전력 설비 부분방전 진단용 준지도 학습 기법 연구 = Semi-Supervised Learning for Partial Discharge Diagnosis in Power Equipment

다국어 초록 (Multilingual Abstract)

Partial discharge (PD) detection and classification are essential to ensure the reliability of gas-insulated switchgear (GIS). However, conventional deep learning approaches require extensive labeled data, which are expensive and time-consuming to obtain. To address this challenge, we propose a novel semi-supervised learning (SSL) framework called CDMAD-SSL, which integrates class distribution mismatch-aware debiasing (CDMAD) into the SSL pipeline. By refining the pseudo-labels through classifier bias correction during both training and testing, the proposed method mitigates the class imbalance and distribution mismatch—two critical challenges that hinder practical PD monitoring. The experimental results demonstrate that CDMAD-SSL achieves an overall classification accuracy of 96.64%, outperforming benchmark SSL methods by up to 2.52%, while maintaining robust precision, recall, and F1 score across all fault types. Furthermore, the framework consistently improved the recognition of minority classes under skewed data distributions, thereby validating its effectiveness under realistic onsite conditions

Keywords: Partial Discharge (PD), Gas-insulated Switchgear (GIS), Semi-Supervised Learning (SSL), Pseudo-Label Refinement, Class Imbalance, Distribution Mismatch, CDMAD

목차 (Table of Contents)

• I. Introduction 1
• 1. Background & Motivation 1
• 2. Partial discharge monitoring & Challenges 2
• 3. Deep learning and Semi-supervised learning approaches 2
• 4. The main contributions of our study 7
• Abbreviations 9
• II. Fault Simulation Experiments 10
• 1. Experiment Setup 10
• 2. PRPD and Online noise analysis 13
• III. Proposed Method 18
• 1. Problem Formulation 18
• 2. Semi-supervised learning framework 20
• IV. Performance Evaluation 28
• 1. Network Architecture and Hyperparameter Optimization 28
• 2. Experimental results 32
• 3. Ablation Studies 40
• V. Conclusion and Discussion 42