Beijing Jiaotong University

A cloud-edge collaborative dual-modal fault detection block for battery packs: Enabling intelligent safety management in electric vehicle battery systems

Intelligent diagnosis of battery pack faults using real-world data has become a key research focus in the era of vehicle-cloud integration. While cloud-based deep learning diagnostics have shown strong capability, edge-based fault diagnosis is increasingly preferred for its real-...

S2DFusion: a statistical and scale difference attention network for infrared and visible image fusion

Infrared and visible image fusion aims to integrate cross-modal complementary information for comprehensive all-weather scene perception. However, existing methods often fail to effectively decouple background noise from modality-specific salient features, leading to contrast deg...

Patient Capital and Corporate High-Quality Development: Evidence from China

Based on signaling theory and principal-agent theory, this study takes the new development philosophy as the entry point and systematically examines the impact of patient capital on corporate high-quality development and its underlying mechanisms. The results show that patient ca...

A deformable tri-prism rolling mechanism constructed with only R joints

In this paper, a novel deformable tri-prism rolling mechanism constructed with only revolute (R) joints is proposed. The rolling mechanism is composed of six vertices and nine planar RRR chains, forming a regular tri-prism structure with a total of seven degrees of freedom (DoFs)...

Robust Optimization of Flexible Train Formation Strategy and Passenger Flow Control in Urban Rail Transit

Abstract To address the mismatch between transport capacity and passenger demand in metro operations, this study investigates the coordinated optimization of flexible train formation and passenger flow control. First, under deterministic passenger demand, a coordinated optimizati...

Online coordinated estimation of origin–destination, path, and link flows in urban rail transit networks via a physically constrained computational graph

Urban rail transit (URT) systems require timely estimates of origin–destination (OD) demand and network-wide link flows to support crowding management and disruption response under rapidly changing conditions. Despite the growing availability of multisource data, online estimatio...

Toward Web 4.0: bidirectional trust between AI agents and blockchain

Autonomous artificial intelligence (AI) agents are increasingly deployed on blockchain platforms, yet the design space governing their interaction remains poorly understood. This convergence, in which autonomous agents operate on and within decentralized systems, characterizes th...

Flexural performance of composite pile–wall structures: Experimental investigation and stochastic fiber-beam modelling

Pile–wall integrated structures combine retaining piles with subsequently cast sidewalls to form composite load-bearing components in urban underground construction. Their flexural performance was investigated through four-point bending tests on four quarter-scale specimens and a...

Evolution mechanism of microstructure and thermal properties in binary fatty acid nanoencapsulated phase change materials

Nanoencapsulated phase change materials hold broad application prospects in the thermal management of electronic devices and energy storage. A binary fatty acid nanoencapsulated phase change materials system was constructed with different ratios of decanoic acid-lauric acid as th...

City-Scale Assessment of Rooftop Photovoltaic Carbon Mitigation in China Using Semantic Segmentation and Interpretable Machine Learning

Urban rooftop photovoltaics (URPV) are crucial for decarbonizing China’s building sector, yet large-scale assessment remains limited by difficulties in rooftop extraction, cross-city generalization, and linkage to forward-looking decarbonization strategies. This study developed a...

An inerter-enhanced piezoelectric tuned mass damper for integrated structural vibration mitigation and energy harvesting

This study proposes an inerter-enhanced piezoelectric tuned mass damper (IEP-TMD) for integrated structural vibration mitigation and vibration energy harvesting under lightweight installation conditions. The proposed device combines a tuned oscillator, an inerter, and a piezoelec...

Development and performance of filler-free buckling-restrained shape memory alloy devices for self-centering seismic applications

This study proposes a novel filler-free buckling-restrained SMA device for self-centering seismic applications. The proposed device consists of an SMA core bar, a confining tube, two swaged sleeves, two restraining sleeves, and two connection parts. The SMA bar includes a fuse pa...

A Prediction-Enhanced Polynomial Kalman Filter Using Higher-Order Predictive Representations for State Estimation

The conventional Kalman filter operates primarily in the original first-order state-prediction space, which limits the explicit utilization of higher-order state-coupling and predictive statistical structures. To enlarge the candidate prediction space, this study proposes a Predi...

Integrated metro train timetable and rolling stock rescheduling with passenger rerouting under multi-location disturbances

The expanding scale of infrastructure and rising passenger demand in metro systems increase the frequency of stochastic disturbances, significantly impacting metro train operations. This is particularly evident in multi-location disturbances (MLD), often occurring during extreme...

How External Regulations Influence ESG Integration in Construction Firms: A Managerial Cognition Perspective

Abstract Limited understanding of how external regulations influence construction firms’ environmental, social, and governance (ESG) integration constrains policy effectiveness and industry sustainability performance. Drawing on neo-institutional theory and managerial cognition (...

Assessing the drivers of green growth: an empirical investigation of green technological innovation, economic complexity, and investments in renewable energy in G20 countries

As the world grapples with the long-term consequences of the changing climate and dreadful ecological conditions, the G20 nations, as the largest and most influential economies, face a particularly daunting challenge: striking the optimal balance between environmental sustainabil...

Compression–Rebound Behavior and Delayed Deformation Mechanism of Cohesive Soils Under Groundwater Level Fluctuations

Long-term groundwater exploitation causes water-level fluctuations, which are a major driver of land subsidence and infrastructure deformation in sedimentary basins. To investigate the stress-history-dependent compression–rebound behavior of deep cohesive soils, soil samples alon...

Chinese Christianity and Knowledge Development: Multi-Perspective Inquiries Toward Integrated Understanding

The encounter between Christianity and Chinese civilization from the late Ming through the Republican period represents one of the most consequential episodes of cross-cultural intellectual exchange in modern history [...]

Temperature field prediction based on a 3D-U-net model

The solidification process of castings involves intricate physical transformations and is critical in the final quality of castings. The temperature field during solidification serve as fundamental indicators for defect prediction and process optimization. Conventional approaches...

Multi-Dimensional Behavioral Signature Analysis for Video Bullet Comment Steganography Detection

The proliferation of bullet comment systems on video-sharing platforms has created novel opportunities for covert communication. Recent research has demonstrated multiple bullet comment-based steganographic paradigms: time modulation, time attribute shifting, live broadcast game-...