Open AccessRobust support vector machine‐based zero‐crossing detector for different power system applications
Author(s) -
Ghosh Minati,
Koley Chiranjib,
Roy Nirmal Kumar
Publication year - 2019
Publication title -
iet science, measurement and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.418
H-Index - 49
eISSN - 1751-8830
pISSN - 1751-8822
DOI - 10.1049/iet-smt.2018.5025
Subject(s) - support vector machine , zero crossing , harmonic , computer science , noise (video) , context (archaeology) , power (physics) , detector , control theory (sociology) , electric power system , electronic engineering , artificial intelligence , engineering , control (management) , telecommunications , physics , acoustics , paleontology , quantum mechanics , image (mathematics) , biology
The detection of zero‐crossing (ZC) points in several power system applications, such as power conversion, grid synchronisation, power conditioning, and power system automation and control, is important toward ensuring a consistent performance even when there is variation in the supply frequency. However, the state‐of‐the‐art techniques of ZC detection are not very accurate in the presence of noise and harmonic distortions. This study introduces the concept of a support vector machine (SVM) in this context and subsequently proposes a robust SVM‐based ZC detection technique that addresses the aforementioned limitations. The simulation results show that the proposed technique obtains accurate values in the presence of transients, noise levels of up to 20%, and harmonic distortions of up to 50%. The experimental results provide similar observations.