Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal International Journal of Electrical, Computer, and Biomedical Engineering (IJECBE)
Oh, Seongmun
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering Materials Science & Nanotechnology Medicine & Pharmacology

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Development of Disturbance Type Detection Using Convolution Neural Network for Fault Signature Analysis Putra, Kharisma Darmawan; Garniwa, Iwa; Jufri, Fauzan Hanif; Oh, Seongmun
International Journal of Electrical, Computer, and Biomedical Engineering Vol. 3 No. 2 (2025)
Publisher : Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62146/ijecbe.v3i2.136

Abstract

The development of technology in electrical systems is growing rapidly, increasing power system complexity, which causes the operation and maintenance of the power system networks to become more complicated, especially when a disturbance occurs in the networks. To overcome the issue, there is a need to utilize the tools available as much as possible to manage the power system networks. Nowadays, the power system network is equipped with protection relays and controls that provide various data about the systems, such as the Disturbance Fault Recorder (DFR), which monitors and records the system’s characteristics during network disturbance events. DFR holds information on the system’s parameters during a fault, but it cannot recognize the type or cause of the disturbance. Hence, this paper proposes a method based on the Convolution Neural Network (CNN) model to analyze the DFR’s data and determine the type/cause of disturbance so it can be used to manage the follow-up actions properly. Based on the research results, CNN, with six types of disturbance classification, has an accuracy of 93,87%. Based on the results obtained, the accuracy of CNN using the VGG19 type in handling disturbance analysis in graphical patterns is satisfactory.
Co-Authors Iwa Garniwa Jufri, Fauzan Hanif Putra, Kharisma Darmawan