Small-Sample Partial Discharge Diagnosis for GIS Based on Improved Capsule Generative Adversarial Network and Dual-Mode Generator Optimization
- 10 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 33 (2) , 1529-1538
Abstract
Data-driven deep learning methods excel in gas insulated switchgear (GIS) partial discharge (PD) diagnosis, but their performance falters in data-scarce scenarios. Constrained by the intricate operating environment of GIS and the transient and stochastic nature of PD, acquiring sufficient PD samples in practical applications remains challenging. Therefore, this paper proposes an improved capsule generative adversarial network (GAN) for small-sample GIS PD diagnosis. Firstly, capsule network is introduced in both the generator and the discriminator to extract more comprehensive feature information from PD signals, thus avoiding the potential loss of crucial features due to pooling operations. Then, a dual-mode optimization method is used to update the model parameters of the generator, and sample quality and diversity are used as evaluation indicators to guide the training process of the generator, realizing automatic optimization of generator parameter-level model construction. Meanwhile, the discriminator stabilizes the GAN training by adopting the Wasserstein distance and incorporating a gradient penalty term. Experimental results show that the proposed method achieves diagnostic accuracy of 97.47% in small datasets, significantly outperforming other methods and exhibiting robust performance, provides a viable solution for high-precision and robust GIS PD diagnosis with limited samples.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB2403700)
This publication has 30 references indexed in Scilit:
- Imbalanced data augmentation for pipeline fault diagnosis: A multi-generator switching adversarial networkControl Engineering Practice, 2023
- WGAN-CL: A Wasserstein GAN with confidence loss for small-sample augmentationExpert Systems with Applications, 2023
- Multi-source partial discharge diagnosis in gas-insulated switchgear via zero-shot learningMeasurement, 2023
- A Novel Small Samples Fault Diagnosis Method Based on the Self-attention Wasserstein Generative Adversarial NetworkNeural Processing Letters, 2023
- Mechanical fault intelligent diagnosis using attention-based dual-scale feature fusion capsule networkMeasurement, 2022
- A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearboxISA Transactions, 2022
- Novel metric-based meta-learning model for few-shot diagnosis of partial discharge in a gas-insulated switchgearISA Transactions, 2022
- Data-augmented wavelet capsule generative adversarial network for rolling bearing fault diagnosisKnowledge-Based Systems, 2022
- Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new frameworkAdvanced Engineering Informatics, 2022
- Conditional Wasserstein generative adversarial network-gradient penalty-based approach to alleviating imbalanced data classificationInformation Sciences, 2020