High traffic flow in a confined tunnel makes fire safety a critical issue. This paper proposed a digital twin framework for tunnel fire safety management in real-time, driven by dynamic sensor data and AIoT technologies. A deep learning model trained by the Transformer network and simulation dataset is used to predict real-time fire location and size. Then, the AI model is integrated into a 3D digital twin platform developed by the game engine Unity 3D. The performance of the proposed digital twin framework is demonstrated using numerical experiments and large-scale tunnel fire tests. Results show that the established AI model achieved promising accuracy in predicting fire location and power for both numerical and experimental data. The digital twin platform can also visualize the 3D fire scene that supports evacuation, firefighting, and emergency rescue. This research demonstrates the feasibility of using a 3D environment and digital twin in real-time fire safety management.

The diagrid structural system has seen significant uptake in medium to high rise buildings because of the architectural and resource advantages that it provides. These arise mainly as a result of flexibility in the topology that this particular structural solution provides. However, as a result of the way in which diagrids carry both horizontal and vertical loading, the diagrid structure itself may be susceptible to fire in ways which are not immediately obvious on the basis of our understanding of more traditional rectilinear construction forms. This study addresses this to improve our understanding of diagrid structures' response to fire. A comprehensive structural analysis on 45 fire load cases is conducted, considering different fire locations and sizes, using parametric design tools and finite element analysis software. The results provide valuable insights into the load redistribution and collapse mechanisms of diagrid structures in fire conditions.

The ‘travelling fire’ models have been used to describe the localised and travelling burning of uniform fuel bed in large open-plan building space. However, fuel is typically distributed non-uniformly in the built environment, leading to complex fire spread behaviours. This paper investigates the effect of non-uniform fuel load distribution on fire development in a sufficiently-ventilated space. A series of fire tests up to 3.5 MW with different wood crib layouts are categorised into two types, i.e., non-uniform and continuous, and non-uniform and discontinuous. The leading and trailing edges of the flame, height of flame, and fire spread rates are estimated using visual evidence. The non-uniform fuel load distribution fundamentally changes the spreading behaviour of fire. On a continuous wood crib, the fire spread rate and fire size are generally proportional to the fuel load density when the arrangement of the wood crib is similar. However, when wood cribs are discontinuous, the fire dynamics depend more on the localised burning size and gaps between fuels. Furthermore, very distinct fire behaviours were observed for fuel loads with different porosity. This work reveals the possible under-estimation of fire hazards of assuming evenly distributed fuel load and suggests considering design fire scenarios of non-uniform fuel load distribution in the performance-based fire safety design.

This study analyses the structural response of an aluminium reticulated roof structure that is constructed at Sichuan Fire Research Institute (Sichuan, China), and to be tested in fire. The structural fire behaviour under 960 localised fire scenarios is considered first, and then used to construct a database for training a modular artificial intelligence (AI) system for real-time forecasting. The system consists of several AI models, each of which predicts the displacement at a specific monitoring point. These individual predictions are then combined to generate a comprehensive forecast of the global structural-fire behaviour. The individual AI model utilized is a Long Short-Term Memory Recurrent Neural Network (LSTM RNN). The modular design allows different models to be modified or added as needed, making the system flexible and adaptable, and improving the accuracy and reliability of the predictions. The results demonstrate the effectiveness of the modular AI approach in accurately forecasting fire-induced structural collapses as indicated by the sensitivity the local models can have. The key objective of this research is to help to make informed decisions and prioritize efforts to minimize the risk of structural collapse in fire.

In performance-based structural fire engineering, “travelling fires” is being gradually accepted as an important fire boundary condition. However, its application is still limited by uncertainties in the selection of different design travelling fire parameters, resulting from the lack of relevant experimental data and corresponding validated structural finite element models which can be used with advanced travelling fire methodologies, e.g. the Extended Travelling Fire Methodology (ETFM) framework. This paper aims to fill this gap through modelling a prototype steel-composite floor structure (representing a “slice” of a large open-plan office), to investigate its true structural response under a wide range of travelling fire scenarios, with an emphasis on considering the effect of concrete slab in a 3D finite element model, using LS-DYNA. To ensure the credibility of this numerical study, the model was first validated against the experimental data of the structural response from the Veselí Travelling Fire Test. In the parametric studies, 32 cases were examined to investigate the thermal and structural response, related to the selection of key design parameters for travelling fires (i.e. fire spread rates, fuel load densities and inverse opening factors (IOF)); fire protection (i.e. different fire protection schemes and required fire resistance rating (FRR)), and the effect of slab specification (i.e. thicknesses and steel reinforcements). It was found that solely satisfying the critical temperature and deflection criteria for the structural members might not guarantee a sufficient structural design for travelling fire scenarios, and it is suggested that the steel stress utilisation should also be examined. Compared with the IOF, it appears that the selection of fire spread rates and fuel load densities are likely to be more critical in identifying the worst travelling fire scenario for the structural response with fire protection. Moreover, the global structural response under travelling fire is also affected by the combination of fire protection (i.e. equivalent FRR in this paper) and fire spread rate. Under a “slow” travelling fire (e.g. 0.5 mm/s) with increasing FRR, the failure of structural elements during the cooling phase was prevented effectively; however, under a relatively “fast” travelling fire (e.g. 2.5 mm/s, 12.5 mm/s), increasing FRR may not always improve the fire performance of the structure. This work also indicates that steel reinforcement ratio has a greater influence on structural response than slab thickness under travelling fires. Furthermore, the 3D finite element model is very important for structural fire analysis, not only due to the more conservative internal force captured by the 3D model (i.e. reduced by over 80 % on the 2D model in our case) thereby reproducing the collapse triggered by the failure of the connection under fire in general, but also the 3D model was able to better represent the deflection and the “internal force reversal” caused by travelling fires.

Large open-plan compartment fires in modern buildings may exhibit a local burning region travelling across the floor plan as a ‘travelling fire’. This phenomenon has been found in the forensic investigations of fire accidents and in the large compartment fire tests. The fire impact in a large compartment is spatially non-uniform and time-variant, which can cause severe local damage to structural components. Advanced from the previous models assuming constant travelling, the natural fire model established in this paper comprises time-variant and test-based travelling behaviour models and localised fire models of various modes. It is demonstrated with the fast-spread Veselí fire test and the slow-spread Malveira fire test. A generic structural model is set up within OpenSees for fire to examine the thermal impact on structural members under various travelling fire scenarios of different travelling parameters, fire travelling directions, and beam sizes. Locally much higher thermal responses are represented after introducing behaviour models while adopting the same design fire load. Based on the work in this paper, a library of design fire models can be potentially enabled to examine the fire safety performance of structures regarding the realistic fire load and fire impact aiming for discovering unknown worse fire scenarios.