Fault detection of vulnerable units of wind turbine based on improved VMD and DBN

被引：0
|
作者：
Zheng X. [1 ]
Chen G. [1 ]
Ren H. [2 ]
Li D. [1 ]
机构：
[1] School of Automation Engineering, Shanghai University of Electric Power, Shanghai
[2] Shanghai Donghai Wind Power Co., Ltd., Shanghai
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2019年 / 38卷 / 08期
关键词：
Deep belief network(DBN); Fault diagnosis; Multi-feature extraction; Variational mode decomposition(VMD);
D O I：
10.13465/j.cnki.jvs.2019.08.023
中图分类号：
学科分类号：
摘要：
Considering that the early fault characteristics of the vibration signals of the vulnerable components such as bearings and gears monitored during the operation of wind turbines are weak and difficult to extract, a fault feature extraction method based on VMD was proposed. The deep belief network was used to troubleshoot the faults. In order to overcome the influence of the parameters of the variational mode decomposition on the feature extraction, the number of decompositions was determined based on the correlation coefficients of each component, and the particle swarm optimization algorithm was used to optimize the penalty factor. The improved variational mode decomposition was applied to the vibration signals analysis and processing. Based on this, the permutation entropy and rms value of each modal component were further extracted and the high-dimensional eigenvectors formed by them were used as the input of the deep beilef network to establish an early fault diagnosis model. Finally, fault diagnosis and analysis of wind turbine drive fault diagnosis experimental platform early fault data and an offshore wind turbine site signal were carried out. The results show that the method can extract the weak features of fault signals of fan vulnerable components more accurately and steadily. © 2019, Editorial Office of Journal of Vibration and Shock. All right reserved.
引用
收藏
页码：153 / 160and179
相关论文
共 15 条
  • [1] Tang G., Pang B., Liu S., Fault diagnosis of rolling bearings based on difference spectrum of singular value and stationary subspace analysis, Journal of Vibration & Shock, 34, 11, pp. 83-87, (2015)
  • [2] Dragomiretskiy K., Zosso D., Variational mode decomposition, IEEE Tran on Signal Processing, 62, 3, pp. 531-544, (2014)
  • [3] Liu C., Wu Y., Zhen C., Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy C means clustering, Proceedings of the CSEE, 35, 13, pp. 3358-3365, (2015)
  • [4] Tang G., Wang X., Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing, Journal of Xi'an Jiaotong University, 49, 5, pp. 73-81, (2015)
  • [5] Zhao H., Guo S., Gao D., Fault feature extraction of bearing faults based on singular value decomposition and variational modal decomposition, Journal of Vibration and Shock, 35, 22, pp. 183-188, (2016)
  • [6] Hinton G., Osindero S., Teh Y.W., A fast learning algorithm for deep belief nets, Neural Computation, 18, 7, pp. 1527-1554, (2006)
  • [7] Li Y., Wang X., Zhang M., Et al., An approach to fault diagnosis of rolling bearing using SVD and multiple DBN classifiers, Journal of Shanghai Jiao Tong University, 49, 5, pp. 681-686, (2015)
  • [8] Li W., Shan W., Zeng X., Bearing fault identification based on deep belief network, Journal of Vibration Engineering, 29, 2, pp. 340-347, (2016)
  • [9] Tang G., Wang X., Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing, Journal of Xi'an Jiaotong University, 49, 5, pp. 73-81, (2015)
  • [10] Ghodousian A., Parvari M.R., A modified PSO algorithm for linear optimization problem subject to the generalized fuzzy relational inequalities with fuzzy constraints, Information Sciences, 418-419, pp. 317-345, (2017)
12