• 품질경영학회지
• /
• 제49권4호
• /
• pp.581-594
• /
• 2021

Purpose: The purpose of this study is to compare machine learning models for anomaly detection of mechanical facility equipment and suggest an anomaly detection system for mechanical facility equipment in subway stations. It helps to predict failures and plan the maintenance of facility. Ultimately it aims to improve the quality of facility equipment. Methods: The data collected from Daejeon Metropolitan Rapid Transit Corporation was used in this experiment. The experiment was performed using Python, Scikit-learn, tensorflow 2.0 for preprocessing and machine learning. Also it was conducted in two failure states of the equipment. We compared and analyzed five unsupervised machine learning models focused on model Long Short-Term Memory Variational Autoencoder(LSTM-VAE). Results: In both experiments, change in vibration and current data was observed when there is a defect. When the rotating body failure was happened, the magnitude of vibration has increased but current has decreased. In situation of axis alignment failure, both of vibration and current have increased. In addition, model LSTM-VAE showed superior accuracy than the other four base-line models. Conclusion: According to the results, model LSTM-VAE showed outstanding performance with more than 97% of accuracy in the experiments. Thus, the quality of mechanical facility equipment will be improved if the proposed anomaly detection system is established with this model used.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 A
• /
• pp.371-373
• /
• 2005

An enhancement for a transmission and substation equipment in power system make the system impedance to be lower. In principle, if the system impedance become low, system stability will be better, but the fault current become very higher. It is a very big problem for CB operating. As a fact of CB operating performance, high amplitude of the fault current may cause CB operation failure because of exceeding standard value in TRV. So we simulated TRV by using the EMTP. Generally there are two types of TRV in actual power system. One is short line fault, the other is bus terminal fault. In this paper, we simulated the TRv at short line fault as installed current limit reactors to reduce fault current in 345kV ultra-high voltage system. Short line fault is caused from single line fault in transmission line.

• 정보학연구
• /
• 제6권3호
• /
• pp.1-10
• /
• 2003

본 논문은 전력선 통신 실험을 보다 빠르고 효율적으로 수행할 수 있는 전력선 채널 모델링에 관한 것이다. 용량성 부하 채널 시뮬레이터는 댁내망 전력선 모뎀 개발에 있어서 필수적인 실험 장비이다. 실제 전력선 채널 환경을 모델링한 이 실험 장비를 이용한 총 245 개의 용량성 부하 채널에 대하여 주파수 응답법에 의한 채널 모델링을 행하였다. 용량성 부하 채널 시뮬레이터를 사용한 실험 데이터 결과와 모델링된 채널 필터를 통과한 결과를 비교하였을 때 큰 오차 없이 실제 전력선 통신상의 용량성 부하 실험을 대체할 수 있음을 확인하였다.

• 정보학연구
• /
• 제7권3호
• /
• pp.1-10
• /
• 2004

옥내${\cdot}$외의 전력선 환경에 대한 정확한 채널 모델링에 관한 노력이 최근에 이루어지고 있다. 알려진 일반표준, 제한과 발표된 모델들은 특별한 형태의 접근들이였다. 본 논문에서는 더 신속하고 효율적인 전력선 통신 실험을 위한 전력선 채널 모델링에 관한 연구이다. 용량성 부하 시뮬레이터는 전력선 옥내 망 모뎀 개발에 필수적인 장비이다. 총 244 경우의 용량성 부하 변화에 대한 주파수 응답 특성 측정으로 채널 모델링을 수행하였다. 본 측정 실험에서 PLC는 일반적으로 알고 있었던 특성 보다 더 확정적인 매체라는 것을 확인하였다.

• 한국전자통신학회논문지
• /
• 제12권3호
• /
• pp.477-484
• /
• 2017

기존의 순환여과식 양식장에서는 전문 인력의 부족, 수입 측정 장비에 대한 높은 의존도 등으로 인하여 많은 어려움을 격고 있다. 이에 본 논문에서는 최신 IoT기술을 적용한 광학식 센서(pH, DO)를 이용하여 양식장 수조 내 오염도를 빠른 시간내에 측정할 수 있는 자동 수질 측정 시스템을 구현하고자 한다. 기존 시스템의 문제점은 양식장 수조를 사람이 일일이 확인하거나, 측정 장비를 수조 속에 넣고 직접 측정을 하여 물고기의 생육에 좋지 않은 영향을 주는 것이다. 본 논문에서는 시스템은 측정 장비를 수조 속에 담그지 않고 간접 측정을 하는 방식을 제안하고 염분 및 다수의 오염 물질이 포함된 환경에서도 양식장 내의 물고기의 생육에 영향을 주지 않고 지속적인 측정이 가능한 시스템을 개발하였다.

• 한국압력기기공학회 논문집
• /
• 제18권2호
• /
• pp.87-100
• /
• 2022

Unit capacity factor (utilization rate) of nuclear power plants (NPPs) is an important performance indicator. Since the first commercial operation of Kori Unit 1 began in April 1978, the utilization rate of domestic NPPs has gradually increased, reaching 90% from the end of the 1990s. However, due to various issues such as the Fukushima accident in 2011, corrosion of the CLP, the utilization rate dropped to 65~80%. In the early 1980s, the utilization rate of the U.S. NPPs was around 60%. However, since 2004, it has been consistently maintained above 90%. Therefore, in this study, we first examined the causes of declining the utilization rate in domestic NPPs. Next, the significances of the utilization rates are reviewed in five aspects: investment capability, electricity rate, safety and export, etc., with discussion on the current status of the utilization rates in the U.S. Based on this, three key factors are derived as the reasons of the increasing: equipment reliability program, on-line maintenance and the pursuit of institutional rationality. And finally, by synthesizing above results, the measures for increasing the utilization rate of domestic NPPs are proposed in terms of equipment management, institutional improvements, and personnel resources.

• 한국정밀공학회지
• /
• 제30권6호
• /
• pp.615-621
• /
• 2013

The robot calibration has greatly improved the absolute accuracy of the industrial robot. However, the accuracy of the relative positions of robotic tool-tip at work-points on a work-piece is only slightly corrected by the robot calibration since there has been no practical method to eliminate the elements of the setup position errors at a robotic workplace. A robotic workplace calibration is demonstrated in this paper to minimize the relative position errors between a robot tool-tip and the work-point on a work-piece. The existing teaching and playback method has been developed for the robotic workplace calibration. This paper uses the work-piece fixed in a robotic work-place as measurement equipment instead of a special robot measurement equipment for the robotic workplace calibration. The positive effect of the robotic workplace calibration is supported by the results of computer simulation on an ideal robotic workplace model and an experiment at the actual robotic workplace.

• 드라이브 ㆍ 컨트롤
• /
• 제14권3호
• /
• pp.32-39
• /
• 2017

In this study, a mathematical model of the pneumatic part in a gas blow-down system is proposed. The mathematical model consists of four major parts: pressure vessel, reservoir, pressure regulator and pipe-line. To ensure accuracy in long-time simulations, heat transfer between gas and pressure vessel is considered. The model is validated by comparing simulation results with experimental data. Experiments are conducted on the ground, where free convection can be assumed. Simulation results indicate the proposed model can accurately describe behavior of a gas blow-down system. Therefore, it may be used for design and analysis of similar systems with a slight modification.

• Journal of Electrical Engineering and Technology
• /
• 제9권3호
• /
• pp.970-977
• /
• 2014

In this paper, the artificial neural network is used to predict the junction temperature of the IGBT power module, by measuring the temperature sensitive electrical parameters (TSEP) of the module. An experiment circuit is built to measure saturation voltage drop and collector current under different temperature. In order to solve the nonlinear problem of TSEP approach as a junction temperature evaluation method, a Back Propagation (BP) neural network prediction model is established by using the Matlab. With the advantages of non-contact, high sensitivity, and without package open, the proposed method is also potentially promising for on-line junction temperature measurement. The Matlab simulation results show that BP neural network gives a more accuracy results, compared with the method of polynomial fitting.

• 실천공학교육논문지
• /
• 제16권2호
• /
• pp.179-184
• /
• 2024

인쇄회로기판(PCB)은 전자 제품 생산에 널리 적용되는 요소부품으로 지속적으로 양적인 성장은 물론 집적도와 같은 질적인 발전도 묵과할 수 없다. 제조현장에서 보편적으로 웨이브 솔더링 장비가 사용되고 있으나 선행 연구 및 시제품 개발 단계에서는 각 PCB 제원에 맞는 전용 장비 환경을 구성할 수 없고, 범용의 고정 장비 환경에서 정해진 시간 내에 장비의 설정 조건만 변경하여 다양한 제품 군을 생산할 수밖에 없는 것이 일반적이다. 본 연구에서는 위와 같이 제한된 환경 내에서 최적의 공정 조건을 선택할 수 있도록 PCB 팔레트 도입 사례를 소개한다. 또한 현재 범용 장비에서 생산 가능 여부를 미리 판단할 수 있는 판별식을 제시하여 범용 웨이브 솔더링 장비 환경의 한계로 인해 발생할 수 있는 문제점을 사전에 파악하고 대응하도록 하고 궁극적으로 개발기간 단축 및 생산성 향상을 기대할 수 있도록 한다.