• Computers and Concrete
• /
• v.33 no.4
• /
• pp.409-423
• /
• 2024

Using an extensive database, a sensitivity analysis across fifteen machine learning (ML) classifiers was conducted to evaluate the impact of various data manipulation techniques, evaluation metrics, and explainability tools. The results of this sensitivity analysis reveal that the examined models can achieve an accuracy ranging from 72-93% in predicting the fire-induced spalling of concrete and denote the light gradient boosting machine, extreme gradient boosting, and random forest algorithms as the best-performing models. Among such models, the six key factors influencing spalling were maximum exposure temperature, heating rate, compressive strength of concrete, moisture content, silica fume content, and the quantity of polypropylene fiber. Our analysis also documents some conflicting results observed with the deep learning model. As such, this study highlights the necessity of selecting suitable models and carefully evaluating the presence of possible outcome biases.

• Fire Science and Engineering
• /
• v.26 no.6
• /
• pp.72-77
• /
• 2012

When the concrete and steel combined composite beam is exposed to high temperature, concrete could delay temperature rising of steel by covering or increase heat capacity of structural member. For becoming of structural reinforcing by unification between materials, fire resistance rate of composite beam would be higher than simple steel beam. The temperature rising of exposed steel of composite beam is directly related with section shape and exposure length of steel. In this study, fire resistant tests were carried out for composite beams and steel beam with same thickness of spray-type fire resistant materials in standard fire, and after that, temperature histories were analysed and compared with shape factor. The correlation between steel temperature and shape factor was showed very high. This result suggests that if it can be predict the comparative advantage of member by factor which cause the performance enhancement, it could be conclude that an Standard Accreditation method can be adjust to members without indivisual certifiicate of accreditation.

• Fire Science and Engineering
• /
• v.23 no.2
• /
• pp.111-116
• /
• 2009

17 kinds of fire resistant paint which are currently used were painted on the MDF(middle density fiber board), which suitable to the regulation of Fire Service Act. And we investigate a ignition delay effect under a exposure condition of radiative heat of fire. Radiative heat flux was controlled from $10kW/m^2$ to $30kW/m^2$ using the cone heater. Ignition time, ignition type and surface temperature of the sample were measured. Based on the experimental result, critical heat flux of the fire resistant paint treated sample was $10kW/m^2$ and there were no ignition delay effect above the $30kW/m^2$. And it was found that it will be difficult to expect the fire resistant effect above $400^{\circ}C$ of sample surface temperature.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.35 no.2
• /
• pp.150-156
• /
• 2015

In this study, the effects of different mix proportions and fire scenarios (exposure temperatures and post-fire-curing periods) on fire-damaged concrete were analyzed using a nonlinear resonance vibration method based on nonlinear acoustics. The hysteretic nonlinearity parameter was obtained, which can sensitively reflect the damage level of fire-damaged concrete. In addition, a splitting tensile strength test was performed on each fire-damaged specimen to evaluate the residual property. Using the results, a prediction model for estimating the residual strength of fire-damaged concrete was proposed on the basis of the correlation between the hysteretic nonlinearity parameter and the ratio of splitting tensile strength.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.

• Journal of the Korean Society of Safety
• /
• v.30 no.6
• /
• pp.40-47
• /
• 2015

In this study, temperature characteristics and fire damage form were analyzed to investigate flame spreading form and fire probability from ignition sources subject to drivit component materials which is finishing material in architecture. Ignition sources were limited to a gas torch and exterior panel board fire, and the size of the sample was manufacture in 30 cm length ${\times}$ 50 cm height ${\times}$ 5cm thickness size. Marble (inner wall) + 3 mm drivit (outer wall), marble (inner wall) + 4 mm plaster stone (outer wall), sandwich panel + 3 mm driver bit (outer wall), sandwich panel + 3 mm driver bit + insulation (outer wall), and gypsum board (inner wall) + 3 mm drivit (outer wall) were prepared for the sample. As result of the research for temperature characteristics, large temperature difference by each material was shown in $218^{\circ}C{\sim}995^{\circ}C$ at 30 seconds and $501^{\circ}C{\sim}1078^{\circ}C$ at 300 seconds. Especially when the inner wall was a plaster board, lowest temperature of $501^{\circ}C$ was shown at 300 seconds and marble inner wall showed the following lowest temperature of $900^{\circ}C$. Temperature rising over $1000^{\circ}C$ was shown in other materials. Regarding fire damage form, drivit or gypsum board outer wall parts exposed to fire showed combustion and carbonization to show calcination(breaking phenomenon) and influence of heat exposure was higher as calcination became more severe.

• Fire Science and Engineering
• /
• v.25 no.6
• /
• pp.64-72
• /
• 2011

The concrete void slab structure with the existing mushroom slab, is the structure that maximizes the advantages, while minimizing the weakness with removing useless body force of the concrete part, located on the center of the slab cross-section, which does not need to support the structural weight. In this research, a fire test is performed to analyze how the blaze behave according to the thickness of slab cover, with the practical span length of concrete void slab for the slab length 7.5 m. With this heating test, we assumed the uniform-load-model considering fixed loads and live loads, and chose the standard fire test condition. We measured the temperature changes and the deflection character according to the depth from the heat exposure side, and assessed the resisting capability according to the standard KS F 2257-1. The result comes out with the EPS model can secure about 2 hour fire-resisting-capability with 50 mm of cover depth.

• Fire Science and Engineering
• /
• v.28 no.2
• /
• pp.1-8
• /
• 2014

Despite advancements in the development of synthetic fibers and materials that provide better insulation, fire burn injuries remain a significant issue. To ensure adequate protection, clothing and equipment must be selected on the basis of performance. There are different standards like ISO standards applicable to each of the various types of clothing used by fire fighters. But, in most cases, the tests are performed in the conditions of high heat flux exposure, the clothing material can be destroyed easily. Thus the effective way to investigate the protective performance for the low (radiant) heat flux conditions should be needed. Therefore improved RPP (Radiant Protective Performance) test method based on the onset of pain burn injury was suggested. Experiments were performed to verify the proposed method with current protective clothing for fire fighters and the transient heat transfer characteristics were identified, also. Moreover, several protective performance indices were acquired from experimental results to analyze their relations.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.705-708
• /
• 2008

To obtain tunnel concrete safety in case of fire, this study analyzed fire proof characteristics by fire proof method change, and the results are as follows. As a fire proof characteristics by RABT temperature heating curve, plain concrete experienced severe spalling by initial extremely high temperature. In view of fire proof method, in the cases of organic fiber mixing method and board method, spalling was prevented, and in the case of spray method, severe spalling of over 100mm depth occurred along with exposure of structural concrete including spray coat by heat stress, etc while metal lath, the stiffener, falls off. As for fire proof characteristics by RWS temperature heating curve, in case of organic fiber inclusion, concrete surface experienced fusion of within 5mm, while in the case of spray method, spray coat was severely spalled to a depth of over 100mm causing structural body concrete to expose its reinforcement, and also in the case of board method, board was fused by high temperature, causing structural body concrete be directly exposed to high temperature, which triggered overall fall-off phenomenon, so in such extraordinary high temperature heating condition, establishment of special fire proof measures is needed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.1
• /
• pp.77-84
• /
• 2015

Tensile tests were conducted on the GFRP reinforcement exposed to high temperature. The exposure condition for this study was below $200^{\circ}C$ for about 3 minutes. This conditioning is minor compared with that presented in experimental program conducted by other researchers. The residual tensile strength and elastic modulus of GFRP reinforcing bars at high temperature and after exposure to high temperature were compared. In results, tensile properties were decreased at high temperatures, but those after exposure to high temperature were recovered to pre-heating level almost completely. These results could be valuable for evaluating GFRP reinforced structure damaged by fire accident.