriers are analyzed based on freight rates, speed, safety, reliability, and convenience to assess their utility. A dynamic game model and a solution approach are developed, aiming to optimize freight-related variables, maximize carriers’ generalized profits, and enhance shippers’ utility. Empirical validation is provided through case studies in Xi’an and Lanzhou, northwest China, affirming the model’s efficacy. The findings reveal the strong competitive edge of the high-speed rail express in the corridor, offering valuable insights for carrier pricing strategies, emission tax rate setting, and macro-policy adjustments in the transport sector.

Against the backdrop of China’s “public-to-railway” freight policy that has led to railway yard congestion and imbalanced modal capacity utilization, this study develops a Dual-Channel Cargo-Transportation Service (DCTS) system model using queuing theory to optimize freight flow allocation and pricing strategies. Integrating the behavioral decisions of governments, carriers, and cargo owners, the research employs M/M/1 queuing models and the Logit choice framework to analyze the dynamic equilibrium between goods waiting times and carrier profits, exploring objectives of minimizing system-average waiting time and maximizing carrier profits. Key findings show that regulating highway pricing can effectively divert freight flows to reduce railway congestion and improve system efficiency, with optimal pricing intervals for highways identified based on service capacity to balance congestion relief and profitability. The model quantifies the trade-off between transportation costs and waiting times to guide cargo owners’ mode choices, and numerical simulations validate that strategic highway price adjustments alleviate bottlenecks and enhance modal synergy. This paper provides a theoretical basis for the government to formulate freight-transportation policies and optimize freight flow allocation. At the same time, it also provides a practical, theoretical basis and methodological reference for carrier pricing decisions, as well as for solving the problem of freight flow congestion and optimizing the pricing of transportation services.

As an important part of modern comprehensive transportation system, high-speed railway (HSR), whether it is a transregional trunk line or an intercity line, always shapes the industrial layout and changes the living environment at different levels. Based on the analysis of the railway network topology and organization process of passenger train, this paper clarifies the connotation of passenger train operation scheme of HSR considering network survivability, and further explains the connotation of railway network system and its relationship with passenger train operation scheme. In this paper, a comprehensive quantitative index of the importance of key nodes and key edges is established, and an evaluation index of the survivability of railway service network based on the operating mileage of passenger trains is constructed, which is applied to the real local HSR network in China. With the aim of improving the survivability of HSR system, an alternative operation route of passenger trains between some OD stations is given according to the specific railway interruption situation.

Disruptions to high-speed rail (HSR) can cause passenger-service losses across cities, while air alternatives depend on transfers and residual capacity. This study evaluates functional robustness in an HSR-centered rail–air network and selects city-level hardening investments under uncertain disruption probabilities. A time-expanded multiplex represents scheduled services, shared enabling components, correlated damage, restoration, and capacity-constrained passenger reassignment. A two-stage Wasserstein distributionally robust optimization (DRO) model minimizes worst-case mean–conditional value-at-risk (CVaR) loss. A decomposition framework is presented for continuous restoration. A reproducible semi-synthetic benchmark with 40 cities and 21 scenarios uses screened exhaustive search and monotone recourse closure. With a four-city budget, nominal planning protects Beijing, Hangzhou, Hefei, and Nanjing, whereas DRO protects Beijing, Shanghai, Guangzhou, and Nanjing. Worst-case mean–CVaR robustness increases from 83.86% to 89.37%, while nominal mean robustness decreases from 96.07% to 95.02%. At each portfolio’s joint worst-case mean–CVaR distribution, 90% CVaR robustness increases from 69.71% to 85.13%. These controlled results illustrate how probability ambiguity changes hardening priorities and the trade-off between nominal performance and adverse-distribution risk. Operational application requires observed timetables, demand, capacities, recovery resources, and hazard frequencies.