• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.31-34
• /
• 2018

대화 시스템에서 사람과 기계와의 모든 발화에서 발생하는 상황들을 모두 규칙화할 수 없기 때문에 자연스러운 대화가 단절되는 breakdown 현상이 빈번하게 일어날 수 있다. 이런 현상이 발생하는 이유는 다음과 같다. 첫째, 대화에서는 다양한 도메인이 등장하기 때문에 시스템이 커버할 수 있는 리소스가 부족하며, 둘째, 대화 데이터에서 학습을 위한 annotation되어 있는 많은 양의 코퍼스를 보유하기에는 한계가 있으며, 모델에 모든 대화 흐름의 히스토리를 반영하기 어렵다. 이런 한계점이 존재함에도 breakdown detection은 자연스러운 대화 시스템을 위해서는 필수적인 기능이다. 본 논문은 이런 이슈들을 해소하기 위해서 memory attention기반의 새로운 모델을 제안하였다. 제안한 모델은 대화내에 발화에 대해 memory attention을 이용하여 과거 히스토리가 반영되기 때문에 자연스러운 대화흐름을 잘 detection할 수 있으며, 기존 모델과의 성능비교에서 state-of-the art 결과를 도출하였다.

• Proceedings of the KIEE Conference
• /
• 2002.07c
• /
• pp.1827-1829
• /
• 2002

This paper describes AC test for long delivered drum length of cable using pre-breakdown partial discharge detection(PPD) method, which can be applied to observe the causes of electrical breakdown of EHV XLPE insulation. This method is to de-energize applied voltage to cable rapidly using pre-breakdown partial discharge, and is able to prevent complete breakdown. By this effect, defects such as voids, metal particles and protrusion in cable can be observed clearly. AC resonant test set was used for PPD method. Localization of partial discharge was performed by time difference detection of the traveling wave. Accuracy of localization was 1% to the length of test cable. Through several experiments with XLPE cable, successful results of PPD method were obtained.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.7 no.6
• /
• pp.42-48
• /
• 1999

Engine misfire causes of the negative effect on exhaust emission such as HC, CO, and NOX . Moreover, it causes damage to the three-way-catalyst(TWC) system permanently. The crankshaft velocity fluctuation(CVF) method has been applied for the real cars as misfire detection system usually, which utilizes the crank angle sensor input to calculate the variation of the crankshaft rotational speed. But this approach has the limit due to the fact that three could be problem under certain engine condition like as deceleration or high speed condition . Therefore the development of new methods are requested today. This study introduced the new method of misfire detection using breakdown voltage(BDV) characteristics between spark plug electrouds.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.1
• /
• pp.23-31
• /
• 2000

Knock and misfire, kinds of abnormal combustion, are highly undesirable effect on the internal combustion engine. So, it is important to detect these avnormal combuition and control the ignition timing etc. to avoid these mal-effect factors in real engine system. In this study, the system which detects the knock and the misfire using by spark plug is presented. This system is based on the effect of modulation breakdown voltage(BDV) between the spark gaps. The voltage drop between spark plug electrodes, when an electrical breakdown is initiated, depends on the temperature and pressure in combustion chamber. So, we can detect knock and misfire that produce changes in gas temperature and pressure (consequently, its density) using by BDV signal change which carries information about the character of combustion.

• Korean Journal of Food Science and Technology
• /
• v.33 no.2
• /
• pp.195-199
• /
• 2001

A study was carried out to establish a detection method for irradiated black pepper using amylograph characteristics. The maximum viscosity, viscosity at $93^{\circ}C$, viscosity after 15 min at $93^{\circ}C$, viscosity at $45^{\circ}C$, viscosity after 30 min at $45^{\circ}C$, and viscosity after 60 min at $45^{\circ}C$ decreased with increasing irradiation doses, but initial pasting temperatures, maximum viscosity temperatures, breakdown, setback, and consistency did not show great changes. The high correlation coefficients $(R^2>0.97)$ were shown between irradiation doses and amylograph characteristics except for breakdown $(R^2>0.75)$, setback $(R^2>0.88)$ and consistency $(R^2>0.31)$. These results suggest that detection of irradiated black pepper is possible using amylograph characteristics.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.1
• /
• pp.27-37
• /
• 1997

Internal combustion engine is the main source of environmental pollutants and therefore better technology is required to reduce harmful elements from the exhaust gases all over the world. Especially, harmful elements from the exhaust gases are caused by incomplete combustion of mixture inside the engine cylinder and this abnormal combustion like misfire or partial burning is the direct cause of the air pollution and engine performance degradation. the object of this research is to detect abnormal combustion like misfire and to keep the engine performance in the optimal operating state. Development of a new system therefore could be applied to a real car. To realize this, the spark-plug in a conventional ignition system is used as a misfire detection sensor and breakdown voltage is analyzed. In this research, bias voltage(about 3kV) was applied to the electrodes of spark-plug and breakdown voltage signal is obtained. This breakdown voltage signal is analyzed and found that a combustion phenomena in engine cylinder has close relationship with harmonic coefficient K which was introduced in this research. Newly developed combustion diagnostic method( breakdown voltage signal analysis) from this research can be used for the combustion diagnostic and combustion control system in an real car.

• Electrical & Electronic Materials
• /
• v.10 no.3
• /
• pp.247-254
• /
• 1997

Internal voids in insulators give rise to partial discharge, which causes a local breakdown and even entire insulation breakdown. Recently, the necessity of establishing the way to diagnose the aging of insulation materials and to predict of insulation breakdown become important. The purpose of our work are to investigate the treeing phenomena with an artificial needle shaped void by the charge of discharge and acoustic emission pulse in each phase angle area at the same time. We analyzed the .PHI.-QA-t pattern and .PHI.-AEA-t pattern using statistic operators such as pulse magnitude, pulse number, skewness, kurtosis. Therefore, the relation between the charge of discharge and acoustic emission pulse will be helpful to predict the breakdown just before the breakdown occur.

• Proceedings of the KIEE Conference
• /
• 1996.07c
• /
• pp.1781-1783
• /
• 1996

Recently, the necessity of establishing the way to diagnose the aging of insulation materials and to predict of insulation breakdown become important. The purpose of our work are to investigate the treeing phenomena with a artificial needle shape void by the charge of partial discharge and acoustic emission pulse in each phase angle area at the same time. We have analyzed the ${\Phi}-Q-n$ pattern and the insulation diagnosis of the samples using statistic operators such as charge magnitude and A.E pulse factor, skweness, kurtosis, G,C. Therefore, the relation between the charge of partial discharge and A.E pulse will be helpful and efficient to predict the breakdown just before the breakdown occure.

• Particle and aerosol research
• /
• v.12 no.3
• /
• pp.57-63
• /
• 2016

The laser-induced breakdown spectroscopy (LIBS) has been used for rapid detection of elemental compositions of various materials in multi-media (solid, liquid, gas, and aerosols). In this study, the aerosol-LIBS has been developed for real-time monitoring of process-induced particles produced during the semiconductor manufacturing. The developed aerosol-LIBS mainly consists of laser, optics, spectrometer, and aerosol chamber. A new aerosol chamber was constructed for the aerosol-LIBS to be applied for various semiconductor manufacturing process, including exhaust tubes, and low pressure and high temperature chamber. The aerosol-LIBS was evaluated by using laboratory generated aerosols for detection of various elements. As a result, P, Fe, Mg, Cu, Co, Ni, Ca, Na, and K emission lines were successfully detected by the aerosol-LIBS. Further evaluation of the aerosol-LIBS is being conducted.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.5
• /
• pp.1660-1669
• /
• 2014

Partial discharge (PD) detection plays a major role in the life time assessment of liquid insulation in power transformers. Many research works are being carried out to replace conventional mineral oil insulation in transformers by vegetable oils. It is necessary to understand the PD characteristics of vegetable oils before recommending them as an alternate for mineral oil. In this paper, the breakdown strength and PD characteristics of palm and corn oil were investigated in both unaged and thermally aged conditions. Laboratory experiments were performed as per IEC test procedures. PD signals were measured using wide band detection system. Phase resolved PD pattern of vegetable oils and mineral oil were compared. Effect of increase in voltage stress on the PD pattern of palm and corn oil were studied. Time and frequency domain analysis of PD pulses at needle-plane electrode configuration was carried out. Statistical analysis of PD pattern i.e. skewness and shape parameter variations with respect to applied thermal stress were also carried out. From the results, it is observed that palm and corn oils have better breakdown strength and PD characteristics even under long-term thermal stress and hence they can be used for power transformer applications.