Identification of ultra‐high‐frequency PD signals in gas‐insulated switchgear based on moment features considering electromagnetic mode. Issue 6 (1st December 2020)

• Record Type: Journal Article
• Authors: Bin, Feng; Wang, Feng; Sun, Qiuqin; Chen, She; Fan, Jingmin; Ye, Huisheng
• Is Part Of: High voltage. Volume 5:Issue 6(2020)
• Page Start: 688
• Page End: 696
• Publication Date: 2020-12-01
• Subjects: feature extraction -- time‐frequency analysis -- learning (artificial intelligence) -- pattern recognition -- support vector machines -- gas insulated switchgear -- particle swarm optimisation -- partial discharge measurement -- power engineering computing; ultra‐high‐frequency partial discharge signals -- typical insulation defects -- time‐frequency representation -- cutoff frequencies -- low‐order moments -- feature selection -- selected moment features -- electromagnetic mode -- nearest neighbour -- real‐time PD detection -- ultra‐high‐frequency PD signals -- gas‐insulated switchgear -- feature extraction -- pattern recognition techniques -- insulation condition; High voltages -- Periodicals; 621.3191
• DOI: 10.1049/hve.2019.0098
• Languages: English
• ISSNs: 2397-7264

Abstract

Abstract : The feature extraction and pattern recognition techniques are of great importance to assess the insulation condition of gas‐insulated switchgear. In this work, the ultra‐high‐frequency partial discharge (PD) signals generated from four types of typical insulation defects are analysed using S‐transform, and the greyscale image in time‐frequency representation is divided into five regions according to the cutoff frequencies of TE m 1 modes. Then, the three low‐order moments of every subregion are extracted and the feature selection is performed based on the J criterion. To confirm the effectiveness of selected moment features after considering the electromagnetic modes, the support vector machine, k ‐nearest neighbour and particle swarm‐optimised extreme learning machine (ELM) are utilised to classify the type of PD, and they achieve the recognition accuracies of 92, 88.5 and 95%, respectively. In addition, the results show that the ELM offers good generalisation performance at the fastest learning and testing speeds, thus more suitable for a real‐time PD detection.