LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Partial Discharge Detection Based on Anomaly Pattern Detection

Photo from wikipedia

Recently, a lot of research has been carried out on partial discharge (PD) using machine learning techniques. However, most of these studies have focused on the identification of multiple PD… Click to show full abstract

Recently, a lot of research has been carried out on partial discharge (PD) using machine learning techniques. However, most of these studies have focused on the identification of multiple PD sources, PD classification, or denoising PD measurements, with few studies on real-time PD occurrence detection. In this paper, we propose a method to detect PD occurrence based on anomaly pattern detection. The proposed method consists of three steps. First, in the data preprocessing step, the pulse sequence data are converted into a feature vector stream by applying a sliding window technique. In the next step, normal data modeling is performed using feature vectors transformed from pulse sequence data collected in a normal state where no PD occurs. Finally, for the monitored pulse sequence, an online process for PD detection is carried out through conversion to a feature vector data stream and an anomaly pattern detection method. Experimental results using simulated PD data demonstrate the capabilities of the proposed method.

Keywords: anomaly pattern; detection; pattern detection; partial discharge; based anomaly

Journal Title: Energies
Year Published: 2020

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.