• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.413-419
• /
• 2004

This paper describes a technique that can predict electric fires by detection of discharge voltage signals caused by the use of electric facilities. In the experiment, various discharge modes, a flashover or a surface discharge through insulation paper and a line to line short, were simulated to acquire electrical information for predicting electrical fire as discharge modes. From the experimental results, it is hewn that electorial discharges which are ranked as majority causes of electric fires generate characterized signals distinguished from power frequency. Finally. We designed a prototype discharge detector based on the experimental results, and the detector is applied to a power lines. This study showed that the prediction of electric fires is possible by monitoring discharge voltage signals in electric power lines.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.1
• /
• pp.57-65
• /
• 2024

In a fire-resistant structure, uncertainties arise in factors such as ventilation, material elasticity modulus, yield strength, coefficient of thermal expansion, external forces, and fire location. The ventilation uncertainty affects thefactor contributes to uncertainties in fire temperature, subsequently impacting the structural temperature. These temperatures, combined with material properties, give rise to uncertain structural responses. Given the nonlinear behavior of structures under fire conditions, calculating fire fragility traditionally involves time-consuming Monte Carlo simulations. To address this, recent studies have explored leveraging machine learning algorithms to predict fire fragility, aiming to enhance efficiency while maintaining accuracy. This study focuses on predicting the fire fragility of a steel moment frame building, accounting for uncertainties in fire size, location, and structural material properties. The fragility curve, derived from nonlinear structural behavior under fire, follows a log-normal distribution. The results demonstrate that the proposed method accurately and efficiently predicts fire fragility, showcasing its effectiveness in streamlining the analysis process.

• 한국방재학회:학술대회논문집
• /
• 2011.02a
• /
• pp.190-190
• /
• 2011

사회 다변화 및 급속한 경제성장과 도시밀집화로 인하여, 화재의 발생으로 인하여 막대한 인명피해 및 대규모의 재산상의 피해가 지속적으로 발생하고 있다. 이러한 화재의 피해를 예측하기 위해서는 실제 규모의 화재실험이 매우 유용하지만, 막대한 비용과 현실적 제약조건으로 인하여 실제 실험에는 많은 어려움이 따른다. 따라서 막대한 예산이 소요되는 실제규모의 화재실험의 대체방법으로 실제를 모사하는 축소모형 화재모의실험 및 컴퓨터를 이용한 화재 시뮬레이션 기법이 널리 이용되고 있다. 본 논문에서는 범용 컴퓨터를 이용한 화재 시뮬레이션 기법(CFAST)을 이용하여 수직 공간 구성을 가지는 단독주택의 화재 성상을 검토하였다. 시뮬레이션 모델로는 단독주택을 대상건물로 하여 2층으로 수직 공간을 가지는 단독주택 건물에 대한 모의 화재 시뮬레이션을 수행 하였다. 화재 시뮬레이션 결과는 각 구획실별 온도, 일산화탄소량, 공기 중 산소량 등을 도출하여 기존 이론에 의한 화재성장 그래프와 시뮬레이션 데이터를 비교하여 정확도를 검토하였다. 본 논문에서는 두가지의 시나리오를 작성하여 화재 시뮬레이션 프로그램의 결과 값을 분석하였다. (1) 시나리오 1 : 화재시뮬레이션 대상건물 1층 거실(2번방)에서 스프링클러 미 설치시 화재가 발생한 경우를 가정하여 수평방향인 3번방과 수직방향인 7번방의 화재 확산 피해정도를 살펴보고, 화재 그래프의 이론값과 실험값의 차이를 비교하여 그 정합성을 검토하였다. 발화물질은 Curtain, TV set, Sofa, Table으로 하며 시간은 60초 간격으로 총 3600초(1시간)를 분석 하였고, 발화지점의 온도, 일산화탄소, 공기중 산소 농도를 분석하였다. (2) 시나리오 2 : 시나리오 1과 동일한 화재발현 조건으로 스프링클러가 설치되어 있을 때 화재 발생 했을 경우, 수평방향인 3번방과 수직방향인 7번방의 화재 확산 피해를 시나리오 1과 비교 검토 하였다. 기존 이론에 의한 화재 성장 그래프와 이번 시뮬레이션 결과값을 토대로 만든 그래프 형태를 비교해보면 두 그래프의 형태가 비슷한 형태를 나타내어 Flash Over 현상과 Back Draft 현상이 이론값과 같은 경향을 나타내고 있음을 확인 할 수 있었다. 따라서, 본 논문에서 수행한 화재 시뮬레이션 기법으로 건축물의 실제 화재시의 피해정도를 예측하는 데 유용하게 활용될 것으로 판단된다.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.245-253
• /
• 2021

Purpose: This study develops a risk prediction model that predicts the risk of a fire site by using initial information such as building information and reporter acquisition information, and supports effective mobilization of fire fighting resources and the establishment of damage minimization strategies for appropriate responses in the early stages of a disaster. Method: In order to identify the variables related to the fire damage scale on the fire statistics data, a correlation analysis between variables was performed using a machine learning algorithm to examine predictability, and a learning data set was constructed through preprocessing such as data standardization and discretization. Using this, we tested a plurality of machine learning algorithms, which are evaluated as having high prediction accuracy, and developed a risk prediction model applying the algorithm with the highest accuracy. Result: As a result of the machine learning algorithm performance test, the accuracy of the random forest algorithm was the highest, and it was confirmed that the accuracy of the intermediate value was relatively high for the risk class. Conclusion: The accuracy of the prediction model was limited due to the bias of the damage scale data in the fire statistics, and data refinement by matching data and supplementing the missing values was necessary to improve the predictive model performance.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2011.04a
• /
• pp.47-52
• /
• 2011

컴퓨터 시뮬레이션과 건물의 센서를 접목한 센서연동 화재모델을 개발하였다. 화재 발생 시 건물 내 상태를 센서로 측정하며 이는 실시간으로 화재모델에 주입이 된다. 모델이 도출하는 시나리오와 센서 측정값을 비교분석하여 모델의 입력 변수를 조율하며 궁극적으로 모델이 실제 화재와 유사한 시나리오를 도출할 수 있도록 한다. 실제 규모의 화재 실험을 실시하였고, 센서연동 화재모델이 화재의 시작위치와 건물 내 출입문의 개폐 상태를 추정할 수 있음을 보였다.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2013.11a
• /
• pp.206-207
• /
• 2013

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.

• Fire Science and Engineering
• /
• v.25 no.5
• /
• pp.93-99
• /
• 2011

In the present study, a numerical simulation was conducted to estimate the prediction performance of FDS on the carbon monoxide production in the under-ventilated compartment fires. Methane and heptane fires located in the a 2/5 scale compartment based on the ISO-9705 standard room was simulated using FDS Ver. 5.5. Through the comparison between the computed results and the earlier published experimental data, the performance of FDS was estimated on the predictions of the combustion gases concentration in the hot upper layer of the compartment and the effects of CO yield rate on the estimation of CO production at local points were analyzed. From the results, it was known that FDS Ver. 5.5, in which the two-step reaction mixture fraction model implemented, was more effective on the prediction of CO concentration compared to the previous FDS version. In addition, controlling CO yield rate made the predicted CO concentration get closer to the experimental data for the fires of the under-ventilated condition.

• Fire Science and Engineering
• /
• v.26 no.3
• /
• pp.21-28
• /
• 2012

The objective of this study is to evaluate the prediction accuracy of FDS(Fire Dynamic Simulator) for the thermal and chemical characteristics of under-ventilated fire with unsteady fire growth in a semi-closed compartment. To this end, a standard doorway width of the full-scale ISO 9705 room was modified to 0.1 m and the flow rate of heptane fuel was increased linearly with time (until maximum 2.0 MW based on ideal heat release rate) using a spray nozzle located at the center of enclosure. To verify the capability of FDS, the predicted results were compared with a previous experimental data under the identical fire conditions. It was observed that with an appropriate grid system, the numerically predicted temperature and heat flux inside the compartment showed reasonable agreement with the experimental data. On the other hand, there were considerable limitations to predict accurately the unsteady behaviors of CO and $CO_2$ concentration under the condition of continuous fire growth. These results leaded to a discrepancy between the present evaluation of FDS and the previous evaluation conducted for steady-state under-ventilated fires. It was important to note that the prediction of transient CO production characteristics using FDS was approached carefully for the under-ventilated fire in a semi-closed compartment.

• Fire Science and Engineering
• /
• v.32 no.2
• /
• pp.7-16
• /
• 2018

In this study, the previous design fire curve for fire simulation was modified and re-suggested. Numerical simulations with the FDS and CFAST were performed for the n-heptane and n-octane pool fires in the ISO 9705 compartment to evaluate the prediction performances of the previous 1-stage and modified 2-stage design fire curves. The numerical results were compared with the experimental temperature and concentrations of $O_2$ and $CO_2$. The FDS and CFAST simulations with the 2-stage design fire curve showed better prediction performance for the variation of temperature and major species concentration than the simulations with 1-stage design fire curve. Especially, the simulations with the 2-stage design fire curve agreed with the experimental temperature more reasonably than the results with the 1-stage design fire curve. The FDS and CFAST simulations showed good prediction performance for the temperature in the upper layer of compartment and the results with the FDS and CFAST were similar to each other. However, the FDS and CFAST showed poor and different prediction performance for the temperature in the lower layer of compartment.