• Fire Science and Engineering
• /
• v.22 no.2
• /
• pp.49-56
• /
• 2008

Smoke propagation for the Daegu Metro fire is reproduced by a reduced-scale model experiment. The three-story station building was modeled with 1/20-scale, and the tunnel connected to the platform was not completely modeled because of its length. To include the flow resistance the tunnel provides the mesh screens were used in the model. The fire scenario was selected based on the fire growth rate of the metro car seat where the fire initiated. The time when smoke arrived at each compartment in the station building was measured by thermocouples and visualization. Regarding fire ventilation, the air supply that has been accepted as conventional design in a subway metro building intensifies smoke spread. The results show that the whole building was filled with smoke in about 10 minutes in case of no ventilation.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.4
• /
• pp.23-30
• /
• 2022

In this paper, we propose an algorithm that can accurately segment a fire even when it is surrounded by smoke of a similar color. Existing fire area segmentation algorithms have a problem in that they cannot separate fire and smoke from fire images. In this paper, the fire was successfully separated from the smoke by applying the color compensation method and the fog removal method as a preprocessing process before applying the fire area segmentation algorithm. In fact, it was confirmed that it segments fire more effectively than the existing methods in the image of the fire scene covered with smoke. In addition, we propose a method that can use the proposed fire segmentation algorithm for efficient fire detection in factories and homes.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.9
• /
• pp.721-736
• /
• 2019

In this paper, the behavior of the fire smoke due to the operation of the ventilation systems when the fire occurred in the underground station (6 basement floors) and the tunnel at the great depth was measured. Fire smoke was generated by using a smoke generator which realized heat buoyancy effect by using hot air blower. The two locations of the fire were selected on the platform and on the platform of the tunnel located outside the screen door. A ventilation mode is generally used in which smoke is exhausted through a vent hole provided in a platform when a platform fire occurs. The tests were performed by operating the exhaust through the ventilation holes of the tunnel part located at both ends of the platform. The smoke density and the wind speed/velocity were measured at various positions, and the videos were taken to analyze the movement and smoke of the smoke. In both cases for fire inside the platform and in the railway tunnel, due to the ventilation mode operation of the fan for the platform and the exhaust of the fans in the tunnel smoke were well exhausted and the smoke propagation to the area near the smoke zone was suppressed. The smoke-control mode, which is applied to both fans for the platform and fans for in the tunnel at both ends of the platform, can provide a safer evacuation environment to the passengers from the fire smoke when the platform fire or fire train stops.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2008.11a
• /
• pp.49-54
• /
• 2008

나노결정입자와 일반 입자를 이용하여 $60cm{\times}60cm{\times}180cm$의 밀폐 공간에서 연기제거 성능을 평가해보았다. MgO, $CeO_2$, $Al_2O_3$, ZnO, $TiO_2$등의 나노결정입자와 $NaHCO_3$ 등의 일반입자를 사용하였다. 실험은 입자를 30초, 1분, 2분 간격으로 연기에 분사하여 시간에 따른 연기 제거 성능을 관찰해 보았고, 아울러 3, $6\;kgf/cm^2$등의 입자 분사 압력 변화에 따른 연기 제거 성능도 평가해 보았다. 평가 결과, $TiO_2{\fallingdotseq}MgO$ > ZnO > $CeO_2$ > $NaHCO_3$ > $Al_2O_3$의 순으로 연기 제거 성능이 우수하였다. MgO와 $TiO_2$를 분사한 경우 자연스럽게 연기가 제거 되는 속도보다 약 10배 정도로 빠르게 연기가 제거되었다. 분사압력이 $6\;kgf/cm^2$에서 $3\;kgf/cm^2$로 감소하면, 입자가 연기와 부딪히는 힘이 약하고 분출양이 작아서 연기 제거 성능도 아울러 감소한 것으로 판단된다. 연기 제거 성능은 입자의 특성, 분출 압력, 분출 양, 분사 노즐의 크기 등에 영향을 받는다. 따라서 효과적인 연기제거를 위해서는 이러한 조건을 최적화하는 것이 중요하다. 본 연구는 이러한 연기 제거 입자가 실제 화재에 적용하는 것을 최종적 목표로 한다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.43-52
• /
• 2011

With the rapid development of technology, skyscrapers are widely spread and they are tightly coupled. If fire occurs in a building, it is easily spread to neighboring buildings, resulting in the large number of victims and property damages. To remove fire disasters, the need for early fire detection techniques is increasing. To detect fire, detecting devices for heat, smoke, and flame have been used widely. However, this paper surveys and presents the latest research which focuses on early smoke and flame detection algorithms and systems with camera's input images. In addition, this paper implements and evaluates the performance of these flame and smoke detection algorithms with several types of movies.

• Fire Science and Engineering
• /
• v.20 no.2 s.62
• /
• pp.8-13
• /
• 2006

Numerical simulations were carried out for a fire in a clean room to confirm needs of a smoke control system and a sprinkler system, and to investigate a possible smoke spread-out. For a 1 MW methanol fire in a space of $39m{\times}13m$ floor and 4 m high, smoke spread-out was scrutinized for failure of the sprinkler system and/or the smoke control system. It was shown that the smoke control system removes smoke safely without the sprinkler system and that the sprinkler system is required to suppress smoke generation and spread of the fire, and to remove the smoke quickly. It was also confirmed that highly reliable sprinkler heads and automatic fire detection system are required for the sprinkler and smoke control systems.

• Fire Science and Engineering
• /
• v.34 no.1
• /
• pp.1-10
• /
• 2020

In this study, boron/silicon sol compounds were applied to wood for construction and durable materials, and fire risks were investigated in terms of smoke performance index (SPI), smoke growth index (SGI), and smoke intensity (SI). The compound was synthesized by reacting tetraethoxyorthosilicate with boric acid and boronic acid derivatives. Smoke characteristics were investigated using a cone calorimeter (ISO 5660-1) equipment for cypress wood. The fire intensity fixed the external heat flux at 50 kW/㎡. The smoke performance index measured after the combustion reaction increased between 13.4% and 126.7% compared with cypress wood. The fire risk due to the smoke performance index decreased in the order of cypress, phenylboronic acid/silicon sol (PBA/Si), (2-methylpropyl) boronic acid/silicon sol (IBBA/Si), boric acid/silicon sol (BA/Si). The smoke growth index decreased between 12.0% and 57.5% compared to the base specimen. The risk of fire caused by the smoke growth index decreased in the order of cypress, PBA/Si, IBBA/Si, BA/Si. The fire risk due to smoke intensity decreased between 3.2% and 57.8%, and in the order of cypress, PBA/Si, IBBA/Si, BA/Si. CO_peak concentrations ranged between 85 and 93 ppm, and decreased between 37% and 43% compared to the base specimen. A comprehensive assessment of the fire risk on smoke hazards decreased in the order of cypress, PBA/Si, IBBA/Si, BA/Si.

• 방재와보험
• /
• s.111
• /
• pp.20-27
• /
• 2006

피난길이가 긴 장대터널에서 화재가 발생되면 생성된 연기가 상승하고 천장을 만나 터널의 길이방향으로 전파된다. 연기의 독성가스에 의해 질식하게 되는 인명피해를 줄이기 위해서는 발생한 화재의 크기에 따라 제연유속이 필요하며, 제연 팬의 용량과 신뢰성을 확보해야 한다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.411-414
• /
• 2009

Many victims and property damages are caused in fires every year. In this paper, intelligent fire-detection systems with embedded fire-detection algorithms for early fire detection and alarm is proposed to reduce fire damages by using image processing technique, high speed digital signal processor(DSP) technique, and information technique. The fire detection algorithms used for the proposed systems consist of flame and smoke detection algorithms. If flame or smoke is detected respectively, the corresponding alarm signal can be transferred to management computer. And if flame and smoke is detected simultaneously, the fire alarm signal shall be generated. Through several experiments in the physical environment, it is shown that the proposed system works well without malfunction.