Bi-Directional Gated Recurrent Unit Approach for Detecting and Classifying High Impedance Fault in Power Distribution DOI
Md Mujahid Irfan,

R. Supriya,

P. Malleswara Reddy

et al.

Published: April 26, 2024

In the recent days, detecting High Impedance Faults (HIF) is an extremely difficult task because it unpredictable, asymmetric, and nonlinear. Due to size of fault current typically much lower than normal load current, these faults are undetectable impossible isolate using traditional over-current approaches. Therefore, this research introduced a novel technique name called Bi-directional Gated Recurrent Unit (Bi-GRU) for power distribution-related HIF detection isolation. The devised makes use voltage as well data from sensors. order clarify procedure, many types algorithms were utilized during phase. For classification purposes, algorithm Bi-GRU applied on IEEE 13- distribution node networks test method's ability recognize detect with both damaged unbroken wires. suggested provides fast flawless output when troubleshooting high impedance issues. considerably increases input processing enhances accuracy. From overall analysis, combines forward reverse GRUs in order, which allows complete operation more quickly accurately existing Morphological Fault Detector by achieving 95.63 % accuracy rate.

Language: Английский

Semantic-Segmentation-based Approach for Early Detection and Type Recognition of Single-Phase Ground Fault in Resonant Distribution Networks DOI
Jian‐Hong Gao, Mou‐Fa Guo, Shuyue Lin

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 112736 - 112736

Published: Jan. 1, 2025

Language: Английский

Citations

0
A novel fault location method for distribution networks with distributed generators based on improved seagull optimization algorithm DOI
Yuan Li, Shijie Su,

Faping Hu

et al.

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 3237 - 3245

Published: March 6, 2025

Language: Английский

Citations

0
Power transformer fault diagnosis method based on multi source signal fusion and fast spectral correlation DOI Creative Commons
Shan Guan, Mingyu Shi, Fuwang Wang

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 27, 2025

Addressing the issues that signal measured by a single sensor can not provide complete description of power transformer fault states and problems selection features relies on manual experience, method based multi source fusion Fast Spectral Correlation is produced for diagnosis. At first, vibration signals from different locations surface case are collected array synchronously, Function Weighting proposed to fuse multi-source multiple sensors in order obtain fused signal; then, subjected belonging cyclic smooth theory construct sample set images; finally, image samples fed into MobileNetV3 model training transfer learning fine-tuned neural network model, which completes Experimental results showed overall recognition accuracy reached 98.75%, was 10.52% higher than diagnosis signal, 10.86% other classical images, providing new tool signals.

Language: Английский

Citations

0
Explainable Deep Learning Approach for High Impedance Fault Localization in Resonant Distribution Networks Considering Quantization Noise DOI
Jian‐Hong Gao, Mou‐Fa Guo, Shuyue Lin

et al.

International Journal of Circuit Theory and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 15, 2024

ABSTRACT In addressing the quantization noise challenge in high impedance fault (HIF) localization within resonant distribution networks, we propose a cutting‐edge, explainable deep learning approach that significantly advances existing methods. This utilizes differential zero‐sequence voltage (DZSV) and current (ZSC) introduces novel “Vague” classification to improve accuracy by effectively managing noise‐distorted signals. extends beyond conventional binary of “Fault” “Sound,” incorporating multi‐scale feature attention (MFA) mechanism for enriched internal explainability applying gradient‐weighted class activation mapping (Grad‐CAM) visualize critical input areas precisely. Our model, validated an industrial prototype, exhibits unparalleled adaptability across various environmental conditions, including noise, variable sampling rates, triggering deviations. Comparative analysis reveals our outperforms methods diverse scenarios.

Language: Английский

Citations

1
An enhanced algorithm for detection of HIAF in active distribution networks and real-time analysis DOI
Fanidhar Dewangan, Monalisa Biswal

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 238, P. 111108 - 111108

Published: Oct. 4, 2024

Language: Английский

Citations

1
Hybrid model of convolutional auto-encoder and ellipse characteristic for unsupervised high impedance fault detection DOI Creative Commons

Junjie Yang,

Benoît Delinchant, Dusit Niyato

et al.

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 238, P. 111166 - 111166

Published: Nov. 4, 2024

Language: Английский

Citations

1
A Method for Single-Phase Ground Fault Section Location in Distribution Networks Based on Improved Empirical Wavelet Transform and Graph Isomorphic Networks DOI Creative Commons
Chen Wang,

Lijun Feng,

S. Hou

et al.

Information, Journal Year: 2024, Volume and Issue: 15(10), P. 650 - 650

Published: Oct. 17, 2024

When single-phase ground faults occur in distribution systems, the fault characteristics of zero-sequence current signals are not prominent. They quickly submerged noise, leading to difficulties section location. This paper proposes a method for location networks based on improved empirical wavelet transform (IEWT) and GINs address this issue. Firstly, kurtosis, EWT is optimized using N-point search decompose signal into modal components. Noise filtered out through weighted permutation entropy (WPE), reconstruction performed obtain denoised signal. Subsequently, employed graph classification tasks. According topology network, corresponding constructed as input GIN. The node GIN autonomously explores features each structure achieve experimental results demonstrate that has strong noise resistance, with accuracy up 99.95%, effectively completing networks.

Language: Английский

Citations

1
Bi-Directional Gated Recurrent Unit Approach for Detecting and Classifying High Impedance Fault in Power Distribution DOI
Md Mujahid Irfan,

R. Supriya,

P. Malleswara Reddy

et al.

Published: April 26, 2024

In the recent days, detecting High Impedance Faults (HIF) is an extremely difficult task because it unpredictable, asymmetric, and nonlinear. Due to size of fault current typically much lower than normal load current, these faults are undetectable impossible isolate using traditional over-current approaches. Therefore, this research introduced a novel technique name called Bi-directional Gated Recurrent Unit (Bi-GRU) for power distribution-related HIF detection isolation. The devised makes use voltage as well data from sensors. order clarify procedure, many types algorithms were utilized during phase. For classification purposes, algorithm Bi-GRU applied on IEEE 13- distribution node networks test method's ability recognize detect with both damaged unbroken wires. suggested provides fast flawless output when troubleshooting high impedance issues. considerably increases input processing enhances accuracy. From overall analysis, combines forward reverse GRUs in order, which allows complete operation more quickly accurately existing Morphological Fault Detector by achieving 95.63 % accuracy rate.

Language: Английский

Citations

0