Subway construction accident reports often take a lot of time and personnel to analyze and contain a large amount of data that require professional identification, which increases the difficulty of the analysis. This study aims to use Generative Pre-trained Transformer (GPT) models for the automated analysis of subway construction accident investigation reports, with the goal of improving the efficiency of accident identification and analysis. By analyzing a dataset of 50 subway reports, this study developed the Accident Investigation Report (AIR) Agent, which utilizes GPTs to automatically identify accident types and extract key details from the reports. The chatbot is composed of three core modules: a conversation module, an instruction module, and a knowledge module. Ablation studies were performed to validate the AIR Agent’s efficiency, and the validation results show that the AIR Agent achieves an accuracy of 80.32% when analyzing new reports with a brief conclusion, demonstrating the AIR Agent’s ability to automatically format and structure reports in a consistent and correct manner. These findings suggest that the AIR Agent can significantly reduce the manual effort involved in accident investigation report analysis and enhance the overall efficiency of analyzing subway construction accident investigation reports, thereby improving the effectiveness of accident investigation and management.

This study is dedicated to an in−depth analysis of the combustion characteristics of extruded polystyrene (XPS) as a building insulation material with the aim of accurately assessing its fire risk in the built environment. Innovatively, this research employed a cone calorimeter equipped with a self−designed insulating sample holder to conduct a systematic experimental study. Additionally, it performed a comprehensive analysis of the ignition characteristics, heat release rate, fire hazard, smoke release, and toxic gas emission of XPS materials. The experimental results revealed that the combustion behavior of XPS is influenced by multiple factors, including the content of flame retardants and external heat flux, which significantly affect the fire hazard of XPS. When the thermal radiation intensity escalates from 25 kW/m² to 55 kW/m², the peak heat release rate of XPS−B1 rises from 428 kW/m² to 535 kW/m², marking an increase of 25.00%. Conversely, the peak heat release rate of XPS−B2 surges from 348 kW/m² to 579 kW/m², reflecting a substantial increase of 66.38%. This research not only provides a solid theoretical foundation and detailed experimental data for the fire behavior of XPS materials but also holds significant practical importance for enhancing the fire safety of buildings. Overall, this research contributes to the scientific understanding of XPS insulation materials and supports the development of more effective fire prevention measures in construction.

A subway transfer station hall is crowded and complex in structure, which makes evacuation more difficult in case of a fire, but also provides more strategic options for smoke extraction. Full-scale experiments and numerical simulations are conducted to investigate the feasibility and performance of coordinated ventilation in a T-shaped transfer station hall, accounting for different fire source locations, ventilation modes, and fire shutter operations. It is found that the optimal ventilation strategy varies based on the fire location within the T-shaped configuration. For fires on the ‘T’s horizontal side, lateral airflow from longitudinal fans can effectively disrupt smoke spreading, with coordinated extraction strategies outperforming the traditional methods. However, for fires on the ‘T’s longitudinal side, horizontal fans are ineffective in controlling smoke flow, making the traditional fire shutter closure optimal. The idea of dispersing hot smoke to a reasonable degree can create better evacuation conditions for people near a fire, while creating almost no new danger zones.

Cellulose-based aerogels are promising sustainable thermal-insulation materials, but their practical application is often limited by insufficient mechanical robustness and intrinsic flammability. Herein, a multiscale network-engineering strategy is proposed to fabricate a cellulose-based composite aerogel integrating structural stability, thermal insulation, and fire safety. By synergistically introducing in situ generated aluminum trihydroxide (ATH) and microencapsulated APP@ATH–MEL into the cellulose scaffold, the flame-retardant components function not only as active fire-safety agents but also as structural regulators that promote the formation of a highly interconnected hierarchical framework. This regulated architecture enhances interfacial interactions, improves load-transfer efficiency, suppresses structural collapse during freeze-drying, and introduces tortuous pathways and abundant interfaces for heat-transfer regulation. As a result, the optimized composite aerogel exhibits a low thermal conductivity of 35 mW·m⁻¹·K⁻¹ together with improved compression resistance. Thermal analysis reveals a reduced mass-loss rate and increased char yield, while cone calorimetry confirms suppressed heat release, reduced gaseous emissions, and improved residue stability. The enhanced fire safety is attributed to a synergistic multi-phase mechanism involving endothermic shielding, gas-phase dilution, condensed-phase char formation, and inorganic-residue reinforcement, which collectively inhibit heat and mass transfer during combustion. This work provides an effective strategy for the design of lightweight, mechanically robust, and fire-safe cellulose-based composite aerogels for advanced thermal-insulation applications.

Unstructured aviation accident narratives are difficult to convert into causal, decision-oriented models. This research presents and validates a generative pre-trained transformer (GPT)-powered automated analysis framework for aviation safety risk. GPT models systematically analysed 23,620 unstructured accident reports from the Aviation Safety Network (ASN) using a templated prompt to extract cause events, identifying 12 effect events, 33 cause events, and their probabilistic dependencies. A Bayesian belief network (BBN) was developed through a simulated annealing structure search guided by the Bayesian Dirichlet equivalent uniform (BDeu) score, and its parameters were estimated through maximum likelihood estimation. The model was validated through five-fold cross-validation, achieving an overall accuracy of 86.58%. Tornado-based sensitivity analysis and composite risk ranking identified aircraft design defect, crew disregard of regulations, dust haze, hydraulic failure, and thunderstorms as the five most critical cause events, forming the basis for targeted risk-control recommendations. This research contributes a GPT-driven extraction and mapping workflow that turns narratives into cause events, and is deployed as a BBN for aviation risk inference on 23,620 ASN accidents with recommendations. This research shows that the GPT-powered extraction process supports systematic risk analysis; on an expert-adjudicated benchmark, it achieved higher recall, micro-F1, and macro-F1 than keyword and TF–IDF baselines, while the BBN translated the extracted events into risk-control priorities.

Developing lightweight, eco-friendly, and fire-safe materials is essential for sustainable engineering applications. Here, we report a structurally engineered biomass aerogel constructed from a cellulose–lignin–chitosan skeletal framework reinforced with nanoencapsulated P/N–Si flame-retardant hybrids. Ammonium polyphosphate(APP) was encapsulated within a silica shell and combined with melamine (MEL) to form a multifunctional flame-retardant phase uniformly anchored onto the bio-derived network. The synergistic structural–chemical design yielded a robust, highly porous microarchitecture with enhanced hydrophobicity (water contact angle up to 73.4°), improved thermal stability (T_max increased from 195°C to 234°C), and outstanding flame retardancy (> 74% reduction in peak heat release rate), while maintaining low bulk density. Mechanistic studies reveal that during combustion, APP@SiO₂–MEL promotes phosphorylation–dehydration reactions, triggering early char nucleation and catalytic graphitization in the condensed phase. The resulting P/N-rich, SiO₂-reinforced intumescent char forms a cohesive barrier with an “indirect path” effect, significantly slowing down the transport of heat and flammable volatiles. Simultaneously, released P = O• radicals quench flame-propagating radicals in the gas phase, further suppressing combustion. This dual-phase synergistic mechanism effectively preserves structural integrity under fire exposure. This work provides a scalable, environmentally friendly strategy for producing high-performance, fire-safe biomass aerogels, offering significant potential for applications in thermal insulation, construction safety, and energy storage protection. The combination of renewable bio-based matrices and advanced flame-retardant nanotechnology represents a promising pathway toward next-generation sustainable fire-protection materials.