AI in arcing-HIF detection: a brief review

• Published in: IET Smart Grid Vol. 3; no. 4; pp. 435 - 444
• Main Author: Hao, Bai
• Format: Journal Article
• Language: English
• Published: Durham The Institution of Engineering and Technology 01.08.2020; John Wiley & Sons, Inc; Wiley
• Subjects: Algorithms; arcing-hif database construction method; arcing-hif detection-based ai algorithm; arcing-high-impedance fault detection problems; arcs (electric); Artificial intelligence; artificial intelligence method; Asymmetry; B0170N Reliability; B8120J Distribution networks; C6170 Expert systems and other AI software and techniques; C7410B Power engineering computing; classifier selection; Cognition & reasoning; Data acquisition; distribution network-based ai algorithm; Electricity distribution; Energy; fault diagnosis; feature extraction; grounded distribution network; Morphology; power distribution faults; power distribution reliability; power engineering computing; reliability; Simulation; Software; Special Issue: Machine Learning in Power Systems; fault diagnosis; arcing-HIF detection-based AI algorithm; reliability; power distribution faults; arcs (electric); grounded distribution network; power engineering computing; artificial intelligence; artificial intelligence method; classifier selection; arcing-HIF database construction method; power distribution reliability; feature extraction; distribution network-based AI algorithm; arcing-high-impedance fault detection problems; data acquisition
• ISSN: 2515-2947; 2515-2947
• DOI: 10.1049/iet-stg.2019.0091

In the past few decades, the arcing-high-impedance fault (arcing-HIF) detection problems have become an important issue in the effectively grounded distribution network. Many solutions have been proposed to address this problem. The most attractive way is artificial intelligence (AI) method. The paper gives a comprehensive review of arcing-HIF detection in distribution network-based AI. First, characteristics and models of arcing-HIF are analysed, the arcing-HIF database construction method is also explained; this part is a foundation work for arcing-HIF detection. Next, arcing-HIF detection methods based AI are summarised in details including data acquisition, feature extraction and classifier selection. Then, a set of criteria are proposed to evaluate the reliability of arcing-HIF detection algorithm. Finally, the future trends and challenges to arcing-HIF detection are also fully accounted. This review can be a valuable guide for researchers who are interested in arcing-HIF detection-based AI.