• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.1065-1070
• /
• 2018

These days there are many researches on the vision based technology using deep learning. The lots of studies on the intelligent operation and maintenance for railway station system used technologies with vision analysis function. This paper analyzes the papers which studied the intelligent station system with vision analysis function for passengers and facilities monitoring, platform monitoring, fire monitoring, and effective operation and design. Also, this paper proposes research which uses the more powerful vision technology with deep-learning for smart railway station system.

• Fire Science and Engineering
• /
• v.17 no.4
• /
• pp.98-104
• /
• 2003

Smoke control in il space 10 m${\times}$3 m floor and 5.4 m high around the stairway of a subway station platform was simulated by using FDS to investigate problems of smoke control in Daegue subway stations. Distributions of temperature and smoke particles, and variation of the number of particles with time for a 200 ㎾ polyurethane fire were compared. It was shown that the purge system fails to remove smoke efficiently and that the extraction system has the highest perfor-mance among the three smoke control systems for the given situations. Simply switching the purge system into extraction mode might improve much the smoke removal performance.

• Fire Science and Engineering
• /
• v.17 no.3
• /
• pp.7-12
• /
• 2003

A 50 kW polyurethane fire in a compartment of 4 m ${\times}$ 1 m ${\times}$ 1.5m with large openings similar to a subway station was simulated by a large eddy simulation to investigate the fire and smoke control. The NIST FDS, which employed a mixture fraction combustion model and a finite volume method for radiation, was utilized. Distribution of temperature and smoke particles was compared with in the lower and upper corridors for three different smoke control systems, ventilation, purge, and extraction, starting in 5 sec from the ignition of the fire. For the given geometries, the ventilation system showed the best smoke removal rate and lowest temperature distribution in the both corridors. It was confirmed that the purge system is not recommended for a subway station since the smoke removal rate of the purge system was worse than that without a smoke control system.

• 한국가시화정보학회:학술대회논문집
• /
• 2005.12a
• /
• pp.64-68
• /
• 2005

In this study, the smoke flows of the inner subway station were visualized through a numerical analysis and visualization experiment in the subway fire. A transparent acrylic model was designed and installed as 1:25th scale-down as the actual subway station by using geometrical similarity The properties of subway fire were reconstructed according to Densimetric Froude Similarity. The 47 to 53 ratio of the mixed air and Helium was inputted in the inner acrylic model to describe 1MW fire intensity with reference to the experiment paper. For the same time, the fire smoke from a smoke generator was inputted in the inner acrylic model with the mixture. At this time, the buoyancy effect of Helium gas went up the smoke to the acrylic model. When the sheet beam of Ar-lon laser was given out to the top and stair of subway model, the digital camcorder took the images of the scattered cluster of smoke particles when applying the smoke management system and PSD.

• Journal of the Korean Society of Safety
• /
• v.21 no.6 s.78
• /
• pp.1-6
• /
• 2006

Subway platform is divided into Side-platform type and Center-platform type. In this study does quantitative fire risk assesment of subway platform types in numerical analysis by using CFD model. From the result of this study, 1) All exhaust mode was low-end result it seems most fire risk at Side-platform station. 2) All exhaust mode was low-end result it seems most fire risk at Center-Platform station. 3) When comparing same type exhaust mode of Side-platform and Center-platform that last thing was visible $9.1{\sim}72.34%$ low-end fire risk. Center-platform is more opera-tive than Side-platform that reduce fire risk when that was same dimension and external environment. Designer look upon a fire characteristic of subway platform types when he make smoke control air volume and platform area design.

• Proceedings of the KIEE Conference
• /
• 2005.10c
• /
• pp.261-263
• /
• 2005

본 연구는 지하철 역사 내에서 일어나는 사고를 예방하기 위한 역사 내 안전사고 유형 분석을 실시하였다. 지하철 역사 내에 일어나는 사고에 대한 조사를 통해 역사 내 안전사고 유형을 파악하여 안전사고 예방시스템 구현에 활용하고자 한다. 역사 내 사고 유형 분석을 통해 이용승객의 안전성 확보와 승강장 선로에 물건이나 사람이 떨어진 경우 혹은 화재 등의 비상상황발생시 안전시스템을 통해 컴퓨터가 신속히 검지하여 차량과 종합사령실에 알려 차량의 진입을 막아 사전에 피해를 줄이는데 활용할 것이다. 따라서 본 연구를 통해 위급상황에 대한 안전시스템 구성에 도움을 줌으로써 사회적으로 귀중한 생명을 보호하며, 경제적으로는 안전사고 발생에 따른 처리 비용과 안전사고에 따른 지하철 운행지연. 운행 중지 등으로 인한 경제적 비용을 절감할 수 있다.

• Fire Science and Engineering
• /
• v.25 no.4
• /
• pp.89-93
• /
• 2011

It is not recommended that elevator use for egress at (super) high rise buildings because elevator shaft main roles to spread of fire smoke. But in North America used to protect this area by elevator shaft pressurization. These tests are performed at high rise apartment to verify that elevator shaft pressurization can protect to spread of fire smoke or not. and verify to used for egress at fire. Pressurization at elevator shaft make pressure difference of 50 Pa all floor at 150 CMM because this method have low friction loss from air flow. Also when dwelling door and elevator door are opened that critical velocity is performed to protect of back-layering from fire room for escape routs by 180 CMM. Therefore through out these pressurization tests by elevator shaft are estimated to have less overpressure because supply air difference are low between to satisfy critical velocity at one door opened and maintain to pressure difference all doors closed. Finally we verified that disable or residual people can use elevator for egress at fire by elevator shaft pressurization.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.845-856
• /
• 2017

In the long railway tunnel, in order to secure safety in case of fire, it is required a emergency station. However, there is no standard or research results on smoke exhaust method and exhaust flow rate in emergency station, so it is necessary to study the smoke exhaust system for emergency station. In this study, we are created a numerical analysis model for emergency station where the evacuation cross passage connected to the service tunnel or the relative tunnel was installed at regular intervals (40 m intervals). And the fire analysis are carried out by varying the fire intensity (15, 30MW), the smoke exhaust method (only air supply, forced air supply and exhaust, forced air exhaust only), and the air flow rate (7, 14, $40m^3/s$). From the results of fire analysis, temperature and CO concentration are analyzed and ASET based on the limit temperature are compared at various condition. As a result, in the case with fire intensity of 15 MW, it is shown that a sufficiently safe evacuation environment can be ensured by applying forced air supply and exhaust method or forced air exhaust only method when the air flow rate is $7m^3/s$ above. In case of fire intensity of 30 MW, it is impossible to maintain the safety evacuation environment for more than 900 seconds when the exhaust air volume is below $14m^3/s$. And when the air flow rate is $40m^3/s$, the exhaust port is disposed at the side portion of the upper duct, which is most advantageous for securing the temperature-based safety.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.1809-1815
• /
• 2008

This experiment simulated the fire driven flow of an underground station through parallel processing method. Fire analysis program FDS(Fire Dynamics Simulation), using LES(Large Eddy Simulation), has been used and a 6-node parallel cluster, each node with 3.0Ghz_2set installed, has been used for parallel computation. Simulation model was based on the Kwangju-geumnan subway station. Underground station, and the total time for simulation was set at 600s. First, the whole underground passage was divided to 1-Mesh and 8-Mesh in order to compare the parallel computation of a single CPU and Multi-CPU. With matrix numbers($15{\times}10^6$) more than what a single CPU can handle, fire driven flow from the center of the platform and the subway itself was analyzed. As a result, there seemed to be almost no difference between the single CPU's result and the Multi-CPU's ones. $3{\times}10^6$ grid point one employed to test the computing time with 2CPU and 7CPU computation were computable two times and fire times faster than 1CPU respectively. In this study it was confirmed that CPU could be overcome by using parallel computation.