Combining multi-level feature extraction algorithm with residual graph convolutional neural network for partial discharge detection

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F25%3A10256665" target="_blank" >RIV/61989100:27240/25:10256665 - isvavai.cz</a>

Alternative codes found

RIV/61989100:27730/25:10256665

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S0263224124020360?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0263224124020360?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.measurement.2024.116151" target="_blank" >10.1016/j.measurement.2024.116151</a>

Result language

angličtina

Original language name

Combining multi-level feature extraction algorithm with residual graph convolutional neural network for partial discharge detection

Original language description

Partial discharge (PD) identification is critical for the insulation diagnosis of cable conductors; however, there is still scope for enhancement in the existing adaptive extraction capabilities and feature utilization for PD signals. In this context, this paper introduces a method that integrates a one-dimensional convolutional neural network (1D-CNN) with a residual graph convolutional neural network (ResGCN) to recognize PD signals. Noise analysis is performed using various combinations of mother wavelets, and Bayesian optimization is employed to mitigate background noise. Key features of PD signals are progressively abstracted through a 1D-CNN-based multilevel automatic feature learning method, while signal timing attributes are maintained to minimize manual intervention. The graph data is constructed using the signal feature matrix and the signal timing feature similarity matrix. This is followed by the development of a ResGCN utilizing a graph attention mechanism to integrate node feature information and the topology of the PD graph data. This approach aims to fully exploit the correlation between local regions of the feature space and the temporal numerical properties of the signals. Additionally, it jointly optimizes feature extraction and model classification to facilitate adaptive diagnosis. The method is validated with extensive real experimental data obtained from medium voltage overhead power lines. It demonstrates exceptional performance and practicality, achieving an accuracy rate of 97.3% and a recognition rate of 96.1% for PD samples, thus offering reliable theoretical support for effective PD detection. © 2024 Elsevier Ltd

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20201 - Electrical and electronic engineering

Project

—

Continuities

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Measurement

ISSN

0263-2241

e-ISSN

1873-412X

Volume of the periodical

242

Issue of the periodical within the volume

January

Country of publishing house

US - UNITED STATES

Number of pages

15

Pages from-to

nestránkováno

UT code for WoS article

001356071600001

EID of the result in the Scopus database

2-s2.0-85208460709