• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.225-232
• /
• 2004

Recently, there has been a rapid development in computer technology, which has in turn led to develop the automated welding system using Artificial Intelligence (AI). However, the automated welding system has not been achieved duo to difficulties of the control and sensor technologies. In this paper, the classification of the optimized bead geometry such as bead width, height penetration and bead area in the Gas Metal Arc (GMA) welding with fuzzy logic is presented. The fuzzy C-Means algorithm (FCM), which is best known an unsupervised fuzzy clustering algorithm is employed here to analysis the specimen of the bead geometry. Then the quality of the GMA welding can be classified by this fuzzy clustering technique and the choice for obtaining the optimal bead geometry can also be determined.

• Journal of the Korean Institute of Gas
• /
• v.19 no.2
• /
• pp.45-53
• /
• 2015

In order to improve the performance of the visual inspection process, in addition to existing automatic visual inspection machine and human inspectors have developed a new process configuration using a Naive Bayes classifier. By applying the classifier, defect leakage and human inspector's work amount could be improved at the same time. New classification method called AMPB was applied instead of conventional methods based on MAP classification. By experimental results using the filter product for camera modules, it was confirmed that it is possible to configure the process at the level of leakage ratio 1.14% and human inspector's work amount ratio 75.5%. It is significant that the result can be applied in such a wide range as gas leak detection which is the collaboration process between inspection machine and human inspector's

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.479-482
• /
• 2003

We propose a real time gas monitoring system for classifying various gases with different concentrations. Using thermal modulation of operating temperature of two sensors, we extract patterns of gases from the voltage across the load resistance. We adopt the relative resistance as a pre-processing method and an ART2 neural network as a pattern recognition method. The proposed method has been implemented in a real time embedded system with tin oxide gas sensors, TGS 2611, 2602 and an MSP430 ultra-low power microcontroller in the test chamber.

• Journal of Environmental Impact Assessment
• /
• v.22 no.3
• /
• pp.195-201
• /
• 2013

Local governments are establishing their own greenhouse gas reduction goal and are playing a important role to respond to climatic changes. However, there are difficulties in quantitative analyses such as estimation of future greenhouse gas emission and computation of reduction potential, which are procedures required to establish mid to long term strategies to realize of low carbon society by each local governments. Also, reduction measures must reflect characteristics of each local government, since the reduction power of each local government can differ according to characteristics of each. In order to establish strategies that reflect characteristics of local governments, types of greenhouse gas emission from cities were classified largely into residential city, commercial city, residential commercial city, agriculture and fishery city, convergence city, and industrial city. As a result of analyzing basic unit of greenhouse gas emission by local government during 2007 in terms of per population, household and GRDP based on the type classification, significant results were deduced for each type. To manage the amount of the national greenhouse gas, reduction measures should be focused on the local governments that emits more than the average of each type's GHG emission.

• Korean Journal of Materials Research
• /
• v.16 no.10
• /
• pp.633-638
• /
• 2006

Silica powders with spherical shape and narrow size distribution were prepared by large-scale ultrasonic spray pyrolysis applying the droplet classification apparatus. On the other hand, silica powders prepared by large-scale ultrasonic spray pyrolysis without droplet classification apparatus had broad size distribution. Droplet classification apparatus used in this paper applied the principles of cyclone and dispersion plate with small holes. The droplets formed from the ultrasonic spray generator applying the droplet classification apparatus had narrow size distribution. The droplets with fine and large sizes were eliminated by droplet classification apparatus. The optimum flow rate of the carrier gas and diameter of the hole of the dispersion plate were studied to reduce the size distribution of the silica powders prepared by large-scale ultrasonic spray pyrolysis. The size distribution of the silica powders prepared by large-scale ultrasonic spray pyrolysis at the optimum preparation conditions was 0.76.

• Journal of the Society of Naval Architects of Korea
• /
• v.54 no.1
• /
• pp.1-9
• /
• 2017

LNG has significant advantages in regard to environmental aspects comparing with conventional fuel oil. In fact, it is estimated that NOx and SOx emission can be reduced by about 90% and 100%, respectively in case of using LNG as a fuel. LNG-fuelled ship has been considered to be the best option both from an environmental and an economic point of view. Along with these trends, some major shipyards and Classification Societies have started to carry out the risk-based system design for LNG-fuelled ship such as passenger ship, platform supply vessel and large container vessel etc. However, new conceptual gas fuelled ship has high risk level compared with vessel using traditional crude oil especially in view of gas explosion accident. Therefore safety area where installed fuel gas supply system is required risk based system design with special considerations. On this paper, the entire process necessary for the quantitative risk analysis was explained to meet the satisfactory safety level of gas fuelled ship.

• Journal of Korean Institute of Fire Investigation
• /
• v.11 no.1
• /
• pp.1-8
• /
• 2008

The purpose of this paper is to report gas fire accident based on classification of the major gas fire causes (including handling mistakes, inferior goods, etc.), fire classifications (fire, explosion, leakages, etc.), damage levels(1st, 2nd, 3rd, 4th grade levels), casualties (death, serious wound, slight injury) since gas fire has been generated according to growth of gaseous fuel consumption on home and enterprises with various accident causes. Among gaseous fuels, LPG facility can be c1assified as gas container, pressure regulator, gas hose, interim valve, combustion port. Any fire or any explosion can be caused from handling mistakes, inferior goods on each parts as stated above. Exact gas fire causes shall be identified based on previous case studies on similar fires with consideration of lesson learns.

• Journal of the Korea Safety Management & Science
• /
• v.4 no.4
• /
• pp.15-26
• /
• 2002

The quantitative evaluation method of the safety management cost was suggested to prevent a gas accident as a major industrial accident. In a gas governor station, process risk assessments such as the fault tree analysis(FTA) and the consequence analysis were performed. Based on process risk assessments, potential accident costs were estimated and the cost-benefit analysis(CBA) was performed. From the cost-benefit analysis for five classification items of safety management cost, the order of the cost/benefit ratio was estimated.

• Proceedings of the Optical Society of Korea Conference
• /
• 1989.02a
• /
• pp.39-42
• /
• 1989

The limitations of high-power electrical lasers due to heating of the gas and the instability of the glow discharge can be alleviated by the flow of the lasing medium. In order to achieve high power and efficient laser, we are developing a fast-axial flow CO2 laser. We describe here the classification of gas-discharge CO2 lasers according to the cooling methods of the lasing medium and the design features of the fast-axial flow CO2 laser.

• Journal of Korean Institute of Fire Investigation
• /
• v.11 no.1
• /
• pp.59-65
• /
• 2008

Among the various cases of fire accident, gas accident which is roost essential have a lot of forms and causes. The quantity consumed of gas is increasing because of increment of gas-using families and variations of gas machinery. The quantity consumed of gas in 2007 was 35078 tons and the average rate of increasement was 9.4%. The amount of gas accident was on the peak at 1995 when 557 accidents occurred in a year. In 2007, 123 gas accidents was occurred and the average rate of diminution was 11.5%. Accidents by LP gas took 80% of the whole accident and city gas and high pressure gas took 20%. In case of LP gas, accidents were usually occurred because of lack of blocking after the removal of gas machinery and moveable butane burner. Especially, the accidents cause by carelessness of a provider is increasing. Gas accidents which generate damage of human life and property, are caused by users' carelessness, providers' carelessness, inferiority of structure and old products. In this thesis, We will classify the gas accidents. Furthermore through the classification of accidents by forms, causes and regions, this thesis going to be a reference to understand and prevent the accidents.