Optimal Feature Extraction for Partial Discharge Recognition.
|
Accession number;02A0423802
|
| Title;Optimal Feature Extraction for Partial Discharge Recognition. |
| Author;
WANG W
(Tsinghua Univ., Beijing, Chn)
TAN K
(Tsinghua Univ., Beijing, Chn)
GAO K
(Tsinghua Univ., Beijing, Chn)
GAO W
(Tsinghua Univ., Beijing, Chn)
|
Journal Title;Proceedings of the Symposium on Electrical and Electronic Insulating Materials and Applications in Systems
|
Journal Code:G0398B
|
ISSN:
|
|
VOL.33rd;NO.;PAGE.115-118(2001)
|
| Figure&Table&Reference;FIG.3, TBL.4, REF.9 |
| Pub. Country;Japan |
| Language;English |
| Abstract;Pattern recognition of partial discharge(PD) is significant for condition judgment of power equipment. Using more features to describe partial discharge data could make patterns more separable. On the other hand, it is also sensible to ensure that no more features than necessary are utilized when performing the classification. To select the optimal features out of the original PD features, this paper introduces a novel feature extraction algorithm, which is based directly upon the decision boundary between the classes, and determines the feature transformation according to the separability as opposed to the more common approach of fitting, such as principal component transformation. Experiment calculations are conducted on PD data obtained through measurements on industrial models of generator stator winding bars. Statistical and moment features, drawn respectively from each PD sample, are used in the experiments. Results show that when used together, the two sets of features are more powerful in discrimination. It is also shown that most discriminant information is concentrated in a subset of features, which can be determined and extracted successfully using the proposed algorithm. With the few selected features, approximate recognition accuracy could be achieved while substantial increases in computation complexity are refrained. (author abst.) |
|
|
|
Related Articles;
|
|
