Vibration fault identification method of hydropower unit based on EEMD-SDCCⅠ-HMM

被引：0

作者：

Hu X. ^{[1
]}

Xiao Z. ^{[1
,2
]}

Liu D. ^{[3
]}

Zhao W. ^{[4
]}

Wang H. ^{[4
]}

Jiang W. ^{[1
]}

机构：

[1] School of Power and Mechanical Engineering, Wuhan University, Wuhan

[2] Key Laboratory of Hydraulic Machinery Transients, Ministry of Education, Wuhan University, Wuhan

[3] State Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan University, Wuhan

[4] National Energy Group Xinjiang Kaidu River Basin Hydropower Development Co., Ltd., Korla

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2022年 / 41卷 / 03期

关键词：

Curve trend coding (CC); Ensemble empirical mode decomposition (EEMD); Fault identification; Hidden Markov model (HMM); Hydropower unit;

D O I：

10.13465/j.cnki.jvs.2022.03.020

中图分类号：

学科分类号：

摘要：

Here, aiming at problems of fault diagnosis of hydropower units, a fault identification method based on ensemble empirical mode decomposition (EEMD), curve trend coding (CC) and hidden Markov model (HMM) was proposed. Firstly, EEMD was used to process the unit's vibration signals, obtain a series of intrinsic mode functions (IMFs) and calculate their standard deviations (SDs), and then the curve formed with SDs of IMFs was coded (CC) to construct feature vectors. Finally, feature vectors were input into HMM as learning samples, and HMM's various states were obtained through training. When the sample to be tested was input into HMM's various states, the sample's state was determined by comparing log-likelihood probability values output by HMM's various states. The test results showed that the proposed method can effectively extract fault features of the unit and identify fault type; compared with the conventional fault identification method, it has a higher accuracy. © 2022, Editorial Office of Journal of Vibration and Shock. All right reserved.

引用

页码：165 / 175and230

共 17 条

[1] (2010)
[2] PENG Wenji, LUO Xingqi, LI Fusong, Et al., Vbration faultdiagnosis of hydroelectric generation sets based onspectrun analysis and IRN network, Mechanical Science and Technology, 25, 11, pp. 1281-1284, (2006)
[3] LU C, WANG Y, RAGULSKIS M, Et al., Fault diagnosis for rotating machinery: a method based on image processing[J], Plos One, 11, 10, (2016)
[4] HUANG N E, STEVER R L., A new view of nonlinear water waves: the Hilbert spectrum[J], Annual Review of Fluid Mechanics, 31, 1, pp. 417-457, (1999)
[5] HUANG N E., A new method for nonlinear and nonstationary time series analysis: empirical mode decomposition and Hilbert spectral analysis[J], Proceedings of SPIE-the International Society for Optical Engineering, 4056, pp. 197-209, (2000)
[6] (2010)
[7] WU Z, HUANG N E., Ensemble empirical mode decomposition: a noised-assisted data analysis method, Advances in Adaptive Data Analysis, 1, 1, pp. 1-41, (2009)
[8] (2019)
[9] (2007)
[10] JIANG Wenjun, HU Xiao, ZHANG Pei, Et al., Vibration feature extraction of hydropower unit based on ensemble empirical mode decomposition and approximate entropy, Journal of Hydroelectric Engineering, 39, 6, pp. 18-27, (2020)

← 1 2 →