Characteristic Parameters Extraction and Pattern Recognition of Partial Discharges based on Envelope of Ultra-high Frequency Signal
- 10.2991/icsmim-15.2016.228How to use a DOI?
- gas insulated switchgear; partial discharge; ultra-high frequency; characteristic parameters; pattern recognition
With the help of the Hilbert transform, the low-frequency signals modulated by high-frequency signals can be demodulated. This article proposed a method to extract the time-domain features of ultra-high frequency (UHF) signals regarding the partial discharges (PD) in a gas insulated switchgear (GIS). Utilizing the Hilbert transform, the envelope of a PD signal can be solved, and further the corresponding characteristic parameters of some key time domains can be acquired. An experimental platform for the detection of artificial insulation faults in a GIS was established. Thus, the experimental data of 3 types of typical PD signals were gained, and then used for the analysis and verification of the presented algorithm. The result shows that different types of PDs were accurately recognized. It can be concluded that the method presented is practical and effective.
- © 2016, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Zhaoli Gao AU - Yingtao Sun AU - Lingen Luo AU - Gehao Sheng AU - Xiuchen Jiang PY - 2016/01 DA - 2016/01 TI - Characteristic Parameters Extraction and Pattern Recognition of Partial Discharges based on Envelope of Ultra-high Frequency Signal BT - Proceedings of the 2015 4th International Conference on Sensors, Measurement and Intelligent Materials PB - Atlantis Press SP - 1233 EP - 1241 SN - 2352-538X UR - https://doi.org/10.2991/icsmim-15.2016.228 DO - 10.2991/icsmim-15.2016.228 ID - Gao2016/01 ER -