A Two-Level Multisensor Fusion Network With Incremental Learning for Insulation Defect Diagnosis in Gas-Insulated Switchgear
- 28 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (7) , 6337-6348
Abstract
Gas-insulated switchgear (GIS) insulation defect diagnosis faces persistent challenges due to heterogeneous multisensor signals, the lack of structured fusion across sensor types, and severe catastrophic forgetting under source-free streaming conditions. To address these issues, this article proposes a two-level fusion multisensor network with incremental learning (TFMNIL) for on-site diagnosis. Unlike conventional one-stage fusion strategies, the proposed framework separates multisensor fusion into channel-level fusion of homogeneous sensors to preserve consistent physical characteristics, and feature-level fusion of heterogeneous sensors to reduce cross-modal semantic discrepancies and redundancy. To support continual adaptation under evolving operating conditions, an incremental domain adaptation strategy is further developed. It integrates dynamic prototype updating to compensate for feature drift with classifier-weight–anchored cross-domain contrastive alignment, enabling stable class-level supervision without access to source data. Experiments on large-scale real-world multisensor GIS datasets show that TFMNIL achieves a diagnostic accuracy of 95.86% and maintains strong adaptability to newly emerging fault types in practical on-site scenarios.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB2403700)
This publication has 36 references indexed in Scilit:
- Semi-supervised feature contrast incremental learning framework for bearing fault diagnosis with limited labeled samplesApplied Soft Computing, 2025
- CCMnet: A cluster-level contrastive cross-domain framework for GIS insulation defects diagnosisKnowledge-Based Systems, 2025
- Human centric attention with deep multiscale feature fusion framework for activity recognition in Internet of Medical ThingsInformation Fusion, 2023
- MIFDELN: A multi-sensor information fusion deep ensemble learning network for diagnosing bearing faults in noisy scenariosKnowledge-Based Systems, 2023
- Dual-level Deep Evidential Fusion: Integrating multimodal information for enhanced reliable decision-making in deep learningInformation Fusion, 2023
- Semantic alignment with self-supervision for class incremental learningKnowledge-Based Systems, 2023
- Continuous transfer of neural network representational similarity for incremental learningNeurocomputing, 2023
- Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation2022
- Task-incremental broad learning system for multi-component intelligent fault diagnosis of machineryKnowledge-Based Systems, 2022
- Defect recognition and condition assessment of epoxy insulators in gas insulated switchgear based on multi-information fusionMeasurement, 2022