Time-frequency Domain Monitoring Method for the Fault of HTS HVDC Systems Based on AI Classifiers

Since high-temperature superconductor (HTS) based HVDC systems are affected by temperature and cooling system performance, noise, the monitoring system which can classify the temporal disturbance and anomalies must be developed to ensure stable system operation. To solve this, it needs anomaly detec...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on applied superconductivity Ročník 33; číslo 5; s. 1 - 6
Hlavní autoři: Sim, Yeon-Sub, Chang, Seung Jin
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Anomalies
Anomaly detection
Artificial neural networks
CNN
Convolutional neural networks
Cooling systems
Fault severity classifier
Feature extraction
High temperature superconductors
HTS-based HVDC
HVDC transmission
Image acquisition
Image processing
Image reconstruction
Noise monitoring
Power cables
Quench
Superconducting cables
Time-frequency analysis
ISSN:1051-8223, 1558-2515
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Since high-temperature superconductor (HTS) based HVDC systems are affected by temperature and cooling system performance, noise, the monitoring system which can classify the temporal disturbance and anomalies must be developed to ensure stable system operation. To solve this, it needs anomaly detection that accounts for system sensitivity and is able to continuously manage the response to disturbances. In this paper, we propose an integrated solution for fault severity diagnosis and anomaly detection colorred with AI based reflectometry. Anomalies such as the quench phenomenon can be detected through the anomaly score based on the reconstruction error calculated through the proposed autoencoder(AE) method. After anomaly detection, a fault classification algorithm based on the convolutional neural network (CNN) using a 2D image of a converted reflected signal through the proposed image processing was conducted. Based on the signal acquired from the <inline-formula><tex-math notation="LaTeX">7 m</tex-math></inline-formula> length 1st generation 22.9 kV/50 MVA HTS cable, PSCAD simulation was utilized to construct a long-distance line model and verified the performance of the proposed algorithm.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1051-8223
1558-2515
DOI:10.1109/TASC.2023.3248541