• 대한안전경영과학회지
• /
• 제16권4호
• /
• pp.379-389
• /
• 2014

Fire detectors are designed to minimize loss of life from a fire alarm system as an alarm to help evacuate more quickly until the completion of the evacuation alarm should be continued. the purpose of such alarms in order to achieve the characteristic fire heat release rate reaches a certain level, or when a certain time has elapsed, when the heat detector is to be alarms to answer. Requires a quick response, it is desirable to install the sensor as much as possible, but taking into account the cost of installation problems by engineering approach to minimize the quantity and rapidity of detection capability should be increased. In order to increase the rapidity of fire detectors in a room according to the height of the sensing period is to be maintained the optimum distance of the fire detector detects characteristics should be considered. Differential spot-type heat detectors installed domestic basis, depending on the type of sensor that can detect one sensor area is limited and less than 4m ceiling height regulations and simply double the number in excess of 4m and intended to be installed.

• 한국화재소방학회:학술대회논문집
• /
• 한국화재소방학회 2004년도 하계학술논문발표회 논문집
• /
• pp.138-143
• /
• 2004

• 조명전기설비학회논문지
• /
• 제17권4호
• /
• pp.64-73
• /
• 2003

빌딩자동제어시스템은 여러 서브시스템의 통합을 통한 고도의 서비스 제공, 관리비의 절감 등을 효과적으로 실현할 수 있다. 통합운전의 전제조건은 표준 프로토콜을 가진 개방형 네트워크를 이용하여 합리적인 네트워크 설계에 있다. 따라서 본 논문에서는 BAS에 가장 걸림돌이 되었던 화재경보시스템(소방법 명칭)을 ANSI/FIA 709.1인 LonTalk 프로토콜을 이용하여 BAS에서의 통합을 위한 개념적인 새로운 설계방안을 제시하였다. 기존 시스템에서 사용되는 중계기를 대체하는 지능형제어모듈을 개발하고 이를 이용하여 개방된 지능형 화재경보시스템의 설계방안을 제안한 것이다. 이는 오보률의 저감 실현은 물론 빌딩의 통합운전에도 크게 기여할 것으로 판단된다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.1275-1281
• /
• 2011

This paper presents synthetic circumstantial judgement system that detects and predicts a fire in subway station. Unlike conventional fire surveillance systems that judge the fire or not through smoke, CO, temperature or variation of temperature, a proposed system discovers a fire more easily or gives the alarm high possibility of fire to operator through recognition of fire levels based on Fuzzy Inference System using by FCM and information of objects from video data.

• 한국화재소방학회논문지
• /
• 제10권4호
• /
• pp.37-42
• /
• 1996

The "Intelligent Fire detecting and Extinguishing System" is an up-to-date fire protection system for modern high-rise buildings, international airports, enormous industrial facilities, dome stadiums such as specific areas in which the application of our local fire protection regulation could not be satisfied. The state-of-the art initiating devices communicated with sophisticated network control panels enable peoples to get reliable and powerful suppressions using water or gas, providing absolute protection. The Intelligent Water Cannon System, the Low Pressure $CO_2$ System and the MXL Networking Fire Alarm System introduced in this paper accomplish the dynamic protection for the special hazards.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.411-414
• /
• 2009

화재로 인해 많은 물적 인적 피해가 발생한다. 본 연구에서는 영상처리기법과 고속의 DSP 프로세서 기술 그리고 IT 기술을 활용하여 발화 초기에 화재를 인식하고 경보를 발생하여 화재에 조기 대응하는 화재 검출 알고리즘을 실장한 지능형 화재검출 시스템을 제안한다. 제안하는 지능형 시스템의 화재 검출 알고리즘은 화염검출과 연기검출 알고리즘으로 구성되어진다. 화염 또는 연기만 발생하는 경우에는, 각각의 경보를 관리용 컴퓨터에 전송한다. 화염과 연기가 동시에 발생하면 화재경보를 발생하도록 하였다. 다양한 환경에서의 실제 실험을 통해 오작동 없이 잘 동작하는 것을 확인할 수 있었다.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.468-474
• /
• 2022

본 논문에서는 딥러닝을 이용하여 실시간 화재경보 시스템을 구현하는 방법을 제안한다. 화재경보를 위한 딥러닝 학습 이미지 데이터셋은 인터넷을 통하여 1500장을 취득하였다. 일상적인 환경에서 취득된 다양한 이미지를 그대로 학습하게 되면 학습 정확도가 높지 않은 단점이 있다. 본 논문에서는 학습 정확도 향상을 위해 화재 이미지 데이터 확장 방법을 제안한다. 데이터증강 방법은 밝기 조절, 블러링, 불꽃사진 합성을 이용해 학습 데이터 600장을 추가해 총 2100장을 학습했다. 불꽃 이미지 합성방법을 이용하여 확장된 데이터는 정확도 향상에 큰 영향을 주었다. 실시간 화재탐지 시스템은 영상 데이터에 딥러닝을 적용하여 화재를 탐지하고 사용자에게 알림을 전송하는 시스템이다. Edge AI시스템에 적합한 YOLO V4 TINY 모델을 custom 학습한 모델을 이용해 실시간으로 영상을 분석해 화재를 탐지하고 그 결과를 사용자에게 알리는 웹을 개발하였다. 제안한 데이터를 사용하였을 때 기존 방법에 비하여 약 10%의 정확도 향상을 얻을 수 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 춘계학술발표대회
• /
• pp.35-38
• /
• 2009

The paper presents an effective method to detect fire in video surveillance and monitoring system. The main contribution of this work is that we successfully use the Hidden Markov Models in the process of detecting the fire with a few preprocessing steps. First, the moving pixels detected from image difference, the color values obtained from the fire flames, and their pixels clustering are applied to obtain the image regions labeled as fire candidates; secondly, utilizing massive training data, including fire videos and non-fire videos, creates the Hidden Markov Models of fire and non-fire, which are used to make the final decision that whether the frame of the real-time video has fire or not in both temporal and spatial analysis. Experimental results demonstrate that it is not only robust but also has a very low false alarm rate, furthermore, on the ground that the HMM training which takes up the most time of our whole procedure is off-line calculated, the real-time detection and alarm can be well implemented when compared with the other existing methods.

• 방재기술
• /
• 통권28호
• /
• pp.48-54
• /
• 2000

The technique detects radiant energy form a flaming fire of fuels contained carbonaceous material can be applied to fast growing fires. This technique applied detectors are ultimately effective when early detecting fire alarm system is required or the smoke and heat detectors can not applied. In Korea Fire regulation, a flame detector should be install in case that the installation height is higher than 20[m], chemical plant, hangar refinery. Therefore it is really necessary that a flame detector has to be developed as soon as possible. With foundation technique of flame detector, ideal sensing element and stable circuit design, a trial UV flame detector is manufactured. The stable and reliable technique of flame detector is established through the repeateed perfomance test and modification. An early detecting fire alarm device is developed through the modification, supplement of the structure and circuit. Results of the R & D for the manufacture of an excellent flame detecting device is carried out with the establishment of technique for the mass production and the qualified manufacturing process.

• 한국안전학회지
• /
• 제24권3호
• /
• pp.13-18
• /
• 2009

This paper is purposed to develop DAQ H/W, S/W and DB which can be used in developing electrical fire alarm system or in analyzing electrical fire cause, by detecting and monitoring precursor signals which have high possibility leading to electrical fire on electrical distribution wires. In this paper, developed was DAQ H/W adopting the C8051FXXX CPU which can analyze the measurement signals of current and voltage in electrical distribution wires, other CPU was investigated in view of the best digital sampling rate on the basis of previous researches for electrical fire alarm system. Also, the S/W which can interface with DAQ H/W's communication protocol and can be applied for electrical fire causes analysis, are embodied by LabVIEW. The combined DAQ H/W and S/W could analyze efficiently normal as well as abnormal electrical signals such as RMS value, instantaneous value of current and voltage, frequency signals etc, on the electrical wires. Also, DB system was constructed for recording various analysis results for precursor signals including voltage and current signals. The results by simulator and experiment showed that the suggested scheme with DAQ H/W, S/W and DB in this paper has high usability.