• Clean Technology
• /
• v.17 no.1
• /
• pp.62-68
• /
• 2011

Hydrodynamic characteristics in multistage annular type fluidized bed (riser: $0.01{\times}0.025{\times}2.8m^3$, J-valve: $0.009{\times}0.015m^2$)were investigated. Glass beads ($d_p=101{\mu}m$, ${\rho}_b=1,590kg/m^3$, $U_{mf}=1.25{\times}10^{-2}m/s$, Geldart classification B) was used as a bed material. Accumulated weight by the electronic balance was measured to determine the solid flow rate in batch-type. In circulation condition, we measured the accumulated weight of particle transported from riser. At the steady state condition, solid circulation rate was calculated from time interval of the heated bed material passing between two thermocouples. Solid flow rate increased with increasing inlet gas velocity ($1.2-2.6U_{mf}$) and the static bed height (z, 0.24-0.68 m) from 2.2 to 23.4 kg/s. However, mean residence time decreased with increasing inlet gas velocity ($1.2-2.6U_{mf}$) and the static bed height (z, 0.24-0.68 m) from 1,438 to 440 s. The solid holdup in the riser was determined by measuring pressure differences according to the riser height. These results showed a similar trend to that of simple exponential decay type except for the top section of the riser. To verify the gas bypassing from top bubbling beds to middle bubbling beds, $CO_2$ gas was injected by tracer gas in constant ratio, and then was measured $CO_2$ concentration in outlet gas by gas chromatography. Gas bypassing occurred below 2.6% which is negligible value.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.11a
• /
• pp.275-278
• /
• 2007

Dissolved gases analysis (DGA) is one of the most useful techniques to detect incipient faults in power transformers. Criteria interpreting DGA result is the most important. Because of difference of operation environment, construction type, oil volume, and etc, the interpretative criteria of DGA at KEPCO must be different with other standard like IEC-60599, Rogers and Doernenburg. In this paper, we collected the DGA data of the normal condition transformers and the incipient fault transformer to suggest the most appropriate criteria. Using these data, this paper suggests appropriate condition classification algorithm. Suggested algorithm can help to detect incipient fault earlier without unnecessary sampling.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.183-186
• /
• 2003

In this paper, we proposed fuzzy adaptive resonance theory(ART) combined with principle component analysis(PCA) to recognize and classify indoor environmental gases. In experiment Taguchi gas sensors(TGS) are used to detect VOCs. Using thermal modulation of operating temperature of two sensors, we extract patterns of gases from the voltage across the load resistance. We use the PCA algorithm to reduce dimension so it needs less memory and shortens calculation time. Simulation is accomplished to two directions for fuzzy ART with and without PCA.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.1113-1120
• /
• 2004

This paper proposes a novel hybrid genetic algorithm for the feature selection. Local search operations are devised and embedded in hybrid GAs to fine-tune the search. The operations are parameterized in terms of the fine-tuning power, and their effectiveness and timing requirement are analyzed and compared. Experimentations performed with various standard datasets revealed that the proposed hybrid GA is superior to a simple GA and sequential search algorithms.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.05a
• /
• pp.209-212
• /
• 2006

In this study, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. Effect of altitude variation on the Defect Diagnostics algorithm has been included and evaluated. Separate learning Algorithm(SLA) suggested with ANN to loam the performance data selectively after classifying the position of defects by SVM improves the classification speed and accuracy.

• Journal of The Korean Astronomical Society
• /
• v.47 no.6
• /
• pp.219-233
• /
• 2014

The main site of dust formation is believed to be the cool envelopes around AGB stars. Nearly all AGB stars can be identified as long-period variables (LPVs) with large amplitude pulsation. Shock waves produce by the strong pulsation and radiation pressure on newly formed dust grains drive dusty stellar winds with high mass-loss rates. IR observations of AGB stars identify various dust species in different physical conditions. Radio observations of gas phase materials are helpful to understand the overall properties of the stellar winds. In this paper, we review (i) classification of AGB stars; (ii) IR two-color diagrams of AGB stars; (iii) pulsation of AGB stars; (iv) dust around AGB stars including dusty stellar winds; (v) dust envelopes around AGB stars; (vi) mass-loss and evolution of AGB stars; and (vii) contribution of AGB dust to galactic environments. We discuss various observational evidences and their theoretical interpretations.

• Journal of Sensor Science and Technology
• /
• v.13 no.6
• /
• pp.454-461
• /
• 2004

We have designed a portable electronic nose (e-nose) system using an array of commercial gas sensors and personal digital assistants (PDA) for the recognition and analysis of volatile organic compounds (VOC) in the field. Field screening of pollutants has been a target of instrumental development during the past years. A portable e-nose system was advantageous to localize the special extent of a pollution or to find pollutants source. The employment of PDA improved the user-interface and data transfer by Internet from on-site to remote computer. We adapted the Lavenberg-Marquardt algorithm based on the back-propagation and proposed the method that could predict the concentration levels of VOC gases after classification by separating neural network into two parts.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.517-519
• /
• 2002

침입탐지 시스템은 정밀성자 적응성, 그리고 확장성을 필요로 한다. 이와 같은 조건을 포함하면서 복잡한 Network 환경에서 중요하고 기밀성이 유지되어야 할 리소스를 보호하기 위해, 우리는 더욱 구조적이며 지능적인 IDS(Intrusion Detection Systems) 개발의 필요성이 요구되고 있다. 본 연구는 데이터 마이닝(Data mining)을 통해 입 패턴, 즉 침입 규칙(Rules)을 생성한다. 데이터 마이닝 기법 중 분류(Classification)에 초점을 맞추어 분석과 실험을 하였으며, 사용된 데이터는 KDD데이터이다. 이 데이터를 중심으로 침입 규칙을 생성하였다. 규칙생성에는 유전자알고리즘(Genetic Algorithm : GAs)을 적용하였다. 즉, 오용탐지(Misuse Detection) 기법을 실험하였으며, 생성된 규칙은 침입데이터를 대표하는 규칙으로 비정상 사용자와 정상 사용자를 분류하게 된다. 규칙은 "Time Based Traffic Model", "Host Based Traffic Model", "Content Model" 이 세 가지 모듈에서 각각 상이한 침입 규칙을 생성하게 된다. 본 시스템에서 도출된 침입 규칙은 430M Test data set에서 테스트한 결과 평균 약94.3%의 성능 평가 결과를 얻어 만족할 만한 성과를 보였다.의 성능 평가 결과를 얻어 만족할 만한 성과를 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1846-1848
• /
• 2015

가스를 사용하는 산업 영역이 지속적으로 확장됨에 따라, 가스작업의 안전 관리 문제가 중요하게 대두되고 있다. 이는 특히 최근 발전 중인 사물네트워크(이하 IoT)를 활용하여 작업안전관리를 보다 용이하게 이루어가는 방향으로 연구되고 있다. 본 논문에서는 국내외에서 개발 중인 가스 시설 안전을 위한 IoT 시스템과 작업자를 효과적으로 연동시킬 수 있는 모바일 앱의 설계 방안을 모색하기 위해 우선적으로 작업자의 사용 용이성을 확보하기 위한 설계 방향을 설정하고, 이를 기준으로 석유화학산업에서 이루어지는 작업을 분류하여 배치하였다.

• Current Optics and Photonics
• /
• v.7 no.5
• /
• pp.511-517
• /
• 2023

Pipelines play an important role in urban water supply and drainage, oil and gas transmission, etc. This paper presents a technique for pattern recognition of fiber optic vibration signals collected by a distributed vibration sensing (DVS) system using a deep learning residual network (ResNet). The optical fiber is laid on the pipeline, and the signal is collected by the DVS system and converted into a 64 × 64 single-channel grayscale image. The grayscale image is input into the ResNet to extract features, and finally the K-nearest-neighbors (KNN) algorithm is used to achieve the classification and recognition of pipeline damage.