Fire TechnologyPub Date : 2025-02-20DOI: 10.1007/s10694-025-01709-x
Prateep Chatterjee, Karl V. Meredith, Justin A. Geiman, Yi Wang
{"title":"Sprinkler Protection of Storage under Sloped Ceilings—Part 1: Numerical Modeling","authors":"Prateep Chatterjee, Karl V. Meredith, Justin A. Geiman, Yi Wang","doi":"10.1007/s10694-025-01709-x","DOIUrl":"10.1007/s10694-025-01709-x","url":null,"abstract":"<div><p>In the present study, a numerical model-based investigation has been conducted to understand the automatic sprinkler protection challenges associated with sloped ceilings. The modeling study has been conducted using the computational fluid dynamics (CFD) code FireFOAM. Ceiling jets resulting from growing fires on a 3-tier high cartoned unexpanded plastic (CUP) rack-storage commodity have been simulated to investigate the effect of ceiling slope and obstruction (purlin) depth on sprinkler activations. For quick-response, ordinary temperature-rated sprinklers, simulation results show that for the fire source being evaluated, ceilings with <span>(le 18^circ)</span> inclination and purlin depths of <span>(le 0.2)</span> m have similar activation times and patterns as non-sloped ceiling for the four sprinklers immediately adjacent to the fire source. Spray transport simulations have also been conducted to evaluate the effect of ceiling slope and sprinkler installation orientations on water flux distributions. Results indicated that the sprinkler deflector parallel to the floor is a preferable orientation.\u0000</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 5","pages":"2901 - 2923"},"PeriodicalIF":2.4,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-19DOI: 10.1007/s10694-025-01714-0
Shariful Islam Tushar, Sumit Mandal, Ishmam Zahin Chowdhury, Adriana Petrova, Lynn M. Boorady, Robert J. Agnew
{"title":"Thermal Protective Performance of Oil and Gas Field Workers’ Clothing: A Review","authors":"Shariful Islam Tushar, Sumit Mandal, Ishmam Zahin Chowdhury, Adriana Petrova, Lynn M. Boorady, Robert J. Agnew","doi":"10.1007/s10694-025-01714-0","DOIUrl":"10.1007/s10694-025-01714-0","url":null,"abstract":"<div><p>Over half of the world’s countries produce oil and gas, which occasionally leads to fatalities and injuries, specifically skin burns among workers in the oil and gas fields (OGFs) due to fire hazards, i.e., flash fire. Hence, flame-resistant clothing (FRC) is a requirement for OGF workers. To ensure safety, it’s important to regulate and verify the thermal protective performance (TPP) of FRCs, which depends on their constituent materials (i.e., fiber, yarn, and fabric). Also, the workplaces of OGFs are full of multiple oily substances, including hazardous and flammable liquids, i.e., crude oil, drilling fluid, pipe dope, etc. Most workers frequently come into contact with these substances, which can contaminate their FRCs and affect their TPP. This article provides a systematic review of how the physical and mechanical factors of fiber, yarn, fabric, and clothing design impact the TPP of FRC. Also, the presence of different substances in the OGF and their impact on the TPP has been thoroughly discussed to provide a holistic understanding of the parameters influencing the TPP. Additionally, the current limitations and challenges of FRC have been described, along with potential solutions that can benefit future research to improve the TPP of OGF workers’ protective clothing.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 5","pages":"3025 - 3067"},"PeriodicalIF":2.4,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Interpretability Analysis Framework to Enhance Deep Learning Model Transparency: With a Study Case on Flashover Prediction Using Time-Series Sensor Data","authors":"Linhao Fan, Qi Tong, Hongqiang Fang, Wei Zhong, Wai Cheong Tam, Tianshui Liang","doi":"10.1007/s10694-025-01713-1","DOIUrl":"10.1007/s10694-025-01713-1","url":null,"abstract":"<div><p>Deep learning model has been a viable approach to forecast critical events in fire development. However, prior to its implementation in real-life firefighting, it is imperative to further understand the black box and assess its rationale. In this paper, an interpretability analysis framework was proposed to reliably enhance the transparency of deep learning models in time series. The framework was applied to a flashover forecasting model as a case study, including employing an interpretability method to obtain attributions and adapting the evaluation metrics to validate the method’s effectiveness and determine its optimal parameter setting for the model. Results show that the use of the interpretability method, named DeepLIFT, can provide precise attributions to the model inputs in both temporal and spatial domains. Based on the quantitative analysis, suitable parameters were found and the relevance of the attribution results to the model decision was validated, which means the attribution results are reliable to be utilized to interpret the model. It is believed this work would contribute to bringing trustworthy deep learning models for fire research.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 5","pages":"2999 - 3024"},"PeriodicalIF":2.4,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-12DOI: 10.1007/s10694-025-01711-3
Mohd Zahirasri Mohd Tohir, César Martín-Gómez
{"title":"Evaluating Fire Severity in Electric Vehicles and Internal Combustion Engine Vehicles: A Statistical Approach to Heat Release Rates","authors":"Mohd Zahirasri Mohd Tohir, César Martín-Gómez","doi":"10.1007/s10694-025-01711-3","DOIUrl":"10.1007/s10694-025-01711-3","url":null,"abstract":"<div><p>This study provides a comprehensive statistical analysis of heat release rate (HRR) profiles in electric vehicles (EVs) and internal combustion engine (ICE) vehicles, addressing fire safety challenges in performance-based design. Using experimental data, key parameters such as peak heat release rate (PHRR), time to peak heat release rate (TPHRR), total heat released (THR), and growth coefficients were analysed. Results reveal that EVs, exhibit distinct fire dynamics, often displaying higher PHRR values than ICE vehicles, which highlights the potential for greater fire intensity and growth rates in EV fires. A design fire model was constructed based on this analysis, offering fire engineers a probabilistic alternative to conventional deterministic approaches for simulating vehicle fire scenarios in various infrastructural contexts. This probabilistic approach provides a more flexible framework for decision-making in fire risk assessments. Additionally, the study observed a correlation between larger battery sizes and increased fire severity in EVs, though this should be interpreted cautiously given the limited dataset. This work highlights the importance of adapting fire safety standards to keep pace with advancements in vehicle technology, especially with the growing prevalence of EVs. Future research should aim to expand the dataset with more diverse experiments to enhance the robustness of design fire models, supporting the development of tailored fire safety strategies for different vehicle types across various environments.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 5","pages":"2957 - 2998"},"PeriodicalIF":2.4,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10694-025-01711-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-12DOI: 10.1007/s10694-025-01710-4
Ravikant Singh, Avik Samanta
{"title":"Fire-Induced Thermal Gradients in Cold-Formed Steel Flexural Members: A Numerical Parametric Study for Structural Application","authors":"Ravikant Singh, Avik Samanta","doi":"10.1007/s10694-025-01710-4","DOIUrl":"10.1007/s10694-025-01710-4","url":null,"abstract":"<div><p>The cold-formed steel (<i>CFS)</i> members are highly susceptible to the fire and the presence of full or partial insulation can significantly influence the overall thermal profile of the member. Unlike uniformly heated members, a gradient thermal exposure can reduce the member’s mechanical properties unevenly. This study investigated the effects of uniform and gradient thermal exposure on the structural behaviour of flexural members. The non-linear finite element (<i>FE</i>) model is developed and validated with the experimental and numerical results available in the existing literature. A series of numerical <i>FE</i> parametric studies on 1425 members is performed considering several member geometry and spans ranging for different beams covering non-dimensional slenderness ranging from 0.28 to 1.81. Two common loading patterns (4-point loading and uniform moment) and five thermal distribution patterns are considered, covering thermal bowing in the direction of loading as well as in opposite to that. Results of the extensive parametric study indicate the fact that the failure temperature of the member is largely dependent on the applied thermal profile of the member. Parameters like depth of the member cross-section, non-dimensional slenderness and thermal bowing of the member, which largely influenced the critical temperature of the CFS flexural member, are studied in detail. In several cases, the failure temperature of a partially heated member can be lower than that of the member fully exposed to fire. Parametric study results also highlighted the fact that the existing limiting temperature of 350° of the European design rules (Eurocode 3, Part 1.2) for CFS members is highly over-conservative.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 5","pages":"2925 - 2955"},"PeriodicalIF":2.4,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-11DOI: 10.1007/s10694-025-01702-4
Tao Li, Jianing Yuan, Wenxuan Zhao, Yuchun Zhang, Xiaosong Li, Longfei Chen, Yunping Yang
{"title":"Prediction-Inversion Models of Tunnel Fires by Tunnel Flame Images Under Machine Learning","authors":"Tao Li, Jianing Yuan, Wenxuan Zhao, Yuchun Zhang, Xiaosong Li, Longfei Chen, Yunping Yang","doi":"10.1007/s10694-025-01702-4","DOIUrl":"10.1007/s10694-025-01702-4","url":null,"abstract":"<div><p>In this paper, a machine learning-based tunnel fire prediction-inversion model is proposed to solve the dynamic evolution relationship model of fire image-ceiling temperature-heat radiation-heat release rate, which is difficult to establish from mathematical relationships. And the caution of fire data is primally due to the difference and high cost associated with conducting real-scale tunnel fire experiments. In order to establish a fire information database, this paper conducted fire experiments in 1:10 scale tunnels, collected fire parameters such as roof temperature, thermal radiation, heat release rate and flame images under different scale tunnel fires, and constructed a fire database. Subsequently, a neural network prediction model for tunnel fires based on machine learning was proposed. The prediction model is able to predict the development of tunnel fires. Meanwhile, the tunnel fire inversion model was established by recognizing the inversion of the prediction results and obtaining other fire parameters such as the heat release rate of the fire source corresponding to the image. The dynamic correlation of information such as flame image-heat release rate-fire temperature-heat flux was realized. The prediction accuracy of the model reaches 90% in terms of indicators such as mean absolute error and structural similarity index. The model can be used as a prediction method to guide fire suppression and rescue operations in tunnel fires.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 4","pages":"2689 - 2711"},"PeriodicalIF":2.4,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-11DOI: 10.1007/s10694-025-01701-5
Bartosz Miechówka, Wojciech Węgrzyński
{"title":"Systematic Literature Review on Passenger Car Fire Experiments for Car Park Safety Design","authors":"Bartosz Miechówka, Wojciech Węgrzyński","doi":"10.1007/s10694-025-01701-5","DOIUrl":"10.1007/s10694-025-01701-5","url":null,"abstract":"<div><p>To allow future creation of knowledge-based design fire scenarios for car fires, a systematic literature review was performed. Keywords “fire + passenger vehicle” and “fire + car” were filtered in Scopus, Science Direct and Web of Science databases for 1990–2024 period yielding 11 papers containing relevant data. A further citation mining on references revealed another 33. A total of 148 individual records of fire experiments were identified, with records of the heat release rate (or mass loss rate), total heat release and time to reach peak heat release rate. The database was subdivided by the car size and drivetrain, as well by the age of experiments. Analysing the course of experiments, common phases of fires have been identified, leading to another sub-division of the database by the location of the ignition source. It was found that fires initiated from the underneath the car did lead to higher peak HRR and a shorter time to peak compared to fires starting at other locations. Statistical distributions of peak HRR, time to peak HRR and THR are given for each sub-set of data. The average Heat of Combustion value of 25 MJ/kg (± 7 MJ/kg) was identified for the entire dataset.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 4","pages":"2651 - 2688"},"PeriodicalIF":2.4,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10694-025-01701-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-11DOI: 10.1007/s10694-024-01686-7
Yansheng Song, Guang Xiao, Haoran Wang
{"title":"Machine Learning Based Flashover Prediction Models Using Synthetic Data and Fire Images","authors":"Yansheng Song, Guang Xiao, Haoran Wang","doi":"10.1007/s10694-024-01686-7","DOIUrl":"10.1007/s10694-024-01686-7","url":null,"abstract":"<div><p>Flashover is a sudden fire propagation that occurs within a room, where all items in the room bursting into the fire, making it one of the main causes of casualties. This paper presents the development of two models, the Ensemble of Long Short-Term Memory (E-LSTM) and the Ensemble of Gated Recurrent Unit (E-GRU), for predicting the occurrence of flashover in various compartment structures, and the development of Vision Transformer (ViT) to calculate the heat release rates in fire images supports the practical application of E-LSTM and E-GRU. Synthetic data from 1500 fire cases were collected, including temperature, heat release rates, oxygen volumetric fractions, carbon dioxide volumetric fractions, compartment floor area, and vent area, covering a wide range of fire scene conditions. ViT was trained on 4860 fire images, R<sup>2</sup> value of 0.9117 demonstrates the model accurately acquires the heat release rate in fire. E-LSTM and E-GRU, comprising 11 LSTM and GRU sub-models, achieved average accuracies of 94.88% and 95.76% respectively. In real fire scenario tests, E-LSTM and E-GRU exhibited accuracies of 88.31% and 93.90%, showcasing their ability to predict flashover occurrences with a high degree of precision within a 60 s lead time. The results of this study indicate that the proposed machine learning models E-LSTM, E-GRU, and ViT can provide support for smart firefighting, reducing casualties and property losses.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 4","pages":"2389 - 2413"},"PeriodicalIF":2.4,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fire TechnologyPub Date : 2025-02-11DOI: 10.1007/s10694-025-01706-0
Elvan Sahin, Peter Henkes, Bruno P. Serrao, Mohammed A. Allaf, Brian Y. Lattimer, Juliana P. Duarte
{"title":"Development of HRR Distributions in Electrical Enclosure Fire Scenario Through Machine Learning","authors":"Elvan Sahin, Peter Henkes, Bruno P. Serrao, Mohammed A. Allaf, Brian Y. Lattimer, Juliana P. Duarte","doi":"10.1007/s10694-025-01706-0","DOIUrl":"10.1007/s10694-025-01706-0","url":null,"abstract":"<div><p>Electrical enclosure fire scenarios represent a major hazard in nuclear facilities, underscoring the critical need to reduce its uncertainties in risk assessments. This study aims to refine and enhance peak heat release rate (HRR) distributions of electrical enclosure fires using a machine learning (ML) approach by quantifying the uncertainties of existing data analysis, thereby improving the reliability of fire probabilistic risk assessments (PRAs). Utilizing data from over 100 enclosure fire experiments, an artificial neural network (ANN) model was developed, achieving an R<sup>2</sup> of 0.85, RMSE of 21.70 kW, and MAE of 14.69 kW. SHapley Additive Explanations (SHAP) analysis evaluated the importance of input features, including ignition source, cabinet properties, cable properties, and ventilation conditions. The refined model provided denser peak HRR data, enriching cumulative function distributions. A Monte Carlo (MC) interface was integrated with the ML model applying 5%, 15%, and 25% uncertainties to input parameters. Sensitivity analysis, including Sobol indices, clarified the impacts of input uncertainties on model outputs. This 'MC-ML UQ Framework' was compared with current recommendations, demonstrating its contribution in the analysis of electrical enclosure fires in nuclear facilities.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 5","pages":"2843 - 2864"},"PeriodicalIF":2.4,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Progressive Collapse of Steel Frames in Fire Using Hybrid Models with Explicit Formation of Connections","authors":"Liang Yin, Yifan Cao, Jian Jiang, Haifeng Li, Wei Chen, Jihong Ye, Xian Wu","doi":"10.1007/s10694-025-01700-6","DOIUrl":"10.1007/s10694-025-01700-6","url":null,"abstract":"<div><p>Failure of beam-column connections is one of the main reasons for progressive collapse of steel structures under fire. The computation cost in a high-fidelity model is becoming an issue for accurately considering the effect of connections on structural collapse. A hybrid model of steel frame that integrates solid elements for simulating top-and-seat-angle with double web-angle (TSDW) connections and beam elements for other components is presented in this study, and its performance efficiency is confirmed. The collapse behavior of steel frames simulated by the hybrid model is investigated by addressing the effect of load ratios, connection forms, number of TSDW connections and fire scenarios. It is found that the proposed hybrid modeling method can accurately and efficiently predict the collapse mode and collapse temperature of structures in fire. The collapse temperature of structures decreases in a range of 11% to 45% with the increase of load ratio by an interval of 0.3. The form of connections has a great impact on the collapse behavior of steel frames. The collapse modes of steel frames significantly depend on the fire-exposed area, and it is necessary to define a set of real fire scenarios for accurately predicting realistic collapse behavior of steel frames in fire.</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"61 4","pages":"2621 - 2649"},"PeriodicalIF":2.4,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145164022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}