• 컴퓨터교육학회논문지
• /
• 제11권3호
• /
• pp.81-89
• /
• 2008

광범위 분산 컴퓨팅 시스템인 그리드 컴퓨팅에서는 자원 결함의 발생 정도가 기존의 병렬 컴퓨팅보다 더 높다. 그리드 컴퓨팅에서 자원들의 결함은 작업 수행에 있어서 치명적인 영향을 줄 수 있기 때문에 결함 포용 기능은 필수적인 요소이다. 그리고 그리드 서비스들은 바람직한 작업의 수행을 위해 그리드 자원들의 최소한의 서비스 품질을 요구한다. 하지만 그리드 컴퓨팅 서비스를 제공하는 대표적인 미들웨어인 글로버스(Globus)는 결함 탐지 서비스와 관리 서비스 그리고 QoS 요구사항을 만족하는 결함 포용 서비스를 제공하지 않는다. 이에 본 논문에서는 그리드 컴퓨팅에서 QoS 요구사항을 만족하는 결합 포용 서비스를 제안한다. 이를 위해 본 논문에서는 프로세스 결함, 프로세서 결함, 네트워크 결함과 같이 결함의 정의를 확장한다. 그리고 자원 스케줄링 서비스, 결함 탐지 서비스, 결함 관리 서비스를 제안하고 구현 및 실험 결과를 제시한다.

• 한국항공우주학회지
• /
• 제50권8호
• /
• pp.541-550
• /
• 2022

IMM 필터 및 GLRT 기법을 이용하여 무인기용 엔진의 효과적인 실시간 결함 진단 방안을 도출하였다. 이를 위해서 엔진 동적 사이클해석으로부터 선형 진단 모델을 유도하고 잔차 추정을 위한 칼만필터를 도입한 후 각 기법의 특성을 고찰하여 엔진 제어 구동기 및 센서의 결함 진단에 적용하였다. 이 과정에서 IMM 필터로부터 효과적인 FDI 방안을 도출하였고 구동기 결함으로 인한 상태변수의 반응값을 추정하였으며, GLRT로부터는 구동기 및 센서의 결함값 추정과 FDI 기능을 확인하였다. 수치 모의시험 결과를 통해서 FDI를 위한 IMM 필터의 효용성과 각 결함 모드의 결함값 추정을 위한 GLRT 기법의 효용성을 확인하였다.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2096-2106
• /
• 2023

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

• 한국기계연구소 소보
• /
• 통권17호
• /
• pp.61-68
• /
• 1987

The main objective of this paper is to develop the computer-aided vibrational signal processing and monitoring system of rotating machinery. This system has an automatic data acquisition capability and analyze for machine fault diagnosis. By spectrum analysis, machine’s failure can be identified. The monitoring system enables diagnosis of the fault in rotating machinery. In this study, the conventional electrical fans are selected as a model case. The date processing and fault monitoring system proposed here can be applied to the automation of the inspection process in assembling motor-shaft systems. The automatic inspection can enhance the product quality and keep it stable. Since the proposed system is developed for personal computers, it might be cheap in cost and easy in installation.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2009년도 추계학술대회 논문집
• /
• pp.44-44
• /
• 2009

Fault detection is necessary for yield enhancement and cost reduction in semiconductor manufacturing. Sensory data acquired from the semiconductor processing tool is too large to analyze for the purpose of fault detection and classification(FDC). We studied the techniques of fault detection using statistical method. Multiple regression analysis smoothly detected faults and can be easy made a model. For real-time and fast computing time, the huge data was analyzed by each step. We also considered interaction and critical factors in tool parameters and process.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.203-207
• /
• 1998

In this paper, it is shown how Fuzzy Pattern Matching can be applied to diagnosis of the most common faults of Rotating Machinery. The whole diagnosis process has been divided in three steps : Fault Detection, Fault Isolation and Fault Identification, whose possible results are described by linguistic patterns. Diagnosis will consist in obtaining a set of matching indexes that indexes that express the compatibility of the fuzzified features extracted from the measured vibration signals, with the knowledge contained in the corresponding patterns.

• Tribology and Lubricants
• /
• 제14권3호
• /
• pp.74-80
• /
• 1998

The morphologies of the wear particles are directly indicative of wear process occuring in the machine. The analysis of wear particle morphology can therefore provide very early detection of a fault and can also ofen facilitate a dignosis. For this work, the neural network was applied to identify friction coefficient through four shape parameters (50% volumetric diameter, aspect, roundness and reflectivity) of wear debris generated from the machine. The averages of these parameters were used as inputs to the network. It is shown that collect identification of friction coefficient depends on the ranges of these shape parameters learned. The various kinds of the wear debris had a different pattern characteristics and recognized relation between the friction condition and materials very well by neural network. We discuss how the network determines difference in wear debris feature, and this approach can be applied for machine condition monitoring and fault diagnosis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.32.2-32
• /
• 2002

In this paper, an efficient FFT-based fault detection algorithm is proposed. In our proposed method, fault detection is accomplished by process similar to the conventional FFT-based fault detection. However, the proposed technique adopts fast algorithms for preprocessing, where the conventional operation such as averaging is replaced with recursive average operation that outperforms the former in computational cost. And, the proposed approach utilizes the feature vector with the small dimension, which is extracted from spectral components of the lower and upper sidebands around the fundamental frequency. The mean absolute difference (MAD) criterion is used to finally determine whether motor...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.139-144
• /
• 1987

The problem of process(Sensor) fault management in Observer Based Control System are considered and structures of Fault Tolerant Observer based Control Systems (FMCS) that function well in the face of the faults are proposed. The FTOCSs include detection logic unit and an additional observer driven by residuals of primary observer and estimate estimation errors of primary observer and fault variables. Since the FTOCSs have the ability to detect and accomodate the faults the original control objectives can be accomplished without considerable control performance deterioration even in the faulty environments. Therefore, the Proposed FMCSs can effectively be used for enhancing the functional reliability of the Observer Based Control Systems.

• 대한전자공학회논문지
• /
• 제17권2호
• /
• pp.37-52
• /
• 1980

산업프로세스(industrial _Process)가 점차 복잡하여지고 자동화됨에 따라 계통(system)의 신뢰도를 높이고 인간의 한계능력을 해결하기 위하여 경보분석(alarm analysis)흑은 고장진단(fault diagnosis)의 필요성이 절실화 되어 가고 있다. 본 논문에서는 화학 반응기 (chemical reactor)의 고장진단을 위한 방법으로 시이퀸스 콤퓨터 프로그램밍(sequence computer programming )에 의한 "사전(dictionary)" 작성방법이 시도 되었고 실험을 통해 그 유용성이 입증 되었다. 그리고 점차 복잡되어가고 있는 경보 시스템(alarm system)을 단순화 시킬 수 있는 결과 시스템 설계에 대한 제안을 마련하였다.