Partial Discharge Diagnosis Based on Variational Mode Decomposition and Multiscale Permutation Entropy

Partial discharge diagnosis is considered as an important means to diagnose the insulation state of gas insulated switchgear (GIS). Aiming at the non-stationary characteristics of partial discharge (PD) signals, a feature extraction method based on variational mode decomposition (VMD) and multi-scale permutation entropy (MPE) is proposed. Firstly, VMD is used to decompose the PD signal, and multiple intrinsic modal functions are obtained; Then, the MPE of each modal component is calculated as the eigenvector. Finally, the MPE of modal component is input into SVM as feature vector for classification. Empirical mode decomposition (EEMD) and empirical mode decomposition (EMD) are compared to highlight the advantages of the proposed algorithm. The comparative simulation results demonstrate that, compared with the other two algorithms, this method can effectively extract the characteristic parameters, which provides a reference scheme for GIS PD diagnosis.