• 반도체디스플레이기술학회지
• /
• 제23권1호
• /
• pp.19-24
• /
• 2024

It is not an exaggeration to say that a single fire causes a lot of damage, so fires are one of the disaster situations that must be alerted as soon as possible. Various technologies have been utilized so far because preventing and detecting fires can never be completely accomplished with individual human efforts. Recently, deep learning technology has been developed, and fire detection systems using object detection neural networks are being actively studied. In this paper, we propose a new fire detection system that improves the previously studied fire detection system. We train the YOLOv8 model using refined datasets through improved labeling methods, derive results, and demonstrate the superiority of the proposed system by comparing it with the results of previous studies.

• 센서학회지
• /
• 제33권3호
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2004년도 춘계학술대회 논문집
• /
• pp.165-170
• /
• 2004

As industry develop rapidly, a possibility of railway-disasters (fire), are growing in consideration of speedy railway and increasing long tunnels. In Korea, KTX consists $46\%$ of tunnels constructed since early 1990, prescribed prevention disasters standard, taking into account that the train accident occurred. On this provision which refers other country's a high-speed railway fire safety regulation and is synthetically reflected topographical circumstance and tunnel size in Korea, in order to minimizing valuable casuality and securing safety operation of train from rapid evacuation and rescue a passenger from accident in tunnel.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.196-201
• /
• 2006

Due to the damage which is caused by with the smoke, in the analysis statistics of a fire accident smoke is becoming the important evaluation index of fire quality. We must follow the procedures to use interior material for railway car as stated the Safety regulation for the urban railway car. In this study, we compared the Smoke Density of the train seat by test between Cone-Calorimeter and Smoke Density-Chamber. The results showed that the smoke density by test between Cone-Calorimeter and Smoke Density-Chamber is visible a similar tendency.

• 한국자동차공학회논문집
• /
• 제20권4호
• /
• pp.82-91
• /
• 2012

This paper deals with the development and feasible study of the train to pedestrian protection airbag. The concept of the airbag system is to protect the pedestrian like as workers on railroad. The airbag system includes cushions, gas generators, a housing, sliding fixture, anti-bouncing airbag, and a leg protection bumper. Those things were designed and fabricated. The performance of the airbag system was evaluated in the sense of the static deployment test, drop test, dynamic motion test and field(train level) test. The deployment logic, TTF(Time to fire), and the inner pressure of the cushion were also investigated for the airbag.

• 한국안전학회지
• /
• 제23권4호
• /
• pp.1-6
• /
• 2008

This experiments are perfol1ned to investigate the effect of ventilation velocity on a high pressure water mist tire suppression in train. The experiment is conducted in half scale modeled train of a steel-welled enclosure (5.0m${\times}$2.4m${\times}$2.2m). The ventilation velocity is controlled by the ventilation duct through an inverter in the range of 0 to 3m/s. The coverage-radius and an injection angle of an high pressure water mist system are measured. The mist nozzle with 5-injection holes is operated with pressure 60bar. The heptane pool fires are used. The fire extinguishment times and the temperature are measured for the ventilation velocities. In conclusion, because the momentum of injected water mist is more dominant than that of ventilation air, the characteristics of water mist, the fire extinguishment times and the temperature are affected very little by ventilation velocity.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2007년도 하계학술발표대회 논문집
• /
• pp.96-96
• /
• 2007

• 한국터널지하공간학회 논문집
• /
• 제19권5호
• /
• pp.705-715
• /
• 2017

본 연구에서는 해저터널 내부에서 발생하는 해저유출수를 소화용수로 사용하기 위해서, 압축공기포(CAF) 소화설비의 소화용수 적용성을 확인하였다. KS B ISO 7203-1(비수용성 액체에 적용되는 상부주입식 저팽창 포원액 사양) 규격에 따라 포수집기를 제작하였으며, 소화용수를 담수로 19회, 해수로 15회로 총 34회 실험을 하였다. 포 환원시간은 담수는 평균 237.73초, 해수는 평균 215.60초로 측정되어, 해수의 압축공기포(CAF) 소화용수 적용성을 확인하였다. 아울러, 열차 내 화재를 직접적으로 소화할 수 있도록 창문 파괴장치를 제작하고, 3차례 실물화재 실험을 수행하였다. 마지막 3차 실험에서는 2초만에 유리를 파괴하고 소화활동을 할 수 있는 구멍을 만들었으며, 이동식 압축공기포(CAF) 소화기를 사용하여 3초 만에 화재를 진압하였다.

• 한국터널지하공간학회 논문집
• /
• 제24권4호
• /
• pp.327-339
• /
• 2022

본 연구에서는 지하철 승강장에서 열차화재가 발생하는 경우, 승강장 제연풍량 및 제연모드(급기 또는 배기)에 따른 정량적 위험도 평가를 통해 안전확보에 효과적인 제연풍량 및 모드를 제시함을 목적으로 한다. 이를 위해 중앙계단을 갖는 상대식 승강장을 모델로 하여 화재발생 시나리오를 작성하였으며, 시나리오별 화재해석을 수행하여 연기전파특성과 ASET을 비교·분석하고 대피해석을 수행하여 사망자수를 예측하였다. 또한, 시나리오별로 화재사고 발생률(F)/사망자수(N)선도(F/N선도)를 작성하여 제연풍량 및 제연모드에 따른 위험도를 비교·평가하였다. 소방시설 등의 성능위주 설계 방법 및 기준에서 정하는 유해요소(일산화탄소, 온도, 가시거리)에 대한 ASET 분석에서는 가시거리의 영향이 가장 크게 나타나고 있으며, 화재열차의 승강장 진입지연을 고려하지 않은 경우에 풍량을 4 × 833 m³/min할 때 ASET은 약 800초 정도로 분석되었다. 예상사망자수는 화재차량위치에 따라 큰 차이가 있으며, 계단부에 인접한 차량에서 화재가 발생하는 경우에 선두부 차량대비 3배 까지 증가하는 것으로 나타나고 있다. 또한 제연풍량이 증가하면 사망자수가 감소하며 배기 보다는 급기방식이 감소율이 증가한다. 급기풍량이 4 × 833 m³/min일 때 예상 사망자수는 제연을 수행하지 않는 경우 대비 13%수준으로 감소하는 것으로 나타났다. 위험도 평가결과, 제연을 수행하는 경우에는 현행 사회적 위험도 평가기준을 만족하는 것으로 나타나고 있으며, 예상사망자수는 제연을 수행하지 않는 경우, 10,000년에 29.9명에서 제연을 수행하는 경우에는 풍량이 4 × 833 m³/min일 때 4.36명으로 감소하는 것으로 분석되었다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.585-593
• /
• 2011

Actual fire test under a laboratory and fire simulation by using computer are considered into main methodology in order to estimate and predict fire size of railway train. Even if practical fire size could be obtained from the full-model railway car test such as a large scale cone-calorimeter test, it is not always possible and realistic due to that expensive cost and attendant dangers could in no way be negligible. In this point of view, fire simulation analysis method based on the computational fluid dynamics could be proposed as an alternative and it seems to be also efficient and reasonable. However, simulation results have to be verified and validated in accordance with the proper procedure including comparing analysis with the actual fire test. In this paper, fire load and growth aspect was investigated through the room corner test (ISO 9705) for the mock-up model of the actual railway car. Then, it was compared with the output data derived from the simulation by using Pyrolysis Model of the FDS (Fire Dynamics Simulator, by NIST) for the exact same domain and condition corresponding with pre-performed room-corner test. This preliminary verified and validated fire modeling method could enhance the reliability of output data derived from the fire simulation under the similar domain and condition.