| Title |
A Study on the Application of Artificial Intelligence Recognition Algorithm for Partial Discharge of Ultra-High Voltage Power Equipments |
| DOI |
http://dx.doi.org/10.5207/JIEIE.2019.33.4.048 |
| Keywords |
Artificial Intelligent ; Partial Discharge ; Recognition ; UHF |
| Abstract |
In this study, a study was conducted to improve the defect recognition rate by converting the PRPS Raw-Data acquired in the event of partial discharge of high voltage power equipment into PRPD type and using the extracted parameter as input data of artificial intelligence algorithm. As a result, it was confirmed that sufficient recognition rate was obtained to accurately recognize the type of defect compared to the conventional partial discharge recognition method using the input image. Since it is much more advantageous in terms of computational speed than image recognition method, it is reasonable to use artificial intelligence algorithm method using parameter as a way to process vast signals generated in the field. There is no authorized regulation on the recognition rate of partial discharge measurements. The only recognition rate presented by the Korea Electric Power Corporation purchase specification is 90%. Considering this, the recognition rate obtained in this study is more than 99%, which shows that the learning speed and recognition rate are improved compared to the existing method. |