• 전기학회논문지P
• /
• 제61권1호
• /
• pp.41-46
• /
• 2012

Electrolytic power capacitors have been widely used in power conversion system such as inverter or UPS because of characteristics of large capacitance, high-voltage and low-cost. The electrolytic capacitor, which is most of the time affected by the aging effect, plays a very important role for the power-electronics system quality and reliability. Therefore it is important to diagnosis monitoring the condition of an electrolytic capacitor in real-time to predict the failure. In this paper, the on-line remote diagnosis monitoring system for UPS DC link electrolytic capacitors using low-cost single-chip zigbee communication modules is developed. To estimate the health status of the capacitor, the equivalent series resistor(ESR) of the component has to be determined. The capacitor ESR is estimated by using RMS computation using BPF modeling of DC link ripple voltage/current. Zigbee-based hardware experimental results show that the proposed remote capacitor diagnosis monitoring system can be applied to UPS successfully.

• 한국콘텐츠학회논문지
• /
• 제7권3호
• /
• pp.25-33
• /
• 2007

전력계통의 갑작스런 고장은 막대한 경제적 손실을 초래함으로 이를 방지하기 위한 전력계통의 상태를 진단하는 모니터링은 무엇보다도 중요하다. 본 논문에서는 FCM과 SOM을 이용하여 다양한 전력설비 중에서 가장 중요한 역할을 담당하는 전력용 변압기의 고장진단 알고리즘을 개발한다. 즉, FCM은 효과적인 특징점을 선택과 학습시간을 줄이기 위해 수행하고, SOM에 의해 변압기의 고장진단이 이루어진다. 제안된 방법은 변압기의 고장진단 뿐만 아니라 열화진행추이 특성까지 분석한다. 제안된 방법은 다양한 사례 연구를 통해 우수성을 입증하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 E
• /
• pp.1734-1736
• /
• 1998

On-line partial discharge monitoring system for generator stator insulation is developed. This system consists of remote and host units. The remote unit detects partial discharge signals from SSC(Stator Slot Coupler) installed between wedge and stator windings. The host unit monitors the condition of winding insulation. This system will be used as a module of a generator on-line monitoring system utilizing global network.

• 유공압시스템학회논문집
• /
• 제6권2호
• /
• pp.22-30
• /
• 2009

An in-process method of diagnosing the spool wear of hydraulic servovalves was explored. The diagnostic method discussed in this paper is for force-control hydraulic servo systems. The key principle used is that pressure sensitivity of a servovalve drops as the valve spool wears out so that it is possible to determine the spool condition by monitoring pressure sensitivity. A diagnostic algorithm was developed and evaluated through numerical simulation and experiments. Two major steps of diagnosis are the evaluation of null bias of the servovalve and the approximation of pressure sensitivity, both of which could be successfully done during normal operation of a servo system. The difference between a new servovalve and a worn valve could be clearly detected in-process, and the diagnostic test was found to be repeatable.

• 한국유체기계학회 논문집
• /
• 제7권2호
• /
• pp.41-49
• /
• 2004

Condition monitoring is very important in turbo machinery because single failure could cause critical damages to its plant. So, automatic fault recognition has been one of the main research topics in condition monitoring area. We have used a relatively new fault recognition method, Hidden Markov Model(HMM), for mechanical system. It has been widely used in speech recognition, however, its application to fault recognition of mechanical signal has been very limited despite its good potential. In this paper, discrete HMM(DHMM) was used to recognize the faults of rotor system to study its fault recognition ability. We set up a rotor kit under unbalance and oil whirl conditions and sampled vibration signals of two failure conditions. DHMMS of each failure condition were trained using sampled signals. Next, we changed the setup and the rotating speed of the rotor kit. We sampled vibration signals and each DHMM was applied to these sampled data. It was found that DHMMs trained by data of one rotating speed have shown good fault recognition ability in spite of lack of training data, but DHMMs trained by data of four different rotating speeds have shown better robustness.

• 한국정밀공학회지
• /
• 제15권4호
• /
• pp.105-110
• /
• 1998

In this study, statistical and neural network methods were used to recognize the cutting tool states. This system employed the tool dynamometer and cutting force signals which are processed from the tool dynamometer sensor using linear discriminent function. To learn the necessary input/output mapping for turning operation diagnosis, the weights and thresholds of the neural network were adjusted according to the error back propagation method during off-line training. The cutting conditions, cutting force ratios and statistical values(standard deviation, coefficient of variation) attained from the cutting force signals were used as the inputs to the neural network. Through the suggested neural network a cutting tool states may be successfully diagnosed.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 E
• /
• pp.1740-1742
• /
• 1998

This paper describes the technique of deterioration diagnosis for ZnO element. Due to the non-linear resistance of ZnO block, the total leakage current contains harmonics when arrester deteriorated. The most significant harmonics is the 3rd order component. So, it can be used as an indicator of the arrester condition. An iron core, which has a very high relative permeability, is used for increasing detection sensitivity and the 3th order harmonics of leakage current was detected by band-pass circuit. And we have verified the reliability and performance of the sensing device through several laboratory tests.

• Tribology and Lubricants
• /
• 제36권6호
• /
• pp.307-314
• /
• 2020

In this paper, studies on application cases of machine condition monitoring using oil sensors are reviewed. Owing to rapid industrial advancements, maintenance strategies play a crucial role in reducing the cost of downtime and improving system reliability. Consequently, machine condition monitoring plays an important role in maintaining operation stability and extending the period of usage for various machines. Machine condition monitoring through oil analysis is an effective method for assessing a machine's condition and providing early warnings regarding a machine's breakdown or failure. Among the three prevalent methods, the online analysis method is predominantly employed because this method incorporates oil sensors in real-time and has several advantages (such as prevention of human errors). Wear debris sensors are widely employed for implementing machine condition monitoring through oil sensors. Furthermore, various types of oil sensors are used in different machines and systems. Integrated oil sensors that can measure various oil attributes by incorporating a single sensor are becoming popular. By monitoring wear debris, machine condition monitoring using oil sensors is implemented for engines, automotive transmission, tanks, armored vehicles, and construction equipment. Additionally, such monitoring systems are incorporated in aircrafts such as passenger airplanes, fighter airplanes, and helicopters. Such monitoring systems are also employed in chemical plants and power plants for managing overall safety. Furthermore, widespread application of oil condition diagnosis requires the development of diagnostic programs.

• 대한기계학회논문집A
• /
• 제32권7호
• /
• pp.583-589
• /
• 2008

For the purpose of monitoring by ultrasonic test of the ball bearing conditions in rotating machinery, a system for their diagnosis was developed. ultrasonic technique is used to detect abnormal conditions in the bearing system. And various data such as frequency spectrum, energy and amplitude of ultrasonic signals, and ultrasonic parameters were acquired during experiments with the simulated ball bearing system. Based on the above results and practical application for power plant, algorithms and judgement criteria for diagnosis system was established. Bearing diagnosis system is composed of four parts as follows : sensing part for ultrasonic sensor and preamplifier, signal processing part for measuring frequency spectrum, energy and amplitude, interface part for connecting ultrasonic signal to PC using A/D converter, graphic display and software part for display of bearing condition and for managing of diagnosis program.

• 문화기술의 융합
• /
• 제9권3호
• /
• pp.845-850
• /
• 2023

본 논문에서는 전이학습을 이용하여 볼베어링의 진동진단을 수행하는 방법을 제안한다. 고장을 진단하기 위해 진동신호를 시간-주파수로 분석할 수 있는 STFT을 CNN의 입력으로 이용하였다. CNN 기반의 딥러닝 인공신경망을 빠르게 학습하고 진단 성능을 높이기 위해 전이학습 기반의 딥러닝 학습 기법을 제안하였다. 전이학습은 VGG 기반의 영상 분류 모델을 이용하여 특징 추출기와 분류기를 선택적으로 학습하였고, 학습에 사용한 데이터 세트는 Case Western Reserve University 대학에서 제공하는 공개된 볼베어링 진동 데이터를 사용하였으며, 성능평가는 기존의 CNN 모델과 비교하는 방법으로 수행하였다. 실험 결과 전이학습이 볼베어링 진동 데이터에서 상태 진단에 유용하다는 것을 증명할 수 있을 뿐만 아니라 이를 통해 다른 산업에서도 전이학습을 사용하여 상태 진단을 개선할 수 있다.