• Proceedings of the Safety Management and Science Conference
• /
• 2013.04a
• /
• pp.471-484
• /
• 2013

Large and complicated firefighting environment is accelerating in the early activities in the field of fire officials at the time limit situation leads to people's lives and property damage, as well as the loss of the Fire Service. Therefore, the state-of-the-art technology that can respond to rapidly changing fire environment urgently in the field of fire fighting have been introduced should be utilized. These intelligent firefighting robots build daegukmin firefighting safety net that can be used when. Other advanced technology industries, the most effective ways that can be introduced into the firefighting shall be provided in the current situation of the industry's initial firefighting robots.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.320-330
• /
• 2020

Fire is difficult to achieve good performance in image detection using deep learning because of its high irregularity. In particular, there is little data on fire detection in underground utility facilities, which have poor light conditions and many objects similar to fire. These make fire detection challenging and cause low performance of deep learning models. Therefore, this study proposed a fire detection model using deep learning and estimated the performance of the model. The proposed model was designed using a combination of a basic convolutional neural network, Inception block of GoogleNet, and Skip connection of ResNet to optimize the deep learning model for fire detection under underground utility facilities. In addition, a training technique for the model was proposed. To examine the effectiveness of the method, the trained model was applied to fire images, which included fire and non-fire (which can be misunderstood as a fire) objects under the underground facilities or similar conditions, and results were analyzed. Metrics, such as precision and recall from deep learning models of other studies, were compared with those of the proposed model to estimate the model performance qualitatively. The results showed that the proposed model has high precision and recall for fire detection under low light intensity and both low erroneous and missing detection capabilities for things similar to fire.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1257-1262
• /
• 2018

In this paper, a deep learning method is proposed to detect the fire effectively by using video of surveillance camera. Based on AlexNet model, classification performance is compared according to kernel size and stride of convolution layer. Dataset for learning and interfering are classified into two classes such as normal and fire. Normal images include clouds, and foggy images, and fire images include smoke and flames images, respectively. As results of simulations, it is shown that the larger kernel size and smaller stride shows better performance.

• Fire Science and Engineering
• /
• v.9 no.1
• /
• pp.3-9
• /
• 1995

This paper is a study to dectect the tracking owing to deterioration of indoor wiring, and to prevent the electrical fire. After analysing the harmonics of waveshapes in load current and tracking current by FFT, a method of identifying the tracking was developed by using neural network. Fluoscent lamp, witch was mostly used in indoor, was chosen as the load used in this study. When the learning number in neural network was more then 30,000 times, an excellent neural net-work which could correctly identify the tracking was established. Therefore, the result of this study can be utilized as a basic material in various measuring instruments, such as an hotline inslation tester, earth tester in vehicles, and tracking fire alarm device, witch can detect the tracking under the condition of hotline.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2005.11a
• /
• pp.316-320
• /
• 2005

• Nuclear Engineering and Technology
• /
• v.49 no.2
• /
• pp.342-348
• /
• 2017

Precursor analysis is widely used in the nuclear industry to judge the significance of events relevant to safety. However, in case of events that may damage equipment through effects that are not ordinary functional dependencies, the analysis may not always fully appreciate the potential for further evolution of the event. For fires, which are one class of such events, this paper discusses modelling challenges that need to be overcome when performing a probabilistic precursor analysis. The events used to analyze are selected from the Organisation for Economic Cooperation and Development (OECD) Fire Incidents Records Exchange (FIRE) Database.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.719-720
• /
• 2024

센서 기반의 자동화재탐지설비의 역할을 지원할 목적으로, 합성곱 신경망 기반의 AI 화재 감시장비등이 연구되어왔다. ai 기반 화재 감지에 사용되는 알고리즘은 전이학습을 주로 이용하고 있고, 이는 화재 감지에 기여도가 낮은 프로세스가 내장되어 있을 가능성이 존재하여, 딥러닝 모델의 복잡성을 가중시키는 원인이 될 수 있다. 본 연구에서는 이러한 모델의 복잡성을 개선하고자 다양한 딥러닝 및 해석 기술들을 분석하였고, 분석 결과를 토대로 화재 감지에 최적화된 아키텍처인 "IF2bNet" 을 제안한다. 구현한 아키텍처의 성능을 비교한 결과 동일한 성능을 내면서, 파라미터를 약 0.1 배로 경량화 하여, 복잡성을 완화하였다.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1157-1166
• /
• 2021

In this study, a numerical sensitivity analysis was performed to determine the fire suppression time for a large number of water mist nozzles in a large fire compartment. Fire simulations were performed using FDS (Fire dynamics simulator) 6.5.2 under the same condition as the test scenario 5 of the International Maritime Organization (IMO) 1165 test protocol. The sensitivities of input parameters including cell size, extinguishing coefficient (EC), droplets per second (DPS), and peak heat release rate (HRR) of fuel were investigated in terms of the normalized HRR and temperature distribution in the compartment. A new method of determining the fire suppression time using FDS simulation was developed, based on the concept of the cut-off time by cut-off value (COV) of the heat release rate per unit volume (HRRPUV) and the cooling time by the HRR cooling time criteria value (CTCV). In addition, a method was developed to determine the average EC value for the simulation input, using the cooling time and cut-off time.

• Fire Science and Engineering
• /
• v.17 no.4
• /
• pp.7-12
• /
• 2003

The heat of combustion is one of the major physical properties used to determine the fire and explosion hazards of the flammable substances. Empirical equations have been developed to pre-dict the net heats of combustion of organic halogenated compounds based on the atomic contribution method. The method developed in this study was compared with Cardozo's method and Hanley's method. As can be seen from the average absolute deviation(A.A.D.), the proposed equation was found to be best. The proposed equation may serve as an estimation scheme for the heats of combustion of the other organic halogenated compounds.