Faults In Power Distribution Systems Research Articles

A customised artificial neural network for power distribution system fault detection

AbstractMachine learned fault detection approaches are being increasingly used for fault detection in distribution grid. However, the performance of the models can be improved by customizing the models. In this regard, a customised artificial neural network (CANN) for fault detection in a distribution grid is proposed in this paper. The proposed work develops a CANN that combines the “up‐pyramid” and “down‐pyramid” model of ANN into a “custom‐pyramid” model. As a result, the same model can be used both for determining the types of fault as well as its location. The data needed to train the model has been taken from a reconfigured IEEE‐33 bus distribution system developed in Typhoon HIL real‐time simulator. Spectral‐kurtosis is utilized for extraction of features of the faulted transient signals which are used as input data to develop the CANN. The result showcases that the reduction of input features reduces computational complexity without compromising its accuracy. The proposed model classifies fault location with an accuracy of 95.43%. The proposed method also identifies fault type with an accuracy of 96.08%. Several test cases have been developed to test the method. The method proved to be able to perform in most of the cases.

Analysis of Faults in Power Distribution Systems With Distributed Generation

The paper studies the location of single-phase faults abstract in power distribution systems with distributed generation by means of impedance-based methods. These methods are based on the measurement of voltages and currents and in one measurement point and distributed generation cause errors in the estimated location. The paper shows the influence of parameters such as the magnitude of distributed generation, the fault impedance and the relative position of the fault location and the distributed generation in the estimated location.

Precise PMU-Based Localization and Classification of Short-Circuit Faults in Power Distribution Systems

Knowing the exact location of a short-circuit fault in a power distribution system (PDS) is essential for rapid restoration of service to customers and has a direct impact on the operational costs and reliability of the system. In this paper a phasor measurement unit (PMU) based method for fault localization and classification is presented. By introducing the concept of a virtual bus, the exact fault location on the line is determined rather than just a bus closest to the fault. Moreover, after determining the fault location, a generic fault model (GFM) is introduced to classify the type of fault by solving a minimization problem, which also provides fault impedances as a result. These can then be further used to determine if the fault occurred on the lateral instead of the main feeder without using additional PMU at the end of that lateral. The effectiveness of the proposed approach is verified by simulating various fault scenarios in two test systems based on real PDSs using a real-time digital simulator. In addition, a sensitivity analysis of the method is performed for different noise levels in the input parameters to verify its applicability to the real system.

Radial Power Distribution System Fault Classification Model Based on ANFIS

The classification of problems in power systems plays an extremely important part and has evolved into a necessity that is of the utmost importance to the operation of energy grids. For the purpose of fault classification in IEEE 13 node radial distribution systems, this paper makes use of both an Artificial Neural Network (ANN) and a Neural Fuzzy adaptive Inference System (ANFIS). Simulations of the suggested models are carried out in MATLAB/SIMULINK, and fault currents from all three phases are analyzed in order to extract statistical characteristics. Input data vectors include the standard deviation and correlation factors between the currents of any two phases, while output data vectors include the different sorts of faults. The findings demonstrate that the devised method is appropriate for the classification of all symmetrical and unsymmetrical faults.

Fault Classification in Power Distribution System with Distributed Generation

The primary aim of Power System is to provide uninterrupted power supply to consumers but the performance of Power System is frequently affected by Power Distribution System faults. In order to maintain the continuity of supply and to improve the efficiency of Power System the Power Distribution System fault should be rapidly diagnosed and treated accurately. This paper describes the development of Wavelet-Artificial Neural Network method for classification of Faults in Power Distribution System with Distributed Generation. The disturbances characterized are events from an IEEE 14 bus test system with Distributed Generation. The main purpose of the algorithm is to classify the unsymmetrical faults, single-line-to-ground fault (LG), double line fault (LL) and double line to ground fault (LLG). Along with this some other parameters are also discussed in this work like impact of DG on voltage regulation, impact of DG on harmonics, impact of DG on losses and the impact on short circuit level of the network

Fault locating and severity assessment for power distribution systems based on elasticity network topology mapping

Although fault locating in power distribution systems has been widely studied, very few research works consider fault severity assessment, i.e., fault influence on other lines. The main reason behind this is the lack of a unified standard to quantify and assess the severity of different type of faults. In this paper, a novel power distribution system fault locating and severity assessment method is proposed based on elasticity network mapping. The principle of the proposed method is based on elastic coefficient, which reflects the state of the elastic spring by its numerical value. The partial derivative of distribution line power flow to its phase difference, denoted as distribution rate (DR), is analyzed to map the line fault occurrence to the numerical change in DR. Besides, the method normalizes the DR values of different distribution lines into standardized values between 0 and 1, so that normalized comparison can be achieved. Because DR value is inversely proportional to the severity the fault, by comparing the DR of each line, the fault location and severity can be accurately evaluated. Simulation tests are performed in 10 different test feeders with around 35% of nodes installed with measurement units, reporting a 99% accuracy.

Identification of Single Phase to Ground Faults in Power Distribution Systems with RG Technique

Fault in a power system is an irregular condition that interrupts the stability of the system and causes a high fault current to flow through the power systems and its devices. Single phase to ground fault is an unsymmetrical fault that takes place between any phase of the system and ground. It is the most frequently occurring fault (70%-80%) that happens in the power system. Resonant Grounding (RG) is the proposed approach that reduces a fault current of a single phase to ground fault to a minimum level that is often independent of fault impedance. In this case, the single phase to ground fault current is too small and the typical overcurrent relay does not respond in this circumstance. As a result, a new and improved approach for detecting single phase to ground fault failures in arc suppression coil grounding distribution system with very low fault currents, though the fault impedance is low, is required. The faults are initially detected based on the neutral voltage displacement by a regionalized fault detection technique. The statement is validated by simulating a single phase to ground fault on an IEEE thirteen node test system and the results are presented. Since it employs local voltage and current information to detect power system fault condition, the suggested technique does not require communication between circuit breaker, relays, transformer, transmission lines etc. This approach can be used to a variety of different forms of unsymmetrical faults.

Intelligent fault diagnosis for power distribution system-comparative studies

Short circuit is one of the most popular types of permanent fault in power distribution system. Thus, fast and accuracy diagnosis of short circuit failure is very important so that the power system works more effectively. In this paper, a newly enhanced support vector machine (SVM) classifier has been investigated to identify ten short-circuit fault types, including single line-to-ground faults (XG, YG, ZG), line-to-line faults (XY, XZ, YZ), double line-to-ground faults (XYG, XZG, YZG) and three-line faults (XYZ). The performance of this enhanced SVM model has been improved by using three different versions of particle swarm optimization (PSO), namely: classical PSO (C-PSO), time varying acceleration coefficients PSO (T-PSO) and constriction factor PSO (K-PSO). Further, utilizing pseudo-random binary sequence (PRBS)-based time domain reflectometry (TDR) method allows to obtain a reliable dataset for SVM classifier. The experimental results performed on a two-branch distribution line show the most optimal variant of PSO for short fault diagnosis.

High-impedance faults in power distribution systems: A narrative of the field’s developments

High-impedance faults in power distribution systems is a lasting problem with decades of steady investigation. Due to the complexity of the problem, the field can also be challenging to navigate. Although there exist surveys of the field in the literature, it is not easy to find a comprehensive contextualization of how and when the field developments unfolded. This paper presents the historical narrative of the progress and developments based on the most cited papers since the inception of the field. The accounts are not limited to archaic and obsolete works. They are all contextualized from the seminal papers to contemporary methods and related technology. Quantitative figures on the survey of the methods and relevant knowledge gaps are also discussed at the closing of the paper.

Incipient Fault Identification in Power Distribution Systems via Human-Level Concept Learning

Incipient faults in power distribution systems potentially lead to catastrophic failures. Detection of incipient faults contributes to proactive fault management and predictive maintenance, which effectively improves power supply reliability. Since the faults are infrequent and transient, few samples can be procured in real applications. In this paper, a detection method based on human-level concept learning (HLCL) is proposed to address this problem. The method contains two steps: human-level waveform decomposition (HLWD) and hierarchical probabilistic learning (HPL). HLWD, inspired by human perception, decomposes waveform into primitives: segments of general shape and residuals, which identify a waveform. HPL learns waveform through a generative process based on primitives, where the probability for an abnormal event to be an incipient fault can be hierarchically calculated. Experiments on simulation data and field data, which contain subcycle incipient faults, multicycle incipient faults, permanent faults and transient disturbances, indicate that the proposed method outperforms other three generally used classifiers.

A New Approach for Faults Detection and Classification in Overhead Line Systems Using Multiple Methods

Faults in power systems can be described by a sudden increase in current compared with the flow of normal current. The phenomenon of fault affects energy quality, security, and reliability of the system. Several events play a key role in causing faults such as trees falling on overhead lines, insulation breakdown, and lightning strikes. Thus, determining the location of faults is a very important subject, especially in Power Distribution System’s and this can be achieved by applying several methods to classify and detect a fault in order to identify the correct type of faults. this paper, Clarke Method Transformation and Phase Angle Shift techniques are used to classify faults in Power Distribution System and to determine if the fault is grounded or ungrounded. On the other hand, Smooth Support Vector Machine and Discrete Wavelet Transform techniques are used to determine the accurate fault types. The data taken are the faulted voltage phases, which are stored and imported in MATLAB from ATPDraw, which design and build the proposed system of 33 kV power supply, overhead lines with 20 km length and frequency of 50 Hz. The obtained results from MATLAB simulation demonstrate that the proposed algorithm works very properly and it can detect and classify the existence of faults within the transmission line in the Power Distribution System. The inclusion of the multi-phase faults is the future step to enhance the performance of this work.

Cloud Based IoT Solution for Fault Detection and Localization in Power Distribution Systems

Power restoring time in power distribution systems (PDS) can be minimized by using efficient fault localization techniques. This paper proposes a novel, robust and scalable cloud based internet of things (IoT) solution for identification and localization of faults in PDS. For this purpose, a new algorithm is developed that can detect single and multiple simultaneous faults in the presence of single and multiple device or sensor failures. The algorithm has utilized a zone based approach that divides a PDS into different zones. A current sensing device (CSD) was deployed at the boundary of a zone. The function of CSD is to provide time synchronized current measurements and communicate with a cloud server through an edge device (ED). Another contribution of this research work is the unique implementation of context aware policy (CAP) in ED. Due to CAP, only those measurements are transmitted to cloud server that differ from the previously transmitted measurements. The cloud server performed calculations at regular intervals to detect faults in PDS. A relational database model was utilized to log various fault events that occur in PDS. An IEEE 37 node test feeder was selected as PDS to observe the performance of our solution. Two test cases were designed to simulate individual and multiple simultaneous faults in PDS. A third test case was implemented to demonstrate the robustness and scalability of proposed solution to detect multiple simultaneous faults in PDS when single and multiple sensor failures were encountered. It was observed that the new algorithm successfully localized the faults for all the three cases. Consequently, significant reductions were noticed in the amount of data that was sent to the cloud server. In the end, a comparison study of a proposed solution was performed with existing methods to further highlight the benefits of our technique.

Research on Islanding Strategy for Fault Recovery of Distribution System with Micro-grid

In order to adapt to the actual situation of power distribution system fault recovery with micro-grid, a recovery strategy for micro-grid to operate on island with important system load at first under fault conditions is hereby studied. Due to the weak overload capacity, large fluctuation and obvious influence of weather and time period of renewable energy in micro-grid, the dynamic changes of distribution generation and loads in non-fault power loss areas should be considered as much as possible when generating islands. According to historical data, the daily random fitting functions of photovoltaic power generation, fans and various loads are respectively generated by using respective optimization models. For judging the start and duration of the fault, using the fitting function to set the fitting power value of each unit in the distribution system and other information, and calculating the dynamic importance information of each load node as the heuristic condition for subsequent island search. The search strategy in this paper is to guide the load added to the island according to the dynamic importance of the load, and to analyze the reliability of island operation. This method controls the direction of island search, and gives priority to ensuring the recovery of important loads. At the same time, it can ensure the balance between the stability of island generation and the maximum utilization of renewable energy.

Detection and Classification of High Impedance Fault in Power Distribution System using Hybrid Technique

In this paper, a hybrid strategy is introduced for detecting and classifying the High Impedance Fault in Power Distribution System. For hybridization, Gravitational Search Algorithm is combined with Artificial Neural Network to crease the classification performance. The ANN is utilized to characterize the blame signal from the reference signal and the execution is enhanced in view of the GSA calculation. The yield of the proposed method is recognized and arranged whether it is HIF fault or no-fault. At first, the ordinary practices of the appropriation framework are assessed. After that, the deficiencies are connected and the signals are measured. At that point, these are given to the contribution of the enhanced ANN procedure, which gives the dataset to breaking down the framework exhibitions. Finally, the proposed strategy is implemented in the MATLAB/Simulink model and its execution is assessed and compared with other conventional techniques like DWT-ANFIS, DWT-RBFFN, MWT-ANFIS, and MWT-FLC based GA. From the experimental results, it shows that the proposed method achieved better performance than existing methods.

Power distribution system fault monitoring device for supply networks in Nigeria

Electric power is the bedrock of our modern way of life. In Nigeria, power supply availability, sufficiency and reliability are major operational challenges. At the generation and transmission level, effort is made to ensure status monitoring and fault detection on the power network, but at the distribution level, particularly within domestic consumer communities there are no fault monitoring and detection devices except for HRC fuses at the feeder pillar. Unfortunately, these fuses are sometimes replaced by a copper wire bridge at some locations rendering the system unprotected and creating a great potential for transformer destruction on overload. This study is focused on designing an on-site power system monitoring device to be deployed on selected household entry power cables for detecting and indicating when phase off, low voltage, high voltage, over current, and blown fuse occurs on the building’s incomer line. The fault indication will help in reducing troubleshooting time and also ensure quick service restoration. After design implementation, the test result confirms design accuracy, device functionality and suitability as a low-cost solution to power supply system fault monitoring within local communities.

An Injection Methodology for Testing Master Stations’ Fault-Processing Capability

Due to the lack of available tests and equipment, the ability of master stations to process faults in power distribution systems cannot be evaluated systematically or comprehensively during their commissioning. As a solution, this paper presents an injection methodology that consists of a research system and an evaluation technique. The same system is also employed for on-site tests. Standardized test networks and corresponding cases are integrated into the system, where a traversal fault-setting scheme can specify the location for short-circuit faults anywhere along the test network. The Tabu Search is adopted to optimize network reconfiguration for complex fault scenarios. Additionally, the system can validate the configuration and settings of peripheral equipment, including relays. More than one-hundred master stations have been tested and graded by the proposed methodology, leading to acceptance of the injection test.

A Decentralized Fault Detection Technique for Detecting Single Phase to Ground Faults in Power Distribution Systems With Resonant Grounding

This paper presents a decentralized fault detection technique for power distribution systems with resonant grounding. The aim of this paper is to detect single phase to ground faults and identify the faulty feeder within three cycles of the fault occurrence. In the proposed technique, faults are first detected based on the neutral voltage displacement. The pre-fault and post-fault voltages (phase to ground) are then used to identify the faulty phase. Finally, the faulty feeder (as well as the faulty area of a long feeder) is identified from the relationship between the initial transient of the zero-sequence current and the faulty phase voltage just after the occurrence of faults. A signal processing tool called mathematical morphology is utilized to identify the faulty feeder. To identify the faulty feeder, it is also required to know the fault occurrence time that is estimated using the slope of the neutral voltage. The main feature of the proposed scheme is that this technique only uses voltage and current signals from the corresponding voltage transformers and current transformers. Therefore, it does not require communication among protection devices in the same or different feeders to identify the faulty feeder. The proposed technique also has the ability to distinguish the nature of faults, i.e., whether the faults are permanent or temporary. The effectiveness of the proposed scheme is tested, on an IEEE test system as well as on a practical test system, using MATLAB/SimPowerSystems . Simulation results show that the proposed technique can quickly detect the single phase to ground faults in a resonant grounding power distribution system and identify the faulty feeder. It is also capable of distinguishing faults from other disturbances. Moreover, it works under different compensation levels as well as for different fault inception angles.

Travelling waves‐based identification of sub‐health condition of feeders in power distribution system

The majority of faults in power distribution system are caused by natural degradation of feeders. In addition, travelling waves will be generated during degradation of feeders. This study proposes a method based on travelling waves to identify sub-health condition, which represents the degradation of feeder before the feeder fails into a permanent fault. In the method, traveling waves in the power distribution system are monitored in real time. Then, the location of travelling wave source is determined by the polarity of travelling waves, which is extracted using wavelet transform. Finally, the degradation of feeder is identified when all the other possibilities to generate travelling waves are ruled out using the characteristics of power-frequency voltages and currents accompanied with travelling waves. Simulation results have verified that the proposed method is feasible and effective.

Fault location approach for distribution systems based on modern monitoring infrastructure

This study presents an approach based on short-circuit theory and on modern monitoring infrastructure for locating permanent and temporary faults in power distribution systems. The main innovative aspects of the proposed approach are: (i) no fault classification is required if phasor measurements are adopted, (ii) both current and voltage measurements may be included in the problem, (iii) in the fault location criterion the measurements are weighted according to their proximity to the fault location, (iv) a refinement scheme allows finding the fault on branches and not only at buses. The proposed approach can cope with magnitude measurements, synchronised phasors obtained via micro phasor measurement unit and unsynchronised phasors, which are being used for the first time for fault location purposes. Case studies are carried out considering a real 134-bus feeder. Initially, the performance of the proposed approach is assessed with respect to fault location, fault type and fault resistance. Next, studies regarding the influence of the number, position and type of measurements are presented. Statistical simulations are performed for assessing the influence of the random errors inherent to measurements, load forecasting and distribution system parameters. The results indicate that the proposed approach is accurate and very promising.

High impedance fault detection in power distribution systems using wavelet transform and evolving neural network

This paper concerns how to apply an incremental learning algorithm based on data streams to detect high impedance faults in power distribution systems. A feature extraction method, based on a discrete wavelet transform that is combined with an evolving neural network, is used to recognize spatial–temporal patterns of electrical current data. Different wavelet families, such as Haar, Symlet, Daubechie, Coiflet and Biorthogonal, and different decomposition levels, were investigated in order to provide the most discriminative features for fault detection. The use of an evolving neural network was shown to be a quite appropriate approach to fault detection since high impedance faults is a time-varying problem. The performance of the proposed evolving system for detecting and classifying faults was compared with those of well-established computational intelligence methods: multilayer perceptron neural network, probabilistic neural network, and support vector machine. The results showed that the proposed system is efficient and robust to changes. A classification performance in the order of 99% is exhibited by all classifiers in situations where the fault patterns do not significantly change during tests. However, a performance drop of about 13–24% is exhibited by non-evolving classifiers when fault patterns suffer from gradual or abrupt change in their behavior. The evolving system is capable, after incremental learning, of maintaining its detection and classification performance even in such situations.