A5004218725- High voltage insulation and dielectric phenomena
- Power System Reliability and Maintenance
- Infrastructure Maintenance and Monitoring
- Smart Grid and Power Systems
- Elevator Systems and Control
- Advanced Computational Techniques and Applications
- High-Voltage Power Transmission Systems
- Power Systems and Technologies
- Geoscience and Mining Technology
- Machine Fault Diagnosis Techniques
- Power Transformer Diagnostics and Insulation
- Vacuum and Plasma Arcs
- Combustion and Detonation Processes
- Geological Modeling and Analysis
Institute of Electrical Engineering
2024
Xi'an Jiaotong University
2023-2024
State Key Laboratory of Electrical Insulation and Power Equipment
2023-2024
Abnormal discharge in gas-insulated switchgear (GIS) is a key cause of insulation failure, and it also an external manifestation defects. Sensitive source localization important goal GIS partial (PD) monitoring. However, most existing PD methods rely on time-delay estimation, which not only requires high-precision synchronous sampling device but suffers from serious interference. To this end, collaborative domain adaptation network (CDAN) proposed for localization. First, squeezing wavelet...
High-voltage circuit breakers (HVCBs) handle the important tasks of controlling and safeguarding electricity networks. In case insufficient data samples, improving accuracy traditional HVCB mechanical fault diagnosis method is difficult, so it poses challenges in meeting performance requirements for diagnosis. this study, a introduced. It utilizes combination grey wolf optimization (GWO) multi-grained cascade forest (gcForest) algorithms to resolve these issues improve To simplify original...
With the rapid development of deep learning, its powerful capabilities make it possible to perform mechanical fault diagnosis high-voltage circuit breakers (HVCBs). Among learning approaches, convolutional neural network is widely used. However, while can extract features effectively, also has some limitations. Specifically, depends on a large number training data and only takes information into account without considering structural information. These shortcomings lead unused unsatisfactory...
Deep learning methods, especially convolutional neural networks (CNNs), have achieved good results in the partial discharge (PD) diagnosis of gas-insulated switchgear (GIS) laboratory. However, relationship features ignored CNNs and heavy dependance on amount sample data make it difficult for model developed laboratory to achieve high-precision, robust PD field. To solve these problems, a subdomain adaptation capsule network (SACN) is adopted GIS. First, feature information effectively...
In recent years, convolutional neural networks (CNNs) have achieved worth seeing results in mechanical fault diagnosis of high-voltage circuit breakers (HVCBs) due to their powerful classification capabilities. However, the discrepancy vibration signals different voltage levels and types HVCBs, it is difficult for model developed on one dataset be generalized deployed all scenarios, especially case small samples field. To this end, paper proposes a method HVCB based meta-learning (ML)...