Modern Transportation and Metallurgical Materials

From localized intelligence to systemic intelligence: strategy and governance architecture for building a large‑scale AI traffic model system for China' s expressways

At present， generative artificial intelligence （AI） represented by foundation models is driving a profound transformation in transportation cognition and governance paradigms. As the world's largest large-scale and complex transportation system， China's expressway network can no longer be effectively managed through traditional approaches that rely on localized perception and decentralized decision-making. Meanwhile， the development of transportation foundation models across different regions has shown a fragmented pattern in the absence of a unified top-level framework， posing the risk of creating new “intelligent islands.” This paper argues that China's transportation intelligence development urgently requires a paradigm shift from local intelligence to system intelligence. Based on this perspective， the study systematically elaborates on the strategic urgency， top-level architecture， and implementation pathways for building a nationally unified and coordinated AI foundation model system for transportation. In terms of system design， an integrated closed-loop paradigm of perception –cognition-decision-making-execution is proposed as the core framework， supported by a two-level organizational structure of national coordination and provincial implementation， and a layered capability ecosystem characterized by foundation models for cognition and lightweight models for execution. In terms of practical implementation， the paper further proposes three key pathways， that is， establishing institutional foundations through standards-first governance， driving value realization through scenariooriented applications， and fostering innovation through collaborative ecosystem development. This study aims to provide theoretical guidance for the modernization of China's transportation governance capacity and offer policy references for the implementation of the national strategy of building a transportation powerhouse.

Research on reconstruction of the comprehensive traffic management system in urban villages and key technologies for traffic improvement

Adopting a classification-and-hierarchy-based analytical approach， this paper systematically summarizes 16 major categories and 33 subcategories of key influencing factors across five dimensionstraffic networks， traffic nodes， traffic venues， traffic services， and traffic safety. It synthesizes a mature and replicable set of systematic analytical strategies and methods for comprehensive traffic management in urban villages， and distills “micro-design， micro-innovation， and micro-renovation”measures that can be promoted under conditions of constrained space and tight land use. Taking Nanzhuang New Village in Guangming District as a case study， this paper formulates a detailed comprehensive traffic planning and design scheme aligned with the theoretical framework. After implementation， the urban village's appearance and traffic operation environment are significantly improved. This paper can serve as both a theoretical and practical reference for other cities seeking to systematically carry out comprehensive traffic management in urban villages.

Voiceprint recognition method for security early warning monitoring of rail transit station based on ECAPA‑TDNN model

This paper proposes a voiceprint recognition method for rail transit stations based on the ECAPA⁃TDNN model， and applied this method to security early warning monitoring under complex background noise. To address the limitations of traditional video surveillance in sound event detection，this paper constructs a domain⁃specific dataset comprising 4384 audio samples， including screams， explosion sounds， and environmental noises. An optimization strategy that integrates the Squeeze⁃and⁃Excitation （SE） module for channel attention mechanism with Attentive Statistical Pooling （ASP） is proposed， significantly enhancing the model's robustness in noisy environments. Experiments demonstrate that the module achieves an accuracy of 0.8742 on the test set， with an explosion sound recognition recall rate exceeding 96.17%， validating its practical value in rail transit scenarios.

Research on the long‑term service performance maintenance and risk control system for urban underground rail transit facilities

Focusing on the long-term service performance and risk control of subway tunnels， this study investigates influencing factors such as train-induced vibrations， foundation pit excavation， and dewatering associated with external operations. Based on mechanistic research， deformation prediction methods for tunnels under various influencing factors are proposed. Subsequently， a classification standard for tunnel structural safety states is established. Through the analysis of the transverse and longitudinal mechanical performance of shield tunnels， quantitative grading indicators for curvature radius and cross-sectional convergence are defined. By comprehensively considering total deformation and residual deformation margins， a dual-control indicator system integrating “additional deformation” and “cumulative deformation” is introduced. Furthermore， a collaborative control system featuring “active protection + dynamic restoration” is developed， centered on structural deformation monitoring during operational phases. This establishes a structural safety protection mechanism that achieves a dynamic equilibrium between external operation process control and internaltunnel reinforcement. Regarding internal defects， a hierarchical treatment methodology is established， detailing specific remediation pathways.

Analysis on mechanical behavior and influencing factors of locked double‑wall steel cofferdam

To meet the construction requirements of the foundation works for Hailong Bridge on the Guangzhou –Zhuhai Expressway reconstruction and expansion project， a locked double-wall steel cofferdam is proposed. To investigate the correlation between the mechanical behavior of the locked double-wall steel cofferdam and four structural parameters， namely the wall plate thickness， internal steel pipe thickness， waling position and base concrete thickness， a cofferdam numerical model is established using the finite element software Abaqus to analyze the variation trends of its stress and deformation. The analytical results indicate that increasing the thickness of wall plates and internal steel pipes can effectively reduce the stress and deformation of the cofferdam wall. When the wall plate thickness increases from 6 mm to 8 mm， the maximum reduction rate of wall stress reaches 10.2%. When the steel pipe thickness rises from 8 mm to 12 mm， the maximum reduction rate of diagonal brace stress is 10.82%. On contrast， the stress and deformation of cross braces are most sensitive to the waling position and base concrete thickness. As the waling moves downward， the maximum displacement of cross braces shows a decreasing trend， with a maximum reduction of 67.09%. When the base concrete thickness increases from 0 m to 1.5 m， the maximum displacement of cross braces drops by up to 27.19%.

Experimental study on full‑scale fatigue test of high‑toughness coldmixed resin pavement system for orthotropic steel bridge decks

The fatigue and durability performance of orthotropic steel bridge decks are closely related to the structure of the paving layer. Aiming at a new type of high-performance paving material featuring high-toughness cold-mixed resin， this paper systematically analyzes the material's load-bearing capacity， high-and-low temperature stability， and other properties through composite structure tests and large-segment full-scale tests， so as to verify the interfacial bonding reliability and fatigue resistance durability of the composite structure. The results indicate that the fracture energies of RAC and RSMA mixtures reach 1775 J/m² and 5631 J/m² respectively， with a fatigue life of 500000 cycles under 1200 με.Compared with epoxy asphalt mixture， the crack propagation resistance is improved by 50% and the flexural fatigue life is doubled. The dynamic stability of the composite structure exceeds 26000 times/mm at 70℃， and the service life is estimated to be 80 million standard axle loads when the rutting control depth is 5 mm. No damage is observed after 12 million load cycles under 5 kN. Furthermore， a cumulative 2 million cycles of full-scale accelerated loading tests were conducted under the conditions of 300 kN load and 65 ℃ high temperature， which verifies the excellent stability and fatigue resistance durability of the coupling system between the steel bridge deck and the paving layer. This material can significantly enhance the service safety and long-term performance of orthotropic steel bridge decks.

Evolution of microstructure and mechanical properties of high‑nickel austenitic stainless steel microwire during cold drawing

This study systematically investigates the microstructural evolution and mechanical properties of a high nickel austenitic stainless steel microwire subjected to large strain cold drawing. By combining multiple microstructural characterization techniques with mechanical property measurements，the deformation and strengthening mechanisms of the material are elucidated. The results show that the material remains single phase austenitic during the drawing process， and the tensile strength increases significantly from 560 MPa to 2200 MPa. Deformation twinning and dislocation slip are identified as the dominant deformation mechanisms. With an increase of drawing strain， the high density of deformation twin boundaries effectively subdivides the original grains， resulting in the formation of a submicron/nano scale twin lamellar structure. This study provides theoretical guidance for the development of ultra high strength austenitic stainless steel microwires.

Effect mechanism of homogenization treatment on the evolution of dispersoid in Al‑Cu‑Sc alloy

In order to explore the mechanism by which homogenization processes affect the evolution of dispersed phases in Al⁃Cu⁃Sc alloys for automotive engines and identify appropriate heat treatment procedures to improve the comprehensive properties of the alloys， comparative systematic investigations of alloys under various homogenization conditions are carried out via a combination of mechanical property tests and microstructural characterizations. The results indicate that homogenization treatment at 500 ℃ enables the complete dissolution of primary Al₂Cu phases into the Al matrix，yielding a maximum hardness of 79.2 ±0.7 HV. The optimal homogenization process is determined as 500 ℃ × 50 h + 250 ℃ × 1 h. In summary， this homogenization process can optimize the alloy's microstructure and significantly enhance its mechanical and heat⁃resistant performances， providing theoretical and technical support for the development of novel aluminum alloys for automotive engines and the formulation of corresponding heat treatment processes.

Special Topic Introduction

Intelligent innovation and policy orientation for expressway capacity expansion

Guided by national strategies such as the Transportation Powerhouse Strategy and Digital China， China's expressways are undergoing a transition from traditional physical capacity expansion toward intelligent capacity expansion. Intelligent capacity expansion mainly relies on new-generation information technologies， including big data， artificial intelligence， vehicle-road collaboration， and vehicle-road-cloud integration， to optimize traffic organization and operational control， thereby unlocking the latent capacity of existing infrastructure while ensuring traffic safety. Based on a keyword-based analysis of recent policy hotspots and literature in China's expressway sector， this paper reviews the current development of intelligent capacity expansion at both national and local government levels， and clarifies specific policy orientations and their underlying logical relationships. Furthermore， in light of the “Artificial Intelligence+Transportation” action plan， this paper analyzes and discusses potential directions for the next stage of intelligent development in the expressway sector.