article · IEEE Transactions on Dielectrics and Electrical Insulation
Partial discharge serves as an important early sign of insulation wear in high-voltage rotating electrical machines. Manufacturing flaws and operational stresses can trigger discharge activity within stator windings, accelerating the breakdown of insulation. Because of the winding geometry, multiple discharge sources frequently occur together, producing distinct phase-resolved patterns that overlap. These overlapping signals cause visual suppression, occlusion, and distortion that hinder standard classification tools. To address this, a deep learning method using Detection Transformers was developed alongside a flattening augmentation technique designed to mimic pattern distortions. The global self-attention mechanism reduces the masking of weaker signals by dominant discharges. Evaluated on a dataset containing six defect types across 63 combinations, the model reached 97.4 percent accuracy for single-source defects and 90.9 percent for multisource scenarios, achieving an overall accuracy of 93.7 percent.
Insulation failure in large electrical machinery can lead to unexpected breakdowns and costly power interruptions. By accurately identifying multiple overlapping discharge defects early, maintenance teams can diagnose deteriorating machine insulation before severe operational failures occur.
This software technique could be integrated into diagnostic tools used by machine operators, maintenance engineers, and asset managers monitoring high-voltage rotating equipment. Tested on a dataset spanning 63 defect combinations, the technology represents applied research that has undergone diagnostic evaluation, though the abstract does not indicate immediate commercial deployment or field integration.
AI-generated from the published abstract. Always read the original work before citing.
Partial discharge (PD) is a critical early indicator of insulation degradation in high-voltage rotating machines. Minor undetected defects during manufacturing, combined with operational stresses, often trigger PD activity that accelerates insulation aging. The elongated structure of stator windings increases the possibility of multiple PD sources occurring simultaneously, each generating a distinct Phase-Resolved Partial Discharge (PRPD) pattern. However, when multiple defects are present, these patterns overlap, leading to challenges such as occlusion, nesting, and the Multisource Partial Discharge Horizontal Flattening Effect (MPD-HFE), where weaker discharges are visually suppressed, which challenge conventional classifiers due to signal occlusion and distortion effects. This work proposes a Detection Transformer (DETR)–based deep learning approach, enhanced with flattening augmentation to replicate dominant pattern distortions. The method enables simultaneous detection and classification of overlapping PRPD patterns by utilizing DETR’s global self-attention to mitigate discharge dominance and feature suppression. Evaluated on a multisource PRPD dataset comprising six defect types and 63 class combinations, the proposed model achieved 97.4% accuracy on single-source PD defects and 90.9% on multisource cases, with an overall accuracy of 93.7%.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/tdei.2025.3648258
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
