• Nuclear Engineering and Technology
• /
• 제50권8호
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.

• 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.

• 한국지반환경공학회 논문집
• /
• 제16권5호
• /
• pp.43-53
• /
• 2015

본 연구에서는 빅데이터 범주에 포함되는 각종 계측 데이터를 대상으로 각종 이상치를 판단하기 위한 기법을 고안하고, 인공 데이터 및 실 계측 데이터를 이용한 이상치 분석을 수행하였다. 계측결과에 대한 1차 차분 값 및 오차율을 적용한 규칙기반 방법은 큰 규모의 Short fault 분석 및 일정 기간 계측값에 변화가 발생하지 않는 경우의 Constant fault 분석에 효과적으로 적용될 수 있었으나, 독립적인 단일 데이터셋만을 이용하는 관계로 큰 변화폭을 보이는 실 계측 데이터의 정상 데이터를 이상치로 오판하는 문제점이 있었다. 규칙기반 방법을 이용한 Noise fault 분석은 적정 데이터 윈도우 사이즈의 선택 및 이상치 판정용 한계값 선정상의 문제로 인해 실 계측 데이터 적용에 한계가 있었다. 이종 데이터 간 상관분석 방법은 학습 데이터의 적정범위 선정이 선행된다면 장단기 계측 데이터의 이상 거동 및 국부적 이상치 판정에 매우 효과적으로 이용될 수 있음을 알 수 있었다.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1552-1564
• /
• 1995

A fault detecting method of ternary logic is proposed by using the spectral coefficients of the Chrestenson function. Fault detecting conditions are derived for a stuck-at fault in case of single input, multiple inputs and internal lines in the ternary logic. The detecting conditions for min/max bridging faults are also considered. When using this fault analysis method, it is possible to detect faults without the test vector and minimize high volume memory for storing the vector and response data. Thus, the computational complexity for the test vector can be decreased.

• 전기전자학회논문지
• /
• 제25권3호
• /
• pp.548-555
• /
• 2021

본 논문에서는 산업 공정, 설비 및 모터 드라이브에 적용되는 고장 진단 및 고장 허용 제어 기술의 기본 개념, 접근법과 연구 동향에 대해서 개괄적으로 기술하였다. 산업 공정을 위한 고장 진단의 주요 역할은 공정의 결함 상태를 파악할 수 있는 효과적인 지표를 만든 후 고장이나 위험한 사고에 대해 적절한 조치를 취하는 것이다. 산업 공정에 패턴이 있는지 특정 프로세스 변수가 정상적으로 동작하는지 확인하기 위해 많은 고장 검출 및 진단 기법이 개발되었다. 먼저 본 논문에서는 데이터 기반 기법과 모델 기반 기법에 대하여 살펴본다. 두 번째로 산업 공정을 위한 고장 검출 및 진단 기법을 살펴본다. 세 번째로 수동형 및 능동형 고장 허용 제어 기법을 살펴본다. 마지막으로 AC 모터 드라이브에서 발생하는 주요 고장을 열거, 그 특성을 살펴보고 이를 위한 고장 진단 및 고장 허용 제어 기술을 살펴본다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.301-305
• /
• 2001

A novel approach based on parameters estimation is presented far fault detection and diagnosis in sensors. Based on known precise parameter of normal working sensors system model is built from real laboratory inputs-outputs data, sequentially residual serial is obtained. Where decision-making rule of detection the fault is given via the use of beys theory, whilst a filter least-square computative algorithm for estimating fault parameters is given. The algorithm is a fast and accurate to calculate value of sensors faults when system model contains noise and sensors outputs contain measured noise. The method can solve both gain type and bias type fault in sensors. Simulated numerical example is included to demonstrate the use of the proposed approaches.

• 전기학회논문지P
• /
• 제57권2호
• /
• pp.102-108
• /
• 2008

AC generator plays an important role of power system. The large AC generator fault may lead to large impacts or perturbations in power system. And then the protection of a generator has very important role in maintaining stability in a power system. In present, the DFT(discrete Fourier transform) based RDR(ratio differential relay) had been widely applied to a internal fault of a generator stator winding. But DFT has a serious drawback. In the course of transforming a target signal to frequency domain, time information is lost. DWT uses a time-scale region. This paper proposes an advanced fault detection algorithm using DWT(discrete Wavelet transform) to enhance the drawback of conventional DFT based relaying. To evaluate the performance of the proposed relaying, we used the test data which were sampled with 720 [Hz] per cycle and obtained from ATP(alternative transient program) simulation. And we made a comparative study of conventional DFT based RDR and the proposed relaying.

• 전기학회논문지
• /
• 제62권2호
• /
• pp.155-163
• /
• 2013

As the increasing HIF(High Impedance Fault) with the arc cannot be easily detected for the low fault current magnitude compared to actual load in distribution line. However, the arcing current shows that the magnitude varies with time and the signal is asymmetric. In addition, discontinuous changes occur at starting point of arc. Considering these characteristics, wavelet transformation of actual current data shows difference between before and after the fault. Althogh raw data(detail coefficient) of wavelet transform may not be directly applied to HIF detection logic in a device, there are several developing methods of HIF monitoring data using the original wavelet coefficients. In this paper, a simple and effective developing methods of HIF monitoring data were analized by using the signal data through an actual HIF experiment to apply them to economic devices. The methods using the sumation of the wavelet coefficient squares in one cycle of the fundamental frequency as the energies of the wavelet coefficeits and the sumation of the absolute values were compared. Besides, the improved method which less occupies H/W resouces and can be applied to field detection devices was proposed. and also Verification of this HIF detection method through field test on distribution system in KEPCO power testing center was performed.

• Smart Structures and Systems
• /
• 제17권6호
• /
• pp.1031-1053
• /
• 2016

The health conditions of in-service civil infrastructures can be evaluated by employing structural health monitoring technology. A reliable health evaluation result depends heavily on the quality of the data collected from the structural monitoring sensor network. Hence, the problem of sensor fault diagnosis has gained considerable attention in recent years. In this paper, an innovative sensor fault diagnosis method that focuses on fault detection and isolation stages has been proposed. The dynamic or auto-regressive characteristic is firstly utilized to build a multivariable statistical model that measures the correlations of the currently collected structural responses and the future possible ones in combination with the canonical correlation analysis. Two different fault detection statistics are then defined based on the above multivariable statistical model for deciding whether a fault or failure occurred in the sensor network. After that, two corresponding fault isolation indices are deduced through the contribution analysis methodology to identify the faulty sensor. Case studies, using a benchmark structure developed for bridge health monitoring, are considered in the research and demonstrate the superiority of the new proposed sensor fault diagnosis method over the traditional principal component analysis-based and the dynamic principal component analysis-based methods.

• 한국전자통신학회논문지
• /
• 제18권3호
• /
• pp.527-534
• /
• 2023

삼중구조 시스템에서는 하나의 프로세서에서 고장이 발생해도 여유도 때문에 주어진 임무를 계속 수행할 수 있다. 본 연구에서는 삼중구조 시스템에 체크포인터 기법을 도입한 후 고장 탐지와 체크포인터를 분리하는 새로운 고장 극복 방법을 제안한다. 먼저 한 개 프로세서에서 고장이 발생하면 고장 탐지와 동시에 모든 프로세서의 상태를 동기화함으로써 고장을 복구한다. 또한 두 개 이상의 프로세서에서 동시에 고장이 발생하면 직전의 체크포인터로 회귀하여 태스크를 재실행함으로써 고장을 복구한다. 본 논문에서는 태스크가 데드라인 이내에서 성공적으로 수행될 확률을 최대화하는 고장 탐지 구간과 체크포인터 구간의 선정 방법을 제안한다. 제안된 방식을 탑재한 삼중구조 시스템을 마코프 체인으로 모델링하고 실시간 태스크의 성공적 수행 확률을 도출하는 모의실험을 수행하여 최적의 해를 구하는 과정을 제시한다.