Predictive Maintenance Trafo Distribusi Menggunakan Machine Learning untuk Meningkatkan Keakuratan Pengambilan Keputusan
Keywords:
Predictive Maintenance, Trafo Distribusi, Machine Learning, K-Means Clustering, Extreme Gradient Boosting (XGBoost), Benefit Cost Analysis
Abstract
PT PLN (Persero) adalah BUMN yang bergerak di bidang ketenagalistrikan, dengan tugas memberikan pelayanan terbaik kepada pelanggan di seluruh Indonesia. Untuk menjaga kinerja keandalan distribusi, PLN mengukur kinerja menggunakan KPI seperti SAIDI, SAIFI, ENS, Gangguan Penyulang 20 kV, Kubikel, dan Trafo. Dalam upaya mengurangi gangguan pada Trafo Distribusi, PLN menerapkan pemeliharaan prediktif berbasis kondisi (Condition Based Maintenance/CBM). Namun, Predictive Maintenance yang diterapkan saat ini belum cukup efektif karena belum menggunakan alat ukur canggih, database inspeksi tidak dimanfaatkan dengan baik, dan pengambilan keputusan belum berbasis pendekatan ilmiah. Penelitian ini menggunakan Machine Learning untuk Predictive Maintenance Trafo Distribusi, dengan pemodelan Unsupervised Learning menggunakan K-Means Clustering untuk mengelompokkan aset trafo berdasarkan indikator kesehatannya. Hasil cluster ini digunakan untuk melatih model Supervised Learning dengan metode XGBoost, menghasilkan prediksi akurat terkait pemeliharaan trafo. Variabel input dalam penelitian ini meliputi usia trafo, suhu, pembebanan, dan ketidakseimbangan beban trafo. Dari pengolahan data 2709 Trafo, diperoleh klasifikasi tingkat keandalan dalam 4 kelas: Trafo Sehat (46,99%), Beban Tinggi dan Rawan Gangguan (30,53%), Tua dan Rawan Gangguan (17,53%), serta Trafo Losses (4,95%). Model ini memiliki akurasi 97%, precision 92-97%, dan recall 95-98%, dengan efisiensi biaya 80,88%.
Downloads
Download data is not yet available.
References
Honarmand N .(2015). Key performance indicators modeling for optimized microgrid configuration.
Mojtaba Shirvani, Ahmad Memaripour, Mostafa Abdollahi, Asadollah Salimi. Calculation of generation system reliability index: Expected Energy Not Served. Life Sci J 2012;9(4):3443-3448]. (ISSN: 1097-8135). http://www.lifesciencesite.com. 510.
I.D. Pranowo. (2015). Sistem dan Manajemen Pemeliharaan. Deepublish.
PT PLN (Persero). (2014). Edaran Direksi No. 0017.E/DIR/2014. Metode Pemeliharaan Trafo Distribusi berbasis Kaidah Manajemen Aset.
Moleda, et al. (2023). From Corrective to Predictive Maintenance - A Review of Maintenance Approaches for the Power Industry. MDPI.
Tran et al., (2020). A Review of Health Assessment Techniques for Distribution Transformers in Smart Distribution Grids. MDPI.
Syukri, Muliadi, & Setiawan, T. (2022). Kajian Pemeliharaan Trafo Distribusi Menggunakan Metode Condition Based Maintenance (CBM). Aceh Journal of Electrical Engineering and Technology, 18-23.
Sutaryono, G. L. (2015). Analisa Indeks Kesehatan Transformator Daya Berbasis Neural Network Untuk Mereduksi Jumlah Test Pada Trafo. Master Thesis Jurusan Teknik Elektro Fakultas Teknologi Industri Institut Teknologi Sepuluh Nopember Surabaya.
A, A. N., Jaiswal, G. C., Ballal, M. S., & Tutakne, D. R. (2015). Remote condition monitoring system for distribution transformer. Indian Institute of Technology Kanpur.
Ballal, M. S., Jaiswal, G. C., Tutkane, D. R., Venikar, P. A., Mishra, M. K., & Suryawanshi, H. M. (2017). Online condition monitoring system for substation and service transformers. The Institute of Engineering and Technology, 1187-1195.
Tamma, W. R., Prasojo, R. A., & Suwarno. (2020). High voltage power transformer condition assessment considering the health index value and its decreasing rate. The Institution of Engineering and Technology.
McArthur, S. D., Strachan, S. M., & Jahn, G. (2004). The design of a multi-agent transformer condition monitoring system. IEEE Transactions on Power Systems, 1845-1852.
Sukadana, I. W., Darmawan, K. D., & Sutama, I. W. (2021). Deteksi Dini Gangguan Transformator Berbasis Manajemen Transformator Untuk Meningkatkan Kinerja Operasi dan Finansial Di PT.PLN ULP Singaraja. Jurnal Teknik Elektro Institut Teknologi Padang, 78-85.
Benren Pan et al. (2019). Analysis and Research of Three-phase Unbalance in Distribution Transformers. IOP Conf. Ser.: Earth Environ. Sci. 252 032196.
Alauddin Yousif Al-Omary, dkk. (2006). A new approach of clustering based machine-learning algorithm, science direct.
Daniel Riano Kaparang dan Eko Sediyono. (2013). “Penentuan Alih Fungsi Lahan Marginal Menjadi Lahan Pangan Berbasis Algoritma K-means di Wilayah Kabupaten Boyolali.” JdC. 2. 20.
Ali Bou Nassif, dkk. (2021). Machine Learning for Anomaly Detection: A Systematic Review, Institute of Electrical and Electronics Engineers.
Guanghui Fan, dkk. (2021). Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance, Institute of Electrical and Electronics Engineers.
Muhammad Usama, dkk. (2019). Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges, Institute of Electrical and Electronics Engineers.
Razan Abdulhammed, dkk. (2019). Features Dimensionality Reduction Approaches for Machine Learning Based Network Intrusion Detection, Electronics 2019, mdpi.
Chen, T., & Carlos Guestrin. (2016). XGBoost: A Scalable Tree Boosting System. Paper presented at the proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
Suhadi, dkk. (2008). Teknik Distribusi Tenaga Listrik Jilid 1-2. Jakarta : Direktorat Pembinaan Sekolah Menengah Kejuruan, Direktorat Jenderal Manajemen Pendidikan Dasar dan Menengah, Departemen Pendidikan Nasional.
Nasteski, V. (2017). An overview of the supervised machine learning methods. Horizons. b, 4(51-62), 56.
Cunningham, P., Cord, M., & Delany, S. J. (2008). Supervised learning. In Machine learning techniques for multimedia: case studies on organization and retrieval (pp. 21-49). Berlin, Heidelberg: Springer Berlin Heidelberg.
Caruana, R., & Niculescu-Mizil, A. (2006, June). An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd international conference on Machine learning (pp. 161-168).
Khormarudin, A. N. (2016). Teknik data mining: Algoritma K-Means clustering. J. Ilmu Komput, 1-12.
Agatonovic-Kustrin, S., and Beresford, R. (2000). Basic concepts of artificial neural network (ANN) modelling and its application in pharmaceutical research. Pharmaceutical and Biomedical Analysis 22:717727.
Turhan, C., Kazanasmaz, T., Uygun, I.E., Ekmen, K.E., and Akkurt, G.G. (2014). Comparative study of a building energy performance software (KEP-IYTEESS) and ANN-based building heat load estimation. Energy and Buildings 85:115-125.
Vita, et al. (2023.) Predictive Maintenance for Distribution System Operators in Increasing Transformers’ Reliability. MDPI.
Wu et al., (2021). Improved Genetic Algorithm and XGBoost Classifier for Power Transformer Fault Diagnosis. Frontiers in Energy Research.
Raichura et al., (2020). Efficient CNN-XGBoost technique for classification of power transformer internal faults against various abnormal conditions. IET Generation, Transmission & Distribution.
Xing et al., (2022). Health evaluation of power transformer using deep learning neural network. ScienceDirect.
Alqudsi et al., (2019). Application of Machine Learning in Transformer Health Index Prediction. MDPI.
Sudha et al., (2022). Classification of faults in distribution transformer using machine Learning. ScienceDirect.
Bjelic et al., (2023). Machine learning for power transformer SFRA based fault detection. ScienceDirect.
Zeinoddini-Meymand et al., (2016). Health index calculation for power transformers using technical and economical parameters. IET Journals.
Liu et al., (2019). Fault diagnosis of power transformer based on tree ensemble model. IOP Conference Series: Materials Science and Engineering.
Nugraha, R. H. (2022). Analisis Perilaku Pembayaran Rekening Listrik Pelanggan Menggunakan Kombinasi Klaster K-Means Dan Klasifikasi Xgboost Guna Percepatan Pendapatan (Studi Kasus : Pln Ulp Panakkukang). TESIS – BM185407.
Tianqi Chen dan Carlos Guestrin. (2016). XGBoost: Sistem Pendorong Pohon yang Dapat Diskalakan.
Das, B. P. (2021). Investigating cost-benefit analysis for digital distribution transformers – Part I. In B. P. Das, TRANSFORMERS MAGAZINE (p. vol.8). New Zealand: University of Canterbury, New Zealand.
Zhouyang Ren1, Y. J. (2021). Probabilistic cost-benefit analysis-based spare transformer strategy incorporating condition monitoring information. IET Generation, Transmission & Distribution, 2.
Rudresh Babu Magadum, S. C. (2022). Cost Benefit Analysis for Distribution Transformer Placement in Electrical Networks. Grenze International Journal of Engineering and
Mojtaba Shirvani, Ahmad Memaripour, Mostafa Abdollahi, Asadollah Salimi. Calculation of generation system reliability index: Expected Energy Not Served. Life Sci J 2012;9(4):3443-3448]. (ISSN: 1097-8135). http://www.lifesciencesite.com. 510.
I.D. Pranowo. (2015). Sistem dan Manajemen Pemeliharaan. Deepublish.
PT PLN (Persero). (2014). Edaran Direksi No. 0017.E/DIR/2014. Metode Pemeliharaan Trafo Distribusi berbasis Kaidah Manajemen Aset.
Moleda, et al. (2023). From Corrective to Predictive Maintenance - A Review of Maintenance Approaches for the Power Industry. MDPI.
Tran et al., (2020). A Review of Health Assessment Techniques for Distribution Transformers in Smart Distribution Grids. MDPI.
Syukri, Muliadi, & Setiawan, T. (2022). Kajian Pemeliharaan Trafo Distribusi Menggunakan Metode Condition Based Maintenance (CBM). Aceh Journal of Electrical Engineering and Technology, 18-23.
Sutaryono, G. L. (2015). Analisa Indeks Kesehatan Transformator Daya Berbasis Neural Network Untuk Mereduksi Jumlah Test Pada Trafo. Master Thesis Jurusan Teknik Elektro Fakultas Teknologi Industri Institut Teknologi Sepuluh Nopember Surabaya.
A, A. N., Jaiswal, G. C., Ballal, M. S., & Tutakne, D. R. (2015). Remote condition monitoring system for distribution transformer. Indian Institute of Technology Kanpur.
Ballal, M. S., Jaiswal, G. C., Tutkane, D. R., Venikar, P. A., Mishra, M. K., & Suryawanshi, H. M. (2017). Online condition monitoring system for substation and service transformers. The Institute of Engineering and Technology, 1187-1195.
Tamma, W. R., Prasojo, R. A., & Suwarno. (2020). High voltage power transformer condition assessment considering the health index value and its decreasing rate. The Institution of Engineering and Technology.
McArthur, S. D., Strachan, S. M., & Jahn, G. (2004). The design of a multi-agent transformer condition monitoring system. IEEE Transactions on Power Systems, 1845-1852.
Sukadana, I. W., Darmawan, K. D., & Sutama, I. W. (2021). Deteksi Dini Gangguan Transformator Berbasis Manajemen Transformator Untuk Meningkatkan Kinerja Operasi dan Finansial Di PT.PLN ULP Singaraja. Jurnal Teknik Elektro Institut Teknologi Padang, 78-85.
Benren Pan et al. (2019). Analysis and Research of Three-phase Unbalance in Distribution Transformers. IOP Conf. Ser.: Earth Environ. Sci. 252 032196.
Alauddin Yousif Al-Omary, dkk. (2006). A new approach of clustering based machine-learning algorithm, science direct.
Daniel Riano Kaparang dan Eko Sediyono. (2013). “Penentuan Alih Fungsi Lahan Marginal Menjadi Lahan Pangan Berbasis Algoritma K-means di Wilayah Kabupaten Boyolali.” JdC. 2. 20.
Ali Bou Nassif, dkk. (2021). Machine Learning for Anomaly Detection: A Systematic Review, Institute of Electrical and Electronics Engineers.
Guanghui Fan, dkk. (2021). Machine Learning Based Quantitative Association Rule Mining Method for Evaluating Cellular Network Performance, Institute of Electrical and Electronics Engineers.
Muhammad Usama, dkk. (2019). Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges, Institute of Electrical and Electronics Engineers.
Razan Abdulhammed, dkk. (2019). Features Dimensionality Reduction Approaches for Machine Learning Based Network Intrusion Detection, Electronics 2019, mdpi.
Chen, T., & Carlos Guestrin. (2016). XGBoost: A Scalable Tree Boosting System. Paper presented at the proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
Suhadi, dkk. (2008). Teknik Distribusi Tenaga Listrik Jilid 1-2. Jakarta : Direktorat Pembinaan Sekolah Menengah Kejuruan, Direktorat Jenderal Manajemen Pendidikan Dasar dan Menengah, Departemen Pendidikan Nasional.
Nasteski, V. (2017). An overview of the supervised machine learning methods. Horizons. b, 4(51-62), 56.
Cunningham, P., Cord, M., & Delany, S. J. (2008). Supervised learning. In Machine learning techniques for multimedia: case studies on organization and retrieval (pp. 21-49). Berlin, Heidelberg: Springer Berlin Heidelberg.
Caruana, R., & Niculescu-Mizil, A. (2006, June). An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd international conference on Machine learning (pp. 161-168).
Khormarudin, A. N. (2016). Teknik data mining: Algoritma K-Means clustering. J. Ilmu Komput, 1-12.
Agatonovic-Kustrin, S., and Beresford, R. (2000). Basic concepts of artificial neural network (ANN) modelling and its application in pharmaceutical research. Pharmaceutical and Biomedical Analysis 22:717727.
Turhan, C., Kazanasmaz, T., Uygun, I.E., Ekmen, K.E., and Akkurt, G.G. (2014). Comparative study of a building energy performance software (KEP-IYTEESS) and ANN-based building heat load estimation. Energy and Buildings 85:115-125.
Vita, et al. (2023.) Predictive Maintenance for Distribution System Operators in Increasing Transformers’ Reliability. MDPI.
Wu et al., (2021). Improved Genetic Algorithm and XGBoost Classifier for Power Transformer Fault Diagnosis. Frontiers in Energy Research.
Raichura et al., (2020). Efficient CNN-XGBoost technique for classification of power transformer internal faults against various abnormal conditions. IET Generation, Transmission & Distribution.
Xing et al., (2022). Health evaluation of power transformer using deep learning neural network. ScienceDirect.
Alqudsi et al., (2019). Application of Machine Learning in Transformer Health Index Prediction. MDPI.
Sudha et al., (2022). Classification of faults in distribution transformer using machine Learning. ScienceDirect.
Bjelic et al., (2023). Machine learning for power transformer SFRA based fault detection. ScienceDirect.
Zeinoddini-Meymand et al., (2016). Health index calculation for power transformers using technical and economical parameters. IET Journals.
Liu et al., (2019). Fault diagnosis of power transformer based on tree ensemble model. IOP Conference Series: Materials Science and Engineering.
Nugraha, R. H. (2022). Analisis Perilaku Pembayaran Rekening Listrik Pelanggan Menggunakan Kombinasi Klaster K-Means Dan Klasifikasi Xgboost Guna Percepatan Pendapatan (Studi Kasus : Pln Ulp Panakkukang). TESIS – BM185407.
Tianqi Chen dan Carlos Guestrin. (2016). XGBoost: Sistem Pendorong Pohon yang Dapat Diskalakan.
Das, B. P. (2021). Investigating cost-benefit analysis for digital distribution transformers – Part I. In B. P. Das, TRANSFORMERS MAGAZINE (p. vol.8). New Zealand: University of Canterbury, New Zealand.
Zhouyang Ren1, Y. J. (2021). Probabilistic cost-benefit analysis-based spare transformer strategy incorporating condition monitoring information. IET Generation, Transmission & Distribution, 2.
Rudresh Babu Magadum, S. C. (2022). Cost Benefit Analysis for Distribution Transformer Placement in Electrical Networks. Grenze International Journal of Engineering and
Published
2025-04-11
Section
Original Articles
Copyright (c) 2025 Aulia Mahdi, Erma Suryani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
