• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.112-119
• /
• 2019

In this paper, we propose a deep learning structure suitable for embedded system. The flame detection process of the proposed deep learning structure consists of four steps : flame area detection using flame color model, flame image classification using deep learning structure for flame color specialization, $N{\times}N$ cell separation in detected flame area, flame image classification using deep learning structure for flame shape specialization. First, only the color of the flame is extracted from the input image and then labeled to detect the flame area. Second, area of flame detected is the input of a deep learning structure specialized in flame color and is classified as flame image only if the probability of flame class at the output is greater than 75%. Third, divide the detected flame region of the images classified as flame images less than 75% in the preceding section into $N{\times}N$ units. Fourthly, small cells divided into $N{\times}N$ units are inserted into the input of a deep learning structure specialized to the shape of the flame and each cell is judged to be flame proof and classified as flame images if more than 50% of cells are classified as flame images. To verify the effectiveness of the proposed deep learning structure, we experimented with a flame database of ImageNet. Experimental results show that the proposed deep learning structure has an average resource occupancy rate of 29.86% and an 8 second fast flame detection time. The flame detection rate averaged 0.95% lower compared to the existing deep learning structure, but this was the result of light construction of the deep learning structure for application to embedded systems. Therefore, the deep learning structure for flame detection proposed in this paper has been proved suitable for the application of embedded system.

• Journal of Internet Computing and Services
• /
• v.14 no.2
• /
• pp.45-51
• /
• 2013

In this paper, the combination of ultraviolet and infrared sensors based design for flame signal detection algorithms was proposed with the application of light-wavelength from burning. And, the performance result of image detection was compared by an ultraviolet sensor, an infrared sensor, and the proposed dual-mode sensors(combination of ultraviolet and infrared sensors).

• 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 Intelligent Systems
• /
• v.20 no.4
• /
• pp.516-521
• /
• 2010

In this paper, we propose a video-based intelligent unmanned fire surveillance system using fuzzy color models. In general, to detect heat or smoke, a separate device is required for a fire surveillance system, this system, however, can be implemented by using widely used CCTV, which does not need separate devices and extra cost. The systems called video-based fire surveillance systems use mainly a method extracting smoke or flame from an input image only. The smoke is difficult to extract at night because of its gray-scale color, and the flame color depends on the temperature, the inflammable, the size of flame, etc, which makes it hard to extract the flame region from the input image. This paper deals with a intelligent fire surveillance system which is robust against the variation of the flame color, especially at night. The proposed system extracts the moving object from the input image, makes a decision whether the object is the flame or not by means of the color obtained by fuzzy color model and the shape obtained by histogram, and issues a fire alarm when the flame is spread. Finally, we verify the efficiency of the proposed system through the experiment of the controlled real fire.

• JOURNAL OF ELECTRICAL WORLD
• /
• no.7 s.127
• /
• pp.100-102
• /
• 1987

변류기는 자가용 수전설비에서는 계측과 보호계전기를 동작시키기 위해 필요한 것이다. 변류기 중 CT라고 하는 것은 회로의 전류를 검출하여 전류계, 전력계, 역률계 등에 접속되는 외에 과전류계전기를 동작시켜 과부하나 단락사고시에 회로를 차단하여 고압기기를 보호한다. 또한 ZCT (영상변류기)는 지락전류는 검출하여 지락계전기를 동작시키는 역할을 한다. 여기서는 이와 같이 중요한 역할을 하는 변류기의 고장사례이다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.113-120
• /
• 2003

Rayleigh was an excellent experimenter as well as a theorist. Rayleigh improved Rijke's sounding device by heat and the singing flame into sources of pure tones. Above all, his making of the artificial bird whistle was a critical achievement in the improvement of experimental sound sources. This source made supersonic waves available in the laboratory and thus paved the way to confirmable observations of reflection, refraction, diffraction and interference of sound in the laboratory Furthermore, Rayleigh augmented the sensitivity of sensitive flames as detectors for sound wave. Besides, he devised a phonic wheel which could precisely control the angular velocity of some acoustical instruments and made the Rayleigh-disk that enabled experimenters to measure the absolute value of the sound intensity. These devices enhanced the exactness of acoustical experiments.

• Journal of the Korean Chemical Society
• /
• v.52 no.2
• /
• pp.155-163
• /
• 2008

.A simple and reproducible method for the rapid extraction and determination of trace amounts of copper(II) ions using mesoporous organo-silicas mesoporous silica and atomic absorption spectrometry is presented. Common coexisting ions did not interfere with the separation and determination. The preconcentration factor was 100 (1 ml elution volume) for a 100 ml sample volume. The limit of detection of the proposed method is 1.0 ng ml-1. The maximum sorption capacity of sorbent under optimum conditions has been found to be 5mg of copper per gram of sorbent. The relative standard deviation under optimum conditions was 2.8% (n=10). Accuracy and application of the method was estimated by using test samples of natural and synthetic water spiked with different amounts of copper(II) ion.

• Fire Science and Engineering
• /
• v.26 no.6
• /
• pp.24-30
• /
• 2012

This study is on the method of the detection for flame and series arc which can be happened at poor contact point added a vibration in part of contact point of low voltage line. In general, the causes of electric fire are over current, short circuit, poor contact, ect. The over-current or short circuit among those causes is detected by measuring a instant current value, but poor contact is difficult to detect by measuring a excessive value of the voltage and current and a distortion of waveforms. And therefore, in this paper, it is studied on the optimal technique of the arc judgement using fuzzy logic and MDET (Multi Dimension Estimation Technique). And it carries out the simulation for arc detection and the experiment for controller and load test. In result, the controller and detection algoristhm, is classified with normal wave and abnormal arc wave without relation with each loads and so the controller can detect a series arc successfully.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.2
• /
• pp.36-43
• /
• 2004

In this paper, the frequency spectra from respective mechanical noise signals detected using ultrasonic wave and AE(Acoustic Emission) sensor were analysed to under spark generation between brush and commutator side with arbitrarily 15$^{\circ}$ rotation for brush from the DC motor in operation. Also, the frequency spectra from respective magnetizing noise signals detected using ultrasonic wave and AE sensor were analysed to under neutral point for brush from the DC motor in normal operation. And the analyses and comparison between the mechanical noise signal and magnetizing noise signal of ultrasonic wave with brush location change from the DC motor in operation. As the experimental results, tile mechanical noise signal of ultrasonic wave under spark generation between brush and commutator side with brush location change from the DC motor in operation were increased about 2.5∼3.0 times than magnetizing noise signal of ultrasonic wave form the DC motor in normal operation. Also, the main frequency band for mechanical noise signals of AE under spark generation between brush and commutator side with brush location change from the DC motor in operation, appeared about 1.3[MHz]∼l.5[MHz] by the fast fourier transform.

• Fire Science and Engineering
• /
• v.16 no.3
• /
• pp.77-83
• /
• 2002

We measured flame extinguishing concentration and flue gas composition in the n-heptane fuel cup-burner system using inert gas agents such as nitrogen, argon, carbon dioxide and their mixtures. The flame extinguishing concentration of binary gaseous mixture was well predicted by model which contains the flame extinguishing concentration and composition of pure components. The higher average specific gravity of the mixed inert gas agents, the more excellent flame extinguishing performance. And the structure of enclosed space also affects the fire extinguishing. The composition of carbon dioxide in the flue gas was decreased with increasing extinguishing agent used. Nitrogen monoxide production is not related with increasing nitrogen, but increased at rapid mass flow rate of air in the cup-burner.