Electrochemical Coupled Federated Multisensor Measurement Framework for GIS Insulation Fault Detection and Diagnosis

Le résumé fourni par la source

Accurate insulation fault diagnosis in gas-insulated substations (GISs) is hindered by the limited sensitivity of single-sensor systems and the heterogeneity of field data. To enhance both measurement sensitivity and detection reliability of GIS insulation faults, this paper proposes an electro-chemical coupled federated multi-sensor fusion network (FMSFN) that integrates multi-modal sensing and distributed analytics into a unified measurement system. The proposed framework introduces a novel electro-chemical coupled detection mechanism that jointly captures electrical discharge characteristics and gas-chemical decomposition signatures to enable homogeneous and heterogeneous feature fusion under a federated cloud–edge architecture. This design supports distributed, privacy-preserving fault diagnosis across multiple users and devices. Within the proposed FMSFN, a deep fusion network equipped with an adaptive hybrid attention module is employed to strengthen cross-sensor feature interaction and enable dynamic modality-aware weighting, while a federated hierarchical optimization strategy with personalized updates and noise-aware aggregation ensures stable and robust convergence under non-IID data distributions. Experimental results demonstrate that the FMSFN achieves 97.23% accuracy and a 96.83% macro F1-score, consistently outperforming existing single-sensor and centralized diagnostic models. These results confirm the robustness, scalability, and practical applicability of the proposed electrochemical-coupled measurement system, which provides a scalable instrumentation approach for GIS insulation fault diagnosis.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.