Transformer Fault

Transformer fault diagnosis is crucial for maintaining reliable power grid operation, focusing on accurately predicting and identifying faults before catastrophic failures occur. Current research emphasizes leveraging advanced data analytics, including deep learning models like convolutional neural networks (CNNs) and gradient boosting decision trees (GBDTs), to analyze diverse data sources such as multichannel sensor readings and dissolved gas analysis (DGA). These methods aim to improve diagnostic accuracy, particularly when dealing with limited fault data, thereby enhancing power system reliability and reducing maintenance costs. The integration of knowledge graphs is also emerging as a promising approach to improve the efficiency and interpretability of fault prediction models.

Papers

February 11, 2024

Power Transformer Fault Prediction Based on Knowledge Graphs
Chao Wang, Zhuo Chen, Ziyan Zhang, Chiyi Li, Kai Song
Knowledge Graph Limited Fault Power Transformer Transformer Fault

October 11, 2023

Multichannel consecutive data cross-extraction with 1DCNN-attention for diagnosis of power transformer
Wei Zheng, Guogang Zhang, Chenchen Zhao, Qianqian Zhu
Transformer Based Medical Diagnosis Multi Channel Input Transformer Fault

April 24, 2023

The State of the Art in transformer fault diagnosis with artificial intelligence and Dissolved Gas Analysis: A Review of the Literature
Yuyan Li
Artificial Intelligence Narrative Review Internal State Deep Learning Algorithm Power System Transformer Fault

Transformer Fault

Papers

Power Transformer Fault Prediction Based on Knowledge Graphs

Multichannel consecutive data cross-extraction with 1DCNN-attention for diagnosis of power transformer

The State of the Art in transformer fault diagnosis with artificial intelligence and Dissolved Gas Analysis: A Review of the Literature