• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.260-267
• /
• 2021

In this paper, we intend to use a new mixed model of YoloV5 and DeepSort. For fire detection, we want to increase the accuracy by automatically extracting the characteristics of the flame in the image from the training data and using it. In addition, the high false alarm rate, which is a problem of fire detection, is to be solved by using this new mixed model. To confirm the results of this paper, we tested indoors and outdoors, respectively. Looking at the indoor test results, the accuracy of YoloV5 was 75% at 253Frame and 77% at 527Frame, and the YoloV5+DeepSort model showed the same accuracy at 75% at 253 frames and 77% at 527 frames. However, it was confirmed that the smoke and fire detection errors that appeared in YoloV5 disappeared. In addition, as a result of outdoor testing, the YoloV5 model had an accuracy of 75% in detecting fire, but an error in detecting a human face as smoke appeared. However, as a result of applying the YoloV5+DeepSort model, it appeared the same as YoloV5 with an accuracy of 75%, but it was confirmed that the false positive phenomenon disappeared.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.29 no.4
• /
• pp.77-84
• /
• 2015

PZT ceramics, usually used pyroelectric materials exhibited a relatively highly Curie temperture(Tc) of $250-450^{\circ}C$ and permittivity constant of 500-1600. In this paper, the pyroelectric infrared detectors are applied two different types of pyroelectric materials, that is tetragonal crystal of ferroelectric $PbTiO_3$ and rhombohedral crystal of $Pb(Zr,Ti)O_3$. PZT ceramics shows not only highly Curie temperture but also excellent pyro and piezoelectric properties at the Zr/Ti(=52/48) ratio. Therefor in this paper, the pyroelectric infrared detectors are applied PZT ceramics, and obtained sensitive sensing characteristics by expriment case studies.

• Journal of Mechanical Science and Technology
• /
• v.18 no.10
• /
• pp.1859-1868
• /
• 2004

Monitoring of OH chemiluminescence through an optical fiber was demonstrated to be a useful method in detecting self-excited combustion oscillations. OH chemiluminescence intensity detected by the optical fiber showed mostly excellent agreement with those obtained by high speed CCD camera measurements when combustion oscillations were strong. Symptoms of self-excited combustion oscillation were also studied in order to predict the onset of combustion oscillation before it proceeded to a catastrophic failure. For the purpose, we have found and proposed unique measures to tell the onset of self-excited combustion oscillations based on the careful statistics of fluctuating properties in flames, such as pressure or emission of OH radicals.

• Journal of Advanced Navigation Technology
• /
• v.13 no.6
• /
• pp.1011-1016
• /
• 2009

In this paper, we propose the method of fire detection. A wide distribution of CCTV cameras (Closed Circuit Television) in many public areas can be used not only for video surveillance systems but also for detecting fire occurrence. A proposed approach is based on visual information through a static camera. Video sequences are analyzed to find fire candidates and then spatial analyses procedure for detected fire-like color foreground is carried out. From the simulation results, our method showed the best performance when spatial and temporal fire candidates changes rapidly and close to fire motion.

• Fire Science and Engineering
• /
• v.32 no.6
• /
• pp.40-45
• /
• 2018

The omnidirectional surveillance camera uses the object detection algorithm to level the object by unit so that broadband surveillance can be performed using a fisheye lens and then, it was a field experiment with a system composed of an omnidirectional surveillance camera and a tracking (PTZ) camera. The omnidirectional surveillance camera accurately detects the moving object, displays the squarely, and tracks it in close cooperation with the tracking camera. In the field test of flame detection and temperature of the sensing camera, when the flame is detected during the auto scan, the detection camera stops and the temperature is displayed by moving the corresponding spot part to the central part of the screen. It is also possible to measure the distance of the flame from the distance of 1.5 km, which exceeds the standard of calorific value of 1 km 2,340 kcal. In the performance test of detecting the flame along the distance, it is possible to be 1.5 km in width exceeding $56cm{\times}90cm$ at a distance of 1km, and so it is also adaptable to forest fire. The system is expected to be very useful for safety such as prevention of intrinsic or surrounding fire and intrusion monitoring if it is installed in a petroleum gas storage facility or a storing place for oil in the future.

• Journal of Soil and Groundwater Environment
• /
• v.8 no.2
• /
• pp.1-8
• /
• 2003

Two types of ground-water sampling techniques for CFCs (chlorofluorocarbons) analysis, the cold-welded copper tube method and flame-sealed borosilicate glass ampule method, were compared and evaluated. CFCs concentrations by the copper tube method showed a poor reproducibility among triplicates whereas those by the glass ampule method showed a good agreement and relative standard deviations of triplicates were less than 5%. The poor reproducibility of the copper tube method appears to be attributed to the incomplete sealing in connection between faucets of wellhead and the sampling apparatus. The copper tube method also showed higher CFCs concentrations than the glass ampule method, which is more pronounced for CFC-11 than for CFC-12. The plastic tubings and rubber gasket of faucets in case of the copper tube method possibly contaminated the samples with CFC-11 and CFC-12. The potential of CFCs contamination for the glass ampule method was eliminated by using stainless steel and Nylon only and by connecting the sampling equipment directly to the main discharge pipe of wellhead. The validity of the glass ampule method were also verified by detecting very low level of CFCs for the ground-water sample which is old enough to have negligible CFCs.

• Journal of Advanced Navigation Technology
• /
• v.24 no.4
• /
• pp.291-298
• /
• 2020

This study proposed a model that can track MPP faster than the existing MPPT algorithm using the particle swarm optimization algorithm (PSO). The proposed model highly sets the acceleration constants of gbest and pbest in the PSO algorithm to quickly track the MPP point and eliminates the power instability problem. In addition, this algorithm was re-executed by detecting the change in power of the solar panel according to the rapid change in solar radiation. As a result of the experiment, MPP time was 0.03 seconds and power was 131.65 for 691.5 W/m2, and MPP was tracked at higher power and speed than the existing P&O and INC algorithms. The proposed model can be applied when a change in the amount of power is detected by partial shading in a Photovoltaic power plant with Photovoltaic connected in parallel. In order to improve the MPPT algorithm, this study needs a comparative study on optimization algorithms such as moth flame optimization (MFO) and whale optimization algorithm (WOA).

• Journal of Korean Society for Atmospheric Environment
• /
• v.19 no.6
• /
• pp.679-687
• /
• 2003

In this study, we investigated the analytical techniques to quantify the ambient concentration of hydrogen sulfide (H$_2$S) in air at ppt concentration level. For this purpose, an on-line GC analytical system equipped with both pulsed-flame photometric detector (PFPD) and thermal desorption unit (TDU) was investigated by collecting ambient air samples. The results of our study generally indicated that calibration conditions of GC system is highly sensitive to affect the accuracy of the analytical technique. Most importantly. we found that the use of different matrices in the the preparation stage of working standards was sensitive to control the overall performance of this technique. The calibration of our analytical system was tested by the two types of working standard (prepared by mixing either with high purity $N_2$ or with the ambient air). According to this test, the latter represented more efficiently the detecting conditions of actual air samples. The peak occurrence patterns of both air samples and standards (prepared by mixing with ambient air) were altered in a similar manner as the function of the loaded volume; however, it was not the case for the $N_2$-mixed standards. Results of our study suggest that detection of H$_2$S is highly different from other sulfides and that its quantification requires minimiaing interfering effects of non -pure substance (like water vapor) and (either sorptive or destructive) loss effects.

• Transactions of the Korean hydrogen and new energy society
• /
• v.30 no.6
• /
• pp.499-504
• /
• 2019

Due to the rapid spread and low minimum ignition energy of hydrogen, rupture is highly likely to cause fire, explosion and major accidents. The self-ignition of high-pressure hydrogen is highly likely to ignite immediately when it leaks from an open space, resulting in jet fire. Results of the diffusion and leakage simulation show that jet effect occurs from the leakage source to a certain distance. And at the end of location, the vapor cloud explosion can be occurred due to the formation of hydrogen vapor clouds by built-up. In the result, it is important that depending on the time of ignition, a jet fire or a vapor cloud explosion may occur. Therefore, it is necessary to take into account jet effect by location of leakage source and establish a damage minimizing plan for the possible jet fire or vapor cloud explosion. And it is required to any kind of measurements such as an interlock system to prevent hydrogen leakage or minimize the amount of leakage when detecting leakage of gas.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.7
• /
• pp.2057-2064
• /
• 2014

Thermochemical sulfate reduction (TSR) was conducted in autoclave on the system of crude oil and $MgSO_4$ at different temperatures. Gas chromatography pulsed flame photometric detector (GC-PFPD) was used to detected the composition of organic sulfur compounds in oil phase products. The results of the analysis indicate that with increased temperature, the contents of organic sulfur compounds with high molecular weight and thermal stability, such as benzothiophenes and dibenzothiophenes, gradually became dominated. In order to gain greater insight into the formation and distribution of organic sulphur compounds from TSR, positive ion electrospray Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) was used in detecting the detailed elemental composition and distribution of them. The mass spectra showed that the mass range of sulfur compounds was 200-550 Da. Four sulfur class species, $S_1$, $N_1S_1$, $O_1S_1$ and $O_2S_1$, were assigned in the positive-ion spectrum. Among the identified sulfur compounds, the $S_1$ class species was dominant. The most abundant $S_1$ class species increase associated with the DBE value and carbon number increasing which also indicates the evolution of organic sulfur compounds in TSR is from the labile series to the stable one. In pure blank pyrolysis experiments with crude oil cracking without TSR, different composition and distribution of organic sulfur compounds in oil phase products were seen from mass spectra in order to evaluate their pyrolysis behaviors without $MgSO_4$. FT-IR and XRD were used in analyzing the products of solid phases. Two distinct crystallographic phases MgO and $MgSO_4$ are found to coexist in the products which demonstrated the transformation of inorganic sulfur compounds into organosulfur compounds exist in TSR.