Beijing Jiaotong University

Crack parameter inversion using an ultrasonic-magnetic fusion neural network

Crack defects in ferromagnetic components may lead to structural degradation and safety risks during manufacturing and service. Ultrasonic testing and magnetic memory testing have complementary advantages, but single-modality methods are often limited in quantitative crack parame...

Numerical investigation of radiative heat transfer effects on liquid ammonia jet spray flames

Radiative heat transfer in liquid-ammonia spray flames remains poorly understood, particularly because liquid evaporation, fuel-side mixing, and product-side heat release are spatially separated. In this study, radiative heat transfer in a spatially developing liquid-ammonia jet...

Safety evaluation of new energy three-electric systems using enhanced physics-informed neural networks

Accurate safety-state measurement of the three-electric system in new energy vehicles is essential for ensuring reliable and secure operation. This paper proposes an artificial-intelligence-assisted safety measurement framework that integrates a searchable encryption mechanism wi...

Comparative study on carbon emissions based on scenario uncertainty analysis: A case of asphalt and composite pavements construction in south China

To improve the accuracy of carbon emission accounting results during the construction of asphalt pavement and composite pavement, and clarify the differences in their carbon emission levels during the construction stage, this study developed a comparative life cycle assessment mo...

Geometry-Aware Risk-Guided Active Learning for Malware Concept Drift Adaptation

Mobile malware evolution induces concept drift, degrading the performance of static supervised detectors. Concept Drift Adaptation with Active Learning (CDA-AL) mitigates this problem by querying informative samples for model updating, but existing methods still face two limitati...

Gate-Programmable Spectral Plasticity in Nanoporous Vertical Organic Synaptic Transistors for Adaptive Neuromorphic Vision

Artificial vision systems capable of dynamically adapting to changing spectral environments are essential for next-generation intelligent perception but remain fundamentally constrained by the fixed spectral responsivity of conventional photodetectors. While narrowband photodetec...

Tunnel-wall-monitoring-based probabilistic risk assessment and inverse control of train-induced ground vibration in metro tunnels

Long-term vibration monitoring in operational metro tunnels provides valuable information for evaluating train-induced ground-surface vibration and its environmental impact. However, it remains challenging to determine whether the ground-surface vibration satisfies environmental...

Interpretable Causal Structure Learning for Multivariate Air Quality Forecasting: An Integrated Evolutionary-Cognitive Approach

Accurate Air Quality Index (AQI) forecasting is essential for public health protection and sustainable urban planning. Existing data-driven forecasting models often provide limited interpretability of pollutant interactions, while conventional Fuzzy Cognitive Map (FCM) learning a...

Electrically Programmable Polarization‐Resolved Photodetector Platform for Filterless Computational Spectroscopy and Imaging

ABSTRACT Conventional spectrometers and polarization‐resolved imagers rely on dispersive optics or filter stacks, significantly limiting their miniaturization and system integration. Herein, a compact perovskite/organic blazed‐grating photodetector that functions as a bias‐encode...

Restabilization and spectrotemporal shaping of pure-quartic solitons by output coupling in fourth-order-dispersion mode-locked fiber lasers

Pure-quartic solitons (PQSs) in fourth-order-dispersion (FOD) mode-locked fiber lasers have attracted considerable attention as a route toward high-energy ultrafast pulse generation beyond the conventional soliton regime. However, the output coupler is generally treated as a fixe...

Confidence-Aware Gaze-Depth Interaction for Reliable 3D Target Selection in Consumer VR Headsets

Gaze-based interaction offers a natural, low-effort input channel for virtual reality (VR), but gaze-depth estimates on consumer headsets vary with viewing distance, fixation stability, head motion, and scene properties. We propose confidence-aware gaze-depth compensation, which...

Research on Reliable Path Planning for Intelligent Park-and-Ride Guidance Systems Using an Accelerated Reliability-Bound Convergence Algorithm

Park-and-ride (P&R) facilities provide a critical mechanism for integrating private and public transport to alleviate urban traffic congestion. However, their limited capacity leads to substantial uncertainty in parking space availability. Few studies systematically integrate par...

Exploring the transcriptomic and metabolomic associations with fetal overgrowth in Holstein cattle derived from in vitro embryo production

Calves derived from in vitro embryo production (IVP) often have higher birth weights than those produced by artificial insemination or in vitro embryo transfer. The overgrowth in uterus may increase the incidence of calving assistance and thus, causes the potential health issue f...

Generative LLM for adaptive taxonomy-informed multi-label classification in construction safety

Accurate hierarchical multi-label classification of construction accident narratives is vital, yet traditional methods struggle with the Occupational Injury and Illness Classification System (OIICS), which contains over 2000 labels across four attributes with four-level hierarchi...

Solidification function of biochar-modified red mud-based geopolymer to heavy metals

This study compared the effects of corn biochar (CB) and bamboo biochar (BB) on the strength development and Cu2+/Cd2+ immobilization performance of a high-strength red mud-based geopolymer (RMG). Red mud (RM), fly ash (FA), and blast furnace slag (BFS) were used to prepare geopo...

Escaping the AI cage: construction workers’ perceived risk with AI gives rise to unsafe behaviors

Reducing unsafe behavior among construction workers remains a central concern in construction management. While artificial intelligence (AI) technologies are increasingly adopted to replace or monitor workers, the negative perceptions workers hold toward the promotion of such tec...

Semitransparent Organic Photovoltaic Achieving 12.98% Efficiency and 33.95% Average Visible Light Transmittance by Employing PPT‐3 With Large Bandgap and Narrow Photon Harvesting Range

ABSTRACT A broad bandgap polymer PPT‐3 with optical bandgap of 2.25 eV and narrow photon harvesting range of 90 nm was deliberately selected to match with one narrow bandgap acceptor BTP‐eC9 for preparing semitransparent organic photovoltaics (ST‐OPVs). The optimal weight ratio o...

Fast, safe and low energy consumption charging for lithium-ion batteries via dynamic safety boundaries and adaptive SOC control

The widespread adoption of electric vehicles necessitates lithium-ion batteries capable of fast charging, yet this process inherently faces the risk of heat generation and lithium plating. Considering the common fast charging scenarios around room temperature and practical implem...

A Study on Power Grid Project Portfolio Based on Multiscale Feature Integration

Power grid companies have established a feasibility study reserve phase to optimize the rolling schedule of annual investments, in which projects undergo preliminary feasibility studies, are incorporated into a project reserve pool, and subsequently proceed through release, imple...

A Dual Task Learning Framework for Multitype Bridge Condition Assessment Using UAV Imagery

Abstract Unmanned aerial vehicle (UAV) imagery combined with artificial intelligence offers unprecedented potential to improve bridge health monitoring, reducing reliance on labor-intensive and potentially hazardous manual inspections. However, the diversity of bridge types and d...