Multiple partial discharge sources separation using a method based on laplacian score and correlation coefficient techniques

• Laplacian score is an effective method to select high performance features in terms of discrimination of multiple PD source types. • Similar features of PD signals do not add much more information in discrimination of multiple PD sources. • Correlation coefficient is a method to evaluation of similarity between different features. • Different sets of features in different case of multiple PD source types presence, are selected by feature selection algorithm. Partial discharge (PD) activity can be destructive to the transformer insulation, and ultimately may result in total breakdown of the insulation. Partial discharge sources identification in a power transformer enables the operator to evaluate the transformer insulation condition during its lifetime. In order to identify the PD source; in the case of presence of multiple sources; the first step is to capture the PD signals and to extract their specific features. In this contribution, the frequency domain analysis, the time domain analysis and the wavelet transform are employed for feature extraction purpose. In practice, there might be plenty of features, and in each scenario, only some of them may be effective. Therefore, among the extracted features, those useful for discrimination of the multiple PD sources are studied. Then, a method, using laplacian score, and the correlation coefficient algorithms; is developed for feature selection. In order to discriminate among the multiple partial discharge sources, a density-based algorithm spatial clustering of applications with noise (DBSCAN) have been employed to cluster among available PD sources and the noise. The results of some case studies demonstrated the great ability of this method in proper discrimination of multiple PD sources.