Sistem deteksi pada transformator menggunakan Dissolved Gas Analysis (DGA) dengan metode Logistic Regression

Kurniawan Indra Wibowo; Hendry Hendry

doi:10.24246/aiti.v21i2.197-209

Authors

Kurniawan Indra Wibowo Fakultas Teknologi Informasi, Universitas Kristen Satya Wacana https://orcid.org/0009-0000-8569-8740
Hendry Hendry Fakultas Teknologi Informasi, Universitas Kristen Satya Wacana https://orcid.org/0000-0002-7387-2622

DOI:

https://doi.org/10.24246/aiti.v21i2.197-209

Keywords:

Dissolved Gas Analysis (DGA), transformer, Logistic Regression

Abstract

This research discusses the implementation of a failure detection system in transformers using dissolved gas analysis (DGA) and the Logistic Regression method. The Logistic Regression method was chosen as a classification tool to identify gas patterns that could indicate critical conditions in the transformer. This research aims to create a system expected to increase transformer reliability, reduce the risk of electrical disturbances, and contribute to industrial practice in implementing more efficient methods for maintaining power transformers. From the training and testing DGA transformers data experiencing various levels of damage show that Logistic Regression provides excellent performance with accuracy, precision, F1-Score, and recall of 97%, 97%, 97%, and 97%. These results reflect a remarkable balance between this method's ability to classify positive and negative results. While Key gas has low accuracy, precision, and F1-Score (42%, 17%, and 24%), The recall value of 42% shows the ability of this method to detect a large number of actual positive data but with a higher error rate. Overall, these findings can potentially improve the reliability of the electric power system through early maintenance and timely detection of potential problems with transformers.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

Y. P. Tondok, L. S. Patras, dan F. Lisi, “Perencanaan Transformator Distribusi 125 kVA,” Jurnal Teknik Elektro dan Komputer, vol. 8, no. 2, hlm. 83–92, 2019.

J. Siburian, “Karakteristik Transformator,” JURNAL TEKNOLOGI ENERGI UDA, vol. VIII, no. 1, hlm. 21–28, 2019.

M. Misto dan H. Haryono, “Analisis Gas Terlarut pada Minyak Isolasi sebagai Indikator Kegagalan Transformator Daya dengan Metode Dissolved Gas Analysis,” Jurnal Teknik Elektro dan Komputasi (ELKOM), vol. 1, no. 2, hlm. 99–112, Des 2019, doi: 10.32528/elkom.v1i2.3091. DOI: https://doi.org/10.32528/elkom.v1i2.3091

F. R. Ramadhan, F. Amrullah, dan Kusnadi, “Identifikasi Dan Peningkatan Kinerja Transformator Gis Duren Tiga 150/20 Kv Dengan Metode Dissolved Gas Analysis Dan Filtrasi,” Prosiding Seminar Nasional Teknik Elektro, vol. 5, hlm. 63–70, 2020.

Nurmaisinta dan Kartika, “Deteksi Gas Pada Minyak Transformator Berbasis Mikrokontroler,” Jurnal Teknik Elektro − Universitas Muhammadiyah Surakarta, vol. 23, no. 1, hlm. 37–43, 2023, doi: 10.23917/emitor.v1i1.20977. DOI: https://doi.org/10.23917/emitor.v1i1.20977

Y. D. Almoallem, I. B. M. Taha, M. I. Mosaad, L. Nahma, dan A. Abu-Siada, “Application of logistic regression algorithm in the interpretation of dissolved gas analysis for power transformers,” Electronics (Switzerland), vol. 10, no. 10, Mei 2021, doi: 10.3390/electronics10101206. DOI: https://doi.org/10.3390/electronics10101206

Tristanti, F. Muliani, dan Amelia, “Penerapan Metode Regresi Logistik Multinomial Penggunaan Kemoterapi Pada Kasus Kanker Payudara Di Rsup H. Adam Malik Medan,” Gamma-Pi: Jurnal Matematika dan Terapan, vol. 2, no. 1, hlm. 18–23, Jun 2020.

A. Yulinda, M. Taqiyyudin A, dan B. M. Basuki, “Analisis Kegagalan Trafo Berdasarkan Hasil Pengujian Dissolved Gas Analysis Pada Trafo I 50 Mva 150/20kv Gi Pier,” SCIENCE ELECTRO, vol. 10, no. 1, hlm. 64–69, 2019.

S. Ariyani, “Analisis Dissolved Gas Analysis Dan Klasifikasi Tipe Fault Pada Minyak Trafo Dengan Metode Naive Bayes Classifier Pada Transformator Daya 150 kV,” 2019. DOI: https://doi.org/10.32528/elkom.v1i1.2181

I. M. Sismantara, W. Ariastina, dan A. Amrita, “Penentuan Kondisi Transformator Berdasarkan Kandungan Gas Terlarut Menggunakan Metode Segitiga Duval,” Jurnal SPEKTRUM, vol. 8, no. 1, hlm. 107, 2021. DOI: https://doi.org/10.24843/SPEKTRUM.2021.v08.i01.p12

R. Nisa Sofia Amriza dan D. Supriyadi, “Komparasi Metode Machine Learning dan Deep Learning untuk Deteksi Emosi pada Text di Sosial Media,” Jurnal JUPITER, vol. 13, no. 2, hlm. 130–139, 2021.

M. Tohari, B. Sukoco, dan M. Haddin, “Analisis Kondisi Transformator Daya 20kv/150kv Dengan Metode Uji Dissolved Gas Analysis (DGA) Di Pt.pjb PLTU Rembang,” KONFERENSI ILMIAH MAHASISWA UNISSULA (KIMU) 4, hlm. 337–344, 2020.

R. Furqaranda dan S. Suwarno, “Analisa Minyak Isolasi Transformator Daya dengan Metode Disolved Gas Analysis (DGA) dan Purifikasi,” Jurnal Ilmiah Ecosystem, vol. 23, no. 2, hlm. 441–449, Agu 2023, doi: 10.35965/eco.v23i2.2871. DOI: https://doi.org/10.35965/eco.v23i2.2871

Christiono, M. Reza Hidayat, dan B. Widiyantoro, “Analisis Kemampuan Minyak Isolasi Transformator Daya Merek Unindo Dengan Pengujian Dissolved Gas Analysis dan Breakdown Voltage di Gardu Induk Serpong,” EPSILON : Journal of Electrical Engineering and Information Technology, vol. 18, no. 3, hlm. 100–106, 2020.

R. H. Situngkir dan P. Sembiring, “Analisis Regresi Logistik Untuk Menentukan Faktor-Faktor Yang Mempengaruhi Kesejahteraan Masyarakat Kabupaten/Kota Di Pulau Nias,” Jurnal Matematika dan Pendidikan Matematika, vol. 6, no. 1, hlm. 25–31, 2023. DOI: https://doi.org/10.47662/farabi.v6i1.432

M. Vebrencia Babo dan I. A. Dwiatmoko, “Analisis Faktor-faktor Yang Berhubungan Dengan Terjangkitnya Penyakit Malaria Dengan Menggunakan Model Regresi Logistik Binimial,” Jurnal Kependidikan Matematika, vol. 27, no. 1, hlm. 27–37, 2020. DOI: https://doi.org/10.30822/asimtot.v2i1.498

A. Kurniawan dan H. D. Purnomo, “Sistem Deteksi Anomali Pada Transformator Menggunakan Dissolved Gas Analysis Dengan Metode K-Nearest Neighbour,” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 8, no. 1, hlm. 144–153, 2024, doi: 10.30865/mib.v8i1.7034. DOI: https://doi.org/10.30865/mib.v8i1.7034