• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.23 no.54
• /
• pp.155-165
• /
• 2000

The fault diagnosis is a systematic and unified method to find based on the observing data resulting in noises. This paper presents the fault prediction and diagnosis using fuzzy expert system technique to manipulate the uncertainties efficiently in predictive perspective. We apply a fuzzy event tree analysis to the computer system, and build up the fault prediction and diagnosis using fuzzy expert system that predicts and diagnoses the error of the system in the advance of error.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.5
• /
• pp.612-619
• /
• 2013

This paper proposes an early diagnosis technique for the stator-turn fault (STF) in an interior permanent magnet (IPM)-type brushless DC (BLDC) motor using the impedance parameter. We have analyzed the varying characteristics owing to the STF through various experiments and the finite element method (FEM). As a result, we have presented a simple method for fault detection. This technique can be applied without requiring a fast Fourier transform (FFT) and the calculation of the negative-sequence impedance. The fault detection system works on the basis of the comparison the measured impedance with the database impedance. The variations in the characteristics owing to the STF as well as the proposed technique have been verified through the simulation and experiment.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.8
• /
• pp.1436-1441
• /
• 2016

Currently, partial discharge diagnosis in the field of prevention applied technology and diagnostic equipment is a possible strong limit to remove the noise generated by external or internal I still have one unreliable diagnosis. This technology is the noise removal from signal the time lag analysis algorithms technique is applied by a fundamental. Increasing the reliability in terms of technology spectrum frequence of analysis method for by applying the acquisition through the position of the frequency content and sources of traffic lights partial discharge of the acquisition of signal analysis to judge whether a way diagnosis the environment of the scene, and conditions. Partial discharge signal and make the discharge while building blocks were found through the Analysis. Spectrum frequence of Analysis and wide discharge part, to be more precise, in line with the various functions, including the analysis technique band. Diagnosis and comes up with advanced technology that can detect the presence of a position. This method is portable single device developed for maintenance and mobility and ease and convenience of getting caught by discharge of the pattern analysis and position detection method suitable for a new diagnosis will suggest.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.11-22
• /
• 2023

A radiating elements fault diagnosis method with simplified radiation pattern measurement procedure was presented for planar active phased array antenna system. For presenting the mentioned method, the technique for linear approximation based on the radiation characteristics of a planar array configuration and a technique for solving a unique solution problem that occur in process of diagnosing a fault in a radiating elements were presented. Based on the presented method and a genetic algorithm, experimental simulations were performed for radiating element defect diagnosis according to various planar active phased array antenna configurations. As a result, it was confirmed that the presented radiating element fault diagnosis method can be smoothly applied to planar active phased antennas having various configurations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.8B
• /
• pp.701-706
• /
• 2006

System-level diagnosis plays an important technique for fault detection in multi-processor systems. Efficient diagnosis is very important for real time systems as well as multiprocessor systems. Feng(1) proposed two adaptive diagnosis algorithms HADA and IHADA for hypercube system. The diagnosis cost, measured by diagnosis time and the number of test links, depends on the number and location of the faults. In this paper, we propose an adaptive diagnosis algorithm using the syndrome analysis. This removes unnecessary overhead generated in HADA and IHADA algorithm sand give a better performance compared to Feng's Method.

• Journal of Korean Society for Quality Management
• /
• v.52 no.2
• /
• pp.357-376
• /
• 2024

Purpose: The purpose of this study is to design an objective and comparable diagnostic system for diagnosing the technology level of military maintenance depots and verify its actual applicability. Methods: Literature Review, Capability Maturity Model Integration, Analytic Hierarchy Process. Results: Military maintenance depot maintenance quality level diagnosis items, Maintenance quality level by maintenance technology area, Guidelines for diagnosing maintenance quality level, Quality level comparison results by area and implications for improvement. Conclusion: In order to systematically evaluate the maintenance quality of military maintenance depots, this study was conducted with the goal of designing an overall maintenance quality diagnosis system, including diagnosis areas, diagnosis items, and a diagnosis score award system, by improving the existing evaluation method. In addition, the newly developed maintenance quality diagnosis system was applied to actual evaluation activities and the results were returned to members, confirming the usefulness of the developed maintenance quality diagnosis system in the field.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.1
• /
• pp.57-64
• /
• 2017

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.

• Transactions on Electrical and Electronic Materials
• /
• v.14 no.4
• /
• pp.211-215
• /
• 2013

Partial discharge diagnosis techniques using ultra high frequencies do not affect load movement, because there is no interruption of power. Consequently, these techniques are popular among the prevention diagnosis methods. For the first time, this measurement technique has been applied to the GIS, and has been tested by applying an extra high voltage switchboard. This particular technique makes it easy to measure in the live state, and is not affected by the noise generated by analyzing the causes of faults ? thereby making risk analysis possible. It is reported that the analysis data and the evaluation of the risk level are improved, especially for poor location, and that the measurement of Ultra high frequency (UHF) partial discharge of the real live wire in industrial switchgear is spectacular. Partial discharge diagnosis techniques by using the Ultra High Frequency sensor have been recently highlighted, and it is verified by applying them to the GIS. This has become one of the new and various power equipment techniques. Diagnosis using a UHF sensor is easy to measure, and waveform analysis is already standardized, due to numerous past case experiments. This technique is currently active in research and development, and commercialization is becoming a reality. Another aspect of this technique is that it can determine the occurrences and types of partial discharge, by the application diagnosis for live wire of ultra high voltage switchgear. Measured data by using the UHF partial discharge techniques for ultra high voltage switchgear was obtained from 200 places in Gumi, Yeosu, Taiwan and China's semiconductor plants, and also the partial discharge signals at 15 other places were found. It was confirmed that the partial discharge signal was destroyed by improving the work of junction bolt tightening check, and the cable head reinforcement insulation at 8 places with a possibility for preventing the interruption of service. Also, it was confirmed that the UHF partial discharge measurement techniques are also a prevention diagnosis method in actual industrial sites. The measured field data and the usage of the research for risk assessment techniques of the live wire status of power equipment make a valuable database for future improvements.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.5
• /
• pp.553-560
• /
• 2003

On-site diagnosis of chiller performance is an essential step fur energy saving business. The main purpose of the on-site diagnosis is to predict the COP of a target chiller. Many models based on thermodynamics background have been proposed for this purpose. However, they have to be modified from chiller to chiller and require deep insight into thermodynamics that most of field engineers are often lacking in. This study focuses on developing an easy-to-use diagnostic technique that is based on adaptive neuro-fuzzy inference system (ANFIS). Quality of the training data for ANFIS, sampled over June through September, is assessed by checking COP prediction errors. The architecture of the ANFIS, its error bounds, and collection of training data are described in detail.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.138-140
• /
• 2006

A new diagnosis model was constructed by combining atomic force microscopy (AFM), wavelet, and neural network. Plasma faults were characterized by filtering AFM-measured etch surface roughness with wavelet. The presented technique was evaluated with the data collected during the etching of silicon oxynitride thin film. A total of 17 etch experiments were conducted. Applying wavelet to AFM, surface roughness was detailed into vertical, horizon%at, and diagonal components. For each component, neural network recognition models were constructed and evaluated. Comparisons revealed that the vertical component-based model yielded about 30% improvement in the recognition accuracy over others. The presented technique was evaluated with the data collected during the etching of silicon oxynitride thin film. A total of 17 etch experiments were conducted