Skip to main navigation Skip to search Skip to main content

基于GSA优化VMD-DBN的水电机组故障诊断

Translated title of the contribution: Fault diagnosis of hydropower unit based on GSA optimization for VMD-DBN
  • 王 卫玉
  • , 侯 凯
  • , 何 葵东
  • , 莫 凡
  • , 金 艳
  • , 陈 启卷*
  • *Corresponding author for this work
  • 五凌电力有限公司
  • 国家电力投资集团水电产业创新中心

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, a fault diagnosis method for hydropower units based on gravity search algorithm(GSA)optimization variational mode decomposition-deep belief network(VMD-DBN) is proposed. Firstly, with the goal of minimizing the energy error of VMD, two typical decomposition parameters(decomposition layer K and penalty factor α) of VMD under each sample are optimized in parallel by GSA. Then, the signal after decomposition and denoising is reconstructed, and the feature vector composed of energy entropy, singular spectral entropy and kurtosis is constructed for the reconstructed signal. Finally, the constructed feature vectors are input into the DBN to construct the fault diagnosis model of hydropower unit. Compared with the existing methods, this model can effectively extract the fault features of hydropower units, and the fault identification accuracy is higher.
Translated title of the contributionFault diagnosis of hydropower unit based on GSA optimization for VMD-DBN
Original languageChinese
Pages (from-to)244-250
Number of pages7
Journal武汉大学学报:工学版
Volume56
Issue number2
DOIs
StatePublished - 1 Feb 2023

Funding

国家电力投资集团统筹科研项目(编号:TC2020SD01)。

Indexed by

  • CSCD

Fingerprint

Dive into the research topics of 'Fault diagnosis of hydropower unit based on GSA optimization for VMD-DBN'. Together they form a unique fingerprint.

Cite this