Partial discharges and noise classification under HVDC using unsupervised and semi-supervised learning. (October 2020)

• Record Type: Journal Article
• Authors: Morette, N.; Castro Heredia, L.C.; Ditchi, Thierry; Rodrigo Mor, A.; Oussar, Y.
• Is Part Of: International journal of electrical power & energy systems. Volume 121(2020)
• Publication Date: 2020-10
• Subjects: Semi-supervised learning -- Transductive SVMs -- K-means -- Dunn index -- Partial discharges -- HVDC; Electrical engineering -- Periodicals; Electric power systems -- Periodicals; Électrotechnique -- Périodiques; Réseaux électriques (Énergie) -- Périodiques; Electric power systems; Electrical engineering; Periodicals; 621.3
• DOI: 10.1016/j.ijepes.2020.106129
• Languages: English
• ISSNs: 0142-0615

Abstract

Highlights: PD and noise recognition under HVDC is assisted by unsupervised and semi-supervised learning. Wavelet detail coefficients provides enough and robust features or recognition purposes. Unsupervised learning proves feasible to discover the natural number of clusters in the dataset. Dunn and Silhouette index help to check cluster quality. Unsupervised-discovered features and semi-supervised learning provide efficient-flexible recognition. Abstract: This paper tackles the problem of the classification of partial discharge (PD) and noise signals by applying unsupervised and semi-supervised learning methods. The first step in the proposed methodology is to prepare a set of classification features from the statistical moments of the distribution of the Wavelet detail coefficients extracted from a dataset of signals acquired from a test cell under 40 kVDC. In a second step, an unsupervised learning framework that implements the k–means algorithm is applied to reduce the dimensionality of this initial feature set. The Silhouette index is used to evaluate the number of natural clusters in the dataset while the Dunn index is used to determine which subset of features produces the best clustering quality. Since the unsupervised learning does not provide any method for result validation, then the third step in the methodology of this paper consists of applying a semi-supervised learning framework that implements Transductive Support-Vector Machines. The labeling of the test set that is required in this framework for the result validation is carried out by visual checking of the signal waveforms assisted by GUI tools such as the software PDflex. The results using this methodology showed a high classification accuracy and proved that both learning frameworks can be combined to optimize the selection of classification features.