Article ID Journal Published Year Pages File Type
6860696 International Journal of Electrical Power & Energy Systems 2013 8 Pages PDF
Abstract
This paper presents a novel stator single-phase-to-ground fault protection of Powerformer in parallel based on the fuzzy clustering algorithms. First, the direction and magnitude of zero-sequence current and leakage current are analyzed, and four fault characters are selected as historical data. Then the historical data are divided into two groups by fuzzy clustering algorithms, and cluster center of each group is calculated. The space relative distance among detected pattern and two cluster centers is finally calculated to discriminate the faulty Powerformer. Simulation results have shown that, under different fault conditions, the new scheme can distinguish reliably internal faults from external faults, and can detect stator single-phase-to-ground fault occurred in which Powerformer with resistance 5 kΩ. A 100% of the winding can be fully protected.
Related Topics
Physical Sciences and Engineering Computer Science Artificial Intelligence
Authors
, , , ,