Résumé

Transformer health analysis using Dissolved Gas Analysis is crucial for diagnosing powertransformer faults. This paper proposes an innovative approach to diagnose powertransformer faults by integrating machine learning algorithms with Ensemble techniques.The method involves fusing reduced dimensional input features through PrincipalComponent Analysis with Ensemble techniques such as Bagging, Decorate, and Boost-ing. Various machine learning algorithms, including Decision Tree (DT), K‐NearestNeighbours, Radial Basis Function Network, and Support Vector Machine, areemployed in conjunction with Ensemble techniques. The long short‐term memory al-gorithm was used to create synthetic data to solve the issue of data imbalance. A datasetof 683 samples is used in the study for training, testing, validation, and comparison withcurrent techniques. The results highlight the effectiveness of Ensemble techniques,particularly Boosting, which demonstrates superior performance across all classificationalgorithms. The Boosting with DT algorithm achieves an impressive accuracy of 98.32%,surpassing alternative methods. In validation, the proposed Boosting Ensemble techniqueoutperforms various approaches, showcasing its diagnostic accuracy and superiority overalternative methods. The research emphasises the model\'s effectiveness in smoothinginput vectors, enhancing harmony with ensemble techniques, and overcoming limitationsin prior methods

Information

Item Type:	Journal
Divisions:	» Laboratoire de Recherche en Électromécanique et Sûreté de Fonctionnement » Faculté des Sciences et de la Technologie
ePrint ID:	5236
Date Deposited:	2024-12-08
Further Information:	Google Scholar
URI:	https://www.univ-soukahras.dz/fr/publication/article/5236

BibTex