Prediksi Kegagalan Transformator Daya dengan Metode DGA (Dissolved Gas Analysis) Menggunakan Random Forest Berbasis TDCG

Authors

  • Marcelino Maxwell Sugiman Universitas Kristen Satya Wacana, Salatiga
  • Hindriyanto Dwi Purnomo Universitas Kristen Satya Wacana, Salatiga

DOI:

https://doi.org/10.30865/mib.v8i1.7036

Keywords:

Transformers, Random Forest, TDCG

Abstract

Transformers are critical components, and early detection of potential failures plays an important role in the reliable operation of the power system. This article describes a novel approach for power transformer failure prediction based on dissolved gas analysis (DGA) by applying the TDCG method with Random Forest algorithm. DGA data from operational transformers are used to train and test the predictive model. The Random Forest method based on TDCG enables comprehensive analysis of dissolved gas changes in transformer oil, thus enabling early detection of failure conditions. Experimental results show that the predictive model using the model created by applying hyperparameter tuning for optimal parameter tuning to have high accuracy, the accuracy obtained reaches 96% in detecting potential failures, the standard used for accuracy presentation uses confusion matrix as the accuracy of the predictive model. In addition, it can optimize time efficiency in analyzing failures and prevent human error when calculating gas fault identification or potential failures.

References

R. Hardityo, “Deteksi Dan Analisis Indikasi Kegagalan Transformator Dengan Metode Analisis Gas Terlarut,†Skripsi, Universitas Indonesia, Jakarta, 2008.

M. H. Basri and M. Faisol, “Analysis Effect of Loading on the DGA Results of the UAT 2A Transformer PLTU Paiton 1&2 for Optimizing Self-Use,†jppipa, pendidikan ipa, fisika, biologi, kimia, vol. 9, no. 5, pp. 4029–4035, May 2023, doi: 10.29303/jppipa.v9i5.3379.

R. Sutjipto, “Studi pengaruh pembebanan terhadap perubahan suhu dan perubahan rugi - rugi daya pada transformator,†JE, vol. 18, no. 1, p. 62, Apr. 2020, doi: 10.33795/eltek.v18i1.219.

Y. Y. Rizki and E. Ervianto, “Perkiraan Umur Transformator Berdasarkan Pengaruh Pembebanan Dan Temperatur Lingkungan Menggunakan Metode Trend Linear,†Jurnal Online Mahasiswa (JOM) Bidang Teknik dan Sains, vol. 6, no. 0, Art. no. 0, Jul. 2019.

M. Yazdani-Asrami, S. Asghar Gholamian, S. M. Mirimani, and J. Adabi, “Influence of field-dependent critical current on harmonic AC loss analysis in HTS coils for superconducting transformers supplying non-linear loads,†Cryogenics, vol. 113, p. 103234, Jan. 2021, doi: 10.1016/j.cryogenics.2020.103234.

I. Bayu Tiasmoro, Wirentake, and P. Ali Topan, “Pengaruh Pembebanan Terhadap Efisiensi Dan Susut Umur Transformator Step Up 6kv / 70kv DI PLTU Sumbawa Barat Unit 1 dan 2 2×7 MW PT.PLN (PERSERO) UPK Tambora,†TAMBORA, vol. 5, no. 2, pp. 1–7, Jul. 2021, doi: 10.36761/jt.v5i2.1099.

N. Ardi, S. S, and A. Irmansyah Lubis, “Predicting Missing Value Data on IEC TC10 Datasets for Dissolved Gas Analysis using Tertius Algorithm,†JAIC, vol. 7, no. 1, pp. 44–50, Jul. 2023, doi: 10.30871/jaic.v7i1.5361.

S. Shidiq, A. Sujatmiko, and A. H. Paronda, “Pengujian Dissolved Gas Analysis (DGA) Pada Trafo Tenaga 150/20kv 60mva Di Gardu Induk Tambun,†Journal of Electrical and Electronics, vol. 7, no. 1, 2019.

Sukarman, “Analisis Kondisi Transformator Daya Dengan Metode DGA (Dissolved Gas Analysis) Menggunakan Artificial Neural Network Berbasis Standar IEC Pada PT. PLN Transmisi Jawa Bagian Timur Dan Bali,†Disertasi, Universitas Jember, Jember, 2018.

A. Pradiftha Junfithrana, I. Himawan Kusumah, Anang Suryana, Edwinanto, M. Artiyasa, and A. De Wibowo, “Identifikasi Gas terlarut Minyak Transformator dengan Menggunakan Logika Fuzzy Menggunakan Metode TDCG untuk Menentukan Kondisi Transformator 150 KV,†Fidelity, vol. 1, no. 1, pp. 11–15, May 2019, doi: 10.52005/fidelity.v1i1.122.

A. Lakehal, Z. Ghemari, and S. Saad, “Transformer fault diagnosis using dissolved gas analysis technology and Bayesian networks,†in 2015 4th International Conference on Systems and Control (ICSC), Sousse, Tunisia: IEEE, Apr. 2015, pp. 194–198. doi: 10.1109/ICoSC.2015.7152759.

A. Pramono, M. Haddin, and D. Nugroho, “Analisis Minyak Transformator Daya Berdasarkan Dissolved Gas Analysis (DGA) Menggunakan Data Mining Dengan Algoritma J48,†Telematika, vol. 9, no. 2, p. 78, Sep. 2022, doi: 10.35671/telematika.v9i2.457.

S. S. M. Ghoneim and I. B. Taha, “Artificial Neural Networks for Power Transformers Fault Diagnosis Based on IEC Code Using Dissolved Gas Analysis,†INTERNATIONAL JOURNAL OF CONTROL, 2015.

I. M. T. Sismantara, W. G. Ariastina, and A. A. N. Amrita, “Penentuan Kondisi Transformator Berdasarkan Kandungan Gas Terlarut Menggunakan Metode Segitiga Duval,†SPEKTRUM, vol. 8, no. 1, p. 107, Mar. 2021, doi: 10.24843/SPEKTRUM.2021.v08.i01.p12.

M. Abdullah, Metode Penelitian Kuantitatif. Yogyakarta, 2015. Accessed: Dec. 06, 2023. [Online]. Available: https://idr.uin-antasari.ac.id/5014/

R. Anni, “Analisis Keadaan Minyak Transformator Menggunakan Metode Logika Fuzzy Berdasarkan Kadar Gas Terlarut,†Jurnal Pendidikan Tambusai, vol. 6, no. 2, pp. 16200–16207, 2022.

N. K. Dewi, U. D. Syafitri, and S. Y. Mulyadi, “Penerapan Metode Random Forest Dalam Driver Analysis,†FORUM STATISTIKA DAN KOMPUTASI, vol. 16, no. 1, Art. no. 1, 2011, Accessed: Nov. 22, 2023. [Online]. Available: https://journal.ipb.ac.id/index.php/statistika/article/view/5443

A. T. Wibowo, “Implementasi Algoritma Deteksi Spam Yang Tersisipi Informasi Citra Dengan Metode SVM Dan Random Forest,†Skripsi, Institut Teknologi Sepuluh Nopember, Surabaya, 2016.

E. Elgeldawi, A. Sayed, A. R. Galal, and A. M. Zaki, “Hyperparameter Tuning for Machine Learning Algorithms Used for Arabic Sentiment Analysis,†Informatics, vol. 8, no. 4, p. 79, Nov. 2021, doi: 10.3390/informatics8040079.

I. W. Saputro and B. W. Sari, “Uji Performa Algoritma Naïve Bayes untuk Prediksi Masa Studi Mahasiswa,†Creative Information Technology Journal, vol. 6, no. 1, Art. no. 1, Apr. 2020, doi: 10.24076/citec.2019v6i1.178.

Downloads

Published

2024-01-24

Issue

Vol. 8 No. 1 (2024): Januari 2024

Section

Articles

License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).