Forest is an important resource for human survival, and forest fires are a serious threat to forest protection. Therefore, the early detection of fire and smoke is particularly important. Based on the manually set feature extraction method, the detection accuracy of the machine learning forest fire detection method is limited, and it is unable to deal with complex scenes. Meanwhile, most deep learning methods are difficult to deploy due to high computational costs. To address these issues, this paper proposes a lightweight forest fire detection model based on YOLOv8 (FFYOLO). Firstly, in order to better extract the features of fire and smoke, a channel prior dilatation attention module (CPDA) is proposed. Secondly, the mixed-classification detection head (MCDH), a new detection head, is designed. Furthermore, MPDIoU is introduced to enhance the regression and classification accuracy of the model. Then, in the Neck section, a lightweight GSConv module is applied to reduce parameters while maintaining model accuracy. Finally, the knowledge distillation strategy is used during training stage to enhance the generalization ability of the model and reduce the false detection. Experimental outcomes demonstrate that, in comparison to the original model, FFYOLO realizes an mAP0.5 of 88.8% on a custom forest fire dataset, which is 3.4% better than the original model, with 25.3% lower parameters and 9.3% higher frames per second (FPS).
{"title":"FFYOLO: A Lightweight Forest Fire Detection Model Based on YOLOv8","authors":"Bensheng Yun, Yanan Zheng, Zhenyu Lin, Tao Li","doi":"10.3390/fire7030093","DOIUrl":"https://doi.org/10.3390/fire7030093","url":null,"abstract":"Forest is an important resource for human survival, and forest fires are a serious threat to forest protection. Therefore, the early detection of fire and smoke is particularly important. Based on the manually set feature extraction method, the detection accuracy of the machine learning forest fire detection method is limited, and it is unable to deal with complex scenes. Meanwhile, most deep learning methods are difficult to deploy due to high computational costs. To address these issues, this paper proposes a lightweight forest fire detection model based on YOLOv8 (FFYOLO). Firstly, in order to better extract the features of fire and smoke, a channel prior dilatation attention module (CPDA) is proposed. Secondly, the mixed-classification detection head (MCDH), a new detection head, is designed. Furthermore, MPDIoU is introduced to enhance the regression and classification accuracy of the model. Then, in the Neck section, a lightweight GSConv module is applied to reduce parameters while maintaining model accuracy. Finally, the knowledge distillation strategy is used during training stage to enhance the generalization ability of the model and reduce the false detection. Experimental outcomes demonstrate that, in comparison to the original model, FFYOLO realizes an mAP0.5 of 88.8% on a custom forest fire dataset, which is 3.4% better than the original model, with 25.3% lower parameters and 9.3% higher frames per second (FPS).","PeriodicalId":12279,"journal":{"name":"Fire","volume":"130 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140235836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. T. Couto, Jean-Baptiste Filippi, R. Baggio, Cátia Campos, Rui Salgado
This study aimed to assess fire–atmosphere interactions using the fully coupled Meso-NH–ForeFire system. We focused on the Pedrógão Grande wildfire (28,914 ha), which occurred in June 2017 and was one of the deadliest and most damaging fires in Portugal’s history. Two simulations (control and fully coupled fire–atmosphere) were performed for three two-way nested domains configured with horizontal resolutions of 2 km, 0.4 km, and 0.08 km, respectively, in the atmospheric model Meso-NH. Fire propagation was modeled within the innermost domain with ForeFire, which solves the fire front with a 20 m resolution, producing the heat and vapor fluxes which are then injected into the atmospheric model. A simplified homogeneous fuel distribution was used in this case study. The fully coupled experiment helped us to characterize the smoke plume structure and identify two different regimes: (1) a wind-driven regime, with the smoke plume transported horizontally southward and in the lower troposphere, and (2) a plume-dominated regime, in which the simulated smoke plume extended vertically up to upper levels, favoring the formation of a pyro-cloud. The simulations were compared, and the results suggest that the change in the fire regime was caused by an outflow that affected the main fire front. Furthermore, the fully coupled simulation allowed us to explore the change in meteorology caused by an extreme fire, namely through the development of a pyro-cloud that also induced outflows that reached the surface. We show that the Meso-NH–ForeFire system may strongly contribute to an improved understanding of extreme wildfires events and associated weather phenomena.
{"title":"Triggering Pyro-Convection in a High-Resolution Coupled Fire–Atmosphere Simulation","authors":"F. T. Couto, Jean-Baptiste Filippi, R. Baggio, Cátia Campos, Rui Salgado","doi":"10.3390/fire7030092","DOIUrl":"https://doi.org/10.3390/fire7030092","url":null,"abstract":"This study aimed to assess fire–atmosphere interactions using the fully coupled Meso-NH–ForeFire system. We focused on the Pedrógão Grande wildfire (28,914 ha), which occurred in June 2017 and was one of the deadliest and most damaging fires in Portugal’s history. Two simulations (control and fully coupled fire–atmosphere) were performed for three two-way nested domains configured with horizontal resolutions of 2 km, 0.4 km, and 0.08 km, respectively, in the atmospheric model Meso-NH. Fire propagation was modeled within the innermost domain with ForeFire, which solves the fire front with a 20 m resolution, producing the heat and vapor fluxes which are then injected into the atmospheric model. A simplified homogeneous fuel distribution was used in this case study. The fully coupled experiment helped us to characterize the smoke plume structure and identify two different regimes: (1) a wind-driven regime, with the smoke plume transported horizontally southward and in the lower troposphere, and (2) a plume-dominated regime, in which the simulated smoke plume extended vertically up to upper levels, favoring the formation of a pyro-cloud. The simulations were compared, and the results suggest that the change in the fire regime was caused by an outflow that affected the main fire front. Furthermore, the fully coupled simulation allowed us to explore the change in meteorology caused by an extreme fire, namely through the development of a pyro-cloud that also induced outflows that reached the surface. We show that the Meso-NH–ForeFire system may strongly contribute to an improved understanding of extreme wildfires events and associated weather phenomena.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"100 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140236488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zeqi Wu, Kun Wang, Lin Shao, Huaitao Song, Kunpeng Liu
In a long and narrow corridor, the installation of roof smoke blocking structures is a measure to slow down the spread of fire smoke. When employing multiple smoke blocking structures, the spacing between these structures is a critical parameter that needs to be considered for optimal effectiveness. This paper analyzes the smoke blocking performance of double structures at different spacing and measures the smoke flow velocity both upstream and downstream of the double structures. According to the analysis of the smoke velocity vector obtained from numerical simulation, the smoke can be divided into three zones based on the flow state of the smoke after passing through the front smoke screen structure, namely the vortex zone, surge wave zone, and steady flow zone. When the rear smoke screen is located in the surge zone, the smoke blocking effect is optimal. Analysis of the morphology of the smoke layer indicates that the length of the vortex region is directly proportional to the upstream smoke flow velocity. The numerical and experimental results both indicate that an excessively large or small spacing between the structures fails to achieve optimal smoke control effectiveness. When the spacing is within an optimal range, the smoke velocity is the lowest. Finally, using a real architectural corridor as a case background, this paper presents a design example of roof smoke blocking structures. In order to arrange as many smoke blocking structures as possible, an appropriate spacing between the structures should be slightly larger than the vortex region. The smoke control effectiveness of multiple roof structures was validated through numerical simulation. As a result, the time required for smoke to pass through the corridor increases by 110 s.
{"title":"Research on the Optimal Spacing of Multiple Roof Smoke Blocking Structures in a Long Corridor","authors":"Zeqi Wu, Kun Wang, Lin Shao, Huaitao Song, Kunpeng Liu","doi":"10.3390/fire7030091","DOIUrl":"https://doi.org/10.3390/fire7030091","url":null,"abstract":"In a long and narrow corridor, the installation of roof smoke blocking structures is a measure to slow down the spread of fire smoke. When employing multiple smoke blocking structures, the spacing between these structures is a critical parameter that needs to be considered for optimal effectiveness. This paper analyzes the smoke blocking performance of double structures at different spacing and measures the smoke flow velocity both upstream and downstream of the double structures. According to the analysis of the smoke velocity vector obtained from numerical simulation, the smoke can be divided into three zones based on the flow state of the smoke after passing through the front smoke screen structure, namely the vortex zone, surge wave zone, and steady flow zone. When the rear smoke screen is located in the surge zone, the smoke blocking effect is optimal. Analysis of the morphology of the smoke layer indicates that the length of the vortex region is directly proportional to the upstream smoke flow velocity. The numerical and experimental results both indicate that an excessively large or small spacing between the structures fails to achieve optimal smoke control effectiveness. When the spacing is within an optimal range, the smoke velocity is the lowest. Finally, using a real architectural corridor as a case background, this paper presents a design example of roof smoke blocking structures. In order to arrange as many smoke blocking structures as possible, an appropriate spacing between the structures should be slightly larger than the vortex region. The smoke control effectiveness of multiple roof structures was validated through numerical simulation. As a result, the time required for smoke to pass through the corridor increases by 110 s.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"10 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dener Silva, Tiago Miguel Ferreira, Hugo Rodrigues
Climate change and human interventions can boost wildfires. Although naturally happening, massive events are becoming more frequent and severe. In Portugal’s mainland, many rural settlements are populated mainly by older people, and uninhabited houses are frequently poorly conserved. This combination leaves the Wildland–Urban Interface (WUI) dangerously exposed to the fires. Pursuing the understanding of WUI areas, this study applies the Wildland–Urban Interface Index (WUIX) assessment methodology to an area severely affected by the massive 2017 wildfire of Pedrógão Grande, Leiria, Portugal. The primary objective of this study was to compare the results from WUIX with the areas burned during the fire event. As a result, maps of WUI effect were generated, visually pointing to villages with higher severity compared to the others. A statistical analysis was performed in three villages from the region to validate the results by comparing the accuracy of the results obtained to the actual damages. The results point out a high correlation between the WUIX and the real scenario despite the apparent challenges in determining the variations in different types of fire effect. Finally, the WUIX results align with the data from the Pedrógão Grande wildfire, showing that some are promising in conjunction with other wildfire indicators.
{"title":"Assessing the Accuracy of the Wildland–Urban Interface Index in Portuguese Rural Villages’ Context: A Case Study of the 2017 Pedrógão Grande Wildfire","authors":"Dener Silva, Tiago Miguel Ferreira, Hugo Rodrigues","doi":"10.3390/fire7030090","DOIUrl":"https://doi.org/10.3390/fire7030090","url":null,"abstract":"Climate change and human interventions can boost wildfires. Although naturally happening, massive events are becoming more frequent and severe. In Portugal’s mainland, many rural settlements are populated mainly by older people, and uninhabited houses are frequently poorly conserved. This combination leaves the Wildland–Urban Interface (WUI) dangerously exposed to the fires. Pursuing the understanding of WUI areas, this study applies the Wildland–Urban Interface Index (WUIX) assessment methodology to an area severely affected by the massive 2017 wildfire of Pedrógão Grande, Leiria, Portugal. The primary objective of this study was to compare the results from WUIX with the areas burned during the fire event. As a result, maps of WUI effect were generated, visually pointing to villages with higher severity compared to the others. A statistical analysis was performed in three villages from the region to validate the results by comparing the accuracy of the results obtained to the actual damages. The results point out a high correlation between the WUIX and the real scenario despite the apparent challenges in determining the variations in different types of fire effect. Finally, the WUIX results align with the data from the Pedrógão Grande wildfire, showing that some are promising in conjunction with other wildfire indicators.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"45 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nikolay Abramov, Yulia Emelyanova, V. Fralenko, Vyacheslav Khachumov, Mikhail Khachumov, Maria Shustova, A. Talalaev
This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods.
{"title":"Intelligent Methods for Forest Fire Detection Using Unmanned Aerial Vehicles","authors":"Nikolay Abramov, Yulia Emelyanova, V. Fralenko, Vyacheslav Khachumov, Mikhail Khachumov, Maria Shustova, A. Talalaev","doi":"10.3390/fire7030089","DOIUrl":"https://doi.org/10.3390/fire7030089","url":null,"abstract":"This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"88 S12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140238261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiří Ryšavý, Jakub Čespiva, L. Kuboňová, Milan Dej, Katarzyna Szramowiat-Sala, Oleksandr Molchanov, Lukasz Niedzwiecki, Wei-Mon Yan, S. Thangavel
The possibilities of pistachio shell biochar production on laboratory-scale gasification and pyrolysis devices have been described by several previous studies. Nevertheless, the broader results of the pistachio shell co-gasification process on pilot-scale units have not yet been properly investigated or reported, especially regarding the detailed description of the biochar acquired during the routine operation. The biochar was analysed using several analytical techniques, such as ultimate and proximate analysis (62%wt of C), acid–base properties analysis (pH 9.52), Fourier-transform infrared spectroscopy (the presence of –OH bonds and identification of cellulose, hemicellulose and lignin), Raman spectroscopy (no determination of Id/Ig ratio due to high fluorescence), and nitrogen physisorption (specific surface 50.895 m2·g−1). X-ray fluorescence analysis exhibited the composition of the main compounds in the biochar ash (32.5%wt of Cl and 40.02%wt of Na2O). From the energy generation point of view, the lower heating value of the producer gas achieved 6.53 MJ·m−3 during the co-gasification. The relatively high lower heating value of the producer gas was mainly due to the significant volume fractions of CO (6.5%vol.), CH4 (14.2%vol.), and H2 (4.8 %vol.), while hot gas efficiency accomplished 89.6%.
{"title":"Co-Gasification of Pistachio Shells with Wood Pellets in a Semi-Industrial Hybrid Cross/Updraft Reactor for Producer Gas and Biochar Production","authors":"Jiří Ryšavý, Jakub Čespiva, L. Kuboňová, Milan Dej, Katarzyna Szramowiat-Sala, Oleksandr Molchanov, Lukasz Niedzwiecki, Wei-Mon Yan, S. Thangavel","doi":"10.3390/fire7030087","DOIUrl":"https://doi.org/10.3390/fire7030087","url":null,"abstract":"The possibilities of pistachio shell biochar production on laboratory-scale gasification and pyrolysis devices have been described by several previous studies. Nevertheless, the broader results of the pistachio shell co-gasification process on pilot-scale units have not yet been properly investigated or reported, especially regarding the detailed description of the biochar acquired during the routine operation. The biochar was analysed using several analytical techniques, such as ultimate and proximate analysis (62%wt of C), acid–base properties analysis (pH 9.52), Fourier-transform infrared spectroscopy (the presence of –OH bonds and identification of cellulose, hemicellulose and lignin), Raman spectroscopy (no determination of Id/Ig ratio due to high fluorescence), and nitrogen physisorption (specific surface 50.895 m2·g−1). X-ray fluorescence analysis exhibited the composition of the main compounds in the biochar ash (32.5%wt of Cl and 40.02%wt of Na2O). From the energy generation point of view, the lower heating value of the producer gas achieved 6.53 MJ·m−3 during the co-gasification. The relatively high lower heating value of the producer gas was mainly due to the significant volume fractions of CO (6.5%vol.), CH4 (14.2%vol.), and H2 (4.8 %vol.), while hot gas efficiency accomplished 89.6%.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140242633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Carvalho, S. Ribeiro, M. Gaspar, Teresa Fonseca, J. Lima-Brito
Wildfires act as a selection force threatening the sustainability and diversity of forest genetic resources. Few studies have investigated the genetic effects of forest wildfires. Species with perennial canopy seed banks in serotinous cones and soil or with long-distance seed and pollen dispersion can preserve genetic diversity and population differentiation under normal fire regimes. To test this hypothesis, we characterised molecularly Pinus pinaster Aiton (maritime pine) seedlings produced from seeds sampled in post-fire, naturally regenerated populations that had been subject to different fire regimes in the North of Portugal using inter-simple sequence repeats (ISSRs). The sampled populations burned once (A), twice (B), or three (D) times or had no prior fire history (C, control). Given the globally low seed germination ability, only 104 plantlets regenerated and were described. These plantlets were grouped according to their origin population. Intra-group ISSR polymorphism ranged from 72.73% (B) to 89.41% (D), revealing genetic differentiation among groups originating from populations that had experienced different fire recurrence. Overall, the unaffected genetic diversity of the regenerated plantlets allowed us to accept the hypothesis. Our findings enhance our understanding of the species ability to withstand fire-induced challenges and their responses to wildfires, guiding conservation endeavours and forest management strategies to bolster ecosystem resilience.
{"title":"Molecular Characterisation of Post-Fire Naturally Regenerated Populations of Maritime Pine (Pinus pinaster Ait.) in the North of Portugal","authors":"A. Carvalho, S. Ribeiro, M. Gaspar, Teresa Fonseca, J. Lima-Brito","doi":"10.3390/fire7030088","DOIUrl":"https://doi.org/10.3390/fire7030088","url":null,"abstract":"Wildfires act as a selection force threatening the sustainability and diversity of forest genetic resources. Few studies have investigated the genetic effects of forest wildfires. Species with perennial canopy seed banks in serotinous cones and soil or with long-distance seed and pollen dispersion can preserve genetic diversity and population differentiation under normal fire regimes. To test this hypothesis, we characterised molecularly Pinus pinaster Aiton (maritime pine) seedlings produced from seeds sampled in post-fire, naturally regenerated populations that had been subject to different fire regimes in the North of Portugal using inter-simple sequence repeats (ISSRs). The sampled populations burned once (A), twice (B), or three (D) times or had no prior fire history (C, control). Given the globally low seed germination ability, only 104 plantlets regenerated and were described. These plantlets were grouped according to their origin population. Intra-group ISSR polymorphism ranged from 72.73% (B) to 89.41% (D), revealing genetic differentiation among groups originating from populations that had experienced different fire recurrence. Overall, the unaffected genetic diversity of the regenerated plantlets allowed us to accept the hypothesis. Our findings enhance our understanding of the species ability to withstand fire-induced challenges and their responses to wildfires, guiding conservation endeavours and forest management strategies to bolster ecosystem resilience.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"18 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140244283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Gravit, Vasiliy Prusakov, Nikita Shcheglov, Irina Kotlyarskaya
Fire protection is required to protect metal structures of oil and gas facilities from fires. Such fire protection should provide high fire resistance limits: 60, 90, 120 and more minutes. Specialists of LLC “RPC PROMIZOL ” developed a multilayer, removable type of fire protection made of superfine basalt fibre and ceramic materials for operation in Arctic conditions. Five experimental studies were carried out in standard and hydrocarbon fire regimes. The fire protection effectiveness of the products for I20 beams without load was obtained: a 50 mm thick coating provided 130 min of a standard fire regime; a 15 mm thick coating provided 60 min. The 15 mm thick coating provided 30 min of a hydrocarbon fire regime and the 50 mm thick coating provided 93 min of a hydrocarbon fire regime. The I40 beam under a load of 19.9 tf showed an R243 for the standard fire regime. The coefficients of effective thermal conductivity and specific heat capacity of fire-retardant compositions were determined by solving the inverse heat conduction problem. The problem was solved by modelling using the QuickField 7.0 software package, which implements FEM. Modelling showed that for obtaining the fire resistance limit R120 under the standard fire regime for the sample steel structure from an I40 beam, it is enough to apply fire protection with a thickness of 25 mm instead of 50 mm, which agrees with the experimental data. For the hydrocarbon regime, it is predicted that R120 can be obtained at a thickness of 45 mm instead of 50 mm.
{"title":"Fire Protection of Steel Structures of Oil and Gas Facilities: Multilayer, Removable, Non-Combustible Covers","authors":"M. Gravit, Vasiliy Prusakov, Nikita Shcheglov, Irina Kotlyarskaya","doi":"10.3390/fire7030086","DOIUrl":"https://doi.org/10.3390/fire7030086","url":null,"abstract":"Fire protection is required to protect metal structures of oil and gas facilities from fires. Such fire protection should provide high fire resistance limits: 60, 90, 120 and more minutes. Specialists of LLC “RPC PROMIZOL ” developed a multilayer, removable type of fire protection made of superfine basalt fibre and ceramic materials for operation in Arctic conditions. Five experimental studies were carried out in standard and hydrocarbon fire regimes. The fire protection effectiveness of the products for I20 beams without load was obtained: a 50 mm thick coating provided 130 min of a standard fire regime; a 15 mm thick coating provided 60 min. The 15 mm thick coating provided 30 min of a hydrocarbon fire regime and the 50 mm thick coating provided 93 min of a hydrocarbon fire regime. The I40 beam under a load of 19.9 tf showed an R243 for the standard fire regime. The coefficients of effective thermal conductivity and specific heat capacity of fire-retardant compositions were determined by solving the inverse heat conduction problem. The problem was solved by modelling using the QuickField 7.0 software package, which implements FEM. Modelling showed that for obtaining the fire resistance limit R120 under the standard fire regime for the sample steel structure from an I40 beam, it is enough to apply fire protection with a thickness of 25 mm instead of 50 mm, which agrees with the experimental data. For the hydrocarbon regime, it is predicted that R120 can be obtained at a thickness of 45 mm instead of 50 mm.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140243271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents the critical egress parameters that influence emergency evacuation in a typical hospital building. A parametric study of a 20-story hospital building is conducted using a computer model “Pathfinder” to simulate the evacuation efficiency and assess the influencing parameters. The main egress parameters that influence the evacuation efficiency, including the location of stairways, number of stairways, location of the fire, exit width, and number of low-speed occupants are varied. Two scenarios are simulated: one being the regular (practice) evacuation drill and the other is the actual fire drill. The result shows that the location of stairways significantly affects the total evacuation time with the optimal stairway arrangement consisting of one stairway outside the core of the building. Similarly, the story level at which the fire occurs is another key parameter with fires at lower levels being critical to dictating the evacuation time in a hospital building. The total evacuation time when the fire occurs between the third and sixth floor is found to be 170 min which is 36% and 15% higher than fires at the top story levels (15–18th floor) and the intermediate story levels (9–12th floor), respectively.
{"title":"Critical Egress Parameters Governing Assisted Evacuation in Hospital Buildings","authors":"Venkatesh Kodur, Ankush Jha, Nizar Lajnef","doi":"10.3390/fire7030085","DOIUrl":"https://doi.org/10.3390/fire7030085","url":null,"abstract":"This paper presents the critical egress parameters that influence emergency evacuation in a typical hospital building. A parametric study of a 20-story hospital building is conducted using a computer model “Pathfinder” to simulate the evacuation efficiency and assess the influencing parameters. The main egress parameters that influence the evacuation efficiency, including the location of stairways, number of stairways, location of the fire, exit width, and number of low-speed occupants are varied. Two scenarios are simulated: one being the regular (practice) evacuation drill and the other is the actual fire drill. The result shows that the location of stairways significantly affects the total evacuation time with the optimal stairway arrangement consisting of one stairway outside the core of the building. Similarly, the story level at which the fire occurs is another key parameter with fires at lower levels being critical to dictating the evacuation time in a hospital building. The total evacuation time when the fire occurs between the third and sixth floor is found to be 170 min which is 36% and 15% higher than fires at the top story levels (15–18th floor) and the intermediate story levels (9–12th floor), respectively.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"593 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140246731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aziza Ergasheva, Farkhod Akhmedov, A. Abdusalomov, Wooseong Kim
The maritime sector confronts an escalating challenge with the emergence of onboard fires aboard in ships, evidenced by a pronounced uptick in incidents in recent years. The ramifications of such fires transcend immediate safety apprehensions, precipitating repercussions that resonate on a global scale. This study underscores the paramount importance of ship fire detection as a proactive measure to mitigate risks and fortify maritime safety comprehensively. Initially, we created and labeled a custom ship dataset. The collected images are varied in their size, like having high- and low-resolution images in the dataset. Then, by leveraging the YOLO (You Only Look Once) object detection algorithm we developed an efficacious and accurate ship fire detection model for discerning the presence of fires aboard vessels navigating marine routes. The ship fire detection model was trained on 50 epochs with more than 25,000 images. The histogram equalization (HE) technique was also applied to avoid destruction from water vapor and to increase object detection. After training, images of ships were input into the inference model after HE, to be categorized into two classes. Empirical findings gleaned from the proposed methodology attest to the model’s exceptional efficacy, with the highest detection accuracy attaining a noteworthy 0.99% across both fire-afflicted and non-fire scenarios.
近年来，船舶火灾事故明显增加，海事部门面临着日益严峻的挑战。此类火灾的影响已超越了眼前的安全问题，其后果将波及全球。这项研究强调了船舶火灾探测的极端重要性，它是降低风险和全面加强海事安全的一项积极措施。最初，我们创建了一个自定义船舶数据集，并对其进行了标注。收集到的图像大小不一，如数据集中有高分辨率和低分辨率图像。然后，利用 YOLO（只看一次）物体检测算法，我们开发了一个高效、准确的船舶火灾检测模型，用于辨别在海上航线航行的船舶上是否存在火灾。船舶火灾检测模型是在 50 个历时、25,000 多张图像上训练出来的。此外，还应用了直方图均衡化（HE）技术，以避免水蒸气对图像的破坏，并提高目标检测率。训练完成后，船舶图像被输入 HE 后的推理模型，并被分为两类。从提出的方法中收集的经验结果证明了该模型的卓越功效，在火灾和非火灾场景中，最高检测准确率达到了值得注意的 0.99%。
{"title":"Advancing Maritime Safety: Early Detection of Ship Fires through Computer Vision, Deep Learning Approaches, and Histogram Equalization Techniques","authors":"Aziza Ergasheva, Farkhod Akhmedov, A. Abdusalomov, Wooseong Kim","doi":"10.3390/fire7030084","DOIUrl":"https://doi.org/10.3390/fire7030084","url":null,"abstract":"The maritime sector confronts an escalating challenge with the emergence of onboard fires aboard in ships, evidenced by a pronounced uptick in incidents in recent years. The ramifications of such fires transcend immediate safety apprehensions, precipitating repercussions that resonate on a global scale. This study underscores the paramount importance of ship fire detection as a proactive measure to mitigate risks and fortify maritime safety comprehensively. Initially, we created and labeled a custom ship dataset. The collected images are varied in their size, like having high- and low-resolution images in the dataset. Then, by leveraging the YOLO (You Only Look Once) object detection algorithm we developed an efficacious and accurate ship fire detection model for discerning the presence of fires aboard vessels navigating marine routes. The ship fire detection model was trained on 50 epochs with more than 25,000 images. The histogram equalization (HE) technique was also applied to avoid destruction from water vapor and to increase object detection. After training, images of ships were input into the inference model after HE, to be categorized into two classes. Empirical findings gleaned from the proposed methodology attest to the model’s exceptional efficacy, with the highest detection accuracy attaining a noteworthy 0.99% across both fire-afflicted and non-fire scenarios.","PeriodicalId":12279,"journal":{"name":"Fire","volume":"110 4‐5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140257294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：