Attention-Driven Contrastive Learning for the Identification of Rare Partial Discharge Signal in GIS
Abstract
Gas-insulated switchgear (GIS) is a critical component in high-voltage power transmission systems, where partial discharge (PD) activity can indicate early-stage insulation defects. However, phase-resolved partial discharge (PRPD)-based fault diagnosis remains challenging due to noisy signals, perturbed measurement conditions, and severe class imbalance, particularly for rare floating-electrode defects. This study proposes an attention-driven contrastive learning framework for rare PD signal identification in GIS. PRPD data are represented as two-dimensional density matrices derived from phase angle, discharge magnitude, and occurrence count. The proposed framework applies PRPD-specific data augmentation, followed by ResUNet-based denoising, CBAM-based feature refinement, and supervised contrastive learning to improve feature separability among PD classes. The framework was evaluated using a public 550 kV GIS PRPD dataset containing corona-type, surface-type, floating-electrode-type, and noise classes. The results show that augmentation substantially improved robustness. When trained with raw data, the proposed model achieved 91.90% accuracy and 53.81% F1-score under the original test scenario, but decreased to 48.76% accuracy and 46.26% F1-score under IEC-perturbed testing. After augmentation, the model achieved 98.24% accuracy and 96.58% F1-score under the original scenario, and maintained 97.44% accuracy and 97.76% F1-score under IEC perturbation. These findings indicate that the proposed framework supports robust PRPD representation learning for GIS PD diagnosis under perturbed and imbalanced conditions.
References
Abubakar, A., & Zachariades, C. (2024). Phase-resolved partial discharge pattern recognition using image processing template matching. Sensors, 24(11), 3565. https://www.mdpi.com/1424-8220/24/11/3565
CIGRE Working Group D1.66. (2024). Requirements and application of UHF PD monitoring systems for gas insulated systems (Technical Brochure 933). CIGRE. https://www.e-cigre.org/publications/detail/933-requirements-and-application-of-uhf-pd-monitoring-systems-for-gas-insulated-systems.html
Dalila, R. A. M., & Turkben, A. K. (2025). Artificial intelligence based partial discharge detection using CNN and KNN to increase the quality of electrical insulation. Discover Computing, 28, Article 101. https://doi.org/10.1007/s10791-025-09624-z
Dang, NQ., Kim, YH., Ho, TT., Vo Nguyen, Youn, Choi. (2024). Supervised contrastive learning for fault diagnosis based on phase-resolved partial discharge in gas-insulated switchgear. Energies, 17(1), Article 4. https://doi.org/10.3390/en17010004
Du, X., Zhang, Y., Wang, H., & Li, J. (2024). Partial discharge data augmentation and pattern recognition method based on DAE-GAN. Algorithms, 17(11), Article 487. https://doi.org/10.3390/a17110487
Guo, Y., Dai, J., & Zhang, J. (2025). Few-shot cross-domain fault diagnosis via adversarial meta-learning. Scientific Reports, 15, Article 41876. https://doi.org/10.1038/s41598-025-25854-z
He, S., Yu, M., Yang, Z., & Lei, B. (2024). Transformer partial discharge recognition based on phase-preserving data augmentation. In 2024 6th International Conference on Energy, Power and Grid (ICEPG). IEEE. https://ieeexplore.ieee.org/document/10775399/
Hu, D., Chen, Z., & Yang, W. (2022). Partial discharge pattern recognition of GIS based on CBAM-ResNet. In Proceedings of the 2022 4th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI ’22). Association for Computing Machinery. https://doi.org/10.1145/3584376.3584474
Hu, D., Chen, Z., Yang, W., Zhu, T., Ke, Y., & Yin, K. (2023). A GIS partial discharge pattern recognition method based on improved CBAM-ResNet. Journal of Electrical and Computer Engineering, 2023, Article 9948438. https://doi.org/10.1155/2023/9948438
Jing, Q., Yan, J., Wang, Y., Huang, J., Xiao, H., Ding, R., et al. (2025). A novel small-sample diagnosis method for GIS partial discharge by transfer robust support matrix machine. Measurement, 255, Article 118054. https://doi.org/10.1016/j.measurement.2025.118054
Mier, C., Mor, A. R., & Vaessen, P. (2024). A directional coupler for partial discharge measurements in gas-insulated substations. Measurement, 225, Article 113996. (https://doi.org/10.1016/j.measurement.2023.113996)
Shang, H., Zhao, Z., Zhang, R., Wang, Z., & Li, J. (2024). Transformer partial discharge fault diagnosis based on improved adaptive local iterative filtering-bidirectional long short-term memory. IET Electric Power Applications, 18(10), 1214–1232. https://doi.org/10.1049/elp2.12471
Tai, H. T., Youn, Y. W., Choi, H. S., & Kim, Y. H. (2025). Partial discharge diagnosis using semi-supervised learning and complementary labels in gas-insulated switchgear. IEEE Access. https://ieeexplore.ieee.org/document/10945843/
Wang, Y., Yan, J., Yang, Z., Qi, Z., Wang, J., & Geng, Y. (2023). A novel hybrid meta-learning for few-shot gas-insulated switchgear insulation defect diagnosis. Expert Systems with Applications, 233, 120956. https://doi.org/10.1016/j.eswa.2023.120956
Wu, Z. (2020). Source database for machine-learning-based PD pattern recognition in GIS [Data set]. Mendeley Data. https://data.mendeley.com/datasets/cz8gwg9d2v/1
Xiao, Y., Yin, H., Wang, S.-H., & Zhang, Y.-D. (2021). TReC: Transferred ResNet and CBAM for detecting brain diseases. Frontiers in Neuroinformatics, 15, 781551. https://doi.org/10.3389/fninf.2021.781551
Zhao, Q., Ding, Y., Gong, M., Tao, L., Ning, G., Ma, J., & Lu, C. (2025). Semi-supervised contrastive fault diagnosis with uncertainty-aware and performance-guided adaptive thresholds under limited labeled and imbalanced data. ISA Transactions, 167, 1191–1206. https://doi.org/10.1016/j.isatra.2025.10.038
Zheng, S., Liu, J., & Zeng, J. (2025). A partial discharge pattern recognition method based on multi-scale adaptive denoising network and stacking ensemble learning. Electric Power Systems Research, 241, Article 111392. https://doi.org/10.1016/j.epsr.2024.111392
