An Improved Transformer Early Fault Identification Method Integrating CBAM-SV2 and GAF
Source abstract
Abstract
Transformers are core equipment in power systems, and their failure may cause severe accidents. Dissolved gas analysis (DGA) is one of the dominant techniques for fault diagnosis of oil-immersed transformers. To achieve lightweight design and high identification efficiency, this paper proposes an early fault identification method for transformers based on the integration of the Convolutional Block Attention Module-enhanced ShuffleNetV2 (CBAM-SV2) model and Gramian Angular Field (GAF). First, hybrid oversampling is used for data preprocessing. Then, the preprocessed one-dimensional gas data are converted into dual-channel two-dimensional images via GAF as the input of the classification network. Finally, a CBAM-SV2 model integrating deep convolutional networks and attention mechanisms is constructed, which combines the lightweight advantage of ShuffleNetV2 and the powerful feature representation ability of the Convolutional Block Attention Module (CBAM). Feature extraction and classification are performed by the CBAM-SV2 model to output the identification results. Additionally, t-distributed Stochastic Neighbor Embedding (t-SNE) and a confusion matrix are used to visualize classification performance for intuitive evaluation of the network’s effectiveness. The experimental results show that, compared with other mainstream algorithms, the proposed method achieves higher recognition accuracy in transformer early fault classification under imbalanced data conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Power Transformer Diagnostics and Insulation · Power Systems Fault Detection · Islanding Detection in Power Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China
State Grid Shanxi Extra High Voltage Substation Company, Taiyuan 030032, China
Funding
Shanxi Province Basic Research Program · Taiyuan City “Open Call for Leaders” Project for Tackling Key Core Technologies · Special Fund for Science and Technology Innovation Teams of Shanxi Province
References (34)
Show source-provided references
1. A new approach to identify power transformer criticality and asset management decision based on dissolved gas-in-oil analysis10.1109/TDEI.2012.6215106 ↗
2. Graphical shape in Cartesian plane based on dissolved gas analysis for power transformer incipient faults discrimination10.1109/TDEI.2024.3404365 ↗
3. Development of a new graphical technique for dissolved gas analysis in power transformers based on the five combustible gases10.1109/TDEI.2015.004999 ↗
4. Two graphical shapes based on DGA for power transformer fault types discrimination10.1109/TDEI.2021.009415 ↗
5. A fuzzy dissolved gas analysis method for the diagnosis of multiple incipient faults in a transformer10.1109/59.867146 ↗
6. (2009). IEEE Guide for the Interpretation of Gases Generated in Oil-Immersed Transformers (Standard No. IEEE Std C57.104-2008 (Revision of IEEE Std C57.104-1991)).
7. Rethinking shallow and deep learnings for transformer dissolved gas analysis: A review10.1109/TDEI.2025.3526080 ↗
8. Hybrid DGA method for power transformer faults diagnosis based on evolutionary k-means clustering and dissolved gas subsets analysis10.1109/TDEI.2023.3275119 ↗
9. Dissolved gas analysis for power transformer fault diagnosis based on deep zero-shot learning10.1109/TDEI.2024.3469913 ↗
10. Fault diagnosis of power transformers using graph convolutional network
11. A Gramian angular field for constructing graph-based GNNs and its applications in rolling bearing defect detection10.1109/JSEN.2024.3458409 ↗
12. GAF-PCNN: A multisensor fusion navigation integrity monitoring method based on Gramian angular field and parallel CNN10.1109/JSEN.2024.3518481 ↗
13. GAF-MAE: A self-supervised automatic modulation classification method based on Gramian angular field and masked autoencoder10.1109/TCCN.2023.3318414 ↗
14. A multifault testing method for TSVs based on GAF-DRSN and mirror constant current source structure10.1109/TCPMT.2024.3456228 ↗
15. Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases10.1109/57.917529 ↗
16. Research on early fault identification of cables based on the fusion of MTF-GAF and multi-head attention mechanism features10.1109/ACCESS.2024.3401254 ↗
17. Application of deep feature learning with Gram’s angle field for trace gas concentration identification
18. Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018). ShuffleNet V2: Practical guidelines for efficient CNN architecture design. Proceedings of the European Conference on Computer Vision, Springer.10.1007/978-3-030-01264-9_8 ↗
19. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–23). ShuffleNet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
20. Ba, J., Mnih, V., and Kavukcuoglu, K. (2014). Multiple object recognition with visual attention. arXiv.
21. Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., and Bengio, Y. (2015). Show, attend and tell: Neural image caption generation with visual attention. arXiv.
22. Squeeze-and-excitation networks10.1109/TPAMI.2019.2913372 ↗
23. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13–19). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
24. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018). CBAM: Convolutional block attention module. arXiv.10.1007/978-3-030-01234-2_1 ↗
25. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
26. A study of the behavior of several methods for balancing machine learning training data10.1145/1007730.1007735 ↗
27. Toma, M. (2025). SMOTE vs. SMOTEENN: A study on the performance of resampling algorithms for addressing class imbalance in regression models. Algorithms, 18.10.3390/a18010037 ↗
28. Han, H., Wang, W.Y., and Mao, B.H. (2005). Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. Advances in Intelligent Computing, Springer.10.1007/11538059_91 ↗
29. He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China.
30. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–23). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
31. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
32. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
33. Wang, T., Li, Q., Yang, J., Xie, T., Wu, P., and Liang, J. (2023). Transformer Fault Diagnosis Method Based on Incomplete Data and TPE-XGBoost. Appl. Sci., 13.10.3390/app13137539 ↗
34. Temporal–contextual self-supervised time-series learning for automated fault detection and diagnosis of air handling units in buildings10.1016/j.buildenv.2026.114300 ↗