Transmission line fault detection and classification

Faults in transmission lines cause instability of power system and result in degrading end users sophisticated equipment. Therefore, in case of fault and for the quick restoration of problematic phases, reliable and accurate fault detection and classification techniques are required to categorize the faults in a minimum time. In this work, 500 kV transmission line (Jamshoro‐New Karachi), Sindh, Pakistan has been modeled in MATLAB. The discrete wavelet transform (DWT) has been used to extract features from the transient current signal for different faults in 500 kV transmission line under various parameters such as fault location, fault inception angle, ground resistance and fault resistance and time series data has been obtained for fault classification. Moreover, the temporal convolutional neural network (TCN) is used for fault classification in 500 kV transmission network due to its robust framework. From simulation results, it is found that faults in 500 kV transmission line are classified with 99.9% accuracy. Furthermore, the simulation results of the TCN model compared to bidirectional long short‐term memory (BiLSTM) and Gated Recurrent Unit (GRU) and it has been found that TCN model is capable of classifying faults in 500 kV transmission line with high accuracy due to its ability to handle long receptive field size, less memory requirement and parallel processing due to dilated causal convolutions. Through this work, the meantime to repair of 500 kV transmission line can be reduced.

In power system engineering, Transmission Lines (TLs) plays a major role, an important goal of this is to transmit the generated electricity to various distribution units. Transmission lines act as a bridge between consumers and the powerhouse. In the transmission lines, the faults often occur because they are located in open space. Quick detection and recovery of transmission lines faults are necessary to maintain the normal operation of the power system. To overcome these disturbances, techniques like Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) are used in fault detection and diagnosis. DWT is applied to decompose the fault transients, because it can simultaneously extract the data, in both time and frequency domain. EMD is used to decompose the transmission line voltages into Intrinsic Mode Function (IMFs). Four types of fault signals are generated from the grid-connected power system. Transmission line faults are created using MATLAB/Simulink.

Active learning based on minimization of the expected path-length of random walks on the learned manifold structure

The advanced application of artificial intelligent techniques (AIT) was introduced recently in protection of transmission lines in electric power systems (EPS). Adaptive neuro-fuzzy inference system (ANFIS) is a promising tool among these AIT. In this proposed research, the application of ANFIS for distance relay protection for long transmission line, under different loading conditions, in electrical power systems (EPS) will be introduced and discussed. Based on multiple classified ANFIS and considering different loading conditions for long transmission lines in EPS, the suggested and proposed technique deals with fault detection, classification, and location in long transmission lines. All these tasks will be addressed in details in this article. It considers, firstly, detecting the fault occurrence in very short time and isolate the faulty section of the long transmission lines. Secondly to classify the fault type and deduce which of the three phases are exposed to the fault. Finally, locating the fault will be achieved easily even if the procedure here is completely different from short and medium transmission lines. The input training data of the ANFIS detection units are firstly derived from the fundamental values of the voltage and current measurements [using digital signal processing via discrete Fourier transform (DFT)]. These measurements were simulated considering different loading conditions.

The transmission line experiences the highest number of faults in a power system due to its high exposure and the high number of coincidences that might occur along it. This study presents an approach based on transmission line protection using wavelet transform with a bi-orthogonal wavelet 5.5 signal decomposition. The emphasis is on fault identification, and the proposed method studies the concentration of the coefficients and discriminates faulted phases from healthy phases. Up to Level 1, the signal is decomposed using a wavelet to capture the major features of the signal. A comprehensive assessment framework was used, and a 400 kV system was studied as an infinite bus coupled with a 300 km long transmission line. A contrivance for fault recognition is designed to determine anomalies in the transmission line between the faulted phases and their healthy counterparts with considerably higher detailed coefficients. Fault classification is then performed based on the choice of strict and carefully calibrated threshold values, in which faults are precisely identified and classified. A comparative analysis has been carried out with the relevant FFT, DFT and S-transform on the same MATALB platform. The proposed algorithm is also successfully validate for variation in system conditions like current inversion, CT saturation, non-linear effect of MOV and level of series compensation. An inclusive transmission line protection system is reliably and effectively cultivated through the custom of the planned protection procedure, in which it is shown to be highly capable of precisely sensing and categorizing faults. The replication outcomes demonstrate the effectiveness of the system in practical situations and demonstrate that it may be used in real power systems.

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.

<span lang="EN-US">The regular fault detection approaches are failed to detect the faults in wind integrated transmission networks due to intermittency nature of the wind energy. More reliable schemes are required to accomplish the detection of faults in presence wind. This article proposed empirical mode decomposition (EMD) based fault detection scheme to detect various faults in wind integrated transmission lines during the normal and stressed conditions of the system. The instantaneous current measurements available at either sending or receiving end are processed through EMD to decompose it into a series of intrinsic mode functions (IMFs) and IMF2 is identified as a dominated IMF with numerous case wise investigations. 1/4th cycle moving window is used to calculate the absolute sum of the IMF2 coefficients to detect the faults with the support of a predefined threshold. The efficacy of the method is tested on different types of faults during the normal condition in presence of wind and later extended to stressed conditions such as power swing. The method is reliable during the typical cases and includes remote end and high resistance faults. All the experiments are carried out in Simulink to generate the measurement data and programs are executed in MATLAB.</span>

The present paper focuses on the measurement of fault current signals as well the effect of variation of time and fault resistance on their occurrences on two test systems. First system has two conventional generators at the end of a 100km transmission line without any phase difference. Second system consists of two conventional generators at the end of a 100 km transmission line with a phase difference of 25 degrees. Different types of faults (L-G, L-L, short circuit) are created for different time periods along with different fault resistances and simulated in Matlab. The paper has considered the importance of analyzing the coefficients associated with the magnitude of fault current signals by incorporating the use of Discrete Wavelet Transform (DWT) on them along with mother wavelet of Daubecheis-`db4.' The inclusion of the statistical features have been done for the better interpretation of the test results and also for comparative study between different kinds of faults considered. It is observed in this study that in most of the cases the magnitude of statistical features is higher in Line -Line and Three Phase Short Circuit faults. With inclusion of fault resistances the magnitude of the statistical features reduces.

In this paper, we propose M-estimator based robust kernels for support vector machine. The main motivation for our proposed kernels is that the sum of squared difference in the widely used Gaussian radial basis function kernels is not robust to outlier or noise. In addition, inspired by using a robust loss function in support vector machine regression to control training error and the idea of robust template matching with M-estimator, we apply M-estimator techniques to Gaussian radial basis functions and form a new class of robust kernels for support vector machines. We test our proposed kernels in several classification benchmark datasets and experimental results show that SVM with proposed kernels are better than SVM with Gaussian radial basis function kernels.

This study is inspired by the fact that innovative technology for fault diagnosis is a fundamental and essential part of fault isolation and analysis of faults for the study of power systems using Internet of Things-based technology. This study examined the issue of automatic fault diagnosis. The designed system provides a defect identifier that helps identify and categorize system issues. The primary goal of this study was to locate transmission line faults and report this information to the control room. Transmission lines are employed in this with the assistance of wires connected to a circuit so that the circuit may detect faults and send signals to the microcontroller whenever they occur.The Arduino platform was used for data processing and Internet of Things (IoT) integration. The fault type, line, and range are then displayed on the LCD. The precise position of the issue will then be provided by the GPS module, together with the coordinates, and Node MCU will be used to interact with the control room and transmit the message, which will include information about the approximate location of the overhead transmission line fault (for hardware model) phase short circuits, two-line issue, then two link to milled fault identification will be likely with the last framework plan. A transmission line utilizing MATLAB and Simulink libraries was used to design the model. The novelty of the present work is that a practical fault detection system is designed by integrating multiple sensors and recording IoT data sheets for future use in machine learning models. In the future, it will be strategic to utilize machine learning techniques. Decision trees and random forests were trained using IoT datasheets for power framework checking and transmission line fault identification for line-to-ground, line-to-line, and three-phase faults. Further integration will improve the current system by enabling predictive fault diagnosis.

Kernel methods have long played a central role in machine learning by enabling nonlinear modeling in high dimensional feature spaces. Among them, the Gaussian Radial Basis Function (RBF) kernel is widely used due to its smoothness, universality, and excellent performance in supervised learning. In contrast, the Jaccard/Tanimoto coefficient, originally defined over sets and binary vectors, has achieved notable success in chemoinformatics and information retrieval. Recent studies have shown that the Jaccard/Tanimoto coefficient can be extended to real-valued vectors and interpreted as a valid kernel. In this paper, we propose a natural generalization of the Tanimoto kernel by introducing a bandwidth-like parameter, leading to the Bandwidth-Adjustable Tanimoto (BAT) kernel. We focus on the shared structure of the BAT and the Gaussian RBF kernels in terms of their infinite polynomial expansions and investigate the universality of the BAT kernels, clarifying their relationship to the universal Taylor kernels. In particular, we show that by incorporating a bias term, the BAT kernel attains the universal approximation property comparable to that of the Gaussian kernel. Through experiments on classification, regression, and clustering tasks using benchmark datasets, we demonstrate that the BAT kernel performs comparably to the Gaussian kernel, while even the original Tanimoto kernel achieves competitive results. In particular, the BAT kernel attains performance on par with the Gaussian kernel in classification tasks, and it slightly surpasses the Gaussian kernel in regression and clustering tasks. A comparison of their functional forms, together with experiments on both regression and classification tasks involving nonlinear structures, further shows that the BAT kernel yields smoother predictive surfaces than the RBF kernel. Overall, our results indicate that the BAT kernel offers universality and practical performance, making it an alternative to the Gaussian kernel.

The artificial neural network is a powerful tool for the detection of the transmission line faults due to its ability to differentiate between various patterns. This paper deals with the application of artificial neural networks (ANNs) to the fault detection and classification in high voltage transmission lines for high speed protection which can be used in digital power system protection. The three phase currents of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. The ANN was trained and tested using various sets of field data, which was obtained from the simulation of faults at various fault scenarios (fault types, fault locations and fault resistance) of 230 kV, 193.2 km in length “Mansan-Shwesaryan, Mandalay Region, Myanmar” transmission line using a computer program based on MATLAB/Simulink. Simulation results confirm that the proposed method can efficiently be used for accurate fault classification on the transmission line.

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.

Application of neural networks in electrical power systems have demonstrated that this powerful tool can be employed as an alternative method for solving problems accurately and efficiently. In this paper, an artificial neural networks approach is presented for the detection, classification and isolation (location) of transmission line faults occurring in the system of transmission line. The main aim is to implement a complete scheme for distance protection of a transmission line system. In order to perform this goal, the distance protection task is subdivided into different neural network for fault detection, fault identification (classification) as well as fault location in different zones. 110 KV transmission line system is used to create training and testing data for the neural network by mat-lab program. The result show that the neural network is a powerful analysis tool for providing faults information that is more reliable and accurate than provided by the traditional relay.

High impedance faults (HIFs) are difficult to be detected by overcurrent protection relays. This paper presents an ATP/EMTP fault simulations studies based algorithm for high impedance fault detection in extra high voltage transmission line. The scheme recognizes the distortion of the voltage waveforms caused by the arcs usually associated with HIF. The discrete wavelet transform (DWT) based analysis, yields three phase voltage in the high frequency range which are fed to a classifier for pattern recognition. The classifier is based on an algorithm that uses recursive method to sum the absolute values of the high frequency signal generated over one cycle and shifting one sample. A HIF model of distribution is modified for EHV transmission lines. Characteristics of the proposed fault detection scheme are analyzed by extensive simulation studies that clearly reveal that the proposed method can accurately detect HIFs in the EHV transmission lines.