An NPE-PCA-based Detection Method of Distribution Transformer Closing Surge Waveform

Abstract In order to effectively detect the waveform characteristics of closing inrush current distribution transformers and distinguish between magnetizing fault when closing, this paper proposes a new method based on neighborhood preserving embedding (NPE) principal component analysis (PCA) transformer detection method. This can process global local feature information data. First, NPE-PCA algorithm is used reduce data two-dimensional space, then fitting error σ obtained by space The relationship given threshold identify closing. Finally, model built ATP/EMTP platform test proposed for detecting current. simulation results show that in current, which consistent with second harmonic wave. Algorithm comparison shows performance better.