Smart Trafo: A Random Forest and LLM-Based Decision Support System for Power Transformer Fault Diagnosis via Dissolved Gas Analysis
Jurnal Ilmiah Informatika dan Komputer · 01.06.2026 · 3 (1) · 1-10
DOI: 10.69533/informatech.volume3number1.511 ↗Kurz gefasst
Fachartikel in der Zeitschrift Jurnal Ilmiah Informatika dan Komputer, online erschienen am 01.06.2026. Verfasst von Jeremia David Anthony Paduli und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Manual management of Dissolved Gas Analysis (DGA) data for power transformers at PT. PLN (Persero) UPT Manado has been identified as a critical operational bottleneck, with existing spreadsheet-based workflows susceptible to human error, poor historical traceability, and limited scalability. Prior studies on DGA-based transformer diagnosis have been predominantly confined to standalone classification models without integration into operational management systems, leaving a significant gap in practical field deployment. This research contributes a novel integrated Decision Support System named Smart Trafo, which is the first to combine a Random Forest classification model, Duval Pentagon visualization, historical trending analysis, and an LLM-based conversational assistant (Volty AI) within a unified full-stack web platform. The Random Forest model was trained on 375 DGA samples across six fault classes using five gas parameters conforming to IEEE C57.104, achieving an overall accuracy of 84% and a macro-average F1-score of 0.83. Feature importance analysis revealed Hydrogen (H₂) as the dominant diagnostic indicator at 26.2%. The system successfully automates DGA fault classification, eliminates manual calculation errors, and provides real-time technical recommendations, thereby enabling more efficient and data-driven preventive maintenance decisions at PT. PLN (Persero) UPT Manado.
Zitieren
APA
Paduli, J. D. A., Kaligis, J. G., Yusupa, A., & Rindengan, Y. (2026). Smart Trafo: A Random Forest and LLM-Based Decision Support System for Power Transformer Fault Diagnosis via Dissolved Gas Analysis. Jurnal Ilmiah Informatika dan Komputer, 3(1), 1-10. https://doi.org/10.69533/informatech.volume3number1.511
Vancouver
Paduli JDA, Kaligis JG, Yusupa A, Rindengan Y. Smart Trafo: A Random Forest and LLM-Based Decision Support System for Power Transformer Fault Diagnosis via Dissolved Gas Analysis. Jurnal Ilmiah Informatika dan Komputer. 2026;3(1):1-10. doi:10.69533/informatech.volume3number1.511
BibTeX
@article{Paduli2026,
author = {Paduli, Jeremia David Anthony and Kaligis, Jonathan Gabrillio and Yusupa, Ade and Rindengan, Yaulie},
title = {Smart Trafo: A Random Forest and LLM-Based Decision Support System for Power Transformer Fault Diagnosis via Dissolved Gas Analysis},
journal = {Jurnal Ilmiah Informatika dan Komputer},
year = {2026},
volume = {3},
number = {1},
pages = {1--10},
doi = {10.69533/informatech.volume3number1.511}
}
EUVIMED