• Journal of Hydrogen and New Energy
• /
• v.27 no.2
• /
• pp.230-235
• /
• 2016

The purpose of this study is to evaluate the gas leakage for a 30-inch ball valve. The ball valve was designed and manufactured for a natural gas transportation through a long-distance pipeline mainly installed in the permafrost region. The gas leakage assessment is based on the pressure testing criteria of international standards. Pressure conditions of the gas leakage test was employed 70 bar, 100 bar, and 110 bar. The amount of the gas leakage at each pressure condition was small and had a value under the pressure testing criteria, ISO 5208. Gas leakage with respect to the test pressure was predicted by the polynomial curve fitting using the experimental results. It is found that the gas leakage rate according to the pressure is proportion to a second order curve.

• Tribology and Lubricants
• /
• v.22 no.2
• /
• pp.66-72
• /
• 2006

Leakage reduction through annular type labyrinth seals of steam turbine is necessary for enhancing their efficiency and the precise prediction method of seal leakage is needed. In this study, numerical analysis for leakage prediction of the combination-type-staggered-labyrinth seal has been carried out using FLUENT 6 which is commercial CFD (Computational Fluid Dynamics) code based on FVM (Finite Volume Method) and SIMPLE algorism. The present CFD results are verified with the theoretical analysis based on Bulk-flow concept which has been mainly used in predicting seal leakage. Comparing with the result of Bulk-flow model analysis, the leakage result of CFD analysis shows good agreement within 7.1% error.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.41-44
• /
• 2021

In this paper, we propose a monitoring system that can monitor gas leakage concentrations in real time and forecast the amount of gas leaked after one minute. When gas leaks happen, they typically lead to accidents such as poisoning, explosion, and fire, so a monitoring system is needed to reduce such occurrences. Previous research has mainly been focused on analyzing explosion characteristics based on gas types, or on warning systems that sound an alarm when a gas leak occurs in industrial areas. However, there are no studies on creating systems that utilize specific gas explosion characteristic analysis or empirical urban gas data. This research establishes a deep learning model that predicts the gas explosion risk level over time, based on the gas data collected in real time. In order to determine the relative risk level of a gas leak, the gas risk level was divided into five levels based on the lower explosion limit. The monitoring platform displays the current risk level, the predicted risk level, and the amount of gas leaked. It is expected that the development of this system will become a starting point for a monitoring system that can be deployed in urban areas.

• 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 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 KSFM Journal of Fluid Machinery
• /
• v.16 no.3
• /
• pp.26-31
• /
• 2013

In present 3D CFD study, the method for determining leakage and rotordynamic coefficients of a plain-gas seal is suggested by using the relative coordinate system for steady-state simulation. In order to find the effect of pre-swirl speed at seal inlet, pre-swirl velocity is included as a parameter. Present analysis is verified by comparison with results acquired from Bulk-flow analysis code and published experimental results. The results of 3D CFD rotordynamic coefficients of direct stiffness(K) and cross-coupled stiffness(k) show improvements in prediction. As pre-swirl speed at seal inlet increases, k also increases to destabilize system. However, pre-swirl speed at seal inlet does not show sensitivity to the leakage and rotordynamic coefficients of K and damping(C).

• Explosives and Blasting
• /
• v.40 no.4
• /
• pp.27-34
• /
• 2022

The government is promoting various policies to reduce greenhouse gas emissions for carbon neutrality, one of the key tasks is to revitalize the hydrogen economy. As one of these policies the government has formulated a plan to incorporate hydrogen into existing city gas pipes, and aims to commercialize 20% hydrogen mixing by 2026. In preparation for the commercialization of city gas and hydrogen mixture, this study quantitatively predicts the scale of damage and the range of impact in the event of leakage of these two gas mixtures. The quantitative damage prediction method is to calculate the damage conversion distance through the calculation of the TNT equivalent by setting the leakage amount of the gas mixture in the event of an accident under a virtual scenario.

• Journal of the Korean Institute of Gas
• /
• v.26 no.4
• /
• pp.36-40
• /
• 2022

Recently, the biggest topic in the industry is the area of industrial safety and health management. Since city gas is flammable gas and has a high risk of fire and explosion, much effort is required to prevent serious industrial and citizenry disasters. As part of city gas safety management, this study attempted to quantitatively predict the scope and degree of damage in the event of an explosion accident caused by city gas leakage through the Consequence Analysis. As a result, there was a difference in the accident result value according to various leakage conditions such as pressure and weather conditions. Through this study, a scenario of explosion due to city gas leakage will be prepared when performing city gas safety management work and used to prepare more effective accident prevention and emergency action plans.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.55-56
• /
• 2022

Hypertension is a severe health problem and increases the risk of other health issues, such as heart disease, heart attack, and stroke. In this research, we propose a machine learning-based prediction method for the risk of chronic hypertension. The proposed method consists of four main modules. In the first module, the linear interpolation method fills missing values of the integration of gas and meteorological datasets. In the second module, the OrdinalEncoder-based normalization is followed by the Decision tree algorithm to select important features. The prediction analysis module builds three models based on k-Nearest Neighbors, Decision Tree, and Random Forest to predict hypertension levels. Finally, the features used in the prediction model are explained by the DeepSHAP approach. The proposed method is evaluated by integrating the Korean meteorological agency dataset, natural gas leakage dataset, and Korean National Health and Nutrition Examination Survey dataset. The experimental results showed important global features for the hypertension of the entire population and local components for particular patients. Based on the local explanation results for a randomly selected 65-year-old male, the effect of hypertension increased from 0.694 to 1.249 when age increased by 0.37 and gas loss increased by 0.17. Therefore, it is concluded that gas loss is the cause of high blood pressure.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.172-175
• /
• 2008

In the last five years, 45 people died and 104 were wounded because of carbon monoxide poisoning accident. CO poisoning accident is higher than any other gas accident in the rate of deaths/incidents. Most of these CO poisoning accidents were caused by defective exhaust tube in the old gas boiler and multi-use facility. In this study, the spread of CO gas released from leakage hole of exhaust tube was analyzed by computational flow modeling and concentration measuring test. CO gas leaked form exhaust tube in a building was highest concentrated near the ceiling and formed the circular currents along the walls. Through these experiments and simulation, the reasonable installation location of CO alarm was made certain and suggested.