From limited data to reliable diagnosis: an interpretable deep learning framework for transformer fault analysis

Lin, Jiajian and Yeo, Lit Yen and Afrouzi, Hadi Nabipour and Ektesabi, Mehran Motamed and Tavalaei, Jalal (2025) From limited data to reliable diagnosis: an interpretable deep learning framework for transformer fault analysis. International Journal of Electrical Power & Energy Systems, 172. p. 111227. ISSN 0142-0615

Preview

Text 1-s2.0-S0142061525007756-main.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (7MB)

Abstract

The reliable diagnosis of power transformer faults is important for ensuring the safety and stability of modern power systems. However, existing fault identification techniques suffer from limited diagnostic accuracy due to insufficient feature representation, inadequate handling of data imbalance in Dissolved Gas Analysis datasets, and suboptimal model generalization. Furthermore, the absence of comprehensive theoretical investigations into the underlying fault mechanisms and model interpretability has significantly constrained the development of robust and explainable diagnostic frameworks. To address these problems, the GAN-CNN-BiLSTM-Attention-GOOSE framework was proposed to overcome the limitations of traditional transformer fault diagnosis, address data scarcity challenges and provide new avenues for future transformer protection research. In this study, an attention-based deep learning model was developed to improve the accuracy and reliability of transformer fault diagnosis. To figure out the limitations posed by insufficient data, a generative adversarial network was introduced to enrich the training samples. A GOOSE optimization algorithm was employed to fine-tune the learning process and enhance overall performance. This integrated approach yielded higher classification accuracy compared to conventional methods. To further interpret the model’s predictions, an explainability technique was applied to analyze the input gas data. The analysis revealed clear patterns linking specific gas compounds in transformer oil to operational faults. In particular, two key indicators, C2H2 and C2H4, were found to be strongly associated with high-energy arcing and thermal faults, respectively. These findings highlight the importance of adequate training data and careful model calibration in achieving accurate and interpretable fault identification.

Item Type:	Article
Identification Number:	10.1016/j.ijepes.2025.111227
Dates:	Date Event 30 September 2025 Accepted 8 October 2025 Published Online
Uncontrolled Keywords:	Power Transformer, Fault Diagnosis, Generative Adversarial Networks, Goose Optimization, Attention Mechanism
Subjects:	CAH10 - engineering and technology > CAH10-01 - engineering > CAH10-01-01 - engineering (non-specific)
Divisions:	Architecture, Built Environment, Computing and Engineering > Engineering
Depositing User:	Gemma Tonks
Date Deposited:	30 Apr 2026 15:20
Last Modified:	30 Apr 2026 15:20
URI:	https://www.open-access.bcu.ac.uk/id/eprint/17015

Actions (login required)

View Item