• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권12호
• /
• pp.525-534
• /
• 2023

가스 누출 감지 시스템은 가스의 폭발성과 독성으로 인한 인명 피해를 최소화할 핵심적인 장치이다. 누출 감지 시스템은 대부분 단일 센서를 활용한 방식으로, 가스 센서나 열화상 카메라를 통한 검출 방식으로 진행되고 있다. 이러한 단일 센서 활용의 가스 누출감지 시스템 성능을 고도화하기 위하여, 본 연구에서는 가스 센서와 열화상 이미지 데이터에 멀티모달형 딥러닝을 적용한 연구를 소개한다. 멀티모달 공인 데이터셋인 MultimodalGasData를 통해 기존 논문과의 성능을 비교하였고, 가스 센서와 열화상 카메라의 단일모달 모델을 기반하여 네 가지 멀티모달 모델을 설계 및 학습하였다. 이를 통해 가스 센서와 열화상 카메라는 각각 1D CNN, GasNet 모델이 96.3%와 96.4%의 가장 높은 성능을 보였다. 앞선 두 단일모달 모델을 기반한 Early Fusion 형식의 멀티모달 모델 성능은 99.3%로 가장 높았으며, 또한 기존 논문의 멀티모달 모델 대비 3.3% 높았다. 본 연구의 높은 신뢰성을 갖춘 가스 누출 감지 시스템을 통해 가스 누출로 인한 추가적인 피해가 최소화되길 기대한다.

• 한국자동차공학회논문집
• /
• 제8권6호
• /
• pp.1-8
• /
• 2000

A new method of knock detection in SI engines, using a change of ion concentration in the combustion chamber, was developed. In order to measure in-cylinder ionization current, ionization probes were installed at spark plug and cylinder head of production engine. It was found that the electric current generated by ionized gas in core burned gas region of knocking cycle is between 2 and 10 times larger than that of normal cycle, because the burned gas temperature which is the dominant parameter of a change of ion concentration increases. However, a change of ionization current in boundary region of burned gas is relatively weak. Hence a change of ion concentration in core burned gas region can be used for knock detection.

• 한국전기전자재료학회논문지
• /
• 제31권7호
• /
• pp.521-526
• /
• 2018

In particular, gas sensors require characteristics such as high speed, sensitivity, and selectivity. In this study, we fabricated a $NO_X$ gas sensor by using a multi-walled carbon nanotube (MWCNT)/zinc oxide (ZnO) composite film. The fabricated MWCNT/ZnO gas sensor was then treated by a $450^{\circ}C$ temperature process to increase its detection sensitivity for NOx gas. We compared the detection characteristics of a ZnO film gas sensor, MWCNT film gas sensor, and the MWCNT/ZnO composited film gas sensor with and without the heat-treatment process. The fabricated gas sensors were used to detect $NO_X$ gas at different concentrations. The gas sensor absorbed $NO_X$ gas molecules, exhibiting increased sensitivity. The sensitivity of the gas sensor was increased by increasing the gas concentration. Additionally, while changing the temperature inside the chamber for the MWCNT/ZnO composite film gas sensor, we obtained its sensitivity for detecting $NO_X$ gas. Compared with ZnO, the MWCNT film gas sensor is excellent for detecting $NO_X$ gas. From the experimental results, we confirmed the enhanced gas sensor sensing mechanism. The increased effect by electronic interaction between the MWCNT and ZnO films contributes to the improved sensor performance.

• 대한안전경영과학회지
• /
• 제17권2호
• /
• pp.129-137
• /
• 2015

This study is in regard to the gas detection system and gas detection method utilizing smart phone. This study includes; 1) the sensor module attached to the smart phone to detect and measure flammable gas or toxic gas; and 2) gas detection APP which is installed inside the smart phone and recognizes the user information and location information automatically by reading RFID tag indicating the user or the location to detect gas through the contact area where RFID and blue tooth reader is installed inside of the above mentioned smart phone, and then measures the combustible gas or toxic gas by operating above mentioned sensor module and obtains the data thus measured, and above mentioned smart phone is characterized by its transmission of the above mentioned user information, location information and measured data which are obtained by above mentioned gas detecting APP to operation server via communication network. With this, reliability for the location detecting gas by the user, the result of the measurement, etc. can be secured. Furthermore, this provides the effect of preventing artificial manipulation at the time of input which is associated with the identification of the user to be measured by utilizing removable sensor module and application or the mistake resulted from wrong input by the user. In addition, by transmitting the measured data from the sensor module carrying out gas detection to operation server, this provides the effect of making it possible to process the data thus collected to a specialized data for combustible gas or toxic gas.

• 반도체디스플레이기술학회지
• /
• 제23권1호
• /
• pp.110-116
• /
• 2024

Despite the continuous advancement of science and technology, fire accidents continue to occur without decreasing over time, so there is a constant need for a system that can accurately detect fires at an early stage. However, because most existing fire detection systems detect fire in the early stage of combustion when smoke is generated, rapid fire prevention actions may be delayed. Therefore we propose an early fire detection system that can perform early fire detection at a reasonable cost using LSTM, a deep learning model based on multi-gas sensors with high selectivity in the early stage of decomposition rather than the smoke generation stage. This system combines multiple gas sensors to achieve faster detection speeds than traditional sensors. In addition, through window sliding techniques and model light-weighting, the false alarm rate is low while maintaining the same high accuracy as existing deep learning. This shows that the proposed fire early detection system is a meaningful research in the disaster and engineering fields.

• Journal of Advanced Marine Engineering and Technology
• /
• 제38권9호
• /
• pp.1163-1169
• /
• 2014

$CO_2$ 가스 기포 탐지 기술 개발을 위한 예비연구로 인위적으로 발생시킨 수층의 $CO_2$ 가스 기포 플룸을 다중빔음향측심기, 단일빔음향측심기 그리고 천부지층탐사기(SBP)를 이용해서 탐지 비교하였다. 인위적으로 발생시킨 기포의 상승속도는 가스 탱크에서 압축된 가스의 강제적인 누출이 영향을 미쳐 기존 자료보다 높게 나타나는 것으로 판단된다. 다중빔음향측심기는 단일빔 음향장비에 비하여 넓은 범위를 탐지할 수 있고 가스 누출 위치 및 수층에서 가스 플룸의 3차원적인 정보를 제공하고 있다. 따라서 다중빔음향측심기는 단일빔의 음향장비 보다 더 뚜렷한 가스 플룸을 탐지할 수 있으나, 상호보완적으로 동시에 운영하면 보다 효과적인 탐지기술을 확립할 수 있다. 향후, 본 연구는 특정가스의 음향학적 특징을 파악하여 정량적, 정성적 탐지 기술 향상에 기여하고자 한다.

• 대한화학회지
• /
• 제61권4호
• /
• pp.139-142
• /
• 2017

Ethene ($C_2H_4$), which is produced in plants as they mature, was used to study its photoacoustic properties using photoacoustic spectroscopy. Detection of trace amounts, with $N_2$ gas, of $C_2H_4$ gas was also applied. The gas was tested in various conditions-temperature, concentration of the gas, gas cell length, and power of the laser- to determine their effect on the photoacoustic signal, the ideal conditions to detect trace gas amounts, and concentration of $C_2H_4$ produced by an avocado and a banana. A detection limit of 10 ppm was determined for pure $C_2H_4$. A detection of 5% and 13% (by volume) concentration of $C_2H_4$ was produced for a ripening avocado and banana, respectively, in closed space.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2005년도 추계학술대회 논문집 Vol.18
• /
• pp.323-324
• /
• 2005

To found out the degradation characteristic of transformer insulation, insulation materials and electrodes are deposited into transformer oil. They used to heated and make flashover. Due to the thermal and electrical stress added to insulation materials, the density of carbon dioxide and hydrogen included in transformer oil was increased. The gas density can measured by using the gas density detection equipment of gas sensor and air circulation method.

• 한국재료학회지
• /
• 제28권1호
• /
• pp.1-5
• /
• 2018

Gas detection is necessary for various reasons, including the prevention of gas leakages and the creation of necessary environmental conditions. Among the gas detection methods, leakage of gas can be confirmed using materials that undergo color changes that are easily distinguished by the naked eye. Metal nanoparticles (NPs) experience variations in their absorption wavelengths under the localized surface plasmon effect (LSPR) with mechanical stresses, which change the distance between NPs. In this study, we attempted to detect the presence of gas utilizing the LSPR-related color change of a chain of Au NPs. The assembly of Au NPs, arranged in a chain shape, experienced a color change from dark blue to purple with a change in the distance between the NPs by applying a physical force, i.e., compression, stretching, and gas pressure. As the force of compression and the degree of stretching increased, the absorption wavelength shifted from doublet peaks at 650 and 550 nm to a singlet peak at 550 nm. Further, applying gas pressure caused an identical color change. With this result, we propose a method that could be applied to all gases that require detection based on gas pressure.

• 한국전기전자재료학회논문지
• /
• 제32권5호
• /
• pp.432-436
• /
• 2019

In this study, we produced a light, flexible, wearable gas sensor by depositing MWCNTs (Multi-walled Carbon Nanotubes) into nylon. MWCNTs are widely used as a gas sensor material due to their excellent mechanical, electrical and physical characteristics. We produced a gas sensor to detect NOx gases by depositing nylon yarn in a MWCNT solution. The MWCNT solution was made by mixing 3 mg MWCNT in 5 ml of ethanol. Nylon yarn was placed in the manufactured solution and ultrasonic waves were applied using an ultrasonicator for 3 h, resulting in MCWNT deposition. The MWCNT-deposited nylon yarn was dried at room temperature for 24 h. The MWCNT-thin-film-coated nylon yarn was masked 1 mm apart, and gold was then deposited on the masked nylon yarn to create the gas sensor. The sensor then was installed in a chamber with a controlled atmospheric environment and exposed to NOx gas. The changing signal from the sensor was amplified to analyze its gas detection characteristics.