• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.61 no.1
• /
• 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.

• The Journal of the Korea Contents Association
• /
• v.7 no.3
• /
• pp.25-33
• /
• 2007

The unexpected failure may cause a break in power system and loss of profits. Therefore it Is important to prevent abrupt faults by monitoring the condition of power systems. In this paper, we develop intelligent diagnosis technique for predicting faults of power transformer which plays an important role in the transmission and distribution systems among the various power facilities by using FCM and SOM. More specifically, FCM is used to select the efficient training data and reducing learning process time and SOM is used to diagnosis the power transformer. The proposed technique makes it possible to measures the possibility of aging as well as the faults occurred in transformer To demonstrate the validity of proposed method, various experiments are performed and their results are presented.

• Proceedings of the KIEE Conference
• /
• 1998.07e
• /
• 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.

• Transactions of The Korea Fluid Power Systems Society
• /
• v.6 no.2
• /
• 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.

• The KSFM Journal of Fluid Machinery
• /
• v.7 no.2 s.23
• /
• 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.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.4
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 1998.07e
• /
• 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
• /
• v.36 no.6
• /
• 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.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.7
• /
• 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.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.