Network Fault Research Articles

Semantic Segmentation-Based Intelligent Threshold-Free Feeder Detection Method for Single-Phase Ground Fault in Distribution Networks

Semantic Segmentation-Based Intelligent Threshold-Free Feeder Detection Method for Single-Phase Ground Fault in Distribution Networks

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

Cumulative Damage Effect of the Pin-type Porcelain Insulator Incipient Fault in the Resonant Grounded Distribution Networks

Cumulative Damage Effect of the Pin-type Porcelain Insulator Incipient Fault in the Resonant Grounded Distribution Networks

Adaptive Quasi-Power Differential Protection Scheme for Active Distribution Networks

With the massive integration of distributed generations (DGs), distribution networks gradually become more active and flexible. Conventional overcurrent protection is difficult to adapt to such active distribution networks (ADNs). Current differential protection (CDP) is a good choice for solving this issue, but the multi-branch structure of ADNs especially the unmeasured T-connected load branch affects the protection’s sensitivity. Therefore, the paper proposes a quasipower differential protection (QDP) scheme based on Tellegen’s theorem. First, the feasibility of applying Tellegen’s theorem to ADNs was analyzed. On this basis, reasonable protection criteria were designed for different scenarios of ADNs. Then, an adaptive protection scheme was established, which can automatically adjust the criteria depending on the presence of Tconnected branches within the protected section. Finally, extensive simulations were carried out in an ADN model using PSCAD/EMTDC software. The simulation results demonstrate that the proposed protection scheme has excellent adaptability to network topologies, fault types, fault resistances, and network structures of ADNs.

Performance and Adaptability Testing of Machine Learning Models for Power Transmission Network Fault Diagnosis with Renewable Energy Sources Integration

Performance and Adaptability Testing of Machine Learning Models for Power Transmission Network Fault Diagnosis with Renewable Energy Sources Integration

Transparent Grid Visualization Surveillance and Fault Warning in High Density Distributed Power Access Areas

Abstract Transparent grid, as an advanced form of “Internet + smart energy”, is of great value in supporting energy transformation and promoting the development of new power systems. Based on the grid connection requirements of high-density distributed power supply, this paper provides specific grid connection methods and trend calculations and explores the impact of grid connection on high-density distributed power supply. Subsequently, the technical framework and blueprint of the transparent grid are proposed, combined with the grid visualization system to monitor the grid state visually, and based on the random matrix single-loop theory and ARIMA algorithm to realize fault identification and early warning of the transparent grid. The analysis of the algorithm shows that the fault identification has good rapidity, feasibility, and practicability, and while ensuring that no fault alarm is issued in the case of normal disturbance of distributed power supply, it is able to issue fault alarms for all locations and types of short-circuit faults in the system and determine the fault moment within 0.1s. It is “fast”, “accurate,” and “stable” in the research and judgment of active distribution network faults, and it is more intuitive in the assignment of risk levels, and it can identify the categories and levels of faults and realize the following Visualization of early warning.

Self-Healing Networks AI-Based Approaches for Fault Detection and Recovery

The reliability and robustness of communication networks are critical for ensuring seamless connectivity in today's interconnected world. However, network faults and failures can disrupt services, leading to significant downtime and financial losses. [1]In response to these challenges, self-healing networks empowered by artificial intelligence (AI) have emerged as a promising solution for proactively detecting and autonomously recovering from network faults. This paper presents a comprehensive review and analysis of AI-based approaches for fault detection and recovery in self-healing networks, aiming to enhance network reliability and minimize service disruptions. It provides an overview of the key challenges associated with traditional fault detection and recovery methods in communication networks.[2] It discusses the limitations of reactive approaches that rely on manual intervention or predefined rules to identify and mitigate network faults, highlighting the need for more proactive and adaptive solutions. Subsequently, the paper explores the role of artificial intelligence, particularly machine learning and deep learning techniques, in enabling self-healing capabilities in communication networks. By leveraging vast amounts of network data, AI algorithms can learn complex patterns and anomalies indicative of network faults, enabling timely detection and response. The paper reviews various AI-based fault detection techniques, including anomaly detection, supervised learning, and reinforcement learning approaches. It examines their strengths and limitations in different network environments, considering factors such as data availability, scalability, and real-time processing requirements. Furthermore, the integration of AI-based fault detection with network monitoring systems and telemetry data sources is discussed, highlighting the importance of comprehensive data-driven approaches for accurate fault identification. In addition to fault detection, the paper investigates AI-driven recovery mechanisms for self-healing networks. It explores proactive recovery strategies, such as predictive maintenance and network reconfiguration, enabled by AI-based predictive analytics. By harnessing the power of machine learning and deep learning, communication networks can achieve greater resilience, adaptability, and autonomy in mitigating network faults and ensuring uninterrupted service delivery.

Modeling, Integration and Simulation of the Photovoltaic Power Plant Considering LVRT Capability and Transient Voltage Stability

This paper investigates how high photovoltaic energy penetration impacts dynamic performance and voltage regulation of the modified IEEE-9 bus grid. The transmission power system was modeled and simulated using PSCAD-EMTDC software to conduct the study. Load flow analysis is implemented to explore the power system’s capability to incorporate the desired photovoltaic power. Moreover, the study is based on time response simulations to grid disturbances. The supply and control of reactive power from solar power generation plants are becoming critical issues to study because they can facilitate the integration of PV in power grids under different operating conditions. Network-related faults like a PV solar power plant event outage, a three-phase short-circuit at a conventional bus, and a voltage dip at the PV solar power plant have been considered. The results will help identify the protective devices and strategies needed to maintain the stability and reliability of the system operation and transient analysis of the network under external power network fault and recovery operation. Thus, it has practical significance for real utility studies. Moreover, this comprehensive study will be a valuable guide for assessing and improving the grid’s performance under the study of any other grids, which also gives the vast potential and need for solar energy penetration into the grid systems.

Redundant Topology Design Method for Schedule Traffic Transmission Based on IEEE802.1CB Standard: Optimizing NW-PSP Scheduling Performance

This study proposes a method for designing redundant topologies in time-sensitive networking to transmit scheduled traffic (ST) while considering fault tolerance. In general, redundant topologies enhance network fault tolerance and are used in safety-critical applications that demand high reliability. These applications place a premium on real-time network performance, necessitating the consideration of the quality of service for time-critical traffic during the redundant topology design process. The primary objective of this study is to optimize the flowspan, which pertained to the scheduling performance of the no-wait packet scheduling problem during the redundant topology design phase. Specifically, we introduced a methodology for designing topologies tailored to transmit ST using the IEEE802.1CB mechanism. Comparisons with existing topology design approaches revealed the ability of the proposed method to enhance network fault tolerance and yield a topology that reduced flowspan of ST, thereby freeing up bandwidth for time-critical traffic.

Method of Reducing the Effects of Repeated Ignition during Earth Faults in Compensated Medium Voltage Networks

The article presents the results of research in the field of limiting the effects of overvoltages and improving the conditions for the self-extinguishing of transient faults in medium voltage networks with earth fault current compensation. The aim of the research was to estimate the level of overvoltages generated by an earth fault during re-ignition of the electric arc and to assess the possibility of reducing them by increasing the attenuation of the earth fault circuit. The results of the conducted tests show that to increase the attenuation, which ensures a significant effect of limiting such overvoltages, it is enough to change the way of operation of the devices forcing an additional active component of the earth fault current (AWSCz/ACFA). In Poland, such devices are commonly used to improve the effectiveness of earth fault protection. It was also found that the proposed solution enables accurate tuning of the Petersen coil in networks with natural asymmetry of earth capacitances. Therefore, changes in the operation of AWSCz/ACFA devices may have a beneficial effect on the limiting the effects of repeated ignitions during earth faults and, at the same time, enable the accurate tuning of the Petersen coil and increase its ability to extinguish arc-fed faults. Research and theoretical analysis of the issue were carried out on the basis of data characterizing the parameters of the earth fault circuits of the real 15 kV network.

Results of a statistical study of types of single-phase faults in low-voltage ship electrical networks

The increase in the power supply of ships is manifested in growth of ship power plants' capacity, the total length of cable lines, and the number of electrified mechanisms. With the development of marine technology, the severity of the consequences of damage to ship electrical equipment and the costs of its maintenance and repair increase. The search for ways to improve the reliability and safety of electrical equipment should be based on design and technological solutions at the stages of its development and production, as well as an analysis of various factors that may appear during the operation of marine equipment and affect the condition of ship electrical systems. During studying these factors, it has been revealed that one of the common types of damage to electrical equipment of marine equipment is single-phase short circuits, the causes of which are varied. Preventing short circuits is labour intensive and in some cases impracticable. However, understanding the characteristics of this type of damage to low-voltage equipment is necessary to improve the reliability and safety of ship electrical systems. The conducted research is based on a survey of ship electrical mechanics. The results of the surveys have made it possible to analyze the frequency of occurrence of single-phase insulation faults, the duration of their existence, to identify the most likely places of occurrence of short circuits and equipment that is more susceptible to such damage compared to other elements of the electrical power system.

Unsupervised rolling bearing fault diagnosis method across working conditions based on multiscale convolutional neural network

In practical engineering, the features of rolling bearing vibration signals often vary in distribution under different working conditions, and obtaining sample labels for target working conditions can be challenging. Therefore, a multi-scale depth subdomain adaptive convolutional neural network (MS-DSACNN) fault diagnosis method is proposed. The MS-DSACNN method is based on a multi-scale feature extraction method combined with an improved 1D-ConvNeXt architecture, which fuses low- and high-level features into multi-scale fault features. A channel attention mechanism is also introduced to adaptively assign weights to the fused multi-scale features. The local maximum mean discrepancy is constructed by extracting features and their corresponding source and pseudo-label inputs for the source and target working conditions, respectively, to construct the loss function for backpropagation. The MS-DSACNN model was evaluated in experiments with two different loads and one variable speed dataset. The experimental results indicate that MS-DSACNN has higher feature extraction capability and diagnostic accuracy than other unsupervised cross-condition fault diagnosis techniques. Additionally, the scenario where the signal captured by the sensor contains a considerable amount of noise in actual working conditions is considered.

Fault nature identification and location scheme for distribution network based on active injection from IIDG

In view of the difficulty in passively identifying the nature of faults in distribution networks and the high equipment cost of existing active detection schemes, a permanent fault identification and location scheme using an inverter-interfaced distributed generator (IIDG) connected to feeders for signal injection is proposed. After the faulty feeder is isolated, the power electronics in the IIDG are switched on for a short time and a voltage signal is injected into the feeder through the modified LCL filter and grid-connected transformer. The analysis shows that the aerial mode voltage of the feeder will not remain 0 under permanent faults. A highly sensitive criterion with fixed thresholds is constructed using approximate entropy (ApEn) to identify fault nature. Then the fault distance is further calculated based on the detected mutation point of the aerial mode voltage under permanent faults. The correctness of the theory and the effectiveness of the scheme are verified in PSCAD/EMTDC simulations.© 2017 Elsevier Inc. All rights reserved.

Research on distribution network fault processing technology based on knowledge of graph

Safety and reliability are the basis of the development of a distribution network. To analyze the risk transmission process in the distribution network and ensure the safe and reliable operation of the power system, this paper intends to use the knowledge graph method to realize the risk analysis of the distribution network information system. Firstly, the knowledge graph method is used to extract and integrate the risk knowledge of the multi-dimensional information collected by the distribution network. Secondly, the knowledge graph model of distribution network risk analysis is constructed, and the multi-dimensional distribution network fault handling and knowledge graph construction oriented to the feeder and platform area are designed. The distribution line parameters of the low-voltage distribution network model, neutral point grounding mode, and different fault types are analyzed, and the non-planned island is searched based on the knowledge graph adjacency matrix. Finally, combined with the simulation experiment, it is verified that the proposed method can effectively depict the information risk process of the distribution network. The structure of this paper starts from the multi-node complex distribution network, combined with a knowledge graph and deep learning method, which can solve the distribution network fault more quickly.

Design of Online Intelligent Detection System for Power Quality and Fault Identification in Distribution Networks

Abstract This paper lays the foundation for the subsequent analysis of power quality in distribution networks by briefly describing the indicators of power quality. Utilizing the zero sequence voltage mutation detection fault of a small current routing algorithm, the instantaneous values of voltage and current of each phase of the three-phase circuit are quickly calculated based on the electrical parameters of instantaneous reactive power and the online intelligent detection system is established. The effectiveness and feasibility of the designed detection system and detection algorithm in detecting electrical energy parameters have been verified through experiments. The results show that the error of voltage measurement is within 0.0003-0.002, the frequency error of the system is up to 0.0117%, the measurement error of three-phase unbalance is distributed between 0.001 and 0.1, and the error of negative sequence and zero sequence is between ±0.003, which meet the system design requirements. It shows that the use of online intelligent detection systems can improve the quality of distribution network operation and fault identification accuracy, improve power quality, and effectively improve the reliability of power supply.

A Digitalization Algorithm Based on the Voltage Waveform of the Multifunction Vehicle Bus

The MVB is a kind of widely used vehicle-level bus, which is crucial for the normal operation of trains. However, the MVB bus contains device node terminals and the topology is complex, which makes fault location difficult. The voltage waveform of the MVB physical layer can reflect the electrical characteristics and fault characteristics of a network in real time and has the value of assisting the diagnosis of MVB network faults. Based on the characteristics of the MVB physical-layer voltage waveform, this paper studies the optimal sampling rate and feature-extraction algorithm of the MVB voltage waveform and the combination of the data of the data-link layer to assign accurate timestamps to waveform data, and finally presents a design for an MVB dual-mode data-acquisition platform with multiple sampling rates/test conditions. Experimental results show that the proposed algorithm can accurately extract waveform feature information under the optimal sampling rate of 62.5 MHz, which makes the collection of MVB voltage waveform data more reliable and practical.

Distribution network restoration supply method considers 5G base station energy storage participation

This paper proposes a distribution network fault emergency power supply recovery strategy based on 5G base station energy storage. This strategy introduces Theil's entropy and modified Gini coefficient to quantify the impact of power supply reliability in different regions on base station backup time, thereby establishing a more accurate base station's backup energy storage capacity model that can fully utilize the base station's energy storage resources to participate in the emergency power supply of distribution network faults. First, the optimal Copula function in each cycle is determined through the Akaike information criterion and squared Euclidean distance to establish a wind power-photovoltaic output scenario. Secondly, the traditional Gini coefficient is modified using the weighted average node degree and influence rate indicators. A comprehensive vulnerability model is established through the modified Gini coefficient and Theil's entropy indicators. Based on the comprehensive vulnerability model, a backup energy storage time model and a modified backup energy storage capacity model of the base station affected by power supply reliability are established. Thus, the callable energy storage capacity of base stations in different areas is obtained. Finally, a two-stage robust optimization model is introduced to minimize system operating costs to solve the volatility of 5G base station communications and wind-solar output, thereby establishing an emergency power supply recovery model for base station energy storage and wind-solar output. Simulated with the improved IEEE-33 node model, the results show that the proposed base station's energy storage model improves the utilization of the base station energy storage resources and, at the same time, effectively reduces the loss of load during the fault phase of the distribution network and improves the absorption of the PV output.

Robust adaptive backstepping neural networks fault tolerant control for mobile manipulator UAV with multiple uncertainties

The present study outlines the development of an Adaptive Backstepping Radial Basis Function Neural Networks Fault Tolerant Control (ABRBFNNFTC) methodology. The aforementioned methodology is employed to address the challenge of achieving trajectory following in the context of a Mobile Manipulator Unmanned Aerial Vehicle (MMUAV) when subjected to the effects of actuator faults and parametric uncertainties. The utilization of an adaptive radial basis function neural networks (RBFNNs) controller is employed for the purpose of approximating an unidentified nonlinear backstepping controller that relies on the precise model of the MMUAV. The Lyapunov direct method is utilized to establish the stability analysis of the entire system. The closed-loop system guarantees the Uniformly Ultimately Bounded (UUB) stability of all signals. The control methodology put forth ensures the achievement of a prescribed trajectory, and mitigates the impact of uncertainties and actuator faults. The efficiency of the proposed ABRBFNNFTC scheme is demonstrated through the presentation of extensive simulation studies.

Research on the Physical Reproduction Method of Single-phase Grounding Fault in 10 kV Distribution Network Based on Digital Mirroring

It is necessary to construct a physical reproduction environment that conforms to the actual working conditions of single-phase grounding faults in 10 kV distribution networks, to effectively verify the single-phase grounding fault disposal capability of distribution automation equipment. In this article, a physical reproduction method of a single-phase ground fault in distribution networks based on digital mirroring is proposed. A digitized mirror model of a single-phase ground fault of a 10 kV distribution network is constructed. The system architecture for equivalent physical reproduction of single-phase grounding fault characterization is designed. Then the solutions to the critical technical problems in the realization are proposed. The reproduced single-phase ground fault signal was applied in the functional verification work of the first and second fusion distribution equipment. The experimental results show that the single-phase grounding fault in the 10 kV distribution network reproduced by this method comprehensively verifies the correct rate of the equipment for the single-phase ground fault disposal as well as the ability to prevent false action. Moreover, the reasons for the failure of the equipment s single-phase grounding fault disposal function were discovered.

Research on Confidence Analysis Method of Lightning Strike Accidents on Distribution Lines

Currently, lightning is the main cause of power system faults. Due to insufficient equipment and technology, low insulation level, the distribution network being the main part of power outages, and the complex causes of distribution network faults, it is difficult to determine whether each fault in the distribution network is caused by lightning strikes. In this paper, the concept of lightning strike confidence, i.e., the possibility of a line lightning strike fault caused by falling lightning, is proposed, and a lightning strike confidence analysis is performed for a 10 kV distribution line in the mountainous region of South China to determine the possibility of a line lightning strike fault caused by falling lightning based on the lightning locating system data of the distribution line at the moment of the fault. First, the calculation method of the lightning strike confidence is derived; then the distribution law of the distribution line lightning strike confidence, the influence of the ground tilt direction, and ground tilt angle on the distribution line lightning strike confidence are analyzed; finally, the distribution line lightning strike confidence is analyzed by an example.