Fault Classification

In this paper, a fuzzy logic-based faults
classification scheme is proposed to identify all the ten
types of shunt faults for a three phase transmission line.
The technique is developed on the basis of extensive
simulation studies carried out on the transmission line
using MATLAB toolbox. It requires to be measured the
three phase post fault currents at one end (at relaying
point) in r.m.s. at fundamental frequency (50/60Hz). In
order to reduce the harmonic contents and
D.C.components, discrete fourier transform (DFT) for one
cycle at fundamental frequency is included. To illustrate
performance of the proposed technique, it is applied to a
large number of test cases, which is generated for
different type of faults. The output of the technique shows
the high degree of acceptance for a wide variation of the
system’s fault operating conditions. The technique
identifies faults created at different load angles, very high
resistance involved and at various fault inception time as
well. It is valid for any change in fault inception time.
Hence the method is reliable and robust.

Fault detection during power swing condition is a challenge for stable operation of power system due to several reasons. This paper proposes a negative-sequence current-based technique for detecting presence of fault, classification of fault occurred, estimated zone and location of the fault occurred and the fault inception time with respect to system reference clock during the power swing condition in a series compensated line. The technique is tested for different series -compensated power systems including a SMIB system and a WSCC-9bus-3machine power system with their different configurations and contingency combinations. Power swing caused by various faults are simulated with PSCAD / EMTDC and MATLAB/SIMULINK and compared with available techniques to prove the effectiveness of the proposed technique algorithm.

This project deals with the application of wavelet transform for the detection, classification of faults on transmission lines. A Global positioning system synchronizing clock is used to sample three phase voltage and current signals at both the ends of the transmission line over a moving window length of half cycle. The current signals are analysed with db1.1 wavelet to obtain detail coefficients of single decompositions. Fault indices are calculated based on the sum of local and remote end detail coefficients, and compared with threshold values to detect and classify the faults. The proposed algorithm is tested for different type of faults as well as for various incidence angles and fault impedances. The algorithm is proved to be efficient and effective in detecting and classifying the faults.

A vital attribute of electrical power network is the continuity of service with a high level of reliability. This motivated many researchers to investigate power systems in an effort to improve reliability by focusing on fault detection and classification. The penetration of renewable energy resources in distribution power systems would affect the traditional fault current level and characteristics. Consequently, traditional protection arrangements developed in distribution utilities are difficult in coordination; and the reclosing scheme would be affected. With rapid developments in distribution system automation, the protection coordination and reclosing scheme based on information exchange for the distribution power system can be realized flexibly. In this paper, a new protective relaying framework to detect, classify and localize faults in an electrical power distribution system with a high level of penetration of renewable energy resources is presented. This work will extract fault unique signatures by using polarization ellipse. During the healthy condition, polarization will have a circular shape with radius equal the rated voltage of the system. However, during the fault condition, polarization will have an ellipse shape and the fault signature will be defined according to the ellipse parameters: major axis, minor axis, ellipticity and orientation angle. The least squares criterion will be used to define ellipse parameters. This system will identify, classify and localize any fault instantaneously.

A decision support system for fault classification is presented. The fault classification scheme is developed to provide guidance in process improvement and fault-based testing. The research integrates results in fault classification, source code analysis, and fault-based testing research. Initial results indicate that existing change type and fault classification schemes are insufficient for this purpose. Development of sufficient schemes and their evaluation are discussed.

The High Impedance Faults (HIFs) are the faults which are difficult to detect by overcurrent protection relays. In this paper a general logic-based intelligent approach for detecting and classifying the HIF in distribution systems is presented. The proposed approach recognizes the distortion of the current waveforms caused by the arc usually associated with HIF. The Discrete Wavelet Transform (DWT) based pattern recognition is used for extracting the current signals. Single line to ground, double line to ground, and three lines to ground faults are classified using three simple logic functions. In order to detect the faulty feeder a general logic-based intelligent approach has been designed. The proposed approach is verified by applying several fault scenarios on IEEE-34 node test system. The proposed approach can be applied for any configuration, current rating or voltage rating. The results confirm that the proposed approach accurately detects and classifies the HIF in the distribution systems.

This paper proposes Transient monitoring function (TMF) based fault classification approach for transmission line protection. The classifier provides accurate results under various system conditions involving fault resistance, inception angle, location and load angle. The transient component during fault is measured by TMF and appropriate logics applied for fault classification. Simulation studies using MATLAB ® /SIMULINK ™ are carried out for a 400 kV, 50 Hz power system with variable system conditions. Results show that the proposed classifier has high classification accuracy. The method developed has been compared with a fault classification technique based on Discrete Wavelet Transform (DWT). The proposed technique can be implemented for real time protection schemes employing distance relaying.

Fault detection is very tedious task in transmission lines with a fixed series capacitor because of the nonlinear behavior of protection devices and seriesparallel resonance. This paper proposes a new method based on DWT for fault classification in this series capacitor is fixed at the middle of the line. The DWT is used here for extracting the unseen factors from the fault current signal and here harr is used as a mother wavelet. The average values of the wavelet coefficients of the lower frequency band for the currents of three phases and ground are computed and as there are higher frequency components in the faulted phases than that of the unfaulted phases, the fault classification can be done easily. The performance of the proposed scheme is checked for the all possible faults at various locations, different compensation levels and different power angles. This transient fault study is carried out using the PSCAD software and the wavelet transform and protection algorithm is implemented in a MATLAB environment.

After maintenance or repairing of the de-energized distribution feeder there is need of safely energizing of feeder for the utility's safety. The safely energizing can be done by determining the fault exists on the distribution system before energizing the system again. The fault detection in de-energized distribution feeder is more difficult than the energized distribution feeder since it requires the system level voltage production and execution to the downstream. Here we implemented an asymmetrical fault detection method to detect the fault before re-energizing the distribution feeder. A controllable signal is feed into de-energized distribution feeder using a thyristor based device to generate the electrical response. The strength of signal can be adjusted from low to high to detect low impedance fault at the beginning, since the maximum faults on distribution system are low impedance faults. A low strength signal may act as an alarm to the personnel or animal in contact with the live part of the system so that they can get away from the system to avoid getting sudden electric shock. Also the major faults on distribution systems are asymmetrical faults so it is necessary to identify and detect the asymmetrical faults before Re-energizing the feeder. The detection and classification of different asymmetrical faults is also explained in this paper. For the determination of the faults we are analyzing the voltage and current signals of the downstream feeder. The fault detection algorithm and control strategies of thyristors are also described for different faults and analyzed by using computer simulation in MATLAB.

AC drives are employed in process industries for varying applications resulting in a wide range of ratings. The entire process industry has seen a paradigm shift from manual to automated systems. The major factor contributing to this is the advanced power electronics technology enabling power electronic drives for smooth control of electric motors. Induction motors are most commonly used in industries. Faults in the power electronic circuits may occur periodically. These faults often go unnoticed as they rarely cause a complete shutdown and the fault levels may not be large enough to lead to a breakdown of the drive. An early detection of these faults is required to prevent their escalation into major faults. The diagnostic tool for detection of faults requires real time monitoring of the entire drive. In this work, detailed investigation of different faults that can occur in the power electronic circuit of an industrial drive is carried out. Analysis and impact of faults on the per...

dans ce papier on étudie les effets d’élimination des valeurs aberrantes et de leurs imputations sur la sélection des
indicateurs statistiques et la classification d’un défaut d’injection. Le défaut est simulé dans un moteur Diesel à combustion interne à six cylindres. Quatre méthodes de classification supervisée sont exploitées pour la discrimination des trois classes de défaut. Les résultats obtenus montrent que l’élimination des valeurs aberrantes et leurs imputations ont amélioré la classification du défaut pour un nombre des variables fini et surtout pour le classificateur k-plus proches voisins.

This paper presents a new fault classification strategy for transmission lines based on fuzzy logic. The ranking procedure uses the three phase current amplitudes and the current symmetrical components during the fault appearance phase. The suggested technique is able to classify all possible faults to know phase-ground, phase-phase, phase-phase-ground and three-phase with a high accuracy degree. The proposed method is evaluated under several fault conditions such as the inception angle, the fault resistance, the fault location and load angle. Thus, simulations under MATLAB environment were made on a 400KV transmission line. Simulation results confirm the effectiveness of our approach to be used like accuracy mean for the fault classification.

AC drives are employed in process industries for varying applications resulting in a wide range of ratings. The entire process industry has seen a paradigm shift from manual to automated systems. The major factor contributing to this is the advanced power electronics technology enabling power electronic drives for smooth control of electric motors. Induction motors are most commonly used in industries. Faults in the power electronic circuits may occur periodically. These faults often go unnoticed as they rarely cause a complete shutdown and the fault levels may not be large enough to lead to a breakdown of the drive. An early detection of these faults is required to prevent their escalation into major faults. The diagnostic tool for detection of faults requires real time monitoring of the entire drive. In this work, detailed investigation of different faults that can occur in the power electronic circuit of an industrial drive is carried out. Analysis and impact of faults on the performance of the induction motor is presented. A real time monitoring platform is proposed to detect and classify the fault accurately using machine learning. A diagnostic tool also is developed to display the severity and location of the fault to the operator to take corrective measures.

This paper describes the application of an artificial neural network (ANN) based algorithm with modular structure to the fault classification and location of a single-circuit high voltage transmission line. Different fault types containing single-phase to ground, two-phase, two-phase to ground and three-phase are considered. The variation of fault resistance is considered, too. The operation of proposed strategy is not dependent on fault inception angle (FIA). A new classification method is proposed for decreasing of training time and dimensions of ANN. Using the proposed method, high accuracy of fault classification is achieved. Fundamental component of pre-fault and post-fault positive sequence component of currents and voltages of three phases have been used as inputs to proposed ANN. The output of the ANN is the estimated fault location. A two machine power system model is simulated by PSCAD/EMTDC to obtain the mentioned voltages and currents values. The neural network toolbox of MATLAB is used for training and testing of ANN.

Fault detection, diagnosis, identification and location are crucial to improve the sensitivity and reliability of system protection. This maintains power systems continuous proper operation; however, it is challenging in large-scale multi-machine power systems. This paper introduces three novel Deep Learning (DL) classification and regression models based on Deep Recurrent Neural Networks (DRNN) for Fault Region Identification (FRI), Fault Type Classification (FTC), and Fault Location Prediction (FLP). These novel models explore full transient data from pre- and post-fault cycles to make reliable decisions; whereas current and voltage signals are measured through Phasor Measurement Units (PMUs) at different terminals and used as input features to the DRNN models. Sequential Deep Learning (SDL) is employed herein through Long Short-Term Memory (LSTM) to model spatiotemporal sequences of high-dimensional multivariate features to achieve accurate classification and prediction results. The proposed algorithms were tested in a Two-Area Four-Machine Power System. Training and testing data are collected during transmission lines faults of different types introduced at various locations in different regions. The presented algorithms achieved superior detection, classification and location performance with high accuracy and robustness compared to contemporary techniques.

This paper presents a fast and accurate fault detection, classification and direction discrimination algorithm of transmission lines using onedimensional convolutional neural networks (1D-CNNs) that have ingrained adaptive model to avoid the feature extraction difficulties and fault classification into one learning algorithm. A proposed algorithm is directly usable with raw data and this deletes the need of a discrete feature extraction method resulting in more effective protective system. The proposed approach based on the three-phase voltages and currents signals of one end at the relay location in the transmission line system are taken as input to the proposed 1D-CNN algorithm. A 132kV power transmission line is simulated by Matlab simulink to prepare the training and testing data for the proposed 1D-CNN algorithm. The testing accuracy of the proposed algorithm is compared with other two conventional methods which are neural network and fuzzy neural network. The results of test explain that the new proposed detection system is efficient and fast for classifying and direction discrimination of fault in transmission line with high accuracy as compared with other conventional methods under various conditions of faults.

The occurrence of faults in any operational power system network is inevitable, and many of the causative factors such as lightning, thunderstorm among others is usually beyond human control. Consequently, there is the need to set up models capable of prompt identification and classification of these faults for immediate action. This paper, explored the use of artificial neural network (ANN) technique to identify and classify various faults on the 11 kV distribution network of University of Lagos. The ANN is applied because it offers high speed, higher efficiency and requires less human intervention. Datasets of the case study obtained were sectioned proportionately for training, testing, and validation. The mathematical formulations for the method are presented with python used as the programming tools for the analysis. The results obtained from this study, for both the voltage and current under different scenarios of faults, are displayed in graphical forms and discussed. The resu...

Circuits which are designed to be dependable are evaluated after gate-level design. To demonstrate the influence of implementation technology on dependability parameters, we developed a simple method which transforms the evaluation problem into conceptual hardware and then to SAT instances. The method can accommodate any combinational fault model. The performed evaluation demonstrated that the dependability parameters of the implementations correlate to a significant degree.