Building Fire Research Articles

An investigation using resampling techniques and explainable machine learning to minimize fire losses in residential buildings

Urban residential fires seriously threaten public safety, causing significant property damage and severely impacting urban sustainability. To enhance the understanding of urban residential fire risks, a framework that combines tree-based machine learning algorithms and resampling techniques is proposed to predict damage and casualties in residential building fires. All algorithms achieved similar results on the original dataset, with 86 % and 93 % accuracy and the highest average F1 scores of 61 % and 51 %, respectively. Various resampling techniques addressed the issue of data imbalance, with the combination of random undersampling and SMOTE achieving the best model performance, elevating the average F1 scores to 75 % and 77 %, representing improvements of 14 % and 26 % over the original dataset, respectively. Furthermore, the internal mechanisms of the model were explored using the explainable Shapley additive explanations, which identified the key features influencing model outputs. Additionally, the study revealed significant heterogeneity in different regions, sources of ignition, causes of fires, types of residences, locations of fire origin, and types of households. This research not only improves emergency response strategies for urban residential fires but also provides tailored fire safety policies to reduce risks in various urban environments effectively.

Machine learning-driven real-time identification of large-space building fires and forecast of temperature development

In firefighting, real-time knowledge of fire dynamics is crucial yet often unavailable. The building geometry and measured gas temperatures are integrated to ascertain fire states and predict temperature evolution, utilizing a machine learning framework that combines long short-term memory networks and transfer learning. The model is pre-trained on datasets with 1000 samples from parametric fire models and 200 from field simulations, enabling real-time predictions with on-site data. Numerical simulations in portal frame buildings demonstrate over 95% accuracy in identifying fire states and 90% in predicting gas temperatures. A method using correlation coefficients and standard deviations effectively detects damaged thermocouples with over 96% accuracy, given a damage ratio below 30%. Validation in two real fire scenarios showed more than 92% accuracy in locating fires and over 89% in forecasting gas temperatures 20 min ahead, which costs 2.14 s and 1.83 s, respectively. The machine learning framework also exhibits robustness to changes in ventilation conditions by making temperature predictions using reliability theory. The proposed framework provides clear information about the state and development of the fire to firefighters and is useful for promoting smart firefighting.

Multifactor dynamic coupled model for building fire evacuation: Case study of the Karamay Friendship Palace fire

Occupant evacuation during a building fire is a complex system that includes several highly coupled subsystems, such as building characteristics, occupant characteristics, fire behavior, and evacuation behavior. To study the interaction mechanism between these subsystems to maximize occupant safety during fire evacuation in a building, a multifactor dynamic coupled model based on the Fire Dynamic Simulator and floor field cellular automata model for occupant evacuation in a fire was established. In the model, the dynamic impact of smoke diffusion on occupant movement direction and speed, decrease in occupant health points caused by smoke and trampling, and changes in occupant exit choices in the presence of closed exits were considered in detail. The catastrophic fire accident in the Friendship Palace of Karamay, Xinjiang, China, in 1994 was used as the analysis case, in which the spatial model of the Friendship Palace was reconstructed according to real data and architectural design methods. The safety exits open or closed, radius Rtra, possibility of information transmission Psuc, and wait time twait were discussed to study the influence of these parameters on the evacuation process and results. The study shows that the model could reproduce a fire accident well with Rtra = 4, Psuc = 0.5, and twait = 30. The closed exits increased evacuation time by over 120.3 % and resulted in 439 deaths. These conclusions are important for providing better estimates, guiding architectural designs, and enhancing building safety management.

Optimizing phased-evacuation strategy for high-rise buildings in fire

Evacuation in high-rise buildings is a critical safety issue due to multiple floors and high occupant density. Phased evacuation strategies can mitigate this challenge. This research focuses on developing optimal phased evacuation strategies to enhance occupant safety during high-rise building fires. The study demonstrates these strategies in a 25-story building, housing 2400 individuals, across various scenarios. To simulate fire and smoke development, a two-zone model is employed to analyze behavior within the building. Pedestrian evacuation scenarios are simulated using Pathfinder and a mathematical model, providing insights into individual movements and congestion during evacuation to analyze different phased evacuation strategies. Findings underscore the importance of smoke flow and pedestrian motion in optimizing phased evacuation strategies. The modeling results show that implementing the optimal strategy can lead to a 65 % reduction in staircase congestion time. This study provides a quantitative analysis of high-rise building fires, considering dynamic fire and evacuation evolution. It emphasizes the importance of phased evacuation strategies and advocates for their real-life application. This research enhances the understanding of high-rise building evacuations to improve safety measures and provides a robust framework for optimizing evacuation strategies by integrating fire modeling. This study demonstrates the effectiveness of phased evacuation and paves the way for future applications to ensure occupant safety in fire emergencies.

Numerical simulation and safety assessment of fires in historic timber structures based on fire load investigation

Historic timber structures face substantial fire loads and complex fire risks. Subsequent renovations and utilization may influence their fire safety performance. Therefore, accurately predicting indoor fire development in historic buildings and assessing their fire safety performance is crucial. Numerical fire simulation is currently at the forefront of analyzing and assessing fire risks in historic buildings. However, there is a shortage of globally accessible historic building fire data. This paper proposes a method to determine fire scenarios, peak heat release rates, and development curves of indoor fires in wooden historic buildings through a fire load investigation. Using the Guangzhou ancestral hall as an example, PyroSim fire dynamics simulation software is employed to calculate fire development and assess the available safe evacuation time. The simulation results are subsequently input into the Pathfinder evacuation simulation software to ascertain the required safe evacuation time for indoor occupants. A comparative assessment is conducted to evaluate the fire safety performance before and after the renovation of historic buildings. The research findings indicate that installing closed glass curtain walls in the courtyards of ancestral hall buildings in Guangzhou accelerates the infiltration of smoke during fires, leading to rapid fire spread and long-distance ignition, significantly reducing the time available for safe evacuation. Therefore, when renovating and utilizing the ancestral hall buildings in Guangzhou, the installation of ventilation and smoke extraction systems should be prioritized to slow down fire development. Additionally, controlling the number of indoor occupants is an effective management measure to mitigate fire damage in historic buildings.

Evaluating the Combustion Performance of the Usual Timbers in Furniture Using a Grey Correlation Method Based on Thermolysis, Ignition, and Flame Spread

Timber is the most widely used material for furniture in view of its characteristics of light mass, high strength, easy processing, coloring, and decorative appearance. However, the flammability of wood has been frequently associated with increased fire intensity and the rapid spread of fire in buildings. In this paper, the combustion performance of six kinds of common furniture timber was investigated based on thermogravimetric analysis at 25–500 °C, cone calorimetry with 50 kW/m2 thermal radiation intensity, and flame spread experiments with 3 kW/m2 thermal radiation intensity. The ignition, weight loss, thermogenesis, smoke, and flame spread characteristics of these timbers were obtained. Subsequently, a comprehensive index system including thermal stability, heat release ability, smoke production capacity, and flame spreading speed was constructed to evaluate the combustion performance of the selected timbers. In addition, a grey correlation method relying on the game theory to assign weight was proposed for the quantitative analysis of the relevant evaluation indexes. As a result, the combustion performance of the six kinds of timber, which was defined as a specific value from poor to good, was as follows: pine (0.8696) > Chinese fir (0.8568) > Oriented Strandboard (OSB) (0.8425) > density board (0.8122) > plywood (0.8087) > elm (0.7909). Timber with poor combustion performance contributes to the reduction in fire risk in buildings. Our suggestions are of great significance for selecting furniture timber from the perspective of the prevention and control of building fires.

Bibliometrics Analysis Of The Resistance Of Steel Materials In Building Structures To Fire

Fire is the out-of-control burning method of flammable substances, which includes wood, paper, plastic, fuel, or different substances, which produce heat, mild smoke, and toxic gases. Fires can occur, including woodland fires caused by lightning or because of human activities, along with building fires due to electric short circuits or errors in the use of fire. In building design, it is miles vital to apprehend the elements that cause fires and the fireplace's resistance to materials. Metal is a form of metallic made from a primary mixture of iron (Fe) and carbon (C), with the amount of carbon typically being much less than 2 per cent of its general weight. Steel is a very common fabric used in a spread of applications due to its aggregate of robust, long-lasting, and malleable properties.

The Dynamic Change in the Reliability Function Level in a Selected Fire Alarm System during a Fire.

This article discusses fundamental issues associated with the functional reliability of selected fire alarm systems (FASs) in operation during building fires. FASs operate under diverse external or internal natural environmental conditions, and the operational process of FAS should take into account the impacts of physical phenomena that occur during fires. Their operation is associated with the constant provision of reliability. FAS designers should also consider the system's reliability when developing fire control matrices, tables, algorithms, or scenarios. All functions arising from an FAS control matrix should be implemented with a permissible reliability level, RDPN(t), prior to, as well as during, a fire. This should be assigned to the controls saved in the fire alarm control unit (FCP). This article presents the process by which high temperatures generated during a fire impact the reliability of FAS functioning. It was developed considering selected critical paths for a specific scenario and the control matrix for an FAS. Such assumptions make it possible to determine the impact of various temperatures generated during a fire on the reliability of an FAS. To this end, the authors reviewed that the waveform of the R(t) function changes for a given FAS over time, Δt, and then determined the fitness paths. The critical paths are located within the fire detection and suppression activation process, using FAS or fixed extinguishing devices (FEDs), and the paths were modeled with acceptable and unacceptable technical states. The last section of this article defines a model and graph for the operational process of a selected FAS, the analysis of which enables conclusions to be drawn that can be employed in the design and implementation stages.

Common incidents and prevention of urban water supply pipeline accidents

With rapid urbanization, urban water supply pipeline accidents have become increasingly prevalent. Understanding their common occurrences and prevention strategies is crucial for ensuring water safety. This study aims to explore the underlying causes of such incidents, ranging from ageing infrastructure to design flaws and construction issues. By analyzing existing preventive measures and international best practices, this research seeks to contribute to the development of effective strategies for mitigating urban water supply pipeline accidents. This thesis focuses on urban water supply pipeline accidents, addressing both common incidents and preventive measures. It begins by highlighting the unique challenges of fires in high-rise buildings, including their rapid spread and the difficulties in evacuating occupants. The paper then emphasizes the importance of innovative fire-resistant materials, classifying them into various types such as phenolic, sprayed, calcium silicate, and lightweight composite materials. Each type is explored in detail, discussing their properties and potential applications. Finally, the paper outlines the practical use of these materials in fire engineering, emphasizing their role in enhancing the safety and resilience of urban infrastructure. Overall, this thesis contributes valuable insights to understanding and mitigating the risks associated with urban water supply pipeline accidents, promoting disaster prevention and management efforts.

АНАЛИЗ ОТЧЕТОВ ПО РЕЗУЛЬТАТАМ РАСЧЕТОВ ПОЖАРНЫХ РИСКОВ НА ОБЪЕКТЫ ЗАЩИТЫ ПРИ ПРОИЗВОДСТВЕ СУДЕБНЫХ ПОЖАРНО-ТЕХНИЧЕСКИХ ЭКСПЕРТИЗ ПО КРУПНЫМ РЕЗОНАНСНЫМ ПОЖАРАМ В ХОДЕ УГОЛОВНОГО И АРБИТРАЖНОГО ПРОЦЕССА

The most important aspects affecting the analysis of reports on the results of fire risk calculations performed in the framework of the preparation of special technical specifications and design documentation for warehouse facilities are considered. The analysis was performed during the forensic fire and technical investigations of fires in warehouse buildings, including those with the installed multi-tier mezzanines. The fragments of calculations included in the special technical conditions are studied and provided below. Measures aimed at improving the quality of risk calculations are proposed.

BIM-based augmented reality navigation for indoor emergency evacuation

Recently, there has been a growing interest in utilizing augmented reality (AR) technology for indoor emergency evacuation guidance. This study aims to determine whether AR navigation can be intuitively recognized by occupants in a fire situation compared to 2D navigation. An AR navigation system based on Building Information Modeling (BIM) was implemented. Objective assessments using eye-tracking technology and measuring the walking speeds were performed, as well as subjective identifications based on surveys. Comparisons were made between AR navigation and traditional 2D navigation. Results indicated that 88.6% of participants perceived the AR navigation system as offering a simpler and more intuitive path for evacuation. Both navigation systems were considered user-friendly and easy to understand. However, 2D navigation was found to be unsuitable for vulnerable populations. The AR navigation system led to a slight decrease in the walking speed, but it significantly reduced the time required to navigate after encountering stairs and exhibited a faster restart time in emergency scenarios. Both navigation systems proved effective without the need for additional signage beyond the provided maps. Nonetheless, the 2D navigation system may require supplementary information beyond what is readily available on mobile devices. These findings highlight the potential of augmented reality navigation as an intuitive solution for indoor emergency evacuation, contributing to enhanced occupant safety during building fires.

Greenhouse gas emissions related to fires in photovoltaic installations

Life cycle assessments, LCA, can be made on all types of materials and products where the total environmental impact of the production, use and end-of-life is quantified. By including fire as one potential end-of-life scenario, the emissions related to these, and potential benefits from reducing the risk of fire can be quantified. The question addressed in this article is how fires in photovoltaic (PV) installations affect the environmental impact in a life cycle perspective. This will be evaluated by using a methodology called Fire-LCA that is based on standard LCA according to ISO 14040. The total emissions from PV-related fires in buildings and the emissions related to rebuilding and replacing the damaged materials normalised over the amounts of produced electric energy are calculated to 0.3 g CO2eq/kWh. This is two orders of magnitude lower than the typical 43.6 g CO2eq/kWh for the normal life cycle of PV installations. This comparison puts the environmental impact of PV-related fires in perspective and underlines that PV installations still make a large positive impact on the reduction of CO2eq-emissions from electricity production even though they represent a certain fire hazard.

Facade flame depth coming out from the fire compartment opening subject the external sideward wind

When a fuel leakage/energy release (i.e., combustion, fire) inside a compartment, the external facade flame characteristics through opening are of great significance for protecting human life and property, as well as assessment of its risk and impact to urban environment. This work investigates facade flame depth coming out from fire compartment opening with fuel combustion/energy release inside the compartment for under-ventilated condition under sideward wind, which is a fundamental parameter in describing facade morphological characteristics in particular building fire, meanwhile still no work can be found in previous studies. Results show that, as sideward wind speed increases, the flame depth first increases a bit then decreases significantly. A CFD simulation is carried out to understand flow field controlling facade flame depth under windless and sideward wind situations. A physical analysis is presented on account of mechanisms of complex interaction among sideward wind inertial, outflow momentum through opening, and flame buoyancy flux are proposed based on controlling mechanisms, which well represents the facade flame depth by a non-dimensional function under sideward wind condition. This study makes an important new contribution comparing with previous knowledge, and has potential practical value for fuel combustion inside confined space and the corresponding numerical model verification.

The Impact of Air-Tightness on Smoke Transport During High-Rise Building Fires Under Low-Temperature Conditions

The Impact of Air-Tightness on Smoke Transport During High-Rise Building Fires Under Low-Temperature Conditions

Study on Building Types and Fire and Evacuation Safety Reference Guidelines for Quarantine Hotels in Taiwan

<p>國內目前對於防疫旅館之防火避難安全尚未有明確可供依循的規範或指引，本研究以「申請即排序與規劃」的源頭控管概念出發，將防疫旅館進行建築類型化與排序，再配合疫情狀況彈性收斂為「優先組」、「次優組」與「候補組」，並依各群組特性擬訂其所需之申請審查要項。建議防疫旅館以獨棟型為優先、低層型次之，如為單梯應注意要規劃兩方向逃生動線；為複合中高層型時，其他樓層用途單純者為佳，且須確實執行共同防火管理；複合中高層（閒置）則為最不建議之類型。除建築類型評估外，尚應考量設備與消防救助之條件是否符合基本條件，並依據建築類型分組之特性訂定防疫旅館的申請評估要項。最後以「申請即排序與規劃」、 「使用要維護管理與自主評核」、「查核有專業檢查與稽查」三個核心概念出發，研擬「防疫旅館防火避難安全參考指引」。</p> <p> </p><p>This study starts with the concept of "application, namely ranking and planning". After separating by building type, group the types into “Priority Group”, “Sub-Prime Group”, and “Alternative Group” according to the current COVID-19 situation, and plan the required application review items based on the features of each group. It is recommended that quarantine hotels prioritize independent buildings and then lower-floor hotels. For multi-purpose medium-high floor, other floors are better for simple purposes, and common fire escape management must be implemented. Multi-purpose medium-high floor (vacant) are the least recommended type. In addition, due to the complex fire protection and evacuation features of quarantine hotels, it is important to consider whether the conditions for equipment and fire rescue are met. Finally, start with the three core concepts of "application, namely ranking and planning", "maintenance, management, and self-assessment are needed during use", and "inspection, with professional checking and auditing", to research and plan the "Reference Guideline for Fire Evacuation Safety of Quarantine Hotels".</p> <p> </p>

DESIGN AND FABRICATION OF EMERGENCY FIRE RESCUE MACHINE

Building fires pose a serious risk to people, property and the environment. Numerous factors, such as human mistakes, electrical issues, heating systems, combustible items, might cause fire accidents. The effects of fire can be disastrous, resulting in accidents, fatalities, and significant building damage. Compared to fires in low-rise structures, high-rise building fire incidents pose numerous difficulties and a greater risk. High-rise building's vertical structures, greater resident capacity, and intricate infrastructure make fire fighters and evacuating residents more difficult to escape. It is essential to comprehend the causes, effects, and preventive strategies unique to high-rise fires in order to ensure occupant safety and reduce property damage. The disturbingly high rate of fire events, which are frequently brought on by inadequate fire prevention measures and damaged infrastructure, represent a serious threat to people's lives, their property, and the health of the economy. India can reduce the dangers connected with fire incidents in high-rise structures and guarantee the safety and well-being of its residents in the urban environment by giving priorityto the implementation of appropriate rescue systems. So in this project we are going to develop such machine which can help humans to get escape in the case of emergency situation in high rise building.

Artificial intelligence based smoke flow mechanism analysis and prediction patterns of fire for large space building

The deposition and dynamics of smoke layers in large-space building fires are governed by a complex interplay of factors, making the prediction of such dynamics using traditional mathematical models challenging. In response, this study introduces a Back Propagation (BP) neural network model, devised from field simulation data, to efficiently forecast the temporal progression of smoke layers. It was observed that the model exhibits minimal training errors and high processing speeds, thereby fulfilling the stringent accuracy demands of fire engineering. Specifically, the model achieved a minimum relative error of 0.0005 and a maximum of 0.0845 across various prediction points, underscoring its reliability and precision. The ability of this BP neural network model to predict smoke layer changes significantly enhances the design optimization of smoke control systems swiftly and accurately in large buildings and supports rapid, informed decision-making during fire emergencies. Moreover, the model facilitates the development of engineering calculation models tailored for the quick prediction of fire smoke dynamics, which are essential for both theoretical research and practical applications. This approach not only conserves experimental resources but also advances the implementation of scientific, effective rescue operations in the event of large space building fires.

Feasibility analysis of using CO2 as a building fire detection indicator

CO2 has rarely been examined as a fire indicator owing to the uncertainty in its background concentration. Nevertheless, for a specific building space with a detector, the background CO2 concentration signal can be determined and documented using artificial intelligence technology. Based on the aforementioned concept, this study explored the feasibility of using CO2 signal features as fire indicators for building fire detection. First, CO2 concentrations under fire and no-fire conditions were obtained to generate study databases. Second, the deep temporal clustering (DTC) model was used to classify CO2 signal features between fire and no-fire scenes, and the clustering accuracy and purity were selected to determine the clustering performance. Third, the k-means, agglomerative clustering, and spectral bi-clustering models were employed to validate the clustering advantages of the DTC model. The results proved the CO2 concentration to be more suitable as a combustion indicator for fire detection compared to the CO2 concentration rate, exhibiting higher clustering accuracy and purity values. Additionally, for time-series clustering, the DTC model outperformed traditional clustering models. The findings of this study represent a fundamental step toward the realization of space-exclusive multi-sensor fire-detection technology for assisting smart building construction in a cost-effective and accurate manner.

Multi-Objective Evcuation Planning Model Considering Post-Earthquake Fire Spread: A Tokyo Case Study

As an integral part of the 2030 Agenda for Sustainable Development, Disaster Risk Reduction (DRR) is essential for human safety and city sustainability. In recent years, natural disasters, which have had a tremendous negative impact on economic and social development, have frequently occurred in cities. As one of these devastating disasters, earthquakes can severely damage the achievements of urban development and impact the sustainable development of cities. To prepare for potential large earthquakes in the future, efficient evacuation plans need to be developed to enhance evacuation efficiency and minimize casualties. Most previous research focuses on minimization of distance or cost while ignoring risk factors. We propose a multi-objective optimization model with the goal of reducing the risk during the evacuation process, which is called the risk reduction model (RRM). Problem-specific indicators for screening optimal solutions are introduced. The research selects the Ogu area in Tokyo as a case study, where there is a relatively high density of wooden structures, increasing the risks of building collapse and fire spread after an earthquake, and is based on a two-phase evacuation flow that considers secondary evacuation for fire response. The results indicate that, in this case, RRM can, in most situations, reduce the risk level during the evacuation process and improve evacuation efficiency and success rate without significantly increasing the total evacuation distance. It proves to be superior to the traditional distance minimization model (DMM), which prioritizes minimizing the total distance as the objective function.

Advancing building fire safety through heat resistant and flame retardant hybrid silicone sealant

Rapid urbanization and population growth have led to a significant transformation in the urban landscape, characterized by the proliferation of high-rise buildings. However, this urban development has brought about new challenges, particularly in terms of fire safety. The escalating risk of disasters, especially fires, underscores the critical importance of implementing effective fire safety measures across all building types, necessitating legislative reforms. Despite their crucial role in ensuring structural integrity, sealants have often been overlooked in building safety standards, resulting in a lack of comprehensive regulations. The research addresses these challenges by focusing on the development of fire-resistant silicone sealants designed to enhance the fire resistance of building materials. These sealants were formulated independently, incorporating three fire retardants and four heat-resistant agents. While metal oxide flame retardants generally exhibited excellent performance, excessive mixing led to surface deformation and reduced workability. Optimal combinations of flame retardants and heat-resistant agents were identified, with the FR2 specimen demonstrating promising fire resistance performance. Full-scale fire performance tests conducted on FR2 revealed a maximum temperature difference of 40.6 °C between heated and unheated surfaces over a 2-h period, indicating high thermal insulation performance. These findings validate the efficacy of the proposed method and offer significant enhancements to building safety, thereby mitigating fire damage in urban environments.