A5086014361- High voltage insulation and dielectric phenomena
- Elevator Systems and Control
- Machine Fault Diagnosis Techniques
- Power Transformer Diagnostics and Insulation
- Blind Source Separation Techniques
- Infrastructure Maintenance and Monitoring
- Image and Signal Denoising Methods
Xi'an Jiaotong University
2021-2022
Distinguishing the types of partial discharge (PD) caused by different insulation defects in gas-insulated switchgear (GIS) is a great challenge power industry, and improving recognition accuracy relevant models one key problems. In this paper, convolutional neural network long short-term memory (CNN-LSTM) model proposed, which can effectively extract utilize spatiotemporal characteristics PD input signals. First, spatial higher-level signals be obtained through CNN network, but because deep...
Partial discharge (PD) is the main feature that effectively reflects internal insulation defects of gas-insulated switchgear (GIS). It great significance to diagnose types faults by recognizing PD ensure normal operation GIS. However, traditional diagnosis method based on single information analysis has a low recognition accuracy PD, and there are differences in effect various defects. To make most rich state contained we propose novel multi-information ensemble learning for pattern...
Abstract Partial discharge (PD) detection is essential in assessing the insulation state of electrical equipment. However, PD signals are often overwhelmed by interference, resulting inaccurate results. Aiming at this problem, study proposes a method based on singular value decomposition (SVD) and improved spectral subtraction. First, test signal constructed as Hankel matrix, which used trajectory matrix for SVD. Next, mutation point feature set threshold removing narrowband interference...
Accurate and reliable fault analysis is essential to improve the performance of gas-insulated switchgear (GIS) ensure safe stable operation power system. Advances in perception measurement technology primary equipment have increased scale GIS data. Driven by massive samples, deep learning has brought new opportunities for identification intelligence diagnosis. As an unsupervised method, stacked autoencoder (SAE) can automatically extract representative expressions in-depth features from...
Partial discharge diagnosis is considered as an important means to diagnose the insulation state of gas insulated switchgear (GIS). Aiming at non-stationary characteristics partial (PD) signals, a feature extraction method based on variational mode decomposition (VMD) and multi-scale permutation entropy (MPE) proposed. Firstly, VMD used decompose PD signal, multiple intrinsic modal functions are obtained; Then, MPE each component calculated eigenvector. Finally, input into SVM vector for...