Fire Scenarios Research Articles

A Study on the Influence of Mobile Fans on the Smoke Spreading Characteristics of Tunnel Fires

Mobile fans, as flexible and convenient new longitudinal ventilation and smoke extraction equipment for tunnels, demonstrate more significant effectiveness in an emergency response to tunnel fires compared to traditional smoke extraction methods. This study employs computational fluid dynamics simulation methods, selecting two fire scenarios to investigate the effects of fan inclined angles and fan airflow volumes on the longitudinal temperature distribution and smoke back-layering length in tunnels. The results indicate that when using mobile fans for longitudinal ventilation in tunnels, at a lower fan airflow volume, the temperature distribution along the longitudinal axis is nearly symmetrical. The fire source and the fan installed in the upstream are within a certain range, and it is more effective to use the horizontal angle for longitudinal ventilation. As the fan airflow volume increases, the back-layering length significantly decreases (210,000 m3/h < V < 270,000 m3/h). However, as the fan flow volume continues to increase (270,000 m3/h < V < 300,000 m3/h), the reduction in the back-layering length becomes less pronounced, the smoke spread distance of the latter is only 11% of that of the former. Therefore, selecting appropriate fan airflow volumes and fan inclined angles them can effectively enhance the performance of tunnel smoke extraction systems. Moreover, by comparing with traditional fans, we find that mobile fans provide an alternative effective strategy during firefighting by allowing adjustments in distance from the fire source and fan inclination angles, enhancing fire suppression effectiveness while reducing energy losses. The research findings can serve as a reference for tunnel fire prevention design.

A study of staff pre‐evacuation behaviors in a Malaysian hotel

AbstractSimulating fire and evacuation scenarios is crucial for engineers to assess building safety during fire incidents. Accurate simulations require data on occupants' behaviors, particularly during the pre‐evacuation phase as these decisions significantly impact evacuation duration. Gathering comprehensive data from diverse regions while considering cultural and regional variations is necessary to understand how occupants' behavior is influenced. Thus, this study focuses on examining the behavior of Malaysian hotel staff during unannounced fire drill to gain insights into factors affecting their behavior during pre‐evacuation stage, such as fire experience, fire alarm, drill participation, fire training, and awareness. The study categorizes the actions performed by the hotel staff into sequences and analyses them based on influencing factors. The findings indicate that instead of immediately evacuating in response to emergency notification, the hotel staff engage in various actions. Most staff members initially investigate or ignore the emergency, resulting in longer pre‐evacuation times. Moreover, the results suggest that previous drill participation and high awareness levels contribute to shorter pre‐evacuation times. Conversely, previous fire experience, fire training, and fire alarm familiarity have no effect on pre‐evacuation time.

Computational analysis of wildland fire resistance for transmission line tower

Finite element (FE) analysis of the transmission towers under a fire event and the accompanying wind is presented. Several key aspects (including temperature-dependent non-linear material properties, geometric non-linearity, member eccentricity due to the single-leg bolted connection, and the temperature-dependent connection behaviour in both the axial and the rotational directions) are considered. A quasi-static analysis is also employed in the FE model using the explicit solver available in Abaqus. The member temperature variation during a realistic fire event is derived analytically based on the fire intensity and the resultant vertical gas temperature distribution so that the effect of the realistic wildland fire can be input as a member temperature profile. First, fire design guidance in terms of the most critical heating and wind pattern, as well as the effect of fire-affected heights are provided based on the case study results. Then, further fire analysis is carried out to investigate the most critical fire scenario and to evaluate the vulnerability of the tower during a realistic fire event. Lastly, an evaluation of a commonly used spray-on thermal insulation and its effectiveness in reducing the member temperature and preserving ultimate strength during a catastrophic wildland fire event are presented. The FE simulations revealed that a 45-degree wind associated with partial side heating leads to a more critical degradation of the overall strength, whereas the effect of fire height is less obvious. In terms of the fire scenario, a longer fire duration associated with a slower wind is more critical for the fire resistance/rating.

Quantitative Study of Thermal Response of Timber–Concrete Composite Structures Under Traveling Fire Using Energy Equivalence Method

ABSTRACTThe time equivalent method can be used to quantify the fire intensity of a traveling fire into the time of action of the standard fire, which in turn can be used to assess the extent of damage to a structure under a traveling fire. However, an effective time equivalence method for timber structures has not been developed yet. Therefore, this paper proposed an energy‐based time equivalent method, referred to as the “energy equivalence method (EEM)”, for evaluating the fire resistance of timber structures under traveling fire, and validates its effectiveness through a series of fire tests. The results demonstrate that the EEM effectively quantifies the fire intensity endured by glulam under traveling fire as the equivalent exposure time under the standard fire. Furthermore, the EEM was utilized to investigate the damage behavior of a single‐layer Timber‐Concrete Composite (TCC) frame under traveling fire. The results reveal variations in the fire intensity experienced by the structure at different locations under the same traveling fire scenario, with the most severe damage occurring at a position 40% relative to the ignition end. The fire scale determines the non‐uniformity of the fire intensity and the extent of structural damage, as smaller‐scale fires (fire sizes between 10% and 40%) not only result in significant variations in damage levels at different locations but also have a more adverse impact on the structure. In fire safety design, the selection of standard and traveling fire design methods should be based on the fire scale.

Energy-based damage assessment method for masonry walls under seismic and fire loads

The evaluation of the out-of-plane (OOP) behavior for infilled walls is a critical aspect of regional seismic and fire resilience assessment. This study presents a detailed finite element (FE) model that comprehensively captures the seismic and fire behaviors of masonry walls. The FE model incorporates key factors governing the thermo-mechanical behavior of masonry walls, including temperature-dependent material properties, nonlinearities in geometry and material, block cracking and crushing, and mortar damage. Then, an energy-based damage criterion is proposed based on the principle of energy conservation, leveraging the combined mixed fracture energy and internal energy of elements. In addition, this study defines the damage levels of masonry walls under OOP loading and fire and determines corresponding damage indices using the proposed energy-based damage criterion. This criterion is further compared with a stiffness-based damage criterion. Finally, the proposed damage assessment method is employed to evaluate the damage evolution of infilled walls under seismic, fire and post-earthquake fire scenarios, and to conduct a fragility analysis. The results demonstrate a high degree of agreement between the predicted and measured damage states of masonry walls under seismic and fire loads. More severe seismic damage does not always result in diminished fire resilience. Evaluating post-earthquake fire damage requires considering the impact of displacement directions caused by earthquakes and fires.

Spatial-temporal Data Model for Indoor Fire Response Considering Multi-Factors

Abstract. The complexity of high-rise building structures and functions significantly increases the challenges in emergency responses to indoor fire incidents. This complexity is due to multiple factors that must be evaluated for decision-making within the fire scenario, such as the entities within the building, the status of environment, and the actions of people. An effective and precise indoor fire emergency management model should fully take into consideration of multiple factors, aiming to ensure the safety and effectiveness of emergency response action.This paper proposes a spatial-temporal data model to integrate the entity-status-action, for designing the most suitable action strategies in various environmental status by considering all related entities in the indoor fire scenario. Firstly, a list of factors is designed to represent the scenario features including spatial location, semantic description, attribute characteristics, geometric form, evolutionary process, and the relationships among objects. Then, employs an ontology-based descriptive method to integrate multi-dimensions and effectively represents the interrelations among entities, actions, and environmental status within the context of an indoor fire scenario. These environmental status considered in the model focus on the supporting path-planning during execution of direct response actions. Finally, a set of path-planning rules has been developed to infer a series of environmental status supporting to formulate the optimal evacuation strategy to minimize the risk of evacuation failure. The case study shows that the proposed model is effective in unified expression for multitude of factors associated with emergency response in indoor fire scenario and supporting the decision-making of the emergency response actions.

Mapping and assessment of ecological vulnerability to wildfires in Europe

BackgroundWildfires play a significant and complex role in ecosystems, influencing various aspects of their functioning and structure. These natural disturbances can positively and negatively impact ecosystems, shaping landscapes, nutrient cycles, biodiversity, and ecological processes. This study focuses on assessing and integrating the different factors that affect the ecological vulnerability to wildfires at the European scale. Our methodology follows three steps. Firstly, ecological values based on biological distinctiveness and conservation status were estimated to understand pre-fire conditions better. Secondly, we obtain vegetation’s coping capacity (or resistance) to the impacts of fire, considering the functional traits of plants and fire characteristics through a fire extreme scenario. Finally, post-fire recovery time was calculated by considering the species-specific recovery time, recovery starting time, growth recovery rate, and the environmental constraints affecting the optimal vegetation response. These three variables were combined using a dynamic model that assumed the change of value due to wildfires integrated throughout the recovery time.ResultsOur results indicate that the tundra biome emerges as the most ecologically vulnerable to fire, primarily due to its high ecological values and long recovery time, which outweigh its moderate coping capacity. Following closely, the temperate conifer forests also exhibit high vulnerability driven by their high recovery time, despite moderate ecological and coping capacity values. The boreal forests rank next, with moderate vulnerability due to their long recovery time and moderate coping capacity. The Mediterranean region, although having moderate ecological values and recovery time, shows a notable vulnerability influenced by lower coping capacity. The temperate broadleaf and mixed forests demonstrate relatively lower vulnerability owing to their balanced ecological values, moderate recovery time, and substantial coping capacity. Lastly, the temperate grasslands, savannas, and shrublands are the least vulnerable, benefiting from lower ecological values and the fastest recovery time, alongside moderate coping capacity, which collectively reduce their overall fire vulnerability.Furthermore, we found that coping capacity is the factor that most influenced ecological vulnerability to wildfires.ConclusionsThe study identifies key zones for European or national policies on fire prevention and post-wildfire regeneration. It offers insights into effective forest management and conservation policies, applicable to current conditions. Additionally, the methods can predict future ecological vulnerability to wildfires based on climatic and socio-economic trends.

Flexural behaviour and shear capacity of RC flat plate sections during fire exposure

PurposeFire safety is a pivotal requirement in building codes. Prescribed design criteria have been the norm to achieve it, which imposes limitations on engineers, including the inability to accommodate new solutions/materials. The shift towards performance-based design offers the potential to address shortcomings of the prescribed design. However, this shift also significantly increases the workload on structural engineers without a corresponding increase in their engineering fees. Simplified design tools are needed to assist engineers in this transition.Design/methodology/approachThe paper is divided into sections investigating equivalent standard fire duration, thermal deformations, flexural behaviour and shear capacity of flat slabs when exposed to fire. The first section conducts a parametric study correlating equivalent and realistic fire durations using the average internal temperature profile (AITP) method, resulting in statistical equations estimating equivalent fire duration. The second section evaluates thermal deformations and flexural behaviour through a parametric study considering various parameters. This section results in statistical equations estimating thermal deformations and flexural behaviour of flat slab sections during fire exposure. The final section focuses on shear capacity, developing simplified heat transfer formulas and statistical equations predicting compression zone depth reduction. The section presents methodologies predicting flat slab sections' one-way and two-way shear capacities during fire exposure.FindingsStructural engineers can use the proposed methods for daily design work without applying complex heat transfer calculations. When the equivalent standard fire duration is utilized, a flat slab’s thermal deformations, flexural behaviour and shear capacity under an actual fire condition can be calculated. As such, the methods would be highly beneficial in assessing the structural integrity of a building during an active fire incident.Originality/valueThe paper provides engineers with the tools required to evaluate the safety of flat slab sections during fire exposure. The methodologies presented in the paper enable engineers to use performance-based design for slab sections by (1) converting any real fire scenario to a standard fire with an equivalent duration, (2) assessing their thermal behaviour, (3) evaluating their flexural behaviour and (4) evaluating their flexural and shear capacities. The paper concludes with a case study example demonstrating the detailed application of the developed methods.

A Tunnel Fire Detection Method Based on an Improved Dempster-Shafer Evidence Theory

Tunnel fires are generally detected using various sensors, including measuring temperature, CO concentration, and smoke concentration. To address the ambiguity and inconsistency in multi-sensor data, this paper proposes a tunnel fire detection method based on an improved Dempster-Shafer (DS) evidence theory for multi-sensor data fusion. To solve the problem of evidence conflict in the DS theory, a two-level multi-sensor data fusion framework is adopted. The first level of fusion involves feature fusion of the same type of sensor data, removing ambiguous data to obtain characteristic data, and calculating the basic probability assignment (BPA) function through the feature interval. The second-level fusion derives basic probability numbers from the BPA, calculates the degree of evidence conflict, normalizes the BPA to obtain the relative conflict degree, and optimizes the BPA using the trust coefficient. The classical DS evidence theory is then used to integrate and obtain the probability of tunnel fire occurrence. Different heat release rates, tunnel wind speeds, and fire locations are set, forming six fire scenarios. Sensor monitoring data under each simulation condition are extracted and fused using the improved DS evidence theory. The results show that there is a 67.5%, 83.5%, 76.8%, 83%, 79.6%, and 84.1% probability of detecting fire when it occurs, respectively, and identifies fire occurrence in approximately 2.4 s, an improvement from 64.7% to 70% over traditional methods. This demonstrates the feasibility and superiority of the proposed method, highlighting its significant importance in ensuring personnel safety.

Thermally robust hierarchical nanofiber triboelectric yarns for efficient energy harvesting in firefighting E-textiles

Textile-based triboelectric nanogenerators (TENGs) face challenges in achieving high performance and fulfilling functional requirement for special applications. This paper presents the development of a high-performance, thermally robust hierarchical polyimide (PI) nanofiber triboelectric yarns with a charge-trapping interlayer for application in firefighting E-textiles. The hierarchical nanofiber yarns, comprising a stainless-steel core electrode, a PI/MXene interlayer and PI outer tribo-layer, exhibit enhanced triboelectric performance due to the charge-trapping capabilities of MXene, which preventing the recombination of triboelectric and induced charges. When the MXene content in the charge-trapping interlayer reached 1 wt%, the corresponding TENG achieved its optimal output performance, with an output voltage of 153 V and a current of 13.13 μA and a peak power density of 0.84 W/m2 under optimal conditions. It also demonstrates exceptional thermal stability, maintaining stable output at temperatures up to 400 °C. The integration of the TENG into E-textiles enables real-time monitoring of firefighters’ physical activities and location tracking, significantly enhancing their safety and operational efficiency in fire scenarios. Additionally, the TENG powers electroluminescent yarns, improving visibility in dense smoke and dust environments. This research opens new avenues for the application of smart wearable systems in high-temperature environments, providing effective strategies for ensuring the safety of firefighters in fire rescue operations.

A dynamic risk assessment model for evacuation in healthcare facilities during fire scenarios

Evacuation is a critical procedure for safeguarding individuals during a fire incident within a healthcare facility. Assessing the risk associated with the evacuation process is instrumental in enhancing emergency decision-making and developing contingency strategies. Evacuation, a dynamic process, poses challenges in accurate risk evaluation using conventional static quantitative risk assessment (QRA) techniques. This study introduces a dynamic QRA approach to precisely evaluate the evacuation risk to individuals in healthcare settings during a fire. The dynamic event tree methodology is initially utilized to determine the evolving probabilities of various fire scenarios, considering the equipment failure and repair rates. Subsequently, data on fire products and the evacuation of individuals under different fire scenarios are gathered through simulations conducted with Fire Dynamics Simulator (FDS) and Pathfinder software. In addition, this research proposes a dynamic incapacitation model to calculate the consequences of fire, incorporating changes in individuals' locations and the fire products surrounding them during evacuation to accurately estimate the casualty risk. Lastly, the dynamic scenario probability was integrated with the average incapacitation probability for all individuals, introducing the concept of a fire evacuation safety time window to comprehensively assess hospital fire evacuation risk. The findings revealed that the dynamic quantitative risk analysis (DQRA) approach more effectively captures the influence of fire products on the evacuation risk compared to static methods. Specifically, the peak incapacitation probability in a hospital fire reached 0.85, with firefighting equipment, especially the sprinkler system, reducing this risk by over 97% and decreasing evacuation time by 45%. In addition, the risk of fire evacuation in hospitals reaches a critical threshold in the fourth year, enhancing the repair rate of the firefighting system postpones the risk's escalation to a critical threshold until the fourteenth year.

The Study of Flame Length for the Horizontal Jet Flame of Carbon Dioxide and Propane Mixed Gas

Inert gases, such as carbon dioxide (CO₂), are often presented in fuel gases and influence their combustion characteristics significantly. This paper investigates the horizontal length of buoyant turbulent jet flame under different boundary conditions, including different nozzle diameters, heat release rates, and CO₂ volume fractions. According to the experiments, it is found that the horizontal length of jet flame increases with the heat release rate under the same nozzle diameter. Additionally, the flame length initially increases with CO₂ concentration but then decreases. Based on an analysis of the buoyancy and momentum flux of the turbulent jet flame, a new correlation has been developed, which relates the horizontal flame length to the heat release rate and CO₂ volume fraction. This correlation can be served as a valuable reference for fire prevention and control in gas leakage fire scenarios.

Effects of fuel distribution on thermal environment and fire hazard

AbstractFire accidents in buildings are occurring and claiming thousands of lives each year. Due to various architectural designs, fire hazards would be unique to each building layout. This paper discusses how fire hazard varies with the arrangement of the fuel inside buildings. To comprehensively present the effect of fuel distribution on fire behaviour, results from large‐scale experiments, bench‐scale experiments, empirical correlations, and numerical studies are provided. In large‐scale fire tests, two different cases of wood cribs were tested to demonstrate the effects of porosity on heat generation and fire spread behaviour. Due to the limitations of experimental conditions, the variation in heat release rate attributable to differences in fuel porosity and surface area has been also qualitatively investigated using a cone calorimeter test. To bring the gap between experimental observations and real‐word scenarios, a numerical study is also performed. This study further explores the effects of fuel distribution (considering porosity and surface area of fuel throughout the compartment) and ventilation on fire spread beyond the fire compartment. The computational fluid dynamics (CFD) simulations show how the distribution of fuel in different ways can lead fire to spread beyond its origin, as observed in many fire accidents. The paper suggests that designers should consider such critical fire scenarios in performance‐based design.

Numerical study on smoke temperature distribution in naturally ventilated inclined tunnels: Effects of tunnel width and tunnel slope

Inclined tunnel fires exhibit unique characteristics compared to horizontal tunnel fires as a result of the stack effect. Nevertheless, there is still a lack of consensus among previous scholars regarding the smoke temperature distribution in inclined tunnel fires. This work conducts a numerical investigation on the smoke back-layering length upstream of the fire source and the temperature decay downstream of the fire source in naturally ventilated inclined tunnels with varying widths and slopes. Results indicate that as the tunnel slope increases from 0° to 8°, the smoke back-layering length first decreases and then continues at a constant value of 1.47H4/3/W1/3, while the effect of tunnel width is negligible. The decay factor in the one-dimensional flow stage (x/H≥4) exhibits two distinct patterns related to tunnel width: it initially remains constant and then drops when the tunnel is wide, whereas it monotonically drops when the tunnel is narrow. Two empirical models are developed to identify the segmented characteristics and verified through the relevant data from existing literature with similar fire scenarios. This work offers a method for estimating the smoke temperature distribution in inclined tunnels, providing crucial insights for fire prevention, smoke detection, and safety strategies in tunnel engineering.

Air temperature characteristics of cable-girder pin joint node of suspension bridge under pool fire

Under the action of high temperature, the mechanical properties of steel structure will be reduced. Cable-girder pin joint nodes (referred to as the node) of suspension bridges are composed of steel structures. Before studying the fire resistance of structures, it is necessary to accurately predict the air temperature characteristics under fire. In this paper, the FDS calculation model of the node is established for the pool fire. The air temperature characteristics of the node are clarified by numerical simulation and theoretical analysis. The effects of main factors such as fire location, wind speed, leakage hole radius and space height are studied. The unfavorable fire scenario and air heating mathematical model are obtained. The main conclusions are as follows: (1) As the fire source distance increases, the peak value of air temperature at the node gradually decreases, while the heating time steadily increases and eventually reaches a stable state. (2) The air temperature at the node initially increases and then gradually decreases as the wind speed increases. (3) Increasing the leakage hole radius from 0.02 m to 0.06 m results in a decrease of approximately 60 % in the air heating time at the node. (4) Increasing the space height from 0.25 m to 1.7 m leads to a maximum decrease of 72 % in air temperature at the node. (6) In the unfavorable fire scenario, the peak air temperature at the node can reach approximately 1200 °C, and the heating time ranges from 67 s to 149 s (7) A mathematical model of the air temperature rise curve, considering the influence of space height, is developed. This model can serve as a theoretical foundation and reference for the study of fire resistance of the node exposed to pool fires.

GPAC-YOLOv8: lightweight target detection for fire scenarios

Abstract Due to the large number of parameters in the deep network model, it is difficult for existing fire detection methods to adapt to limited hardware configurations. In addition, detecting targets in the early stages of a fire is challenging owing to their small size. Therefore, this study presents a novel fire and smoke detection framework called GPAC-YOLOv8, which is based on the YOLOv8 architecture. Firstly, the integration of the ghost module and the Polarized Self-Attention attention mechanism into the backbone culminates in the CGP module, which is designed to improve computational efficiency while maintaining accuracy. Next, an innovative feature fusion module, AC-Neck, is developed through the application of the adaptive spatial feature fusion strategy and the lightweight content-aware reassembly of features upsampling mechanism, aiming to optimize feature map fusion and increase small target detection efficiency. Finally, a Focal-WIoU loss function, augmented with a dual weighting mechanism, is formulated to precisely delineate the aspect ratios of the predicted bounding boxes, thereby strengthening the generalization capacity of the model. Experimental results, derived from the application of the proposed GEAC-YOLOv8 method to a specially constructed dataset, show significant improvements in detection speed while maintaining detection accuracy compared to conventional methods. Thus, the GPAC-YOLOv8 framework demonstrably improves the effectiveness of object detection in fire and smoke scenarios.

FireDA: A Domain Adaptation-Based Method for Forest Fire Recognition with Limited Labeled Scenarios

Vision-based forest fire detection systems have significantly advanced through Deep Learning (DL) applications. However, DL-based models typically require large-scale labeled datasets for effective training, where the quality of data annotation is crucial to their performance. To address challenges related to the quality and quantity of labeling, a domain adaptation-based approach called FireDA is proposed for forest fire recognition in scenarios with limited labels. Domain adaptation, a subfield of transfer learning, facilitates the transfer of knowledge from a labeled source domain to an unlabeled target domain. The construction of the source domain FBD is initiated, which includes three common fire scenarios: forest (F), brightness (B), and darkness (D), utilizing publicly available labeled data. Subsequently, a novel algorithm called Neighborhood Aggregation-based 2-Stage Domain Adaptation (NA2SDA) is proposed. This method integrates feature distribution alignment with target domain Proxy Classification Loss (PCL), leveraging a neighborhood aggregation mechanism and a memory bank designed for the unlabeled samples in the target domain. This mechanism calibrates the source classifier and generates more accurate pseudo-labels for the unlabeled sample. Consequently, based on these pseudo-labels, the Local Maximum Mean Discrepancy (LMMD) and the Proxy Classification Loss (PCL) are computed. To validate the efficacy of the proposed method, the publicly available forest fire dataset, FLAME, is employed as the target domain for constructing a transfer learning task. The results demonstrate that our method achieves performance comparable to the supervised Convolutional Neural Network (CNN)-based state-of-the-art (SOTA) method, without requiring access to labels from the FLAME training set. Therefore, our study presents a viable solution for forest fire recognition in scenarios with limited labeling and establishes a high-accuracy benchmark for future research.

Real-Time Fire Classification Models Based on Deep Learning for Building an Intelligent Multi-Sensor System

Fire detection systems are critical for mitigating the damage caused by fires, which can result in significant annual property losses and fatalities. This paper presents a deep learning-based fire classification model for an intelligent multi-sensor system aimed at early and reliable fire detection. The model processes data from multiple sensors that detect various parameters, such as temperature, humidity, and gas concentrations. Several deep learning architectures were evaluated, including LSTM, GRU, Bi-LSTM, LSTM-FCN, InceptionTime, and Transformer. The models were trained on data collected from controlled fire scenarios and validated for classification accuracy, loss, and real-time performance. The results indicated that the LSTM-based models (particularly Bi-LSTM and LSTM) could achieve high classification accuracy and low false alarm rates, demonstrating their effectiveness for real-time fire detection. The findings highlight the potential of advanced deep-learning models to enhance the reliability of sensor-based fire detection systems.

Prediction of flashover time in a compartment fire by CNN-LSTM based deep neural network considering wearable data collection equipment

Real-time prediction of flashover in a compartment fire is of great significance for rescue. This paper investigated a CNN-LSTM neural network to predict the flashover based on the temperature and radiative heat flux in 24 compartment fire cases simulated with FDS. Multiple conditions affecting compartment fires have been taken into account, like room size, room height, fire source location, opening size, number of vents, and fire load. Radiative heat flux meters and thermocouples were positioned at specific heights, to simulate sensors worn by firefighters entering a fire scene. The proposed model consisted of a convolutional layer and three LSTM layers. After training, the deep learning model effectively identified the flashover in compartment fires, with an average relative error of 4.1 % for temperature prediction and 11.2 % for radiative heat flux prediction. In addition, the model was validated on other simulated fire cases and full-scale experimental data, and the results showed good performance. In this paper, the sensitivity of the model to lead time was analyzed, and the application range of the model was determined. The model performed well within the lead time of 25s. In view of the strong performance of the proposed deep learning model in predicting flashover based on wearable sensors (temperature and radiative heat flux), it is believed that this model holds potential for application in a broader range of fire scenarios. This demonstrates the feasibility of using deep learning artificial intelligence models to predict compartment fire development, providing scientific guidance for smart firefighting technology.

Development and testing of a thermal self-straining preloading test setup for reinforced concrete beams and slabs to perform thermomechanical action

PurposeAt this moment, there is substantial anxiety surrounding the fire safety of huge reinforced concrete (RC) constructions. The limitations enforced by test facilities, technology, and high costs have significantly limited both full-scale and scaled-down structural fire experiments. The behavior of an individual structural component can have an impact on the entire structural system when it is connected to it. This paper addresses the development and testing of a self-straining preloading setup that is used to perform thermomechanical action in RC beams and slabs.Design/methodology/approachThermomechanical action is a combination of both structural loads and a high-temperature effect. Buildings undergo thermomechanical action when it is exposed to fire. RC beams and slabs are one of the predominant structural members. The conventional method of testing the beams and slabs under high temperatures will be performed by heating the specimens separately under the desired temperature, and then mechanical loading will be performed. This gives the residual strength of the beams and slabs under high temperatures. This method does not show the real-time behavior of the element under fire. In real-time, a fire occurs simultaneously when the structure is subjected to desired loads and this condition is called thermomechanical action. To satisfy this condition, a unique self-training test setup was prepared. The setup is based on the concept of a prestressing condition where the load is applied through the bolts.FindingsTo validate the test setup, two RC beams and slabs were used. The test setup was tested in service load range and a temperature of 300 °C. One of the beams and slabs was tested conventionally with four-point bending and point loading on the slab, and another beam and slab were tested using the preloading setup. The results indicate the successful operation of the developed self-strain preloading setup under thermomechanical action.Research limitations/implicationsGaining insight into the unpredictable reaction of structural systems to fire is crucial for designing resilient structures that can withstand disasters. However, comprehending the instantaneous behavior might be a daunting undertaking as it necessitates extensive testing resources. Therefore, a thorough quantitative and qualitative numerical analysis could effectively evaluate the significance of this research.Originality/valueThe study was performed to validate the thermomechanical load setup for beams and slabs on a single-bay single-storey RC frame with and without slab under various fire possible scenarios. The thermomechanical load setup for RC members is found to be scarce.