Diagnosis of Power Transformer Condition using Dissolved Gas Analysis Technique: Case Studies at Geothermal Power Plants In Indonesia

Prasojo, Rahman Azis; Tamma, Winanda Riga; Mahendrayana, I Gusti Ngurah; Suwarno, &

doi:10.1109/ichveps47643.2019.9011106

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DGA (Dissolved Gas Analysis) is a transformer diagnostic method that is often done by utilities by looking at the gas condition in the insulating oil [2]. Utilities use the DGA test to schedule maintenance for transformers, check status of new and repaired units, and get the latest information about transformer conditions [3]. Generally, faults on power transformers are classified into two types, which are electrical faults like discharge and arcing, the other type is thermal faults (high and low thermal).…”

Section: Introductionmentioning

confidence: 99%

Mixture of Faults Identification on Power Transformers Using Multi-Method Dissolved Gas Analysis

Prasojo

Putra

Neelmani

2022

IJFTE

View full text Add to dashboard Cite

Utilities rely on the various Dissolved Gas Analysis (DGA) interpretation methods to identify incipient fault within power transformers. However, confusion often arises due to the use of different DGA methods which can have different results or fail to detect mixture of faults (multiple faults). This paper implements the combination of Duval Triangle and Duval Pentagon as one of the most consistent methods to do fault identification based on DGA. Recent historical DGA data of generator step up high voltage power transformers and other several previously published historical data were collected and analyzed. This article aims to assist transformer asset manager in detecting mixture of faults using multi method. The use of combined Duval triangle and Pentagon method is done in accordance to the guideline in IEEE C57.104-2019.

show abstract

Section: Introductionmentioning

confidence: 99%

Mixture of Faults Identification on Power Transformers Using Multi-Method Dissolved Gas Analysis

Prasojo

Putra

Neelmani

2022

IJFTE

View full text Add to dashboard Cite

show abstract

“…Several other past researches suggested using improved decision tree-based machine learning algorithms over conventional DGA methods [10][11][12][13]. However, a clear research gap exists in combining the predictions from a group of ensemble tree-based predictors to improve accuracy.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Machine Learning Methods for better Dynamic Assessment of Transformer Status

Ghosh

Dutta

2021

J. Inst. Eng. India Ser. B

View full text Add to dashboard Cite

Analyzing dissolved gases in the transformer's mineral oil helps to detect and classify the systemic faults in electric power transformers. Formerly, empirical methods such as Rogers ratio, Duval triangles 1-4-5, and pentagons 1-2 were used for transformer fault classification. Loose fit for every transformer type is one of the most prominent disadvantages of conventional methods. Formulating robust machine learning algorithms, such as the decision trees, can significantly overcome the loose fit issue. This paper focuses on implementing four different decision tree algorithms, including a regular decision tree classifier, a bagging classifier, a boosting classifier, and a stacking classifier to classify six different transformer fault types distinctly. Further, this study shows that the efficacy and accuracy of the four mentioned classifiers could be far exceeded when combined using a wisdom of the crowd approach. The wisdom of the crowd approach essentially merges the predicted classes from the four individual classifiers and decides on the final prediction via a hardvoting routine. The computational evaluation revealed that the given voting approach could significantly improve power transformers' online diagnostic accuracy up to 91%, thus aiding early forecast of power transformers' preventive maintenance.

show abstract

Diagnosis of Power Transformer Condition using Dissolved Gas Analysis Technique: Case Studies at Geothermal Power Plants In Indonesia

Cited by 2 publications

References 12 publications

Mixture of Faults Identification on Power Transformers Using Multi-Method Dissolved Gas Analysis

Mixture of Faults Identification on Power Transformers Using Multi-Method Dissolved Gas Analysis

Ensemble Machine Learning Methods for better Dynamic Assessment of Transformer Status

Contact Info

Product

Resources

About