• Fire Science and Engineering
• /
• v.28 no.1
• /
• pp.1-11
• /
• 2014

This study aims to address the fire characteristics of Double-skin facade using the Fire Dynamics Simulator (FDS). To end this, Double-skin facade was classified into the four structures, that is Box, Shaft-box, Corridor, Multistory, through PyroSim program which was based on FDS, and further each structure of fire characteristics were analyzed numerically as well as comparatively in the current study. This study also examined smoke movement, smoke density, smoke detectors, and visibility in order to closely identify the each structure of fire characteristics. The results of the study discovered that the Box structure did not significantly affect smoke which was rising in the other rooms, except for the fire room whereas the Corridor structure had positive effects on Double-skin facade horizontally. In addition, the Shaft-box structure showed the fastest vertical movement by means of the shaft, on the other hand, rising smoke influenced the other rooms as well. The Multistory structure along with rising smoke had a great impact on the other divided rooms in a vertical way.

• Journal of the Korean Society of Earth Science Education
• /
• v.8 no.3
• /
• pp.387-398
• /
• 2015

The purposes of this study were to analyze the effect of a scaffold to help in understanding the principle of land and sea breeze through the convection current box experiment and to analyze the students' inference abilities and analogy abilities. For this purpose, the 60 elementary students who had not learned the principle of land and sea breeze were surveyed and analyzed. When using the scaffold to compare the movement of the incense smoke in the convection current box with that of the incense smoke on the outside of the convection current box, the rate of the students who correctly understood the principle of the land and sea breeze between the sea and the land was very low. The result shows that the scaffold used in this study do not help sufficiently in understanding the principle of the land and sea breeze through analogy and it is necessary to introduce a new scaffold for the elementary students to understand it.

• Fire Science and Engineering
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2001

This paper examined the variation in obscuration with height at indoor fire. The experiments were performed using a smoke box which is made for this job. It was found that the degree of smoke obscuration is depending upon the height. The obscurity at low position is less than that of high position. But there exist the deviation of obscurity at the position of air supply height.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.81-83
• /
• 2021

4차 산업 혁명과 함께 인공지능이 발전 하고 있다. 그 CNN 등 과 같은 이미지 관련 신경망들이 발전되어 가스 탐지와 같은 여러 분야에서 사용되고 있다. 하지만 가스 탐지는 Box 형태의 탐지가 일반적이고 Segmentation에 관한 연구는 있지만 연기와 같이 경계선이 불분명한 개체에 대해서는 연구가 미비하다. 본 논문에서는 Segmentation에 강력한 성능을 보이는 U-net을 활용하여 Box 형태가 아닌 Segmentation을 진행하여 픽셀단위로 연기를 탐지하고자 한다.

• Journal of the Korean Society of Tobacco Science
• /
• v.20 no.1
• /
• pp.108-114
• /
• 1998

This study was conducted to evaluate the techniques or analyzing tobacco smoke by statistical treatment method for the analytical data through Asia Collaborative Study V. In addition to five smoke components analysis, consisting of TPM, water, nicotine, NFDPM, and puff count of four cigarettes samples, statistical parameters such as mean, standard deviation, box-and-whisker plots, h plots, k plots, regression coefficients, reproducibility (R), and repeatability (r) were also calculated. Analysis of water content of cigarette smoke was the most difficult task, whereas puff count analysis was the easiest as well recognized by all laboratories. Analysis of nicotine and puff count accounted for both the lowest and the highest variation among four parameters. The water coefficients indicated more randomness or variation in the slops. The NFDPM data exhibited both types of deviations from linearity. Water content of sample D indicated the highest difference between two single results and between two interlaboratory test results. As a whole, KGTRI ranked higher in the analytical techniques for statistical evaluation of results when compared with the practices of 28 other laboratories.

• Journal of the Korean earth science society
• /
• v.31 no.3
• /
• pp.246-258
• /
• 2010

A convective circulation box was redesigned after analyzing reasons why adolescent elementary school students could not derive a convective circulation concept from the convection circulation box experiments. Even though students were in the formal operational period of Piaget, the adolescents felt difficult to understand a concept of the natural phenomena they have never seen before. Thus, we designed a method to help students increase their scientific understandings about the concept through developing a miniature convective circulation box. Findings indicated that an application of redesigned convective circulation box in the classroom experiment significantly increased the students' understanding about the convective circulations of land and sea breezes, and as well as their participation in the activities. In addition, the redesigned convective circulation box motivated students to develop their scientific thinking skills by allowing them to decide where to put visible incenses inside the box and to directly observe the smoke currents circulation formed accordingly. Redesigning and using a convective circulationbox as a miniature of natural phenomenon helps students avoid having misconceptions. The biggest merits of the box are that it is observable in all directions, it provides much clearer convective circulations comparing to the extant box, and it requires low production costs.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.4
• /
• pp.476-481
• /
• 2019

Early detection of fire is an important measure for minimizing the loss of life and property damage. However, fire and smoke need to be simultaneously detected. In this context, numerous studies have been conducted on image-based fire detection. Conventional fire detection methods are compute-intensive and comprise several algorithms for extracting the flame and smoke characteristics. Hence, deep learning algorithms and convolution neural networks can be alternatively employed for fire detection. In this study, recorded image data of fire in a ship engine room were analyzed. The flame and smoke characteristics were extracted from the outer box, and the YOLO (You Only Look Once) convolutional neural network algorithm was subsequently employed for learning and testing. Experimental results were evaluated with respect to three attributes, namely detection rate, error rate, and accuracy. The respective values of detection rate, error rate, and accuracy are found to be 0.994, 0.011, and 0.998 for the flame, 0.978, 0.021, and 0.978 for the smoke, and the calculation time is found to be 0.009 s.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.

• Journal of the Korean Society of Safety
• /
• v.23 no.6
• /
• pp.38-43
• /
• 2008

Significant portion of the fire accident is caused by some troubles in electric circuits. To prevent the fire induced by those electric trouble, some indications of electric fire need to be suitably detected at the first stage of the fire development. With this background, the characteristics of soot yielding of electric cables have been investigated using a light extinction method. In this study, a light scattering method was compared with the light extinction method. A slot-type premixed-flame combustor was traversed to bum three types of electric cables by compulsion, then the mass decrease rate and the soot densities were measured. According to the experimental results, the light scattering method is preferred to the light extinction method when the soot yield ratio is relatively small. Thus the former method is more suitable to detect the occurrence of an electric fire in a power distributer box.