Possibilistic Fuzzy c-Means Clustering Algorithm for Partial Discharge Pattern Recognition Using NLPCA Method

Abstract

Partial discharge (PD) may cause the insulation deterioration in power equipment and impact the reliability. Therefore, the PD detection with pattern recognition is an important tool in insulation diagnosis of High Voltage (HV) equipment. This paper presents the application of Possibilistic fuzzy c-means (PFCM) clustering approach to recognize PD patterns of HV equipment. The PD patterns are measured by using a commercial PD detector. A set of features used as operators for each PD pattern is extracted through statistical schemes. The significant features of PD patterns are extracted by using the nonlinear principal component analysis (NLPCA) method. The proposed PFCM classifier has an advantage of high robustness and efficacy to ambiguous patterns and is useful in recognizing the PD patterns of the HV equipment. To verify the effectiveness of the proposed method, the classifier has been verified on various test samples. The test results show that the proposed approach may achieve quite satisfactory recognition of PD patterns and the number of features in the feature vector will influence the accuracy of pattern recognition.