In this paper, a multi-source partial discharge diagnosis method based on joint detection of pulse current method and ultraviolet pulse method was presented. A multi-source partial discharge experimental platform of switchgear was constructed for four basic defect models. The characteristics of partial discharge information obtained by joint detection were extracted and a database was constructed, and then the discharge types were identified by k-nearest neighbor (KNN) algorithm and directed acyclic graph SVMs (DAG-SVMs) algorithm. The results show that the change of discharge number and discharge quantity in discharge pattern measured by pulse current method are related to the defect type in model. The existence of void and surface defects will increase the discharge quantity and pattern symmetry, and the existence of corona defect will increase the discharge number. The discharge pulse number measured by ultraviolet pulse method is related to the defect number in multisource discharge model and the ratio of ultraviolet to visible light. The higher the number of defects and the ratio of ultraviolet to visible light, the larger the discharge pulse number. The recognition accuracy of the KNN algorithm can reach up to 99.67%.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |