• Proceedings of the KIEE Conference
• /
• 2008.04b
• /
• pp.125-127
• /
• 2008

전기재해에 취약한 장소에서의 화재는 많은 재산상의 피해와 사망자가 발생할 수 있으므로 전기재해에 취약한 장소에서 전기로 인하여 발생할 수 있는 화재를 사전에 예방하고 감시할 수 있는 시스템 개발의 필요성이 있다. 따라서 전기재해에 취약한 장소에서 전기설비를 감시할 수 있는 시스템을 개발하기 위해서는 전기재해 취약장소의 실태조사가 뒤따라야 하므로 전기재해 취약장소 중 하나인 재래시장 분전반을 중심으로 실태조사를 실시하고 그 내용을 분석하여 향후 전기재해에 취약한 재래시장에 알맞은 감시시스템 개발을 위한 기초자료 로 활용하고자 국내 17개소 재래시장 분전반의 실태조사를 실시하고 그 내용을 분석하였다.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2009.04a
• /
• pp.598-605
• /
• 2009

본 논문은 2008년 12월 5일 경기도 이천시 소재의 물류창고 화재사고에 대한 화재원인 및 화재확대요인을 검토하고, 재발방지를 위한 대책을 제시하였다. 본 화재원인 검토결과 용접작업 실화에 의한 화재로 벽체패널인 샌드위치패널과 문틀형 강을 접합하던 중 용접작업시 발생하는 불티 또는 고열에 의해 벽체패널 내부의 스티로폼 및 우레탄폼에 착화된 것으로 추정된다. 화재확대요인은 화재에 취약한 스티로폼 및 우레탄폼 재질의 샌드위치패널 사용과 소방설비의 인위적 기능해제로 판단된다. 이번 사고와 같은 재난을 예방하기 위해서는 급격한 연소확대 특성을 갖는 스티로폼 및 우레탄폼 재질의 샌드위치패널 사용금지, 소방설비의 기능해제에 대한 감시와 처벌강화와 안전관리체계 및 안전규칙 준수여부 관리 강화가 필요하다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.9-12
• /
• 2010

This paper presents design and implementation of infrared thermal image processing system based on the digital media processor for disaster monitoring. The digital thermal image processing board is designed and implemented by using commercial chips such as DM642 processor and video encoder, video decoder. The implemented functions for disaster monitoring are to analyze temperature distribution of a monitoring infrared thermal image and to detect disaster situation such as fire. For the input of infrared thermal image processing system, an infrared camera of type of the $320\;{\times}\;240\;{\mu}$-bolometer is used. The required functions are confirmed with 10 frame/second of processing performance by testing of the prototype and Practicality of the system was verified.

• Fire Science and Engineering
• /
• v.30 no.4
• /
• pp.103-110
• /
• 2016

While the demand for the gas system fire extinguishers increases every year, there are insufficient safety measures for assessing the extinguishing performance, such as system safety and reliability in the preparation of increasing demand, which has emerged as a social problem. One of the most critical causes of accidents occurring with the gas extinguishing system is pressure leakage from the extinguishing agent storage container. This is considered to be one of the critical factors on which the success of fire suppression depends. In this study, its safety measure was studied, Because it was deemed urgently necessary. The newly developed pressure leakage monitoring system is a system monitoring storage condition, pressure, leakage and discharge of the storage container related to agent concentration, which is one of the critical factors for fire suppression. This was developed to be applicable to the $CO_2$ and HFC-23 systems. Therefore, for structural safety analysis, the safety performance was verified by the fluid structure coupling analysis of the safety problems that may occur when the pressure leakage monitoring system is applied to the gas fire extinguisher. For analysis programs, the FloEFD program from Mentor Graphics was used for computational fluid dynamics analysis and ABAQUS from Dassault Systems was used for structural analysis. From the result of numerical analysis, the structure of $CO_2$ did not develop plastic deformation and its safety was verified. However, plastic deformation and deviation issue occurred with the HFC-23 monitoring system and therefore verified the structural safety of pressure leakage monitoring system by data obtained from redesigning and adjusting the condition of numerical interpretation three times.

• Fire Science and Engineering
• /
• v.22 no.3
• /
• pp.265-271
• /
• 2008

This study analyzed on the area of Samcheok, Kangwondo about forest fire alarming area and enlargement of the area. Then, visible area by unattended watching camera and watchtower for forest fire which were run by Samcheok was cross-checked with geographic information system, and it ould be whether effective on watching the area here the forest fire risk was high enough and also it could be expanded to larger forest fire. The result of study, the visible area by watching facilities only holds for 13.4% of the whole forest fire alarming area, but the forest fire can be observed even though it is occurred in small valley because of smoke and all the forest fire have been occurred in daytime. Therefore, it can be determined that watching area will be extended around 50.3% while the observation radii of watching facilities raise by 4km. However, Samcheok has much greater area of mountain area in compared to any other cities or counties, watching facilities should be installed and run additionally for extinguishing the forest fire from the beginning.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.62-64
• /
• 2019

산지등대가 무인화 됨에 따라 모국(우도등대)에서 산지등대의 시설물을 보안, 관리 및 운영에 대해 고민하고 효율적인 관리를 위해 검토 내용을 설명하고 예산절감 사례를 발표하고자 함.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.8
• /
• pp.1597-1603
• /
• 2017

The incidence of fire in underground utility tunnel is lower than other fires, but the damage caused by fire can cause social loss due to social management paralysis as well as economic loss. Hereupon, this paper presents the results of an empirical test on the construction of the underground utility tunnel condition monitoring system using the leakage coaxial cable installed in the underground utility tunnel. For this reason, a verification test was conducted by connecting a inductive coupler 200 Mbps power line communication modem with insertion loss characteristics of $-6{\pm}2dB$ to the installed the leakage coaxial cable installed in the underground utility tunnel. As a result, We confirmed sending/receiving of IP cameras up to 500 m. Therefore, it is judged that it is possible to construct a condition monitoring system for underground utility tunnel by using the leakage coaxial cables installed in the underground utility tunnels without installing additional communication lines for data transmission.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.343-345
• /
• 2020

사물인터넷 시대에 스마트 홈들의 출현으로 엣지 지역에서의 정확한 화재 감지 및 대응 기술에 대한 필요성이 요구되고 있다. 그러나, 화재 감지 동작에서 오작동으로 인한 잘못된 정보를 제공하거나, 감지 기기로부터의 불충분한 정보 제공은 화재 감지/예방을 효과적으로 수행하기 어렵게 한다. 본 논문에서는 사물인터넷 엣지 지역에서 기존의 다양한 센서들을 통해 데이터를 수집하여 온톨로지에서 추론과정을 진행하는 엣지형 온톨로지 시스템을 구현한다. 본 논문에서는 추론된 정보를 바탕으로 사물인터넷 엣지에서 발생되는 화재 사건에 대한 정확한 판단할 수 있게 한다. 제안된 화재 추론 온톨로지를 이용해 기존의 화재감지기가 제공하는 정보 뿐 만 아니라 화재 정보에 대한 확장된 정보를 사용자에게 제공하므로 사용자 유용성을 개선될 수 있음을 보인다.

• Fire Science and Engineering
• /
• v.26 no.1
• /
• pp.96-101
• /
• 2012

The buildings of domestic wear the upper floors and an underground in-depth reconciliation tendency to do and the possibility of fire occurrence at the time of formation accident is coming to be high. Therefore will be scattered to various place and is established and prevention of disaster information of the receiver which will integrate there is a necessity which will manage. In this paper away where each receiver is installed in the fire for the remote monitoring and controld able to connect to the Internet and fiber optic cable that can be networked fire receiver and control desk was constructed. Between each device can be used by the fire, and more depending on the status of monitoring and alarm, control and maintenance can be performed to develop an integrated management system. The system is evaluated by the criteria of the KFI, and for each segment of the signal propagation time to perform experiments confirmed the reliability of the performance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.139-141
• /
• 2017

화재는 다른 재난보다 확산 속도가 빠르기 때문에 신속하고 정확한 감지와 지속적인 감시가 요구된다. 최근, 신속하고 정확한 화재 감지를 위해, CCTV(Closed-Circuit TeleVision)으로 획득한 이미지를 기계학습(Machine Learning)을 이용해 화재 발생 여부를 감지하는 화재 감지 시스템이 주목받고 있다. 본 논문에서는 기계학습의 기술 중 정확도가 가장 높은 딥러닝(Deep Learning)기반의 CCTV 화재 감지 시스템을 제안한다. 본 논문의 시스템은 딥러닝 기술 적용뿐만이 아니라, CCTV 이미지 전처리 과정을 보완함으로써 딥러닝에서의 미지 데이터(unseen data)의 낮은 분류 정확도 문제인 과적합(overfitting)문제를 해결하였다. 본 논문의 시스템은 약 80,000 개의 CCTV 이미지 데이터를 학습하여, 90% 이상의 화재 이미지 분류 정확도의 성능을 보여주었다.