Search

Abstract: This paper proposes an intelligent method based on artificial neural networks (ANNs) to detect bearing defects of induction motors. In this method, the vibration signal passes through removing non-bearing fault component (RNFC) filter, designed by neural networks, in order to remove its non-bearing fault components, and then enters the second neural network that uses pattern recognition techniques for fault classification. Four different categories include; healthy, inner race defect, outer race defect, and double holes in outer race are investigated. Compared to the regular fault detection methods that use frequency-domain features, the proposed method is based on analyzing time-domain features which needs less computational effort. Moreover, machine and bearing parameters, and the vibration signal spectrum distribution are not required in this method. It is shown that better results are achieved when the filtered component of the vibration signal is used for fault classification rather than common methods that use directly vibration signal. Experimental results on three-phase induction motor verify the ability of the proposed method in fault diagnosis despite low quality (noisy) of measured vibration signal. [Copyright &y& Elsevier]

Highlights: [•] This article reviews protection schemes for series compensated transmission lines. [•] In the second section, the impact of series compensation has been summarized for EHV transmission line protection. [•] The third section gives bibliographical survey and general backgrounds of research and development in the field of series compensated line protection. [•] A separate section compiles basic schemes for fault location techniques. [•] Recent implementation and experiences in field of series compensated transmission line protection are summarized. [ABSTRACT FROM AUTHOR]

Abstract: A health index, Mahalanobis distance (MD), is proposed to indicate the health condition of cooling fan and induction motor based on vibration signal. Anomaly detection and fault classification are accomplished by comparing MDs, which are calculated based on the feature data set extracted from the vibration signals under normal and abnormal conditions. Since MD is a non-negative and non-Gaussian distributed variable, Box–Cox transformation is used to convert the MDs into normal distributed variables, such that the properties of normal distribution can be employed to determine the ranges of MDs corresponding to different health conditions. Experimental data of cooling fan and induction motor are used to validate the proposed approach. The results show that the early stage failure of cooling fan caused by bearing generalized-roughness faults can be detected successfully, and the different unbalanced electrical faults of induction motor can be classified with a higher accuracy by Mahalanobis–Taguchi system. Such works could aid in the reliable operation of the machines, the reduction of the unexpected failures, and the improvement of the maintenance plan. [Copyright &y& Elsevier]

As support to fault location algorithms, this paper presents a new method for detecting and classifying faults in active distribution networks using the energy moving averages of the current signals measured at the feeder head. A proposal for updating the energy thresholds for fault detection is introduced, aiming to achieve higher sensitivity in fault detection, especially for scenarios with high penetration levels of distributed generation (DG). Since the power injected by DG can rapidly change, this proposal is essential for maintaining the fault detection method's reliability. Also, the fault classification is based on an analytical approach, making it possible to be easily applied to different operating scenarios of a distribution system. Thus, its potential for real-world implementation is higher when compared to classifiers based on supervised learning algorithms. Performance tests on the IEEE 34-node test feeder showed that this method is reliable for detecting and classifying different fault types, with diverse generation-load scenarios and noisy signals. • Detection thresholds are adaptive to increase detection sensitivity. • Fault classification is based on a simple analytical approach. • The method uses only the current measurements at the feeder head to diagnose faults. • The method is applicable for active distribution networks. [ABSTRACT FROM AUTHOR]

• Use of a novel phase selector algorithm for fault classification on half wavelength lines. • The new algorithm was coded in a RTDS hardware, emulating a relay. It use the derivate of Clarke's components for detect the type fault. • Identification of misoperations from relay commercial, when used to protection on half wavelength lines. • Robustness of proposed algorithm to identify faults with high impedance, conditions of transients caused by energization and tree phase auto recloser of half wavelength lines. • Use of COMTRADE files for the analysis and evaluation of the phase selector by the different types of faults. This study presents a new phase selector algorithm and fault type classification for very long transmission lines, known as the half-wavelength lines (HWL). For this work, the Clarke components variation rate method applied to current magnitudes was used. The method was implemented in a real-time digital simulation hardware-in-the-loop (HIL) test environment. We applied different fault types at each 5% line length, obtaining Clarke component current phasors. The proposed algorithm is stable for the native behavior of the half-wavelength line, including the resonance zones and their mitigation procedures. In addition, the algorithm is immune to the fault insertion angle, fault resistance, and line loading level. Finally, the algorithm could be applied in commercial microprocessor-based relays or could be used as a post-fault analysis tool. [ABSTRACT FROM AUTHOR]

Worm gearboxes (WG) are frequently used in many areas of the industry. WG is different from other gearbox types and due to their working principles they are under high risk of wear and fault. Therefore, detection of faults that may occur in WG and taking measures accordingly are especially important for systems and facilities that require uninterrupted operation. This paper introduces an intelligent feature selection and classification method for fault diagnosis of WGs under different working conditions. The novelty of the study lies in the selection of feature sources and different loading and speed conditions for condition monitoring studies of WGs experimentally. Fault detection and classification were performed based on vibration, sound and thermal images data which were acquired and processed from the healthy and the faulty WG. Apart from classical studies, time and frequency domain features and thermal images features were extracted and evaluated singularly, dual or triple forms with ANN (Artificial Neural Network) and SVM (Support Vector Machines) classifiers. Reasonable classification performances for fault detection were observed when the features of all three sources used (99.2% with ANN and 98.7% with SVM). ANN and SVM classification performances are almost equal for fault classification (98.9% with SVM and 98.6% with ANN). The findings of the study would be a possible means for online condition monitoring of industrial plants, conveyors, elevators, etc. [ABSTRACT FROM AUTHOR]

• In this paper combined DWT and Fuzzy inference system has been utilized for fault detection and classification in distribution system integrated with DGs. • The proposed scheme is suitable for detection of both HIF and LIF. • The proposed scheme based on DWT and Fuzzy inference system has been tested for IEEE 13 Bus system and IEEE 33 bus system. • It considers the effects of various DGs, switching events and impact of noise. • The scheme has been able to distinguish between different conditions such as transformer energization, capacitor bank switching, load switching, evolving faults. Most of the high impedance faults (HIF) remain un-detected by the conventional relays due to non-linear nature of the fault and low magnitude of current. In this work, a combination of discrete wavelet transforms (DWT) and fuzzy inference system (FIS) has been proposed for HIF detection and classification. Modified IEEE 13 node test feeder system has been to validate the proposed scheme. The proposed method uses current signals from one end that are pre-processed using discrete wavelet transform to obtain appropriate input features. The wavelet processed features are given to the FIS for fault detection and classification. Proposed method has been validated using both Mamdani and Sugeno type FIS. Different operating and fault conditions are tested to validate the proposed method such as varying DG parameters, noisy signals, HIFs, evolving faults, fault inception angle, fault resistance, fault location, and non-fault events (e.g. motor load switching, capacitor switching, DG switching, transformer energization, non-linear load switching). The accuracy in detecting and classifying the faults is 100% of all the tested fault cases. Results shows that the overall detection time required to detect the HIFs is minimum 4.25 cycles in most of the cases and maximum 8 cycles in few cases whereas for shunt faults is within 4.25 to 6 cycles only. Advantage of the proposed method is that it can detect adverse situation faults like evolving faults, in presence of noisy signals and remains intact against any switching events. The results of the proposed method are promising and the method is robust against various operating conditions. [ABSTRACT FROM AUTHOR]

Insulators are components of electrical power grid that have the function of mechanically supporting cables and isolating electrical potential. The proper functioning of the insulators is essential for the continuity in the supply of electrical energy. When an insulator has its properties damaged, disruptive discharges may shut down the system and impairs the network's reliability. For this reason, classifying adverse conditions is a critical task to keep the system running. In this paper, the echo state network is used for the classification of the insulators based on the ultrasound signal. Hypertuning is applied to automate the evaluation of the parameters and optimize the network to have a general application. The insulators are evaluated in the laboratory under controlled conditions from the application of 7.95 kV (phase-to-ground), under the same conditions that are found in the field. The assessment is made on perforated and contaminated insulators, which were removed from service due to defects. The echo state network achieves 87.36 % accuracy for the multiclassification and 99.99 % for the specific classification of drilling. For comparative analysis, the multilayer perceptron and support-vector machines are evaluated based on the fast fourier transform. The results show that echo state network is promising to classify the evaluated conditions, being more accurate than the multilayer perceptron and support-vector machines based on fast fourier transform. [ABSTRACT FROM AUTHOR]

• Sensitivity analysis of different transfer function components for different faults. • Correlation coefficient drawbacks investigation on fault detection. • Proposing a new index for the classification of different faults. • Investigation of fault classification accuracy of transfer function components. • Detection and classification of fault type, location and extent of faults. Frequency response analysis is one of the best methods to diagnose mechanical defects in the power transformer winding. In this paper, sensitivity analysis of four components of the transfer function (TF), i.e., amplitude, phase, real and imaginary components of TF is investigated for different defects. The classification of type, location, and extent of different defects is carried out using support vector machine with cubic polynomial kernel. The accuracy of different indices and four different components of TF are investigated. Moreover, a new index based on fitting performance is defined. The results show that despite widespread use and popularity of amplitude of TF, the phase, imaginary, and real components of TF, have more sensitivity to the defects respectively and are more accurate for classification. Also, compared with the results of some high usage indices, the proposed index has the best classification accuracy. [ABSTRACT FROM AUTHOR]

Abstract: This paper discusses how to use the warping information obtained after batch synchronization for process monitoring and fault classification. The warping information can be used for i) building unsupervised control charts or ii) fault classification when a rich faulty batches database is available. Data from realistic simulations of a fermentation process of the Saccharomyces cerevisiae cultivation are used to illustrate the proposal. [Copyright &y& Elsevier]

Abstract: Circuits which are designed to be dependable are evaluated after gate-level design. For circuits actually implemented in programmable devices, where different fault mechanisms dominate, it is unclear whether such evaluation is relevant. To explore the difference in 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. We evaluated circuits constructed from benchmarks using Modified Duplex Scheme (MDS). The performed evaluation demonstrated that the dependability parameters of the implementations correlate to a significant degree. The number of points vulnerable under the chosen fault models in circuits constructed using the MDS scheme depends much more on the circuit than on implementation type. [Copyright &y& Elsevier]

Abstract: Fault classification is very important for power system operation because it is the premise of fault analysis process. In this paper, an ANFIS (Adaptive Neural Fuzzy Inference System) based fault classification scheme in neutral non-effectively grounded distribution system is proposed. The transient currents are obtained by wavelet transform after faults occur. According to the statistic characteristic of transient currents in different fault types, the fault identifiers are defined. The fault identifiers can characterize the traits of fault type and show different disciplinarian in different fault types. They are inputted into three ANFISs to obtain the fault type. The proposed approach only needs the voltages and currents measured at substation, and can identify ten types of short-circuit fault accurately. The simulation model is established in PSCAD/EMTDC environment, and the performance of the proposed approach is studied. The results show that it has high accuracy. Besides, the adaptability of proposed approach to the neutral compensated grounding system, different network configurations and so on are verified through simulation. Through simulation, the proposed approach exhibits good performance. [Copyright &y& Elsevier]

Abstract: The paper presents a new approach for fault classification in transmission line using a systematic fuzzy rule based approach. Fault classification is one of the important requirements in distance relaying for identifying the accurate phases involved in the fault process. The proposed technique starts with preprocessing the fault current signal using advanced time–frequency transform such as S-transform to compute various statistical features. After the required features are extracted, the Decision Tree (DT), a knowledge representation method, is used for initial classification. From the DT classification boundaries, the fuzzy membership functions (MFs) and corresponding fuzzy rule-base is developed for final classification. Thus a systematic fuzzy rule base is developed for fault classification, reducing the redundancies and complexities involved compared to Heuristic fuzzy rule-based approach. Also a qualitative comparison is made between S-transform and Wavelet transform, where S-transform based DT-fuzzy provides highly improved results compared to the later during simulation as well as experimental tests. [Copyright &y& Elsevier]

Abstract: This paper presents a statistical algorithm for classification of faults on power transmission lines. The proposed algorithm is based upon the wavelet transform of three phase currents measured at the sending end of a line and the Classification and Regression Tree (CART) method, a commonly available statistical method. Wavelet transform of current signal provides hidden information of a fault situation as an input to CART algorithm, which is used to classify different types of faults. The proposed technique is simulated using MATLAB/SIMULINK software and it is tested upon the data created with the fault analysis of the 400kV sample transmission line considering wide variations in the operating conditions. The classification results are also compared with the results obtained using back propagation neural network. [Copyright &y& Elsevier]

Abstract: This paper proposes a new approach based on combined Wavelet Transform-Extreme Learning Machine (WT-ELM) technique for fault section identification (whether the fault is before or after the series capacitor as observed from the relay point), classification and location in a series compensated transmission line. This method uses the samples of fault currents for half cycle duration from the inception of fault. The features of fault currents are extracted by first level decomposition of the current samples using discrete wavelet transform (DWT) and the extracted features are applied as inputs to ELMs for fault section identification, classification and location. The feasibility of the proposed method has been tested on a 400kV, 300km series compensated transmission line for all the ten types of faults using MATLAB simulink. On testing 28,800 fault cases with varying fault resistance, fault inception angle, fault distance, load angle, percentage compensation level and source impedance, the performance of the proposed method has been found to be quite promising. The results also indicate that the proposed method is robust to wide variation in system and operating conditions. [Copyright &y& Elsevier]

Abstract: This paper presents a new fault classification technique using support vector machine (SVM) for a series compensated transmission line with a fixed series capacitor placed at the middle of the line. The proposed method uses the samples of one cycle duration of three line currents (IR , IY and IB ) and zero sequence current (I 0) as features of SVM to accomplish the fault classification task. For each of these four currents (IR , IY , IB and I 0), one corresponding SVM has been used. The samples of individual line currents and zero sequence current are fed to individual SVMs which, in turn, identify the involvement of the corresponding phase or ground in the fault. The feasibility of the proposed algorithm has been tested on a 300km, 400kV series compensated transmission line through detailed digital simulation studies using PSCAD/EMTDC for a large data set of 25,200 test cases comprising of all the 10 types of faults with varying fault resistances, different fault inception angles, different fault positions (before and after series capacitor), pre-fault power transfer levels, percentage compensation levels and source impedance values. The results indicate that the proposed technique is fast, accurate and robust for a wide variation in system and fault conditions. [Copyright &y& Elsevier]

Abstract: This paper proposes two approaches based on wavelet transform-support vector machine (WT-SVM) and wavelet transform-extreme learning machine (WT-ELM) for transmission line protection. These methods uses fault current samples for half cycle from the inception of fault. The features of the line currents are extracted by first level decomposition of the current samples using discrete wavelet transform (DWT) and extracted features are applied as inputs to SVM and ELM for faulted phase detection, fault classification, location and discrimination between fault and switching transient condition. The feasibility of the proposed methods have been tested on a 240-kV, 225-km transmission line for all the 10 types of fault using MATLAB Simulink. Upon testing on 9600 fault cases with varying fault resistance, fault inception angle, fault distance, pre-fault power level, and source impedances, the performance of the proposed methods are quite promising. The performance of the proposed methods is compared in terms of classification accuracy and fault location error. The results indicate that SVM based approach is accurate compared to ELM based approach for fault classification. For fault location, the maximum error is less with SVM than ELM and the mean error of SVM is slightly higher than ELM. [Copyright &y& Elsevier]

Abstract: This paper exploits the Wavelet Transform (WT) analysis along with Artificial Neural Networks (ANN) for the diagnosis of electrical machines winding faults. A novel application is presented exploring the problem of automatically identifying short circuits of windings, which often appear during machine manufacturing and operation. Such faults are usually resulting from electrodynamics forces generated during the flow of large short circuit currents, as well as forces occurring when the machines are transported. The early detection and classification of winding failures is of particular importance, as these kinds of defects can lead to winding damage due to overheating, imbalance, etc. Application results and investigations of windmill generator winding turn-to-turn faults between adjacent winding wires are presented. The ANN approach is proven effective in detecting and classifying faults based on WT features extracted from high frequency measurements of the admittance, current, or voltage responses. [Copyright &y& Elsevier]

Abstract: The ability to detect and classify the type of fault plays a great role in the protection of power system. This procedure is required to be precise with no time consumption. In this paper detection of fault type has been implemented using wavelet analysis together with wavelet entropy principle. The simulation of power system is carried out using PSCAD/EMTDC. Different types of faults were studied obtaining various current waveforms. These current waveforms were decomposed using wavelet analysis into different approximation and details. The wavelet entropies of such decompositions are analyzed reaching a successful methodology for fault classification. The suggested approach is tested using different fault types and proven successful identification for the type of fault. [Copyright &y& Elsevier]

Abstract: This paper presents a high speed, computationally efficient scheme for protection of transmission lines. The relay logic consists of three parts: directional protection, fault classification and fault location. Wavelet transform is used for extracting information from the fault transients and only the first level high frequency details of the voltages and currents are used. Proposed protection logic compares the directional signals from both terminals to discriminate between faults inside and outside the zone of interest. Fault classification is achieved using local terminal current information. An estimate of the location of the faults is obtained utilizing single faulted phase current information from both terminals. The logic is deterministic and can work reliably in the presence of fault resistance, load variation and CT saturation. The validity of the proposed logic was exhaustively tested by simulating various types of faults on a four bus meshed system modeled in EMTP/ATP. [Copyright &y& Elsevier]

Abstract: Malfunctions in machinery are often sources of reduced productivity and increased maintenance costs in various industrial applications. For this reason, machine condition monitoring is being pursued to recognise incipient faults. In this paper, the fault diagnostic problem is tackled within a neuro-fuzzy approach to pattern classification. Besides the primary purpose of a high rate of correct classification, the proposed neuro-fuzzy approach also aims at obtaining an easily interpretable classification model. The efficiency of the approach is verified with respect to a literature problem and then applied to a case of motor bearing fault classification. [Copyright &y& Elsevier]

Condition monitoring of machine is recognized as effective strategy for undertaking the maintenance in wide variety of industries. Planetary gearbox is a critical component in helicopters, wind turbines, hybrid vehicles and so forth. Planetary gearbox are complex in nature due to its size and meshing components. Condition monitoring and fault diagnosis of planetary gearbox is challenging due to complexity in dependable fault extraction from raw vibration signal. The mechanism of planetary gearbox is complex as there are several gears meshing at the same time. To find out the nature of fault and defective component in planetary gearbox is difficult. In this paper, the fault detection and fault type identification diagnostic approach using auto regression model (AR) and continuous wavelet transforms (CWT) by considering different frequency range is established. The experimental research conducted with different type of fault vibration signals in the gearbox have been diagnosed and identified the fault type using AR Modelling, Impulse and Shape Factor for validation purposes. The unique behaviors and fault characteristics of planetary gearboxes are identified and analyzed. The fault frequency identification and extraction of features from the non-stationary signals in different fault severity level of vibration data demonstrates the reliability of proposed method. The developed algorithm adds efficacy in detecting the nature of fault and defective component without performing a visual inspection. [ABSTRACT FROM AUTHOR]

• A new fault classification approach is presented for series-compensated line. • One-end current-based fault location method is proposed. • Different series-capacitor compensation configurations are analyzed. • The scheme is economic, reliable, fast, and generalized. This paper proposes a new efficient method for fault detection, faulty phase selection, and fault point identification on series capacitor-compensated transmission line. The method is based on sensing only the three phase current at the relay site. A reverse synchronous reference frame (RSRF) approach is proposed for fast fault detection and classification. Then, an analytical algorithm based on symmetrical components theory is presented for accurate estimation of fault location. Three possible arrangements of the series capacitor bank (SCB) on the line are analyzed. The SCB and the associated protective metal oxide surge arrestor (MOV) are modeled thoroughly to characterize its behavior during fault. In addition to its simplicity and practicality, the proposed scheme is equipped with decaying DC offset removal technique that allows fast extraction of the current phasors within one fundamental cycle. The proposed method works well for all ground and non-ground faults; it does not need pre-fault information; does not require any communication facilities; avoids high voltage measurement; and works smoothly for a wide range of fault resistance values. The efficacy of the proposed method is proved by a large number of simulated cases under a variety of operating conditions. [ABSTRACT FROM AUTHOR]

The Open Circuit (OC) faults occurring in switches of Multilevel Converters (MLC) may lead to undesirable operation of the converter. Therefore, fault detection and its localization in minimum time are necessary. This paper focuses on the fast fault detection algorithm based on the two samples technique and the fault localization algorithm using the Entropy of Wavelet Packets (EWP) as a feature. The EWP feature is used to classify and localize the OC faults in Insulated Gate Bipolar Transistors (IGBTs) of three-phase, three-level inverter using Support Vector Machine (SVM) based fault classification algorithm. The proposed technique can detect the fault in single IGBT and multiple IGBTs in a lesser time range of microseconds to 0.33 ms. It gives better performance and accuracy (99.70%) than previously proposed SVM algorithms, as the EWP-based feature extraction process used in this paper is simple and accurate with a less computational burden. [Display omitted] • An observer-based algorithm is proposed using two samples-based technique. • The Entropy of Wavelet Packets (EWP-SVM) technique is used for fault diagnosis. • The proposed algorithm can detect the faults in a single IGBT and multiple IGBTs. • The technique is faster and accurate than techniques available in the literature. • The comparison of detection time of different techniques is also discussed. [ABSTRACT FROM AUTHOR]

Recently, deep learning has become a popular tool for fault detection and diagnosis in chemical processes to learn complex nonlinear features. However, the features extracted from most traditional deep networks are only good representation for the raw input data, which may contain irrelevant information with the faults and are not beneficial for the fault classification task. Thus, a novel classification-driven neuron-grouped stacked autoencoder (CG-SAE) is proposed for hierarchical fault-related feature representation in this paper. During the pre-training phase of CG-SAE, the hidden neurons in each CG-AE are divided into several groups, the number of which is equal to that of the data categories. Each group is mainly associated to one type of fault. Moreover, the supervised information is introduced without additional weights by comparing the error between the actual label and the average activation of the corresponding group. In this way, the extracted deep features can contain category-related information and be clustered to different categories. In terms of the classification accuracy and training efficiency, CG-SAE performs better than some advanced supervised methods as verified by the Tennessee Eastman (TE) benchmark and an industrial hydrocracking process. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a real-time wavelet-Fuzzy combined approach for digital relaying. The algorithm for fault classification employs wavelet multi resolution analysis (MRA) to overcome the difficulties associated with conventional voltage and current based measurements due to effect of factors such as fault inception angle, fault impedance and fault distance. The proposed algorithm for fault location, different from conventional algorithms that are based on deterministic computations on a well-defined model to be protected, employs wavelet transform together with fuzzy logic. The wavelet transform captures the dynamic characteristics of the non-stationary transient fault signals using wavelet MRA coefficients. The fuzzy logic is employed to incorporate expert evaluation through fuzzy inference system (FIS) so as to extract important features from wavelet MRA coefficients for obtaining coherent conclusions regarding fault location. Computer simulations using MATLAB have been conducted for a 300Km 400KV line. Simulation results indicate that both the classification and localization algorithms are immune from effects of faults inception angle, impedance and distance. The most significant contribution of this paper is that the proposed location algorithm has a maximum error of 6.5% with a computational time of about one cycle. Thus both classification and location algorithms can be used as effective tools for real-time digital relaying purpose. [Copyright &y& Elsevier]

Abstract: This paper describes a new algorithm to identify the reflective waves for fault location in noisy environment. The new algorithm is based on the correlation of detail components at adjacent levels of stationary wavelet transform of current signal from one end of the cable. The algorithm is simple and straightforward. Simulation results based on a real power transmission system proved it can detect and locate the fault in very difficult situations. [Copyright &y& Elsevier]

Abstract: An approach for classification of transmission line faults is presented. The approach is based on fuzzy logic and requires the consideration of the samples of three phase currents at one end of transmission line. To illustrate the effectiveness of the proposed approach extensive simulation studies, using EMTP and MATLAB, have been carried out for different types of fault considering wide variations in the operating conditions. [Copyright &y& Elsevier]

Fault classification based upon vibration measurements is an essential building block of a conditional based health usage monitoring system. Multiple sensors are incorporated to assure the redundancy and to achieve the desired reliability and accuracy. The shortcoming of using multiple sensors is the need to deal with a high dimensional feature set, a computationally expensive task in classification. It is vital to reduce the feature dimension via an effective feature extraction and feature selection algorithm. A simple wavelet based feature selection scheme is proposed herein, uniquely built by local discriminant bases and genetic optimization. This scheme overcomes the disadvantages faced by the existing feature selection methods by producing a generic feature set, reducing the dimensionality of features, and requiring no prior information of the problem domain. The proposed feature selection scheme is based upon the strategy of "divide and conquer" that significantly reduce the computation time without compromising the classification performance. The simulation results show the proposed feature selection scheme provides at least 65% reduction of the total number of features at no cost of the classification accuracy. [ABSTRACT FROM AUTHOR]

Abstract: Present nomenclature of faults and flanking structures is ambiguous. This paper presents a system for description of flanking structures, based on geometric parameters and independent of kinematic frame. The description can be made using two levels of accuracy. A qualitative method is described using four geometric features: tilt, slip, lift and roll. This method is suggested for practical use in the field, since it does not involve measurements or complicated procedures. In parallel, a quantitative approach is also presented, based on analytical modelling of Bézier curves. This method requires measurement of geometric features and involves mathematical treatment, but allows comparison between different flanking structures. [Copyright &y& Elsevier]

Abstract: This paper presents a new method for identification and classification of faults based on wavelet multiresolution analysis (MRA). Daubechies eight (D-8) wavelet transforms of the three phase currents on a transmission line fed from both ends are used. The peak absolute value, the mean of the peak absolute values and summation of the 3rd level output of MRA detail signals of current in each phase extracted from the original signals are used as the criterion for the analysis. The effects of fault distance, fault inception angle and fault impedance are also examined. Extensive simulations are carried out to generate time domain input signal using EMTP (Microtran) on a 230kV, 200km long line fed from both ends and simulation results show that the proposed method is a simple, effective and robust method suitable for high impedance faults also. [Copyright &y& Elsevier]

Discrete wavelet transform is used to analyze faulty signals for a transmission system employing a thyristor controlled series capacitor at the midpoint of a line. Different frequency components of current signals are considered to select the phase(s) involved with a fault. To identify the fault section the new approach utilizes the difference in high frequency components of the current signals. For both phase selection and section identification tasks new energy and standard deviation-based indices are also calculated for the transmission system. [Copyright &y& Elsevier]

Accurate detection and classification of faults on transmission lines is vitally important. In this respect, many different types of faults occur, inter alia low impedance faults (LIF) and high impedance faults (HIF). The latter in particular pose difficulties for the commonly employed conventional overcurrent and distance relays, and if not detected, can cause damage to expensive equipment, threaten life and cause fire hazards. Although HIFs are far less common than LIFs, it is imperative that any protection device should be able to satisfactorily deal with both HIFs and LIFs.Because of the randomness and asymmetric characteristics of HIFs, the modelling of HIF is difficult and many papers relating to various HIF models have been published. In this paper, the model of HIFs in transmission lines is accomplished using the characteristics of a ZnO arrester, which is then implemented within the overall transmission system model based on the electromagnetic transients programme.This paper proposes an algorithm for fault detection and classification for both LIFs and HIFs using Adaptive Network-based Fuzzy Inference System (ANFIS). The inputs into ANFIS are current signals only based on Root-Mean-Square values of three-phase currents and zero sequence current.The performance of the proposed algorithm is tested on a typical 154 kV Korean transmission line system under various fault conditions. Test results show that the ANFIS can detect and classify faults including (LIFs and HIFs) accurately within half a cycle. [Copyright &y& Elsevier]

A large amount of data is generated when a fault triggers transformer protection. However, no precise information is obtained regarding where and what type of fault has occurred. Consequently, the operator must wait, sometimes for days, before he can switch on the transformer, which may not have been affected by the fault at all. As a result, the network suffers reduced security and transmission capacity. This paper presents two methods that enable the identification of faults affecting power transformer protection based on its signals. These methods should assist the operator in deciding whether the transformer should be left off or switched back into the system immediately after the event. The statistical data on faults and protection operation enable fault classification based on the Bayes'' theorem. The probability could be used as a measure of the event occurrence likelihood regarding a set of alternative events. A second method is further proposed, which uses the norm in the Banach space as a measure for the most probable event. Tests of both methods showed that they yield a fast and successful identification of power transformer faults. [Copyright &y& Elsevier]

A simple and fast method to identify the faulted conductors in a double circuit line with the help of a single circuit transient based fault type classifier is presented in this paper. In addition to a transient based single circuit fault type classifier, only currents locally measured through each conductor are required. Having known the fault type, the magnitudes of the rate of change of currents (ROCOC) through two circuits of faulted phases are compared by calculating three indices to find the conductors involved in the fault. The method can identify faulted conductors during both inter-circuit faults as well as intra-circuit faults. The method can be easily implemented on a simple hardware platform capable of performing filtering and simple mathematical functions. As only the current measurements in the frequency components between 0.5 kHz to 1 kHz are suggested, the need for high bandwidth current transducer is avoided. [ABSTRACT FROM AUTHOR]

The Auxiliary Power Unit (APU) is an integral part of an aircraft, providing electrical and pneumatic power to various on-board sub-systems. APU failure results in delay or cancellation of a flight, accompanied by the imposition of hefty fines from the regional authorities. Such inadvertent situations can be avoided by continuously monitoring the health of the system and reporting any incipient fault to the MRO (Maintenance Repair and Overhaul) organization. Generally, enablers for such health monitoring techniques are embedded during a product's design. However, a situation may arise where only the critical components are regularly monitored, and their status presented to the operator. In such cases, efforts can be made during service to incorporate additional health monitoring features using the already installed sensing mechanisms supplemented by maintenance data or by instrumenting the system with appropriate sensors. Due to the inherently critical nature of aircraft systems, it is necessary that instrumentation does not interfere with a system's performance and does not pose any safety concerns. One such method is to install non-intrusive vibroacoustic sensors such that the system integrity is maintained while maximizing system fault diagnostic knowledge. To start such an approach, an in-depth literature survey is necessary as this has not been previously reported in a consolidated manner. Therefore, this paper concentrates on auxiliary power units, their failure modes, maintenance strategies, fault diagnostic methodologies, and their acoustic signature. The recent trend in APU design and requirements, and the need for innovative fault diagnostics techniques and acoustic measurements for future aircraft, have also been summarized. Finally, the paper will highlight the shortcomings found during the survey, the challenges, and prospects, of utilizing sound as a source of diagnostics for aircraft auxiliary power units. [ABSTRACT FROM AUTHOR]

• A fault detection scheme is proposed for MTDC by using local transient information. • Classify internal and external fault by tracking pulse count in a specific window. • The concept of protection unit is employed for rapid isolation of faulty part. • Results provide evidence for protection scheme's key role in handling MTDC faults. DC faults render hindrance in the flourishment of multi-terminal flexible high voltage DC (MTDC). The fault current rises rapidly, making a sharp peak, however, under a specific fault instance, isolation of the whole network is an impractical solution. For effective reliability of the whole network, rapid and accurate fault detection and selection of faulty pole is mandatory. A fault detection scheme is proposed in this paper to draw transient current harmonics from initial fault current by utilizing Discrete Fourier transform (DFT). Current harmonics employed the fault detection promptly at the converter stations without communication among the MTDC networks. Additionally, the proposed scheme can discriminate internal from external fault by tracking the number of pulse count in a specific interval of the harmonics of the voltage. In this way, the reliability of the protection scheme enhances and escape from the mal-operation of the circuit breaker. For four terminal MTDC transmission network, the simulations are carried out in PSCAD to authenticate the implementation of the proposed scheme and protection units (PU) are utilized for the isolation of faulty part with the combination of hybrid circuit breaker (HCB). A keen analysis of test results authenticated the ability of the proposed scheme to rapidly detect the faults with high precision, along with efficient classification of the nature of faults. Furthermore, consequential results provide a strong evidence for its key role in handling a multitude of MTDC faults. [ABSTRACT FROM AUTHOR]

Many automated sound-based fault diagnosis or classification methods have been presented in the literature. A novel automatic fault diagnosis method is presented by using sounds for the cooling system of the data center. A novel feature generator and an iterative feature selector are used together to present an automated data center cooling system (DCCS) fault diagnosing method. A new feature generator is proposed inspired by knitting hence, it is called a local knit pattern (LKP). A multiple pooling based decomposition method is presented as a preprocessor. The LKP generates features from each signal. Iterative neighborhood component analysis (INCA) feature selector selects the most discriminative. Twelve classifiers are calculated in the classification phase. The selected classifiers were achieved greater than 90.0% classification accuracies, and the best-resulted classifier is Quadratic SVM. It reached 96.40% classification accuracy. Results show that new generation automated sound fault diagnosis applications can also be developed as novel sound-based fault detection applications. [ABSTRACT FROM AUTHOR]

The rapid development of photovoltaic (PV) technology and the growing number and size of PV power plants require increasingly efficient and intelligent health monitoring strategies to ensure reliable operation and high energy availability. Among the various techniques, Artificial Neural Network (ANN) has exhibited the functional capacity to perform the identification and classification of PV faults. In the present review, a systematic study on the application of ANN and hybridized ANN models for PV fault detection and diagnosis (FDD) is conducted. For each application, the targeted PV faults, the detectable faults, the type and amount of data used, the model configuration and the FDD performance are extracted, and analyzed. The main trends, challenges and prospects for the application of ANN for PV FDD are extracted and presented. • Applications of ANN techniques and hybrid application for PV FDD are summarized. • Detectable PV faults with ANN technique and diagnosis performance are investigated. • Reported public PV database of 1D data and 2D images are summarized. • Common trends for the selection of model for different PV faults are identified. • Challenges and prospects for PV FDD using ANN techniques are presented. [ABSTRACT FROM AUTHOR]

• Proposed a deep learning based CNN model for fault classification in Power System distribution network integrated with distributed generators (DGs). • In this proposed work, fault classification is done without any pre-processing or feature engineering steps. • All types of fault in 3-phase power system network including no-fault is classified using proposed model with superior performance. • Proposed model is compared with conventional machine learning methods for fault classification in terms of both performance and computational cost. • The performance of proposed model is also tested on a mixed transmission line and distribution network with PV as DG. Fault detection is the critical stage of the relaying system and their successful completion in minimum time is expected for fault clearance. With the increasing usage of distributed generators (DGs) in a distribution network, the conventional relaying methods are becoming inappropriate due to changing fault current levels. This paper presents a deep learning algorithm i.e. Convolutional Neural Network (CNN) customized for fault classification in the distributed networks integrated with DGs. This is first time that CNN has been used for fault detection using raw and sampled-data of three-phase voltage and current signals of various fault classes and no-fault class. The 10-fold cross-validation is used to demonstrate the performance of the proposed model in terms of different metrics such as accuracy, sensitivity, specificity, precision, and F1 score. The proposed model has attended an average 10-fold cross-validation accuracy of 99.52% for all the tested fault cases. This featureless proposed method has been compared with conventional approaches from literature and has shown better performance in terms of accuracy and computation burden. Further, a similar fault study is conducted on a mixed transmission line and distribution network with PV as DG using the proposed method and found performance accuracy of 99.92% and 99.97%, respectively. [ABSTRACT FROM AUTHOR]

• This article presents a relaying algorithm that works equally well for an EHV transmission line and when the line is subjected to fixed series compensation. • This is also without any functional modification in methodology or adaption in the proposed algorithm. • The algorithm proved to work with various levels of fixed series compensation with same level of accuracy. • This eliminates need of relay setting changes required after introduction of series compensation to any existing transmission line. Moreover, it also eliminate requirement of re-setting of relays in case of bypass operation of the series compensator. • The algorithm has been developed with help of wavelet transform and chebyshev expanded neural network. • The fault detection algorithm converges within half-cycle after fault inception. Therefore, it is proved to be fast also. This article presents a new and fast approach for detection and classification of the fault on a transmission line. The proposed method can effectively detect and classify a fault on a regular uncompensated transmission line. Moreover, the same can detect and classify faults when these lines are subjected to fixed series compensation, with the same accuracy and without any functional customization of the algorithm. Therefore, this method gets rid of the new setting requirement for the inclusion of series compensation. Vice versa can provide protection to a series compensated line during maintenance as well as in the eventuality of bypass of the compensator. This makes the developed algorithm versatile. The proposed algorithm normally converges for fault detection within half cycle from the fault inception, and requires no data after generating fault detection signal for fault classification; which enables the application of faster circuit breaking devices. The two-stage approach uses Wavelet Transform (WT) with Chebyshev Neural Network (ChNN) and uses only measured three-phase current signals at relaying end. The accuracy, speed, and effectiveness of the scheme have been verified with a fault data generation system developed on PSCAD/EMTP with different system parameter variations like fault resistance, load angle, fault inception angle, and types of faults. The results obtained show that the proposed scheme is accurate and fast as well. [ABSTRACT FROM AUTHOR]

• Novel fault classification algorithm (FCA) for GUPFC-compensated transmission lines. • FCA is based on the loci of active and reactive powers calculated using PMU signals. • Presenting faulty area and faulty circuit detection algorithms using new indices. • The proposed method is robust and independent of the operating modes of the GUPFC. • Easily applicable in regular fault locators available in the protection industry. The paper presents a fault area detection and classification algorithm in the phasor domain for double-circuit lines compensated by a generalized unified power flow controller (GUPFC). In the first step, by defining and using a voltage index, the algorithm determines the side of the GUPFC in which the fault has occurred. In the second step, by defining and employing a current index, the algorithm will be able to identify the circuit of the line on which the fault has happened. Finally, the fault is classified. In this step, the algorithm detects the faulty phase by analyzing the loci of three-phase active and reactive powers at the line terminal. The algorithm uses the current and voltage phasors of the line terminals measured by the phasor measurement units (PMUs) in one cycle before and during the fault. The GUPFC and the test system have been modeled in MATLAB/Simulink. The presented algorithm is tested and evaluated under different conditions including different fault types and fault resistances for all normal series and shunt fault types. The results obtained from simulations verify the accurate performance of the algorithm for various fault conditions. [ABSTRACT FROM AUTHOR]

• A dimensionality reduction algorithm based on local-global balanced orthogonal discriminant projection is proposed. • A novel fault diagnosis method of rotor based on LGBODP is presented. • The vibration signals of double-span rotor systems are used to verify the effectiveness of the LGBODP algorithm. • The feasibility of the rotor fault diagnosis method based on LGBODP dimensionality reduction is verified. The rotor is the most important part of the whole rotating machinery. Whether the rotor is normal directly determines the normal operation of the whole rotating machinery. Aiming at the problem of classification difficulty caused by multi-class and high-dimensional complex characteristics of rotor fault data, a fault data set reduction method based on Local-Global Balanced Orthogonal Discriminant Projection (LGBODP) is proposed. The algorithm comprehensively considers the intra-class local information, intra-class non-local information, inter-class local information and inter-class non-local information of the data, so as to avoid the loss of structure information in the dimension reduction process. By maximizing the inter-class distance and minimizing the intra-class distance, the intrinsic manifold structure information of the fault feature data set is effectively extracted while maintaining the global feature information. First of all, the mixed feature of the rotor vibration signal was extracted from multiple angles in time domain, frequency domain and time-frequency domain, and the high-dimensional feature set was constructed. The low-dimensional fault sensitive feature subsets are extracted by the proposed LGBODP algorithm. Then, the K-nearest neighbor (KNN) method is used as a fault feature classifier to recognize different fault types of rotors. The effectiveness of the proposed algorithm is verified by the vibration signal sets of two different types of double-span rotor systems. Application examples show that this method can be used to comprehensively extract the global and local discriminant information of vibration signals of rotors and effectively diagnosis the fault of rotors. [ABSTRACT FROM AUTHOR]

• In this study, motor faults were detected with sound signals. • Novel sound datasets were collected and comprehensively results were calculated. • A high accurate acoustical fault classification method was presented. • The proposed method achieved higher than 99% accuracies for the collected datasets. • This situation shown effectiveness of the proposed BP and NCA based method. Induction motors, which are widely used in industrial applications, are indispensable tools of the industry. Induction motors work in almost every part of the industry, such as production, packaging, and service. In this study, an acoustic-based method is proposed for the detection of the rotor and bearing faults of three-phase induction motors. In the first stage, two fault sound datasets were collected and these datasets are called near and far. For extracting features from these sounds, a multilevel feature generation method is presented and this method uses Discrete Wavelet Transform (DWT) and Local Binary Pattern (LBP) methods together. Neighborhood Component Analysis (NCA) method was used to select the most informative features. Selected features are utilized as the input of SVM (Support Vector Machine) and KNN (K Nearest Neighborhood) classification algorithms. 99.8% classification success was achieved as a result of the SVM algorithm and the KNN algorithm reached 99.9% classification accuracy. [ABSTRACT FROM AUTHOR]

• A systematic review for Smart Grid systems faults. • A classification framework on relevant grid requirements. • Future developments related to fault detection and classification. • Advance Metering Infrastructure under the perspective of power faults. Smart Grid (SG) is a multidisciplinary concept related to the power system update and improvement. SG implies real-time information with specific communication requirements. System reliability relies on the best capabilities for monitoring and controlling the grid. Among other aspects, SG applications involve three main challenges, sufficient real-time capable measurement units, managing large data sets, and two-way low-latency communications. Considering fault detection and classification a key factor to SG reliability, this work provides a systematic review of SG faults from the most significant research databases and state-of-the-art research papers aiming at creating a comprehensive classification framework on the relevant requirements. This paper includes in detail the classification of different fault scenarios in a comprehensive framework that involves system-level of application, e.g. , transmission, distribution, commercial, DG, and EV. To this end, We analyze and indicate relevant topics for future developments related to the monitoring and fault detection and classification in SG systems. [ABSTRACT FROM AUTHOR]

Gas pipelines are prone to faults due to aging, corrosion, and external factors. Undetected faults can result in injuries, damage to properties, and environmental contamination. Several techniques have been developed to help detect faults, though each technique having pros and cons. This review is set out to identify research gaps related to fault detection and diagnostics under transient conditions and associated inputs for a robust design. A closer look at the available literature reveals that there is indeed more research required in terms of addressing pipeline-compressor-valve system, multiple fault scenario, uncertainty quantification, and multiphase condition. Image 1 • Improved classification of fault detection and diagnostics approaches specific to gas pipelines is proposed. • Recently applied computational techniques for fault detection and diagnostics are summarized and compared. • Potential directions for future fault detection and diagnostics studies are suggested. • Commonly used Equations of State for fault detection studies are compiled and critically analysed. • Challenges related to transient model development for gas mixture pipeline are outlined. [ABSTRACT FROM AUTHOR]

• Enhancing the resilience of a compensated parallel line using a differential scheme. • Estimating the spectral energy of the currents by applying a tool known as FDOST. • Evaluating the scheme against various faults and dynamic power system conditions. This paper presents a resilience-oriented protection scheme for TCSC-compensated Line. A cross-differential protection scheme is proposed to enhance the resilience of a parallel transmission line (PTL) in the presence of a thyristor controlled series capacitor (TCSC). The faulty phase(s) is (are) identified by estimating the spectral energy of the three-phase currents and computed by applying an efficient powerful signal processing tool known as fast discrete orthonormal S-transform (FDOST). The proposed scheme is widely evaluated against various faults and dynamic power system conditions. The obtained results indicate the proposed resilience-oriented protection scheme is adaptable to different power system scenarios. The scheme precisely classifies the fault with effective discrimination between internal and external faults on a transmission line and a response time of a maximum one cycle from the fault inception. [ABSTRACT FROM AUTHOR]

Deep transfer network (DTN) has been widely used for classification tasks, which introduces maximum mean discrepancy (MMD) based loss function to extract similar latent features and reduce the discrepancy of distributions across the source and target data. However, it is a little challenging to apply deep transfer learning for fault classification tasks in industrial chemical processes, since process variables have physicochemical properties and occupy different impacts in reflecting the process status. Hence, features extracted from these process variables also have different contributions for domain adaptation in DTN. In this paper, a linear discriminant analysis (LDA)–based DTN is proposed for fault classification ofchemical processes, in which a weighted MMD is designed for domain adaptation. First, the LDA algorithm is introduced to determine how much influence each variable can distinguish samples from source and target domains. Then, a corresponding weight is assigned to each feature variable to design the weighted MMD for network transferring. A Tennessee Eastman (TE) process and a real hydrocracking process are used to validate the fault classification performance of the LDA-based DTN. The results indicate LDA-based DTN has better generalization performance and classification accuracy than traditional DTN. [ABSTRACT FROM AUTHOR]

• Identification of the fault section and fault phase selection are considered the main tasks. • The suggested technique uses the wavelet packet transform. • A fast mother wavelet is used with a three-coefficient high pass filter to analyze signals. • Several fault cases are simulated and analyzed in the ATP/EMTP environment. • The proposed scheme shows high speed and accuracy of fault detection. Identification of the fault section and fault phase selection are considered the main tasks of a multi-terminal transmission line protection scheme. The current study classifies the methods applied to multi-terminal transmission lines. Moreover, investigated solutions for the drawbacks that appeared with the previous methods are suggested. Based on wavelet packet transform, a scheme for a multi-terminal transmission line is presented in this article. The suggested technique uses the wavelet packet transform (WPT) to get the approximate and detail coefficients of the differential current and model voltage for all buses in a system, detects and classifies the faults (FDC) within a half-cycle window, and identifies the faulted section (FSI). A fast mother wavelet is used with a three-coefficient high pass filter to analyze signals of the model voltage and differential. In this regard, two frequency levels were chosen, in which the first level of the differential current signal was chosen to detect and classify a fault, while the first level of the model voltage signal was chosen to identify the faulted section. Several fault cases are simulated and analyzed in the ATP/EMTP environment for an N-terminal system followed by successful testing on three- and five-terminal systems to evaluate the performance of the proposed scheme. The simulation results obtained show that the proposed scheme is efficient and shows high speed and accuracy of fault detection compared to other methods in the literature. [ABSTRACT FROM AUTHOR]

This work deals with robust dynamic probabilistic modeling and fault classification for process data. In dynamic processes, observed variables can be numerous in amount and correlated with each other in both variable-wise and time-wise. While multivariate statistical analysis methods such as principle component analysis (PCA) are widely used to handle variable-wise correlations and also for dimension reduction purpose, the time-wise correlation among process data is typically addressed by constructing dynamical models, e.g. time-series data model, state space model, etc. In this paper, the robust probabilistic principle component analysis (RPPCA) model is introduced for feature extraction from contaminated process data, suffered from outliers, disturbances, heave noises, etc. A dynamic Bayesian network (DBN) is then constructed, with incorporation of a mixture of Gaussian components for approximation of the non-Gaussian characteristics of latent variables. Based on the developed robust dynamic Bayesian network model, a fault classification scheme is proposed. To validate the effectiveness and feasibility of the new method, two well-known benchmark case studies are carried out. Simulation results show that robust dynamic method performs better in outlier contaminated situations, where the performance has been improved by 10%–20% in most cases. [ABSTRACT FROM AUTHOR]