A wavelet-based fault localization in transmission network

A combined image processing and Nearest Neighbor Algorithm tool for classification of incipient faults in induction motor drives

Current signature analysis of induction motor becomes very much popular for its Condition monitoring purpose. Most of these studies in recent years are focused on hardware. Though, to build an experimental set-up for fault emulating machines is not an easy task. It involves too much cost and risk of damage. Moreover, it is not possible to create different types of faults in the same machine. In this paper an accurate but simple model of 3-phase Induction motor is being proposed which describes the machine at low frequency as well as at high frequency for different types of fault situations. The model, based on DM, CM characteristics of the machine, is well suited for power frequency (50 Hz) and high frequency applications like adjustable speed drives (ASDs). A mechanical model of a three-phase induction machine is incorporated to this electrical model to make a universal model of dynamic squirrel cage induction motor for overall simulation. The proposed model has the feature to incorporate different types of electrical fault like, stator inter-turn fault, phase-to-phase and phase-to ground insulation fault etc. The premature conditions of the above faults can also be emulated.

This paper describes the application of an artificial neural network (ANN) for location of transmission line faults. Three phase post fault samples of currents and voltages taken at one end of transmission line are used as inputs. Simulation studies have been carried out extensively on two power system models : one in which transmission line is fed from one end and the other in which transmission line is fed from both ends.The models are subjected to different types of faults at different operating conditions for variations in fault location, fault inception angle and fault point resistance. The results presented confirm the feasibility of the proposed scheme.

Occurrence of unwanted resistance at terminal of IGBTs is a type of Incipient faults which occurs in 3-phase voltage source Inverter. This type of faults does not trigger the protective circuit and in due course of time leads to severe faults. The present work had made an attempt to identify this type of faults related to two IGBTs in the VSI scheme. Rigorous simulation is done with different cases of faults in a PSIM software platform. The current profiles obtained from the simulation are processed by data processing tools to obtain Mean Current vector (MCV). A two phase reference frame shows the distribution of MCV for different types of faults. The distribution is found to follow a particular pattern. This has encouraged the authors to use SVM classifier for analyzing the distributed pattern and classify different types of faults.

This paper presents the development of a wavelet-based algorithm, for distinguishing between magnetizing inrush and internal faults of the power transformer. The proposed technique consists of a preprocessing unit based on Continuous wavelet transform (CWT) in combination with an artificial neural network (ANN) for detecting and classifying faults. The CWT acts as an extractor of distinctive features in the transient current signals at the relay location. This information is then fed into an ANN for classifying fault, normal and magnetizing inrush conditions. The results presented clearly showed that the proposed technique is very fast, computationally efficient and intelligent enough to accurately discriminate between magnetizing inrush, normal and faults in the transformer.

A general framework and a method for model based diagnosis are suggested. In the framework, faults and modeling of faults are formally described. Then the method is used to construct a diagnosis system based on a structure of hypothesis tests. Using these principles, it is possible to diagnose a large variety of different types of faults. The framework and the method are applied to the design of a diagnosis system for an automotive engine. This application clearly shows the strength of these principles because several different types of sensor faults and leakage need to be diagnosed. The resulting diagnosis system is demonstrated using experiments on a real automotive engine.

Cabled seafloor observation networks (CSONs) have evolved over the last decade to provide abundant electric energy and data transmission to enable marine science. To ensure reliable operation of the CSONs, the technology for fault location with high speed and accuracy is essential. However, the existing methods for CSON fault location fail to deeply mine the relation between fault feature and fault distance, hence the location performance is relatively unsatisfactory. In this paper, we prove that there is relation between fault distance and transient current signal created by fault. Based on this, we propose a fault location method based on Fault feature and Fault distance Relation Mining, named FaRM. Firstly, we simulate CSON and acquire transient current signal by PSCAD. Then we employ variational mode decomposition (VMD) to mine the fault feature in the transient current signal. Finally, FaRM is proposed to exploit the mined fault feature to predict the fault distance. Experimental results demonstrate that the fault location performance of FaRM is better than the existing CSON fault location methods.

Distance relays used for protection of transmission lines have problems of under-reach, over-reach and maloperation due to high impedance faults. Further the problem is compounded when the distance relays are used for protection of double circuit transmission lines due to effect of zero sequence mutual coupling. Different types of faults on a protected transmission line should be located correctly. This paper presents a single neural network for fault distance location for all the ten types of faults (3 LG, 3 LLG, 3 LL, 1 LLL) in both the circuits of a double circuit transmission line fed from sources at both the end. This technique uses only one end data and accurate fault distance location is achieved after one cycle from the inception of fault. The proposed Artificial Neural Network (ANN) based Fault Distance Locator uses fundamental components of three phase current signals of both the circuits & three phase voltage signals to learn the hidden relationship in the input patterns. An improved performance is obtained once the neural network is trained suitably, thus performing correctly when faced with different system parameters and conditions i.e. varying fault type, fault location, fault resistance, fault inception angle, presence of mutual coupling and remote source infeed.

Precise knowledge of faults is very exigent to reduce the outage duration as most of the customer minute losses in distribution grids occur due to longer period of interruptions caused by faults. This study proposes a fault location technique combining advanced signal processing and machine learning tools for distribution grids. The proposed technique decomposes three‐phase currents measured from sending end employing wavelet transform (WT) and collects useful features to fetch them as inputs of extreme learning machine (ELM). Satisfactory values of the selected statistical performance measures validate the efficacy of proposed fault location technique. Besides, the efficacy of support vector regression (SVR) and artificial neural network (ANN) are also tested employing the WT extracted features. The presented results show the superiority of ELM‐WT technique over SVR‐WT and ANN‐WT techniques in terms of the selected performance measures and training times. Additionally, the proposed technique is independent of fault resistance, inception angle, the presence of measurement noise, thermal expansion/contraction of the distribution line and pre‐fault loading condition. Furthermore, the hybrid method detects and classifies different types of faults before locating them with different machine learning tools.

Fault detection systems are typically applied in the railway industry to examine the structural health status of the wheel/rail system. We herein propose a time-domain kurtosis beamforming technique using an array of microphones for the fault identification and localisation of the wheel/rail system under an environment with high background noise. As an acoustics-based noncontact diagnosis method, this technique overcomes the challenge of the contact between the sensors and examined structures, and it is more applicable for impulsive signals of broadband nature, such as impact noise generated from faults on the wheel surface. Moreover, the application of kurtosis enables the identification and localisation at low signal-to-noise ratio. Under such circumstance, the impulsive signals generated by faults were totally merged in rolling noise and background noise. Meanwhile, different types of faults on the wheels could be identified and localised by observing the kurtosis value on the beamforming sound map. The effectiveness of the proposed method to diagnose the type of wheel fault with low signal-to-noise ratio and moving source has been validated experimentally. This method may provide a useful tool for the routine maintenance of trains.

A new approach for fault diagnosis and location on electrical power multi-load distribution network is presented. Normally, the bus voltage in the distribution networks is almost constant even in presence of a line fault. Therefore, it is possible to identify and locate different types of faults only through the analysis of current lines. Under this consideration it is possible to convert this problem into a current pattern recognition analysis. Consequently, using a Clarke-Concordia transformation it is possible to obtain a different pattern for each fault and location. To identify those patterns an eigenvalue approach is used. A polynomial function is also used to establish the nonlinear relationship existing between fault location and line current patterns. Results are presented which show the effectiveness of the proposed algorithm for a correct fault identification and location on an electrical power multi-load distribution network.

Internal winding faults are among the most common causes of transformer failure. Once a fault occurs, a fast and efficient method for its detection and location is required to repair and reconnect the device, thus avoiding further delays in the network operation. This paper introduces a simple method for the location of internal winding faults. This method is based on time-domain terminal measurements of wave propagation along the winding. By means of low-cost laboratory components (a lowvoltage DC source and an oscilloscope), different types of faults in layer-type windings can be detected and located with high accuracy. A frequency-domain distributed-parameter winding model is used to predict the transient response of the winding subjected to different types of faults. FEM simulations are used to compute the model parameters. A test case is presented to demonstrate the efficacy of the fault location method.

Fault location and distance protection in transmission lines are essential smart grid technologies ensuring reliability of the power system and achieve the continuity of service. The objective of this chapter is to presents an accurate algorithm for estimating fault location in Extra High Voltage (EHV) transmission lines using Artificial Neural Networks (ANNs) for high speed protection. The development of this algorithm is based on disturbed transmission line models. The proposed fault protection (fault detection/classification and location) uses only the three phase currents signals at the one end of the line. The proposed technique uses five ANNs networks and consists of two steps, including fault detection/classification and fault location. For fault detection/classification, one ANN network is used in order to identify the fault type; the fault detection/classification procedure uses the fundamental components of pre-fault and post-fault sequence samples of three phase currents and zero sequence current. For fault location, four ANNs networks are used in order to estimate the exact fault location in transmission line. Magnitudes of pre-fault and post-fault of three phase currents are used. The ANNs are trained with data under a wide variety of fault conditions and used for the fault classification and fault location on the transmission line. The proposed fault detection/classification and location approaches are tested under different fault conditions such as different fault locations, different fault resistances and different fault inception angles via digital simulation using MATLAB software in order to verify the performances of the proposed methods. The ANN-based fault classifier and locator gives high accuracy for all tests under different fault conditions. The simulations results show that the proposed scheme based on ANNs can be used for on-line fault protection in transmission line.

This paper presents a new approach to fault location on distribution power lines. This approach uses an artificial neural network based learning algorithm and Clarke-Concordia transformation. The /spl alpha/,/spl beta/,0 components of line currents resulting from the Clarke-Concordia transformation are used to detect all types of fault. The neural network is trained to map the nonlinear relationship existing in fault location equations. The proposed approach is able to identify and locate all different types of faults (single line to ground, double line to ground, line-to-line and three-phase short-circuit). This approach is subdivided into several main steps: Data acquisition, corresponding on three-phase current signals; Mathematical treatment by the Clarke-Concordia transformation; Fault identification, obtained by the analysis of fault and pre-fault data; Fault location artificial neural network based learning algorithm. The fault position is presented as the output of the neural network on which, as the input, it was considered the eigenvalue of matrix representing transformed line current. Results are presented which shows the effectiveness of the proposed algorithm for a correct fault location on distribution power system networks.

The automatic vibration monitoring methods of gears and gearboxes due to their extensive applications in industry are improving. Hence, their vibration signal and its derived features, has been an interesting topic for researchers in this field. On the other hand, optimizing the number of vibration signal features used in the detection and diagnosis process is crucial for increasing the fault detection speed of automatic condition monitoring systems. In this paper, a system based on multiple layer perceptron artificial neural networks (MLP ANNs) is designed to diagnose different types of fault in a gearbox. Using a feature selection method, the system is optimized through eliminating unimportant features of vibration signals. This method is based on a simple and fast sensitivity evaluation process, which results in a considerable estimation, despite its simplicity. Consequently, the system’s speed increases, while the classification error decreases or remains constant in some other cases. An experimental test rig data set is used to verify the effectiveness and accuracy of the mentioned method. Four different types of data which are generated through the test rig setup are: no fault condition, 5% fault (5% eroded tooth) gear, 20% eroded tooth gear and the broken tooth gear. The results verify that eliminating some input features of gear vibration signal, using this method, will increase the accuracy and detection speed of gear fault diagnosis methods. The improved systems with fewer input features and higher precision, facilitates the development of online automatic condition monitoring systems.