Maximal overlap discrete wavelet transform and deep learning for robust denoising and detection of power quality disturbance

This study presents a new technique for power quality (PQ) disturbance detection. The technique focuses on voltage sags and interruptions that are related to various faults, i.e. transmission line, feeder, and transformer faults. A maximal overlap discrete wavelet transform-based PQ detection algori...

Full description

Saved in:

Bibliographic Details
Published in:	IET generation, transmission & distribution Vol. 14; no. 1; pp. 140 - 147
Main Authors:	Xiao, Fei, Lu, Tianguang, Wu, Mingli, Ai, Qian
Format:	Journal Article
Language:	English
Published:	The Institution of Engineering and Technology 17.01.2020
Subjects:	backpropagation deep learning detection threshold discrete wavelet transforms disturbance initiation feature extraction improved stacked sparse denoising autoencoder learning (artificial intelligence) maximal overlap discrete wavelet transform neural nets power engineering computing power quality disturbance detection power supply quality power system faults power system harmonics PQ detection algorithm PQ disturbances PQ recording preprocessed PQ waveforms Research Article robust classifier robust denoising signal denoising space vector transformation transformer faults voltage sags detection threshold maximal overlap discrete wavelet transform power quality disturbance detection disturbance initiation signal denoising power system faults deep learning PQ recording feature extraction transformer faults robust classifier space vector transformation learning (artificial intelligence) improved stacked sparse denoising autoencoder power system harmonics PQ disturbances robust denoising discrete wavelet transforms preprocessed PQ waveforms power engineering computing power supply quality voltage sags backpropagation PQ detection algorithm neural nets
ISSN:	1751-8687, 1751-8695
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This study presents a new technique for power quality (PQ) disturbance detection. The technique focuses on voltage sags and interruptions that are related to various faults, i.e. transmission line, feeder, and transformer faults. A maximal overlap discrete wavelet transform-based PQ detection algorithm is proposed to provide accurate points of disturbance initiation and recovery. The proposed PQ detection algorithm is robust even without a detection threshold and independent of the sampling frequency of PQ recording. In consideration of the presence of noise conditions, the preprocessed PQ waveforms are converted into 2D binary vectors using space vector transformation. Then, an improved stacked sparse denoising autoencoder combined with supervised backpropagation training is proposed as a robust classifier. Results show that the proposed method is suitable for detecting various types of PQ disturbances and possesses high recognition accuracy despite insufficient training samples.
ISSN:	1751-8687 1751-8695
DOI:	10.1049/iet-gtd.2019.1121