• Journal of the Korean Society of Safety
• /
• v.29 no.5
• /
• pp.47-53
• /
• 2014

Despite the automatic fire alarm system, according to the national fire data system of national emergency management agency, the fires account for 40,932 incidents, 2,184 injuries and about 430 billion won in property losses in 2013. Since the conventional automatic fire alarm system has several weaknesses related to electrical signal such as noise, surge, lighting, etc. Most fires are mainly caused by electrical faults, mechanical problem, chemical, carelessness and natural. The electrical faults such as line to ground fault, line to line fault, electrical leakage and arc are one of the major problems in fire. This paper describes the development of a novel real-time fire monitoring system algorithm including fault detection function which puts the existing optic smoke and heat detectors for fire detection with current and voltage sensors in order to utility fault monitoring using high accuracy DAQ measurement system with LabVIEW program. The fire detection and electrical fault monitoring with a proposed a new detection algorithm are implemented under several test. The fire detection and monitoring system operates according to the proposed algorithm well.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.374-379
• /
• 2007

This paper focuses on the improvement of fault detection algorithm in FRTU(feeder remote terminal unit) on the feeder of distribution power system. FRTU is applied to fault detection schemes for phase fault and ground fault. Especially, cold load pickup and inrush restraint functions distinguish the fault current from the normal load current. FRTU shows FI(Fault Indicator) when the fault current is over pickup value or inrush current. STFT(Short Time Fourier Transform) analysis provides the frequency and time Information. FCM(Fuzzy C-Mean clustering) algorithm extracts characteristics of harmonics. The neural network system as a fault detector was trained to distinguish the inruih current from the fault status by a gradient descent method. In this paper, fault detection is improved by using FCM and neural network. The result data were measured in actual 22.9kV distribution power system.

• IE interfaces
• /
• v.25 no.2
• /
• pp.170-177
• /
• 2012

Process control is essential to operate the semiconductor process efficiently. This paper consider fault classification of semiconductor based cyclic signal for process control. In general, process signal usually take the different pattern depending on some different cause of fault. If faults can be classified by cause of faults, it could improve the process control through a definite and rapid diagnosis. One of the most important thing is a finding definite diagnosis in fault classification, even-though it is classified several times. This paper proposes the method that one-class classifier classify fault causes as each classes. Hotelling T2 chart, kNNDD(k-Nearest Neighbor Data Description), Distance based Novelty Detection are used to perform the one-class classifier. PCA(Principal Component Analysis) is also used to reduce the data dimension because the length of process signal is too long generally. In experiment, it generates the data based real signal patterns from semiconductor process. The objective of this experiment is to compare between the proposed method and SVM(Support Vector Machine). Most of the experiments' results show that proposed method using Distance based Novelty Detection has a good performance in classification and diagnosis problems.

• Nuclear Engineering and Technology
• /
• v.51 no.1
• /
• pp.146-154
• /
• 2019

An improved principal component analysis (PCA) method is applied for sensor fault detection and isolation (FDI) in a nuclear power plant (NPP) in this paper. Data pre-processing and false alarm reducing methods are combined with general PCA method to improve the model performance in practice. In data pre-processing, singular points and random fluctuations in the original data are eliminated with various techniques respectively. In fault detecting, a statistics-based method is proposed to reduce the false alarms of $T^2$ and Q statistics. Finally, the effects of the proposed data pre-processing and false alarm reducing techniques are evaluated with sensor measurements from a real NPP. They are proved to be greatly beneficial to the improvement on the reliability and stability of PCA model. Meanwhile various sensor faults are imposed to normal measurements to test the FDI ability of the PCA model. Simulation results show that the proposed PCA model presents favorable performance on the FDI of sensors no matter with major or small failures.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.4
• /
• pp.460-467
• /
• 2008

This paper presents a new numerical algorithm for the fault location estimation and arcing fault detection when a single-phase arcing ground fault occurs on a transmission line. The proposed algorithm derived in the spectrum domain is based on the synchronized voltage and current samples measured from the PMUs(Phasor Measurement Units) installed at both ends of the transmission lines. In this paper, the algorithm uses DFT(Discrete Fourier Transform) for estimation. The algorithm uses a short data window for real-time transmission line protection. Also, from the calculated arc voltage amplitude, a decision can be made whether the fault is permanent or transient. The proposed algorithm is tested through computer simulation to show its effectiveness.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2005.11a
• /
• pp.204-205
• /
• 2005

The following instructions give you basic guidelines for preparing camera-ready papers for the proceeding of the KOSME. We recommend you to use the HWP word processor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.247-250
• /
• 2006

Maximizing the productivity in reactive ion etching, early detection of process equipment anomaly became crucial in current high volume semiconductor manufacturing environment. To address the importance of the process fault detection for productivity, support vector machines (SVMs) is employed to assist the decision to determine process faults in real-time. SVMs for eleven steps of etching runs are established with data acquired from baseline runs, and they are further verified with the data from controlled (acceptable) and perturbed (unacceptable) runs. Then, each SVM is further utilized for the fault detection purpose utilizing control limits which is well understood in statistical process control chart. Utilizing SVMs, fault detection of reactive ion etching process is demonstrated with zero false alarm rate of the controlled runs on a run to run basis.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.16 no.5
• /
• pp.45-52
• /
• 2002

This paper presents fault detection scheme of Brushless DC(BLDC) motor drive system by estimating BLDC motor resistance using motor input and output data which is transmitted from data acquisition board to host computer over serial communication channel. Since communication time delay has a serious effect on performance, we use periodic and fixed communication protocol. Hence, the delay time is priory known. Simplified BLDC motor model and recursive least square algorithm is used for estimating motor resistance. By experiment result, we confirm the proposed scheme.

• Economic and Environmental Geology
• /
• v.53 no.4
• /
• pp.479-489
• /
• 2020

A fault is a geological structure that can be a migration path or a cap rock of hydrocarbon such as oil and gas, formed from source rock. The fault is one of the main targets of seismic exploration to find reservoirs in which hydrocarbon have accumulated. However, conventional fault detection methods using lateral discontinuity in seismic data such as semblance, coherence, variance, gradient magnitude and fault likelihood, have problem that professional interpreters have to invest lots of time and computational costs. Therefore, many researchers are conducting various studies to save computational costs and time for fault interpretation, and machine learning technologies attracted attention recently. Among various machine learning technologies, many researchers are conducting fault interpretation studies using the support vector machine, multi-layer perceptron, deep neural networks and convolutional neural networks algorithms. Especially, researchers use not only their own convolution networks but also proven networks in image processing to predict fault locations and fault information such as strike and dip. In this paper, by investigating and analyzing these studies, we found that the convolutional neural networks based on the U-Net from image processing is the most effective one for fault detection and interpretation. Further studies can expect better results from fault detection and interpretation using the convolutional neural networks along with transfer learning and data augmentation.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.4
• /
• pp.537-543
• /
• 2003

Transient vibration generated by developing localized fault in gear can be used as indicators in gear fault detection. This vibration signal suffers from the background noise such as gear meshing frequency and its harmonics and broadband noise. Thus in order to extract the information about the only gear fault from the raw vibration signal measured on the gearbox this signal is processed to reduce the background noise with many kinds of signal-processing tools. However, these signal-processing tools are often very complex and time waste. Thus. in this paper. we propose a novel approach detecting the damage of gearbox and analyzing its pattern using the raw vibration signal. In order to do this, the residual signal. which consists of the sideband components of the gear meshing frequent) and its harmonics frequencies, is extracted from the raw signal by the power spectral density (PSD) to obtain the information about the fault and is used as the input data of the artificial neural network (ANN) for analysis of the pattern of gear fault. This novel approach has been very successfully applied to the damage analysis of a laboratory gearbox.