• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.23-30
• /
• 2020

In this study, the relationship between natural gas (NG) data and gas-related environmental elements was performed using machine learning algorithms to predict the level of gas leakage risk without directly measuring gas leakage data. The study was based on open data provided by the server using the IoT-based remote control Picarro gas sensor specification. The naturel gas leaks into the air, it is a big problem for air pollution, environment and the health. The proposed method is multivariate outlier removing method based Random Forest (RF) classification for predicting risk of NG leak. After, unsupervised k-means clustering, the experimental dataset has done imbalanced data. Therefore, we focusing our proposed models can predict medium and high risk so best. In this case, we compared the receiver operating characteristic (ROC) curve, accuracy, area under the ROC curve (AUC), and mean standard error (MSE) for each classification model. As a result of our experiments, the evaluation measurements include accuracy, area under the ROC curve (AUC), and MSE; 99.71%, 99.57%, and 0.0016 for MOL_RF respectively.

• Journal of the Korean Institute of Gas
• /
• v.23 no.6
• /
• pp.97-102
• /
• 2019

In this study, city gas is the most commonly used in homes, and gas accidents are increasing as demand increases. Among them, accidents due to user carelessness are the most and we try to provide information by establishing scenarios to effectively prevent this. The gas leak in the home is an enclosed space, and the appropriate Gaussian model is applied. As smart home control technology is developed by the 4th industrial revolution, it will make a foundation to provide information through program to predict and prevent gas leakage accidents and apply it to smart home safety platform.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.628-640
• /
• 2021

To investigate the supercavity geometry and gas flow structure for the supercavities with two closure types under the different flow conditions, an inhomogeneous multiphase model with the SST turbulence model was established, and validated by experimental results. The results show that two distinct regions exist inside the supercavity, which include the downstream flow region along the gas-water interface and the reverse flow region. For the twin-vortex supercavity, the internal gas leaks from the supercavity boundary by two paths: the supercavity surface and the two-vortex tubes. Increasing Froude number leads to more internal gas stripped from the supercavity surface. Two types of gas loss exist for the re-entrant jet supercavity with high Froude number, one type is the steady process of gas loss, and the major gas-leaking path is the supercavity surface rather than supercavity closure region. The other type is the unsteady periodic ejection, and the gas cluster of periodic ejection is merely a small part of the gas stored inside the supercavity.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.3 no.2
• /
• pp.131-141
• /
• 1991

A method of optimum design of an axial rotary sensible heat exchanger for the heat recovery of exhaust gas from the air conditioning space was developed in consideration of economics of investment cost and profit according to the installation of heat exchangers. Leakage rate of exhaust gas was calculated and the correlation for the pressure drop due to leakage of exhaust gas was proposed. Heat transfer between the matrix and exhaust and intake gas was analysed to calculate the effectiveness of heat exchanger, which was used for the optimum design of rotary heat exchanger. The results show that optimum rotational speed increases as the length of rotor increases and there exists optimum NTU which maximizes the gain of total cost according to the installation of rotary heat exchanger.

• Journal of the Korean Society of Combustion
• /
• v.16 no.1
• /
• pp.46-51
• /
• 2011

Exhaust gas of an industrial furnace used at such as metallurgy or ceramic manufacturing usually contains thermal energy with high temperature which can be recycled by heat exchanger. However, when the temperature of the exhaust gas is high such as more than $1,000^{\circ}C$, ordinary metallic heat exchanger cannot fully recover the heat due to the limitation of operating temperature depending on the material property. In the present study, a compact ceramic heat exchanger of cross flow type is introduced and evaluated by heat exchange rate and operating temperature. The ceramic heat exchanger can endure the gas temperature more than $1,300^{\circ}C$, and its volumetric heat exchanging rate exceeds 1 MW/$m^3$. The experimental data is also compared with the previous numerical result which shows reasonable agreement. Meanwhile, the gas leakage rate is measured to be about 3~4%, and heat loss to environmental air is about 23~26% of the fuel energy.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1084-1089
• /
• 2000

The basic equations are derived for the analysis of a stepped labyrinth gas seal which are generally used in high performance compressors, gas turbines, and steam turbines. The Bulk-flow is assumed for a single cavity control volume and the flow is assumed to be completely turbulent in circumferential direction. Moody's wall-friction-factor formula is used for the calculation of wall shear stresses in the single cavity control volume. For the reaction force developed by the seal, linearized zeroth-order and first-order perturbation equations are developed for small motion about a centered position. Integration of the resultant first-order pressure distribution along and around the seal defines the rotordynamic coefficients of the stepped labyrinth gas seal. The leakage and rotordynamic characteristic results of the stepped labyrinth gas seal are presented and compared with Scharrer's theoretical analysis using Blasius' wall-friction-factor formula.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.33-41
• /
• 2022

In this article, we proposed to predict natural gas (NG) leakage levels through feature selection based on a factor analysis (FA) of the integrating the Korean Meteorological Agency data and natural gas leakage data for considering complex factors. The paper has been divided into three modules. First, we filled missing data based on the linear interpolation method on the integrated data set, and selected essential features using FA with OrdinalEncoder (OE)-based normalization. The dataset is labeled by K-means clustering. The final module uses four algorithms, K-nearest neighbors (KNN), decision tree (DT), random forest (RF), Naive Bayes (NB), to predict gas leakage levels. The proposed method is evaluated by the accuracy, area under the ROC curve (AUC), and mean standard error (MSE). The test results indicate that the OrdinalEncoder-Factor analysis (OE-F)-based classification method has improved successfully. Moreover, OE-F-based KNN (OE-F-KNN) showed the best performance by giving 95.20% accuracy, an AUC of 96.13%, and an MSE of 0.031.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.577-585
• /
• 2023

This study applied ALOHA Program to predict the damage caused by fire and explosion predicted to occur from gas leakage at LPG stations and presented plans to prevent damages by diagramming the impact range and distance. The propane gas leakage from LPG stations causes human damage like breathing issues and property damage, including building destruction to residents in the surrounding areas. As a way to reduce this, first, the hazardous substance safety manager of the LPG station needs to check frequently whether the meters and safety valves are working properly to prevent leakage in advance. Second, the LPG stations' storage tanks should be worked by the person who received "hazardous substance safety manager training" under the provisions of the Act on the Safety Control of Hazardous Substances and has been appointed as a "hazardous substance safety manager" by the fire department. Third, LPG station's various safety device functions, such as overfill prevention devices, must be checked on a regular basis. Finally, wearing work clothes and shoes that prevent static electricity at LPG stations is highly recommended, as static can cause a fire when gas leaks.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.12
• /
• pp.1108-1115
• /
• 2015

In this study, correlation equations were arranged about mass flow rates of oxygen and volume flow rates of helium using a mouthpiece method. The mouthpiece method can reduce examination cost by using similar empirical formula. Instead of liquid oxygen, in the mouthpiece method, gas helium can be measured in order to determine the leakage amount of liquid oxygen conveniently. Experiment was conducted and compared to understand leakage amount relation between the helium and the oxygen for prototype item under a room and a cryogenic temperature conditions. The leakage volume flow rate [$A.m{\ell}/s$] of the helium was 174 times higher than mass flow rate [g/s] of the oxygen leakage at liquid state. The derived correlation equations were verified using data from the National Institute of Standards and Technology (NIST).

• Journal of the Korean Institute of Gas
• /
• v.23 no.6
• /
• pp.74-80
• /
• 2019

Hydrogen refueling stations that use compressed hydrogen at high pressure provide safety distances between facilities in order to ensure safety. Most accidents occurring in hydrogen stations are accidental leaks. When a leak occurs, various types of ignition sources generate a jet flame. Therefore, the analysis of leaked gas diffusion and jet flame due to high pressure hydrogen leakage is one of the most important factor for setting the safety distance. In this study, the leakage accidents that occur in the hydrogen refueling station operated in high pressure environment are simulated for various leakage source sizes. The results of this study will be used as a reference for the future safety standards.