| Autor: |
Fei Jiao, Zhenyuan Ma, Qikun Chen, Fengda Zhang, Dezong Zhao |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Frontiers in Energy Research, Vol 12 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2296-598X |
| DOI: |
10.3389/fenrg.2024.1340421 |
| Popis: |
Extensive research validates the effectiveness of employing Dissolved Gas Analysis (DGA) for diagnosing electric power transformer failures. However, a significant portion of existing research focuses on static data for classifying failure types, lacking a thorough exploration of causality. This study proposes an approach integrating causality and the DGA framework to infer power transformer failures. Validation through 96 historical samples from diverse transformers demonstrates the capability of this method to identify probable abnormal failures of the power transformer accurately. The proposed causal reasoning method is able to diagnose all common transformer states, accounting for the level of severity in both electrical and thermal failures, and with an accuracy of 95.8%. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
