High Impedance Fault Detection Research Articles

Detection and Location of High Impedance Fault on the Nigerian 330kV Transmission System Using Artificial Neural Network

The effect of the occurrence of high impedance fault (HIF) in power system networks results to low current signal which cannot be detected by the electrical equipment which results to fire outbreaks. Nigerian power system network has witnessed the occurrence of HIF which has led to fire outbreak in buildings and in minor cases grid collapse. In this paper, the performance of ANN in the detection and location of HIF was studied and determined. The transmission network located in south-south region of the Nigerian 330kV power system network was obtained and modeled in SIMULINK. The line distance was split into six points and implemented in the SIMULINK to obtain the current signals at each point of the lines. The current signals were used as the input data with the split distance utilized as the target to the ANN model. The ANN had three input neurons (each neuron represented the phase current signal), the hidden layer had five neurons with each neuron incorporating log sigmoid curve and the output layer having one neuron which was the split distance. The outcome had the least error deviation value of 0.0118 making the performance of ANN effective in the point location of HIF occurrence on the transmission line.

Detection and Classification of High Impedance Fault in Nigerian 330 kV Transmission Network using ANN: A Case Study of the Southeast Transmission Network

High Impedance Fault (HIF) occurs when an energized conductor comes in direct or indirect contact with a quasi-insulator. If not detected and eradicated, it would lead to fire outbreak, pose a risk to human lives, and negate the existing environmental friendliness. The transmission lines data of the 330 kV, south east Nigeria network were obtained and modeled in SIMULINK for the detection and classification of the HIF. The transmission lines modeled were from Afam GS (Generating Station) to Alaoji GS, Alaoji GS to Owerri GS, Alaoji GS to Onitsha TS (Transmission Station), and from Onitsha TS to New Heaven TS. The HIF was situated on the 25 km transmission line connecting Afam GS to Alaji GS which was the central part of the Network. The current signal for each of the HIF classes at each location was used as the input data to the Artificial Neural Network (ANN) model with the HIF classification code used as the ANN target. On inserting the developed ANN in the transmission network and testing its performance, it was observed that the maximum HIF classification deviation occurred on the transmission line connecting Alaoji and Onitsha (two phase HIF) at 0.003 (0.15%). This proved that ANN model is capable and suitable in HIF detection and classification on transmission line network in South East.

LSTM-based low-impedance fault and high-impedance fault detection and classification

LSTM-based low-impedance fault and high-impedance fault detection and classification

A negative sequence current injection (NSCI)-based active protection scheme for islanded microgrids

The growing penetration of converter interfaced generation creates unprecedented challenges to protection strategies at all voltage levels. This paper proposes a novel Negative Sequence Current Injection (NSCI)-based active protection scheme for islanded microgrids. The faulty section identification method based on the negative sequence current increment between the pre-injection and current generation steady state conditions enables the scheme to achieve an excellent High Impedance Fault (HIF) detection capability. The proposed NSCI control algorithm maintains the phase angle of the negative sequence current fixed during injection progress, thus providing a highly discriminative feature which facilitates the correct identification of the faulty section. As no form of communication is required the proposed protection scheme can be very cost-effective and flexible in practical applications. Following the detailed description of the principle of operation and the setting procedure, a systematic simulation-based validation is undertaken considering a variety of influencing factors such as fault type, resistance and position, as well as impact of load distribution under HIFs, and possible presence of Synchronous Generators (SGs). The results show that the scheme has an excellent detection and discrimination ability, especially during unbalanced faults, and is not affected by load distribution or behaviour of other sources, including SG.

Detection and location of high impedance faults in delta 13.8kV distribution networks

This article presents the main results obtained in the project “Automated System of Classification, Detection, and Location of High Impedance Faults in Distribution Networks”, carried out for Brazilian utility COPEL, between 2019 and 2021, as part of ANEEL's R&D program. The project developed an automated system with efficient and robust algorithms for the real-time detection, classification, and location of high impedance faults in the distribution networks. The system consisted of computational tools to automatic high impedance faults detection and location in 13.8 kV delta-connected grid. Field tests carried out in a real feeder turned possible the development of a simple and reliable algorithm, related to the amplitude and phase shift of the zero-sequence current monitored in the substation. The fault location was determined by consulting undervoltage at automatic reclosers, and smart energy meters installed along the feeder. A computational tool was developed to provide relevant information to the utility Operation Center to initiate an emergency maintenance.

High Impedance Fault Detection and Localization Using Fully-Connected Convolutional Neural Network: A Deep Learning Approach

The detection and localization of high impedance faults (HIF) in power systems are challenging due to the low fault current magnitude, which often falls below the detection threshold of conventional devices. HIF events introduce harmonics into the network, posing risks to the safety of connected equipment, including the potential for igniting fire which endangers lives and properties. In this study, Emanuel's HIF model was used to generate HIF signatures resembling real HIF events. Model parameters were adjusted to mimic various contact surface impedances. Two datasets were created: 'no-fault' data, simulating the network without HIF, and 'fault' data, incorporating HIF waveforms by simulating single and multiple lines with the HIF model. The faulted line was divided into five segments along the 33 kV line to capture fault signatures at different locations. The generated data, including current waveforms and magnitudes, were processed and divided into an 80:20 ratio for training, validation, and testing using a deep fully connected Convolutional Neural Network for HIF detection and location. The results showed an impressive accuracy rate of 99.44% and 99.78% for detection and location respectively, representing a significant advancement in HIF detection and location, and offering practical applications for enhancing power line safety.

A Distributed High-Impedance Fault Detection and Protection Scheme in DC Microgrids

A Distributed High-Impedance Fault Detection and Protection Scheme in DC Microgrids

High impedance fault detection in radial distribution network using discrete wavelet transform technique

High impedance fault detection in radial distribution network using discrete wavelet transform technique

High Impedance Faults Detection in Distribution Systems Using Signal Correlations

High Impedance Faults Detection in Distribution Systems Using Signal Correlations

Detection of High-Impedance Fault in Distribution Networks Using Frequency-Band Energy Curve

Detection of High-Impedance Fault in Distribution Networks Using Frequency-Band Energy Curve

High Impedance Fault Detection Based on Arc Changing Tendency and Nonlinear Least Squares for Active Distribution Networks

High Impedance Fault Detection Based on Arc Changing Tendency and Nonlinear Least Squares for Active Distribution Networks

Active High-Impedance Fault Detection Method for Resonant Grounding Distribution Networks

Active High-Impedance Fault Detection Method for Resonant Grounding Distribution Networks

An incremental high impedance fault detection method under non-stationary environments in distribution networks

In the non-stationary environments of distribution networks, where operating conditions continually evolve, maintaining reliable high impedance faults (HIF) detection is a significant challenge due to the frequent changes in data distribution caused by environmental variations. In this paper, we propose a novel HIF detection method based on incremental learning to handle non-stationary data stream with changing distributions. The proposed method utilizes stationary wavelet transform (SWT) to extract fault characteristics in different frequency domains from zero-sequence current data. Subsequently, a complex mapping from signal features to operational conditions is established using backpropagation neural network (BPNN) to achieve online detection of HIF. Additionally, signal features are analyzed using density-based spatial clustering of applications with noise (DBSCAN) to monitor the distribution of data. After encountering multiple distribution changes, an incremental learning process based on data replay is initiated to evolve the BPNN model for adapting to the changing data distribution. It is worth noting that the data replay mechanism ensures that the model retains previously acquired knowledge while learning from newly encountered data distributions. The proposed method was implemented in a prototype of a designed edge intelligent terminal and validated using a 10 kV testing system data. The experimental results indicate that the proposed method is capable of identifying and learning new distribution data information within non-stationary data stream. This enables the classifier model to maintain a high level of detection accuracy for the current cycle data, effectively enhancing the reliability of HIF detection.

A Communication-Assisted Distance Protection for AC Microgrids considering the Fault-Ride-Through Requirements of Distributed Generators

The conventional overcurrent protection is ineffective in isolating faults in microgrids due to the low fault current levels contributed by inverter-interfaced distributed generations (IIDGs). To extend the microgrid protection methods, the distance protection is considered as a common alternative to detect faults. However, the fault-ride-through (FRT) requirements and the high impedance fault (HIF) detection challenge the application of the conventional distance protection. To solve the two problems, a new inverse-time distance (ITD) protection for medium-voltage AC microgrids was proposed in this paper. The primary ITD protection was designed to meet the FRT requirements, and the backup protection was coordinated to isolate faults. The fault resistance and distributed generation infeed effect on the measured impedance were mitigated by a communication-assisted method proposed in this paper. Owing to the shorter communication channel time in distribution feeders and lower communication investments without a synchronous clock, the proposed method can be used to improve the ITD protection performance. An 11 kV AC microgrid was simulated with different fault types in the islanded mode and grid-connected mode. Time domain simulation verified the effectiveness of the proposed ITD protection.

High Impedance Fault Detection and Location in the Nigerian 330 kV Transmission Network Using Adaptive Neuro-Fuzzy Inference System

Fundamentally, the occurrence of high impedance fault (HIF) can be established when an energy filled conductor contacts a semiconductor. The occurrence of HIF can be described to be subtle and disastrous as it results to low current signal and a signal voltage arc if undetected and without implementation of protective measures, leads to the damage of the power system equipment and in many cases fire outbreak. In this study, the occurrence of HIF on the south-south region of Nigerian 330kV transmission line was studied with the data utilized obtained from the Nigerian control center (NCC) Osogbo. The data obtained was modeled in simulink and the outcome at normal condition was obtained. The transmission line distance was split into 4 points with the current signal at each point generated in simulink and exported to the Matlab file. The data in Matlab file was split to train, test and validate at 70%, 15% and 15% respectively. The data analysis performed was sent to Adaptive Neuro-fuzzy inference system (ANFIS) with the current signal at normal condition and at 3-phase HIF was used as input data while the split distance was implemented as the target data to the model. The effectiveness of the model in detecting and locating HIF was obtained and analyzed in a comparative plot of the location distance. From the results presented, the highest error deviation for fault location with ANFIS was 10%. Hence, it was concluded that ANFIS model had a satisfactory outcome in HIF detection and as such should be utilized for the HIF detection and location.

A Critical Analysis on Different High Impedance Fault Detection Schemes

High Impedance Fault (HIF) results due to non-isolation of high intensity transmission line with that of the low intensity conductors like trees and ground etc. The current flowing in the line in this case is so low that the condition usually cannot be detected by conventional technologies such as relays and fuses. However, the condition needs to be detected sooner and addressed quicker as it can be very hazardous to human beings and animals living nearby. As the current is low, detection of HIF is a major challenging task in the distribution side of power utility. This paper presents an analysis of different available HIF detection schemes. This paper focuses on different recent available remarkable HIF detection schemes until 2023. For better understanding about HIF detection schemes, the model and algorithm involved in each scheme are described followed an extensive analysis of the technologies. The analysis includes classification, complexity in evaluation, pros & cons, and scope of application. This paper can be a very useful tool for the researchers and working professional working in maintenance of distribution-side utility network.

An improved high-impedance fault identification scheme for distribution networks based on kernel extreme learning machine

In distribution networks, high-impedance faults (HIFs) occur frequently and have a harmful impact on the distribution network. However, fault detection and fault phase selection of HIFs are challenging due to weak fault characteristics. Therefore, this paper proposes an improved HIF identification scheme based on a kernel extreme learning machine (KELM) that can sensitively identify HIFs and select the fault phase by adaptively extracting the weak fault characteristics. First, a fault feature extraction strategy based on discrete wavelet decomposition (DWT) and the Hilbert–Huang transform (HHT) is proposed to obtain multiple features that describe the weak fault characteristics of HIFs. Second, an XGBoost-based fault feature selection scheme is proposed for screening with sensitive characterization of HIFs. Next, a sensitive and accurate HIF identification scheme based on the improved learning algorithm (KELM) is proposed to enable accurate and sensitive HIF detection and phase selection. Finally, numerical simulations based on PSCAD/EMTDC and MATLAB were carried out, which reveals the effectiveness and accuracy of the proposed HIF identification scheme. Compared with the traditional HIF identification scheme, the proposed method exhibits conciseness and correctness.

High impedance fault detection device based on edge artificial intelligence

The current high impedance fault (HIF) detection devices are mainly based on threshold method, the hardware cannot meet the computing requirements of artificial intelligence (AI), and the software structure is difficult to adapt to the upgrade requirements of AI. These AI detection algorithms are mainly based on simulation analysis and laboratory testing and have not yet been applied practically. The paper develops an edge AI-based HIF detection device, it combines the main body and independent AI module. The AI module embeds an edge identification algorithm and shares the sampling data with the main body. The detection result is achieved from intelligent classifier in edge AI module and fed back to the main device. Finally, the device is tested on the Luohe distribution network true test platform, the detection accuracy for multiple types of fault is 98.6%.

High-Impedance Fault Detection Methodology Using Time–Frequency Spectrum and Transfer Convolutional Neural Network in Distribution Networks

High-impedance fault (HIF) detection has always been difficult in distribution networks due to the lack of field data and the large difference between field and simulation waveforms. Based on the characteristics of zero-sequence currents, a novel HIF detection methodology is proposed, which combines time–frequency spectrum (TFS) and transfer convolutional neural network (TCNN). First, the TFSs are acquired by applying continuous wavelet transform (CWT) to the collected zero-sequence currents. Then, the TFSs of simulated zero-sequence currents are utilized for training source-domain convolutional neural network (SCNN). Next, the SCNN is transfer learned with very few TFSs of field zero-sequence currents to obtain TCNN. The performance of the proposed method is verified by simulation samples and field samples. The results show that the proposed method can effectively extract fault features from small-scale training samples under different fault circumstances. Besides, TCNN can adaptively extract the effective features of field HIF and detect field HIF more accurately than SCNN. Finally, this article provides a visualization scheme for interpretability of the neural network, which offers visual explanations for the decision-making basis of the neural network.

ML-Based Intermittent Fault Detection, Classification, and Branch Identification in a Distribution Network

The accurate detection and identification of intermittent cable faults are helpful in improving the reliability of the distribution system. This paper proposes intermittent fault detection and identification for distribution networks based on machine-learning (ML) techniques. For this reason, the IEEE 33 bus system is simulated in the radial and mesh topologies by considering all possible single- and three-phase electrical faults and limitations to collect high-resolution voltage and current waveforms. Moreover, this simulation investigates and considers various cases including low-impedance faults (LIFs) and high-impedance faults (HIFs) with a short and long duration. The collected data from the simulation are used for high-impedance intermittent fault detection, classification, and branch identification using eight supervised learning methods. A comparison between the accuracy and error of these ML classifiers shows that gradient booster (GB) and K-nearest neighbors (KNN) have the best performance for all three objectives. However, GB has a very high computation time compared to KNN.