• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.2065-2066
• /
• 2011

기계적에너지를 전기적에너지로 변환하는 발전기를 내 외부 고장으로부터 보호하기 위해 보호계전기가 설치되어 있으며, 이러한 보호계전기의 동작신호 중 하나인 전압신호를 검출하기 위해 발전기와 변압기를 연결하는 모선에 설치된 계기용변성기를 이용한다. 본 논문은 발전기의 보호계전기용 계기용변성기 손상원인에 관한 연구로서, 계기용변성기의 철공진에 이한 손상가능성을 고찰하였고 발전소에 많이 사용되는 G사의 계기용변성기와 손상된 I사의 계기용변성기에 대한 전기적 시험결과를 비교하였으며, 계기용변성기를 직접 절개하여 제작 및 적용특성을 분석하였다. 그 결과 발전기 전압신호 검출용 계기용변성기는 발전기 중성점 접지형태에 관계없이 반드시 Line to Line type을 적용해야 함을 도출했다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.10a
• /
• pp.165-173
• /
• 1993

생산일정계획 수립 시스템을 통하여 수립된 생산계획을 현장에서 실천하고자 할 때, 일반적으로 계획수립 후 얼마 지나지 않아 계획수립시 고려할 수 없었던 기계고장 또는 자재조달 지연, 작업 지체, 주문 취소 등과 같은 요인으로 생산일정을 계획대로 실천할 수 없는 경우가 발생한다. 이런 상황에서는 기존의 생산계획을 계속 실행할 수 없으므로 손쉽게 대처할 수 있는 방안이 필요하다. 본 연구에서는 일정계획편집기를 이러한 문제점을 해결할 수 있는 대안으로 제시한다. 일정계획편집기를 GUI, 객체지향적 설계를 통해 구현하므로서 이상상황과 일정변동에 효과적으로 대처할 수 있다. GUI환경을 통해, 수립된 생산일정과 이상상황, 작업진척, 수행도 등을 화면에 Gantt 도표로 표시해 주어 현장 파악을 용이하게 하고 작업추가, 삭제, 작업시간 변경, 대체공정으로의 이동 등의 편집을 mouse와 icon을 이용, 편리하게 수행할 수 있다. 편집작업시 자동으로 생산일정의 타당성을 만족시켜 줄 수 있는 지능화를 위한 기초 단계로서 객체지향설계를 이용한 규칙기반 일정계획 편집기를 설계한다.

• Proceedings of the KIPE Conference
• /
• 2012.11a
• /
• pp.179-180
• /
• 2012

풍력 발전기는 과 풍속 시 전기적이나 기계적인 안전을 고려해 날개의 회전수를 줄이거나 정지하도록 제어된다. 소형풍력발전기는 스위치로 출력을 단락시켜 발전기를 정지시키며, 이때 큰 단락 전류로 인해 발전기 코일 또는 정류기 소손 등의 고장이 발생될 수 있다. 따라서 본 논문에서는 여러 개의 저항을 선택적으로 발전기 출력에 연결하도록 제어하는 방법을 제안하여 발전기가 안전하게 정지되게 하고, 200W 풍력 발전기를 대상으로 제안된 방법을 적용하여 과 풍속 환경에서 실험한 결과 발전기의 안정적인 제동을 확인하였다.

• Annual Conference of KIPS
• /
• 2018.05a
• /
• pp.525-528
• /
• 2018

최근 드론을 이용한 산업이 급부상하면서 드론 사용률이 증가하고 있다. 하지만 이에 따라 드론으로 인한 사고도 증가하고 있는데 그 중 기계고장을 제외한 가장 큰 원인은 사용자 부주의에 의해 발생한다. 이러한 문제점을 해결하기 위해 다양한 연구가 진행되고 있으나 대부분의 연구는 부가적인 장치를 통해 발생하는 센싱데이터를 이용하여 해결하는 방식이다. 이러한 방식은 비용적인 측면과 궁극적으로 사용자의 부주의에서 발생하는 문제를 해결하기 어려운 문제점이 있다. 따라서 본 논문에서는 기존의 컨트롤러와 드론에 내장되어 있은 지자기 센서를 이용하여 사용자 시점 중심적인 드론 컨트롤 시스템을 통해 이 문제를 해결한다.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.53-59
• /
• 2021

The marine transport industry generally applies new technologies later than other transport industries, such as airways and railways. Vessels require efficient operation, and their performance and lifespan depend on the level of maintenance and management. Many studies have shown that corrective maintenance (CM) and time-based maintenance (TBM) have restrictions with respect to enabling efficient maintenance of workload and cost to improve operational efficiency. Predictive maintenance (PdM) is an advanced technology that allows monitoring the condition and performance of a target machine to predict its time of failure and helps maintain the key machinery in optimal working conditions at all times. This study presents the development of a marine predictive maintenance (MPdM; maritime predictive maintenance) method based on applying PdM to the marine environment. The MPdM scheme is designed by considering the special environment of the marine transport industry and the extreme marine conditions. Further, results of the study elaborates upon the concept of MPdM and its necessity to advancing marine transportation in the future.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.10
• /
• pp.1833-1840
• /
• 1992

In the diagnostic process for automobile, Neuro-Fuzzy technique was compared with the conventional diagnostic method for the verification of performance, and proto-type system was developed. For the utilities of the system, 1/3 octave filter(band-pass filter) and A/D converter were used for data acquisition and then data were analyzed using octave band processing and pattern recognition using hamming network algorithm. In order to raise the reliability of the diagnostic results by considering many operating variables and condition of automobile to be diagnosed, fuzzy inference technique was applied in combining several information. The validation of this diagnostic system was examined through computer simulation and experiment, and it showed an acceptable performance for diagnostic process.

• 한국신재생에너지학회:학술대회논문집
• /
• 2009.06a
• /
• pp.798-801
• /
• 2009

소각로를 포함한 다양한 산업설비의 배폐열은 열병합 등의 다양한 방법을 통해 재활용되고 있으나 에너지의 효율적 사용과 편의성을 고려할 때, 단순한 온수공급 등의 방법보다는 전력으로서의 재활용이 매우 필요하다. 특히 재활용이 어려운 $400^{\circ}C$이내의 중저온급 폐열원을 발전할 수 있는 유력한 방안으로 열전발전기술이 최근 부각되고 있다. 열전발전은 발전모듈의 변환효율이 7~10%이고, 시스템 효율은 5%내외로 증기발전에 비해서는 낮지만 기계적 가동부분이 없어 고장발생이 적고 기동정지가 용이하며 열이 있으면 바로 발전이 가능한 차세대 친환경 발전기술이다. 본 연구에서는 현재까지 시도, 개발되지 못한 $100^{\circ}C$에서 $400^{\circ}C$내외 온도영역인 중저온급 소각폐열 회수를 위한 목적으로 중온용 열전발전소재 및 모듈과 저온과 중온에 각기 대응하여 폐열발전의 효용성을 높인 복식열전발전시스템을 개발 중에 있다. 본 고에서는 현재까지 진행된 일부 연구내용들을 소개하고자 하였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.8
• /
• pp.965-970
• /
• 2011

We develop a diagnostic system to monitor failures in an engine-assembly line. Existing techniques such as sensory analysis, time domain analysis, frequency analysis, and statistical analysis have limitations in the diagnosis of engine-assembly failure when there are abnormal vibration waveforms (crashing and damping signals) during the assembly. We use a wavelet technique to deal with crashing and damping signals. We also implement a new technique for developing diagnostic rules from sensor data, and we demonstrate its validity.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.11
• /
• pp.1315-1321
• /
• 2013

This study presents a prognostic technique for the damage state of a ball bearing. A stochastic bearing fatigue defect-propagation model is applied to estimate the damage progression rate. The damage state and the time to failure are computed by using RMS data from noisy acceleration signals. The parameters of the stochastic defect-propagation model are identified by conducting a series of run-to-failure tests for ball bearings. A regularized particle filter is applied to predict the damage progression rate and update the degradation state based on the acceleration RMS data. The future damage state is predicted based on the most recently measured data and the previously predicted damage state. The developed method was validated by comparing the prognostic results and the test data.