• 드라이브 ㆍ 컨트롤
• /
• 제20권4호
• /
• pp.140-149
• /
• 2023

Wire harness is a component for efficient control when electronic parts are required such as construction machinery and electric vehicles. With emerging issues such as autonomous driving and automation in construction, a wire harness composed of multiple cables has become an essential part because more electronic parts are required. However, when a wire harness failure occurs, systems can be stopped, accidents can occur, and economic damage can be significant. Therefore, in this paper, we developed a digital fault screening system that could easily and quickly diagnose faults in the wire harness. The principle of the developed system was to sequentially send pulse signals to the wire harness and use returned signals to perform fault detection. As a result of diagnosing faults using the developed failure detection system, a detection accuracy of 99.9 % was confirmed through the experiments.

• 한국항공우주학회지
• /
• 제43권5호
• /
• pp.449-455
• /
• 2015

Built-In-Test(이하: BIT)는 항공기 비행안전을 위해 반드시 필요한 기능으로 항공전자 장비의 경우 95% 이상의 높은 고장 진단능력을 요구하고 있다. BIT가 요구도에 명시된 고장 진단능력을 만족시키는지 확인하기 위해 BIT 성능분석이 필요하다. BIT 성능분석을 위해 FMECA (Failure Mode Effect Critical Analysis)에 기술된 고장모드를 활용하는 방법이 많이 사용되고 있으나, 본 논문에서는 분석 오류를 최소화할 수 있는 전자부품 기반의 BIT 성능분석 방법론을 소개한다. 또한, BIT 성능분석에서 제외될 수 있는 비행안전에 영향을 미치지 않는 전자부품 및 전자부품의 고장모드를 실제 개발사례에 적용하여 불필요한 BIT 기능 구현을 방지하고 정확한 BIT 성능분석을 수행할 수 있도록 하였다. BIT Demo를 수행하여 BIT 성능분석 결과와 실제 BIT 성능이 일치함을 확인하였다.

• Journal of Electrical Engineering and Technology
• /
• 제11권4호
• /
• pp.848-859
• /
• 2016

System failures in thermal power plants (TPPs) can lead to serious losses because the equipment is operated under very high pressure and temperature. Therefore, it is indispensable for alarm systems to inform field workers in advance of any abnormal operating conditions in the equipment. In this paper, we propose a clustering-based fault detection method for steam boiler tubes in TPPs. For data clustering, k-means algorithm is employed and the number of clusters are systematically determined by slope statistic. In the clustering-based method, it is assumed that normal data samples are close to the centers of clusters and those of abnormal are far from the centers. After partitioning training samples collected from normal target systems, fault scores (FSs) are assigned to unseen samples according to the distances between the samples and their closest cluster centroids. Alarm signals are generated if the FSs exceed predefined threshold values. The validity of exponentially weighted moving average to reduce false alarms is also investigated. To verify the performance, the proposed method is applied to failure cases due to boiler tube leakage. The experiment results show that the proposed method can detect the abnormal conditions of the target system successfully.

• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.113-124
• /
• 2022

데이터센터의 장애 예방을 위해 머신러닝과 빅데이터를 활용한 다양한 방법들이 적용되어 왔다. 그러나 개별 장비 기반의 성능지표를 참조하거나, 인프라 운영환경을 고려하지 않은 접근방법으로 실제 활용되는 데에는 많은 한계가 있었다. 이에 본 연구에서는 개별 인프라 장비들의 성능지표를 통합 모니터링하며, 다양한 장비들의 성능지표를 구간화, 등급화 하여 단일수치화를 진행한다. 인프라 운영에 대한 경험치 기반으로 데이터 전처리를 수행하며, RRCF(Robust Random Cut Forest)분석과 Prophet 분석 모델을 앙상블하여 이상징후 검출에 신뢰도 있는 분석결과를 도출하였다. 데이터센터 내 운영담당자들의 접근을 용이하게 하기 위해 장애분석시스템을 구현하여 데이터센터 장애의 선제 대응과 적정한 튜닝시점을 제시할 수 있다.

• 한국소음진동공학회논문집
• /
• 제12권4호
• /
• pp.287-293
• /
• 2002

The unexpected failure of the induction motor makes the downtime of production, and the cost of the process cessation enormous. To reduce the downtime and increase the reliability of the motor, the vibration measurements for the fault detection have been used previously. Recently motor current signature analysis(MCSA) has been adapted for the fault detection and diagnosis of the motors. MCSA provides a powerful analysis tool for detecting the presence of mechanical and electrical faults in both the motor and driven equipment. In this paper, the fault severity of the rotor bar has been derived in terms of the resistance change which is calculated from the equivalent circuit model. Results show that the fault of the rotor can be easily detected and the measured value of the resistance change is verified by the detected fault from on-site tests using MCSA for the induction motors in an iron foundry.

• 전기학회논문지
• /
• 제62권9호
• /
• pp.1297-1301
• /
• 2013

This paper analyzes of PD occurrence position through an analysis of the arrival time difference between the GIS partial discharge signal. Because of GIS (Gas Insulated Switchgear) is a facility very important power equipment and as part of the equipment that make up the power system, the stabilization of the power industry, which accounted for 88.5% share of GIS substation in the form of a substation is an important equipment for power supply. In the situation where we are gradually expanding the need for preventive diagnosis in order to improve the efficiency of equipment management and failure prevention for Preventive diagnosis. In this paper as a method for extracting pre-defect of failure of GIS Apply the average value method of calculating the 5 times each using a pulse of the first time of the second pulse (${\Delta}t$) with an oscilloscope generation position PD(Partial Discharge). the results of GIS internal inspection, the partial discharge of the actual the position of the partial discharge was confirmed with an accuracy of about 82% of positions. Arrival time difference in the most effective manner if the partial discharge of GIS internal occurs by applying the averaging method and TOA(Time of arrival) method, the partial discharge occurs you through the measurement and analysis of PD signal occurs was confirmed in the experiment are presented and diagnostic methods location tracking.

• 대한임베디드공학회논문지
• /
• 제17권3호
• /
• pp.167-175
• /
• 2022

With the recent expansion of electric kickboards and bicycle sharing services, more and more people use them. In addition, the rapid growth of the delivery business due to the COVID-19 has significantly increased the use of two-wheeled vehicles and personal mobility. As the accident rate increases, the rule related to the two-wheeled vehicles is changed to 'mandatory helmets for kickboards and single-person transportation' and was revised to prevent boarding itself without driver's license. In this paper, we propose a wearable smart safety equipment, called SafetyHelmet, that can keep helmet-wearing duty and lower the accident rate with the communication between helmets and mobile devices. To make this function available, we propose a safe driving assistance function by notifying the driver when an object that interferes with driving such as persons or other vehicles are detected by applying the YOLO v5 object detection algorithm. Therefore it is intended to provide a safer driving assistance by reducing the failure rate to identify dangers while driving single-person transportation.

• 한국인터넷방송통신학회논문지
• /
• 제19권2호
• /
• pp.169-174
• /
• 2019

본 논문은 스마트팜 ICT기기의 고장 오작동으로 인한 이상을 탐지하여 사용자에게 알리는 시스템을 제안한다. 4차 산업혁명이 다가오면서 농업도 경쟁력 향상을 위해 ICT기술과 융합하고 있다. 매년마다 스마트 농업 시장 규모는 빠르게 성장하고 있지만 아직까지 기기의 표준화와 인증제도가 부족한 실정이다. 특히 국내에서 보급되고 있는 스마트팜 기기는 업체마다 제품 규격이 상이하고 소프트웨어와 하드웨어가 별도로 개발되고 있는 등 품질과 호환성이 떨어져 저가의 스마트 팜 기기를 사용하는 농가의 피해가 빈번하게 발생하여 기기의 이상을 인지할 수 있는 시스템이 필요한 상황이다. 본 논문에서는 스마트팜 국내외 정책 동향과 국내 스마트 농업 동향을 알아보고 스마트팜 고장 오작동에 의한 이상 상황을 분석하여 사전에 예방하고 문제 상황이 발생할 경우 사용자에게 알리는 시스템을 제안한다.

• 한국공작기계학회논문집
• /
• 제12권6호
• /
• pp.22-28
• /
• 2003

We should maintain the maximum operation capacity for production facilities and find properly out the fault of each equipment rapidly in order to decrease a loss caused by its failure. The acoustic signals of a machine always carry the dynamic information of the machine. These signals are very useful for the feature extraction and fault diagnosis. We performed a fundamental study which develops a system of fault diagnosis for a pump. We obtained noises by a microphone, analysed and compared the signals converted to Sequency range for normal products, artificially deformed products. We tried to search a change of noise signals according to machine malfunctions and analyse the type of deformation or failure. The results showed that acoustic signals as well as vibration signals can be used as a simple method for a detection of machine malfunction or fault diagnosis.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 춘계학술대회 논문집
• /
• pp.99-104
• /
• 2003

We should maintain the minimum operation capacity for production facilities and find properly out the fault of each equipment rapidly in order to decrease a loss caused by its failure. The acoustic signals of a machine always carry the dynamic information of the machine. These signals are very useful for the feature extraction and fault diagnosis. We performed a fundamental study which develops a system of fault diagnosis for a pump. We obtained noises by a microphone, analysed and compared the signals converted to frequency range for normal products, artificially deformed products. We tried to search a change of noise signals according to machine malfunctions and analyse the type of deformation or failure. The results showed that acoustic signals as well as vibration signals can be used as a simple method for a detection of machine malfunction or fault diagnosis.