Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Perancangan Sistem Deteksi Anomali pada Transformator menggunakan Dissolved Gas Analysis (DGA) dengan Metode K-Nearest Neighbour (KNN)

Authors: Kurniawan, Andre;

Perancangan Sistem Deteksi Anomali pada Transformator menggunakan Dissolved Gas Analysis (DGA) dengan Metode K-Nearest Neighbour (KNN)

Abstract

Transformator merupakan bagian terpenting dalam sistem tenaga listrik, maka dari itu perlu dilakukan pemeliharaan untuk mencegah munculnya anomali-anomali pada Transformator. Dissolved Gas Analysis (DGA) adalah salah satu metode untuk mendeteksi anomali pada trafo, DGA digunakan untuk menguji kondisi minyak isolasi pada Transformator dengan cara mengambil sampel minyak isolasi. Apabila terjadi kejadian anomali pada trafo, maka konsentrasi gas yang dihasilkan akan berbeda-beda tergantung pada jenis kejadian anomali pada trafo tersebut. Tujuan dari penelitian yang dilakukan adalah dapat merancang sistem deteksi anomali pada Transformator menggunakan DGA serta melihat tingkat akurasi dari metode metode DGA yang ada menggunakan KNN. Pada penelitian ini, sistem deteksi anomali pada transformator dan didapatkan hasil tingkat akurasi tertinggi 94% metode key gas dan tingkat akurasi terendah 79% metode Doernenburg Ratio. Simpulan dari penelitian ini adalah mampu membuat sistem yang dapat mempermudah dalam menganalisa anomali pada Transformator, serta dapat dijadikan metode alternatif untuk menentukan kondisi pada Transformator.

The transformer is the most important part of the electric power system, therefore maintenance needs to be carried out to prevent the emergence of anomalies in the transformer. Dissolved Gas Analysis (DGA) is a method for detecting anomalies in transformers. DGA is used to test the condition of the insulating oil in transformers by taking samples of the insulating oil. If an anomalous event occurs in a transformer, the resulting gas concentration will vary depending on the type of anomalous event in the transformer. The aim of the research carried out is to be able to design an anomaly detection system on Transformers using DGA and to see the level of accuracy of the existing DGA method using KNN. In this research, an anomaly detection system for transformers and obtained the highest accuracy rate of 94% using the key gas method and the lowest accuracy rate of 79% using the Doernenburg Ratio method. The conclusion of this research is that it is able to create a system that can make it easier to analyze anomalies in transformers, and can be used as an alternative method for determining the condition of transformers.

Country
Indonesia
Related Organizations
Keywords

K-Nearest Neighbour (KNN), Transformator, Dissolved Gas Analysis (DGA)

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!