Search Results (404)

To enhance the fire safety protection level of deeply buried metro stations, this study conducted full-scale fire experiments based on Wulichong Station of Guiyang Metro Line 3. It systematically investigated the laws of smoke movement and temperature distribution under the coupled effects of different fire source powers and smoke extraction system states. Through the set up of multiple sets of comparative test conditions, the study focused on analyzing the influence mechanism of the operation (on/off) of the smoke extraction system on smoke spread characteristics and temperature field distribution. The results indicate that under the condition where the smoke extraction system is turned off, the smoke exhibits typical stratified spread characteristics driven by thermal buoyancy, with the temperature rising significantly as the vertical height increases. When the smoke extraction system is activated, the horizontal airflow generated by mechanical smoke extraction significantly alters the flame morphology (with an inclination angle exceeding 45°), effectively extracting and discharging the hot smoke and leading to a more uniform temperature distribution within the space. Full article

Smoke appears earlier than flames, so image-based fire monitoring techniques mainly focus on the detection of smoke, which is regarded as one of the effective strategies for preventing the spread of initial fires that eventually evolve into serious fires. Smoke monitoring in mine fires faces serious challenges: the underground environment is complex, with smoke and backgrounds being highly integrated and visual features being blurred, which makes it difficult for existing image-based monitoring techniques to meet the actual needs in terms of accuracy and robustness. The conventional ground-based methods are directly used in the underground with a high rate of missed detection and false detection. Aiming at the core problems of mixed target and background information and high boundary uncertainty in smoke images, this paper, inspired by the principle of information entropy, proposes a method for recognizing smoke from mine fires by integrating entropy-enhanced image processing and improved YOLOv8. Firstly, according to the entropy change characteristics of spatio-temporal information brought by smoke diffusion movement, based on spatio-temporal entropy separation, an equidistant frame image differential fusion method is proposed, which effectively suppresses the low entropy background noise, enhances the detail clarity of the high entropy smoke region, and significantly improves the image signal-to-noise ratio. Further, in order to cope with the variable scale and complex texture (high information entropy) of the smoke target, an improvement mechanism based on entropy-constrained feature focusing is introduced on the basis of the YOLOv8m model, so as to more effectively capture and distinguish the rich detailed features and uncertain information of the smoke region, realizing the balanced and accurate detection of large and small smoke targets. The experiments show that the comprehensive performance of the proposed method is significantly better than the baseline model and similar algorithms, and it can meet the demand of real-time detection. Compared with YOLOv9m, YOLOv10n, and YOLOv11n, although there is a decrease in inference speed, the accuracy, recall, average detection accuracy mAP (50), and mAP (50–95) performance metrics are all substantially improved. The precision and robustness of smoke recognition in complex mine scenarios are effectively improved. Full article

This study presents the design and validation of an integrated fire safety system that leverages edge AI, hybrid sensing, and precision suppression to overcome the latency and collateral limitations of conventional smoke detection and sprinkler systems. The proposed platform features a dual-mode sensor array for early fire recognition, motorized ventilation units for rapid smoke extraction, and a 360° directional nozzle for targeted agent discharge using a residue-free clean extinguishing agent. Experimental trials demonstrated an average fire detection time of 5.8 s and complete flame suppression within 13.2 s, with 90% smoke clearance achieved in under 95 s. No false positives were recorded during non-fire simulations, and the system remained fully functional under simulated cloud communication failure, confirming its edge-resilient architecture. A probabilistic risk analysis based on ISO 31000 and NFPA 551 frameworks showed risk reductions of 75.6% in life safety, 58.0% in property damage, and 67.1% in business disruption. The system achieved a composite risk reduction of approximately 73%, shifting the operational risk level into the ALARP region. These findings demonstrate the system’s capacity to provide proactive, energy-efficient, and spatially targeted fire response suitable for high-value infrastructure. The modular design and SmartThings Edge integration further support scalable deployment and real-time system intelligence, establishing a strong foundation for future adaptive fire protection frameworks. Full article

Despite recent advances in deep learning for fire detection, much of the current research prioritizes model-centric metrics over dataset fidelity, particularly from a fire safety engineering perspective. Commonly used datasets are often dominated by fully developed flames, mislabel smoke-only frames as non-fire, or lack intra-video diversity due to redundant frames from limited sources. Some works treat smoke detection alone as early-stage detection, even though many fires (e.g., electrical or chemical) begin with visible flames and no smoke. Additionally, attempts to improve model applicability through mixed-context datasets—combining indoor, outdoor, and wildland scenes—often overlook the unique false alarm sources and detection challenges specific to each environment. To address these limitations, we curated a new video dataset comprising 1108 annotated fire and non-fire clips captured via indoor surveillance cameras. Unlike existing datasets, ours emphasizes early-stage fire dynamics (pre-flashover) and includes varied fire sources (e.g., sofa, cupboard, and attic fires), realistic false alarm triggers (e.g., flame-colored objects, artificial lighting), and a wide range of spatial layouts and illumination conditions. This collection enables robust training and benchmarking for early indoor fire detection. Using this dataset, we developed a spatiotemporal fire detection model based on the mixed convolutions ResNets (MC3_18) architecture, augmented with Convolutional Block Attention Modules (CBAM). The proposed model achieved 86.11% accuracy, 88.76% precision, and 84.04% recall, along with low false positive (11.63%) and false negative (15.96%) rates. Compared to its CBAM-free baseline, the model exhibits notable improvements in F1-score and interpretability, as confirmed by Grad-CAM++ visualizations highlighting attention to semantically meaningful fire features. These results demonstrate that effective early fire detection is inseparable from high-quality, context-specific datasets. Our work introduces a scalable, safety-driven approach that advances the development of reliable, interpretable, and deployment-ready fire detection systems for residential environments. Full article

Fire refers to a disaster caused by combustion that is uncontrolled in the temporal and spatial dimensions, occurring in diverse complex scenarios where timely and effective detection is crucial. However, existing fire detection methods are often challenged by the deformation of smoke and flames, resulting in missed detections. It is difficult to accurately extract fire features in complex backgrounds, and there are also significant difficulties in detecting small targets, such as small flames. To address this, this paper proposes a YOLO-Multi-scenario Fire Detector (YOLO-MFD) for multi-scenario fire detection. Firstly, to resolve missed detection caused by deformation of smoke and flames, a Scale Adaptive Perception Module (SAPM) is proposed. Secondly, aiming at the suppression of significant fire features by complex backgrounds, a Feature Adaptive Weighting Module (FAWM) is introduced to enhance the feature representation of fire. Finally, considering the difficulty in detecting small flames, a fine-grained Small Object Feature Extraction Module (SOFEM) is developed. Additionally, given the scarcity of multi-scenario fire datasets, this paper constructs a Multi-scenario Fire Dataset (MFDB). Experimental results on MFDB demonstrate that the proposed YOLO-MFD achieves a good balance between effectiveness and efficiency, achieving good effective fire detection performance across various scenarios. Full article

Polyamide 6,6 (PA6,6) fabrics are widely used in textiles due to their high mechanical strength and chemical stability. However, their inherent flammability and melting behavior under fire pose significant safety challenges. In this study, a dual-layer flame-retardant system was developed by integrating atomic layer deposition (ALD) of ZnO with a phosphorus–silane-based flame retardant (DOPO-ETES). ALD allowed precise control of ZnO layer thickness (50, 84, and 199 nm), ensuring uniform coating. Thermal analysis (TGA) and microscale combustion calorimetry (MCC) revealed that ZnO altered the degradation pathway of PA6,6 through catalytic effects, promoting char formation and reducing heat release. The combination of ZnO and DOPO-ETES resulted in further reductions in heat release rates. However, direct flame tests showed that self-extinguishing behavior was not achieved, emphasizing the limitations related to the melting of PA6,6. TG-IR and cone calorimetry confirmed that ZnO coatings suppressed the release of smoke-related volatiles and incomplete combustion products. These findings highlight the potential of combining metal-based catalytic flame retardants like ZnO with phosphorus-based coatings to improve flame retardancy while addressing the specific challenges of polyamide textiles. This approach may also be adapted to other fabric types and integrated with additional flame retardants, broadening its relevance for textile applications. Full article

Timely and accurate detection of forest fires is crucial for protecting forest ecosystems. However, traditional monitoring methods face significant challenges in effectively detecting forest fires, primarily due to the dynamic spread of flames and smoke, irregular morphologies, and the semi-transparent nature of smoke, which make it extremely difficult to extract key visual features. Additionally, deploying these detection systems to edge devices with limited computational resources remains challenging. To address these issues, this paper proposes a lightweight hybrid receptive field model (LHRF-YOLO), which leverages deep learning to overcome the shortcomings of traditional monitoring methods for fire detection on edge devices. Firstly, a hybrid receptive field extraction module is designed by integrating the 2D selective scan mechanism with a residual multi-branch structure. This significantly enhances the model’s contextual understanding of the entire image scene while maintaining low computational complexity. Second, a dynamic enhanced downsampling module is proposed, which employs feature reorganization and channel-wise dynamic weighting strategies to minimize the loss of critical details, such as fine smoke textures, while reducing image resolution. Furthermore, a scale weighted Fusion module is introduced to optimize multi-scale feature fusion through adaptive weight allocation, addressing the issues of information dilution and imbalance caused by traditional fusion methods. Finally, the Mish activation function replaces the SiLU activation function to improve the model’s ability to capture flame edges and faint smoke textures. Experimental results on the self-constructed Fire-SmokeDataset demonstrate that LHRF-YOLO achieves significant model compression while further improving accuracy compared to the baseline model YOLOv11. The parameter count is reduced to only 2.25M (a 12.8% reduction), computational complexity to 5.4 GFLOPs (a 14.3% decrease), and mAP50 is increased to 87.6%, surpassing the baseline model. Additionally, LHRF-YOLO exhibits leading generalization performance on the cross-scenario M4SFWD dataset. The proposed method balances performance and resource efficiency, providing a feasible solution for real-time and efficient fire detection on resource-constrained edge devices with significant research value. Full article

Fire-resistant coatings have emerged as crucial materials for reducing fire hazards in various industries, including construction, textiles, electronics, and aerospace. This review provides a comprehensive account of recent advances in fire-resistant coatings, emphasizing environmentally friendly and high-performance systems. Beginning with a classification of traditional halogenated and non-halogenated flame retardants (FRs), this article progresses to cover nitrogen-, phosphorus-, and hybrid-based systems. The synthesis methods, structure–property relationships, and fire suppression mechanisms are critically discussed. A particular focus is placed on bio-based and waterborne formulations that align with green chemistry principles, such as tannic acid (TA), phytic acid (PA), lignin, and deep eutectic solvents (DESs). Furthermore, the integration of nanomaterials and smart functionalities into fire-resistant coatings has demonstrated promising improvements in thermal stability, char formation, and smoke suppression. Applications in real-world contexts, ranging from wood and textiles to electronics and automotive interiors, highlight the commercial relevance of these developments. This review also addresses current challenges such as long-term durability, environmental impacts, and the standardization of performance testing. Ultimately, this article offers a roadmap for developing safer, sustainable, and multifunctional fire-resistant coatings for future materials engineering. Full article

Wildfire detection in power transmission corridors is essential for providing timely warnings and ensuring the safe and stable operation of power lines. However, this task faces significant challenges due to the large number of smoke-like samples in the background, the complex and diverse target morphologies, and the difficulty of detecting small-scale smoke and flame objects. To address these issues, this paper proposed an improved Oriented R-CNN model enhanced with metric learning for wildfire detection in power transmission corridors. Specifically, a multi-center metric loss (MCM-Loss) module based on metric learning was introduced to enhance the model’s ability to differentiate features of similar targets, thereby improving the recognition accuracy in the presence of interference. Experimental results showed that the introduction of the MCM-Loss module increased the average precision (AP) for smoke targets by 2.7%. In addition, the group convolution-based network ResNeXt was adopted to replace the original backbone network ResNet, broadening the channel dimensions of the feature extraction network and enhancing the model’s capability to detect flame and smoke targets with diverse morphologies. This substitution led to a 0.6% improvement in mean average precision (mAP). Furthermore, an FPN-CARAFE module was designed by incorporating the content-aware up-sampling operator CARAFE, which improved multi-scale feature representation and significantly boosted performance in detecting small targets. In particular, the proposed FPN-CARAFE module improved the AP for fire targets by 8.1%. Experimental results demonstrated that the proposed model achieved superior performance in wildfire detection within power transmission corridors, achieving a mAP of 90.4% on the test dataset—an improvement of 6.4% over the baseline model. Compared with other commonly used object detection algorithms, the model developed in this study exhibited improved detection performance on the test dataset, offering research support for wildfire monitoring in power transmission corridors. Full article

The global market for flame-retardant materials is expected to grow steadily, from USD 7.0 billion in 2022 to USD 16.6 billion in 2030, driven by increasing demand for environment-friendly fire safety solutions in transportation, construction, and electronics. Polylactic acid (PLA), a biodegradable polymer which possesses excellent mechanical properties, is increasingly being considered for future mobility applications. However, it is characterized by high heat release and toxic smoke during combustion, which are significant drawbacks. In order to address this, the chemical modification of Kraft lignin was achieved through a phenolation and subsequent silylation with tetraethoxysilane, aiming to mitigate the degradation of PLA’s mechanical properties while utilizing its inherent char-forming ability. The modified lignins were combined with ammonium polyphosphate (APP) and melt-mixed with PLA using an injection-mixing molder to prepare test specimens. Analysis by FT-IR, NMR spectroscopy, and SEM-EDS confirmed successful grafting of phenolic and silane functionalities, and thermogravimetric analysis demonstrated enhanced thermal stability of the modified lignins compared to unmodified ones. Vertical burning tests and limiting oxygen index (LOI) measurements showed that the PLA/APP/SPKL composite material achieved a V-0 UL-94 rating and 31.95% LOI, demonstrating the highest level of flame retardancy. This compares to the LOI of neat PLA, 19 to 21%. Despite the enhancement in flame retardancy to the V-0 level, the decline in tensile strength was limited, and the composite retained comparable mechanical strength to PLA-APP composites with V-2 flame retardancy. The findings indicate that the combination of phenolation and silylation of lignin with APP, a flame-retardant material, offers a viable and sustainable methodology for the fabrication of PLA composites that exhibit both flame retardancy and mechanical strength. Full article

Epoxy resins are limited by their flammability and brittleness. In this study, a phosphorus- and silicon-based additive was synthesized to improve fire resistance and mechanical performance. The incorporation of just 1 wt% phosphorus from this additive into epoxy resin achieved a limiting oxygen index of 33% and a V-0 fire rating. The modified epoxy exhibited a 52.43% reduction in the peak heat release rate and a 35.70% decrease in total smoke production compared to the unmodified resin, demonstrating enhanced heat resistance and smoke suppression. Notably, the modified epoxy thermoset displayed superior mechanical properties, with tensile and impact strengths increasing by 48.41% and 130%, respectively. This research presents a promising approach for developing high-performance epoxy resins with improved flame retardancy, smoke suppression, and mechanical strength. Full article

This study investigates the spread patterns of tunnel fires and examines issues related to emergency response. It focuses on the temperature characteristics, spread patterns, conditions leading to multi-source fires, and the efficacy of water mist suppression methods in heavy-haul railway tunnel fires. The research employs theoretical derivations and numerical simulations to achieve its objectives. It was discovered that, during a fire in a heavy-haul railway tunnel, the temperature inside the tunnel can exceed 500 °C. Furthermore, depending on the nature of the goods transported by the train and under specific wind speed conditions, the fire source has the potential to spread to other carriages, resulting in a multi-source fire. Using the numerical simulation software Pyrosim 2022, various wind speed conditions were simulated. The results revealed that at lower wind speeds, the smoke demonstrates a reverse flow phenomenon. Concurrently, when the adjacent carriage on the leeward side of the fire is ignited, the high-temperature reverse flow smoke, along with the thermal radiation from the flames, ignites combustible materials in the adjacent carriage on the windward side of the burning carriage. Through theoretical derivation and numerical simulation, the critical wind speed for the working conditions was determined to be 2.14 m/s. It was found that while a higher wind speed can lead to a decrease in temperature, it also increases the flame deflection angle. When the wind speed exceeds 2.4 m/s, although the temperature significantly drops in a short period, the proximity of combustible materials on the leeward side of the carriage becomes a concern. At this wind speed, the flame deflection angle causes heat radiation on the leeward side, specifically between 0.5 m and 3 m, to ignite the combustible materials on the carriage surface, resulting in fire spread and multiple fire incidents. The relationship between wind speed and the angle of deflection from the fire source was determined using relevant physics principles. Additionally, the relationship between wind speed and the trajectory of water mist spraying was established. It was proposed to optimize the position of the water mist based on its deviation, and the results indicated that under critical wind speed conditions, when the water mist spraying is offset approximately 5 m towards the upwind side of the fire source, it can act more directly on the surface of the fire source. Numerical simulation results show a significant reduction in the maximum temperature and effective control of fire spread. Under critical wind speed conditions, the localized average temperature of the fire decreased by approximately 140 °C when spraying was applied, compared to the conditions without spraying, and the peak temperature decreased by about 190 °C. This modification scheme can effectively suppress the threat of fire to personnel evacuation under simulated working conditions, reflecting effective control over fires. Additionally, it provides theoretical support for the study of fire patterns in tunnels and emergency response measures. Full article

This paper investigates the influence of ventilation conditions, including oxidizer flow speed and oxygen concentration, on major species composition in favor of estimating a risk of flame acceleration at reduced gravity. A two-step chemical reaction for gas phase and a soot formation model based on laminar smoke point are used. To calculate thermal radiation from flame, a discrete-ordinates method is coupled with a non-grey model by taking into account the radiative properties of CO, CO₂, H₂O and soot. The predictions provide further insights into the intimate coupling of fuel types, such as heptane and dodecane, with burning rate, flame structure and toxic emissions as a consequence of changes in ventilation conditions such as oxidizer flow velocity and oxygen concentration. From a boundary-layer microgravity flame, the CO₂ to CO ratio is less than 3, and the unburnt hydrocarbons C_mH_n to CO ratio is less than 2, with a concentration of unburnt fuel that exceeds the Lower Flammability Limit. This finding on the production of unburnt species is contrasted to the case of a buoyancy-controlled flame at Earth gravity. Full article

Channel fire poses a great threat to personnel safety and structural strength, in which the temperature profile is worthy of attention. In this paper, the longitudinal temperature profile of a ceiling jet induced by a wall-attached fire with different channel slopes was experimentally investigated using a 1:8 reduced-scale channel. The results show the following: (1) For channel fire with a horizontal ceiling, the influence of the burner aspect ratio and source-ceiling height on the temperature profile is monotonous in the cases considered in this work. With a larger burner aspect ratio and larger source-ceiling distance, more ambient air could be entrained; hence, the longitudinal temperature under the ceiling decays faster. (2) For channel fire with an inclined ceiling, when the burner aspect ratio and source-ceiling distance remain constant, the asymmetric entrainment induced by the flame under larger channel slope leads to more hot smoke being transported upstream. Consequently, the temperature profile is not symmetric, with higher temperatures upstream and lower temperatures downstream. (3) Combining the influence of the burner aspect ratios, source-ceiling distance, and burner aspect ratio, the characteristic length scale was modified. Based on this, a model describing the ceiling temperature profile was proposed and then verified with previous data. Full article

Background and Aims: Cervical arterial dissections (CeAD) are a common cause of stroke in young adults across both sexes. Whether biological sex plays a role in the pathogenesis and outcome of CeAD remains unclear. Methods: In this retrospective analysis of a cohort of patients with CeAD, clinical, imaging, treatment, and outcome data were compared between females and males using multivariate logistic regressions to identify outcome predictors. Propensity score matching (PSM) was used to adjust for imbalances between the groups. Results: Overall, 135 participants were included (79 males and 56 females, median age 44, interquartile range [IQR] 36, 50.5). Of those, 71 patients (53%) were diagnosed with stroke (median age 46, IQR 39.5, 52, median admission NIHSS 3, IQR 1, 7.5). Males had significantly higher rates of smoking (38% vs. 11%, p = 0.0004) but other baseline characteristics did not differ between the groups. Traumatic dissections were numerically more common in men but the difference between the groups did not reach significance. The presence of flame shaped lesion in the extra cranial vessel was more common among men in the initial analysis of the whole group but did not remain significant after PSM. No differences were observed between the groups regarding treatment strategies including administration of systemic thrombolysis and stent placements. The rates of recurrent stroke and recurrent dissections were similar. Favorable outcomes defined as modified Rankin Score (mRS) ≤ 2 and symptomatic intracranial hemorrhage rates were also similar on the univariate analyses and did not change after PSM. Age (odds ratio [OR] 1.12, 95% confidence intervals [CI] 1.04–1.23) and admission NIHSS (OR 0.74, 95%CI 0.60–0.84) were associated with outcomes on regression analysis whereas female sex was not (OR 0.54, 95% CI 0.03–5.87). Conclusions: CeAD occurs more frequently in males, who are more likely to have associated risk factors and traumatic neck injuries. However, sex does not appear to impact outcome in CeAD patients. Full article