Fault diagnosis of star-connected auto-transformer based 24-pulse rectifier

Weilin Li, Wenjie Liu, Wei Wu, Xiaobin Zhang, Zhaohui Gao, Xiaohua Wu

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

This paper proposes a fault diagnosis method for star-connected auto-transformer based 24-pulse rectifier unit (ATRU) by integrating artificial neural networks (ANN) with wavelet packet decomposition (WPD) and principal component analysis (PCA). The WPD is employed to extract the features of different fault waveforms of the output voltage of the rectifier. PCA is adopted to reduce the dimensionality of the extracted feature vectors, which leads to fast computation of the algorithm. Back Propagation (BP) neural network is adopted to classify the fault types and determine the fault location according to the extracted features. These faults are simulated in real-time simulation platform and the obtained data are then analyzed with MATLAB toolbox, and finally verified with digital signal processor. Compared with other diagnosis methods, the proposed method shows better performance and faster computing speed.

Original languageEnglish
Pages (from-to)360-370
Number of pages11
JournalMeasurement: Journal of the International Measurement Confederation
Volume91
DOIs
StatePublished - 1 Sep 2016

Keywords

  • ATRU
  • BP neural network
  • Fault diagnosis
  • PCA
  • WPD

Fingerprint

Dive into the research topics of 'Fault diagnosis of star-connected auto-transformer based 24-pulse rectifier'. Together they form a unique fingerprint.

Cite this