• Nuclear Engineering and Technology
• /
• v.47 no.2
• /
• pp.176-186
• /
• 2015

Pattern classifications have become important tools for fault diagnosis in nuclear power plants (NPP). However, it is often difficult to obtain training data under fault conditions to train a supervised classification model. By contrast, normal plant operating data can be easily made available through increased deployment of supervisory, control, and data acquisition systems. Such data can also be used to train classification models to improve the performance of fault diagnosis scheme. In this paper, a fault diagnosis scheme based on semisupervised classification (SSC) scheme is developed. In this scheme, new measurements collected from the plant are integrated with data observed under fault conditions to train the SSC models. The trained models are subsequently applied to new measurements for fault diagnosis. In comparison with supervised classifiers, the proposed scheme requires significantly fewer data collected under fault conditions to train the classifier. The developed scheme has been validated using different fault scenarios on a desktop NPP simulator as well as on a physical NPP simulator using a graph-based SSC algorithm. All the considered faults have been successfully diagnosed. The results have demonstrated that SSC is a promising tool for fault diagnosis in NPPs.

• Journal of Power Electronics
• /
• v.16 no.3
• /
• pp.1097-1109
• /
• 2016

Fault detection and isolation are related to system monitoring, identifying when a fault has occurred, and determining the type of fault and its location. Fault detection is utilized to determine whether a problem has occurred within a certain channel or area of operation. Fault detection and diagnosis have become increasingly important for many technical processes in the development of safe and efficient advanced systems for supervision. This paper presents an integrated technique for fault diagnosis and classification for open- and short-circuit faults in three-phase inverter circuits. Discrete wavelet transform and principal component analysis are utilized to detect the discontinuity in currents caused by a fault. The features of fault diagnosis are then extracted. A fault dictionary is used to acquire details about transistor faults and the corresponding fault identification. Fault classification is performed with a fuzzy logic system and relevance vector machine (RVM). The proposed model is incorporated with a set of optimization techniques, namely, evolutionary particle swarm optimization (EPSO) and cuckoo search optimization (CSO), to improve fault detection. The combination of optimization techniques with classification techniques is analyzed. Experimental results confirm that the combination of CSO with RVM yields better results than the combinations of CSO with fuzzy logic system, EPSO with RVM, and EPSO with fuzzy logic 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.10
• /
• pp.1774-1779
• /
• 2016

This paper proposes a portable cable fault detection system with automatic fault distinction and distance measurement using time-frequency correlation and reference signal elimination method and automatic fault classification algorithm in order to have more accurate fault determination and location detection than conventional time domain refelectometry (TDR) system despite increased signal attenuation due to the long distance to cable fault location. The performance of the developed system method was validated via an experiment in the test field constructed for the standardized performance test of power cable fault location equipments. The performance evaluation showed that accuracy of the developed system is less than 1.34%. Also, an error of automatic fault type and location by detection of phase and peak value through elimination of the reference signal and normalization of correlation coefficient and automatic fault classification algorithm not occurred.

• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.412-415
• /
• 2003

It is important to classily fault types, discriminate fault section and calculate the fault location by any detecting technique for combined transmission lines. This paper proposes the technique to classily the fault types and fault section using neuro-fuzzy systems. Neuro-fuzzy systems are composed of three parts to perform different works. First, neuro-fuzzy system for fault type classification is performed with approximation coefficient of currents obtained by wavelet transform. The second neuro-fuzzy system discriminates the fault section between overhead and underground with detail coefficients of voltage and current. The last neuro-fuzzy system calculates the fault location with impedance in this paper, neuro-furry system shows the excellent results for classification of fault types and discrimination of fault section.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.534-536
• /
• 2003

It is important to classily fault types and discriminate fault section by any detecting technique for combined transmission lines. This paper proposes the technique to classify the fault types and fault section using neuro-fuzzy systems. Neuro-fuzzy systems are composed of two parts to perform different works. First, neuro-fuzzy system for fault type classification is performed with approximation coefficient of currents obtained by wavelet transform. Another neuro-fuzzy system discriminates the fault section between overhead and underground with detail coefficients of voltage and current. In this paper, neuro-fuzzy system shows the excellent results for classification of fault types and discrimination of fault section.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.5
• /
• pp.209-216
• /
• 2002

Recently, there is greater demand for stable supply of electric power as higher level of our living. It becomes the important problem that the cause of fault in power system is found out in early stage, if once it occurs. In this respect, accurate classification of arcing faults in power systems is vitally important. This paper presents a new classification method for arcing faults in power system. To obtain data of various faults including high impedance fault(HIF) and low impedance fault(LIF), HIF model with the ZnO arrester is adopted and implemented within the overall transmission system model based on the electromagnetic transients program(EMTP). Results of phase plane trajectory if Clarke modal transformation using postfault current and voltage are utilized to classify types of arcing faults. The performance of the proposed method is tested on a typical 154 kV korean transmission system under various fault conditions. As can be seen from results, phase plane trajectory of postfault current should be combined with that of o component from Clarke modal transformation to give reliability of clear fault classification. Thus the proposed method can classify arcing faults including LIFs and HIFs accurately in power systems.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.416-424
• /
• 2016

In this study, automatic detection of stator winding inter-turn short circuit fault (SWISCFs) in surface-mounted permanent magnet synchronous motors (SPMSMs) and automatic classification of fault severity via a pattern recognition system (PRS) are presented. In the case of a stator short circuit fault, performance losses become an important issue for SPMSMs. To detect stator winding short circuit faults automatically and to estimate the severity of the fault, an artificial neural network (ANN)-based PRS was used. It was found that the amplitude of the third harmonic of the current was the most distinctive characteristic for detecting the short circuit fault ratio of the SPMSM. To validate the proposed method, both simulation results and experimental results are presented.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.808-810
• /
• 1996

In this paper, neural network, which has learning capability, is used for fault type classification and fault section estimation for high speed relaying. The potential of the neural network approach is demonstrated by simulation using ATP. The instantaneous values of voltages and currents are used the inputs of neural networks. This approach determines the fault section directly. In this paper, back-propagation network(BPN) is used for fault type classification and fault section estimation and can use for high speed relaying because it determines fault section within a few msec.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1114-1117
• /
• 1998

Recent applications of neural networks to power system fault diagnosis have provided positive results and have shown advantages in process speed over conventional approaches. This paper describes the application of neural network to fault detection and classification in distribution lines using the fundamental component, 2-5th harmonics index, even and odd harmonics index, and zero phase current. The Electromagnetic Transients Program (EMTP) is used to obtain fault patterns for the training and testing of neural networks. The proposed fault detection and classification method in distribution lines is obtained by analysing the difference among normal, HIF, ground fault, short circuit fault condition.