Partial Discharge Localization Method Based on UHF Wireless Sensor Array in Air-insulated Substation
To achieve comprehensive insulation deterioration monitoring of power equipment and fault early-warning of air-insulated substations, we propose a data-driven partial discharge (PD) source localization methodology based on received signal strength indicator (RSSI) and Gaussian process classification...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
State Grid Energy Research Institute
2021-02-01
|
| Series: | Zhongguo dianli |
| Subjects: | |
| Online Access: | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202006006 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | To achieve comprehensive insulation deterioration monitoring of power equipment and fault early-warning of air-insulated substations, we propose a data-driven partial discharge (PD) source localization methodology based on received signal strength indicator (RSSI) and Gaussian process classification (GPC). Compared to the existing ultra-high frequency (UHF) time-difference-based technique, the proposed method needs only to record the RSSI measurements, while needs not require time synchronization between UHF sensors, which provides a low-cost solution with high adaptability. Meanwhile, to mitigate the multipathing and shadowing effects in modeling the UHF signal attenuation, it is proposed to use the GPC algorithm to learn the UHF signal features under different transmission paths so as to generate decision-making regions for identifying the RSSI values that are consistent with the signal attenuation model, and as a result, the localization accuracy is improved. The field test is performed and the results show that the proposed method has a mean PD source localization error of 2.51 meters, which is sufficient to identify the power equipment with insulation deterioration in a substation for fault early-warning. |
|---|---|
| ISSN: | 1004-9649 |