Rotor fault diagnosis method based on parametric optimization SDP analysis

被引：0

作者：

Wan Z. ^{[1
,2
]}

He J. ^{[1
,2
]}

Jiang D. ^{[2
,3
]}

Li J. ^{[4
]}

Zhang D. ^{[1
,2
]}

机构：

[1] School of Mechanical Engineering, Southeast University, Nanjing

[2] Jiangsu Provincial Engineering Research Center of Aerospace Machinery Equipment, Southeast University, Nanjing

[3] School of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing

[4] Hunan Aviation Powerplant Research Institute, Aero Engine Corporation of China, Zhuzhou

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2023年 / 42卷 / 01期

关键词：

beetle antennae search (BAS) algorithm; convolutional neural network (CNN); fault diagnosis; rotor; symmetrized dot pattern (SDP);

D O I：

10.13465/j.cnki.jvs.2023.01.010

中图分类号：

学科分类号：

摘要：

Here, aiming at rotor fault diagnosis problems with various fault types and fault severities, an intelligent diagnosis method based on parametric optimization symmetric dot pattern (SDP) analysis was proposed. Firstly, fault features of multiple sensor signals were extracted using SDP analysis and fused into SDP images. Then, the image discrimination function defined based on Euclidean distance was taken as the fitness function, optimal values of angle domain gain factor and time delay coefficient in SDP analysis were obtained based on beetle antennae search (BAS) algorithm. Finally, SDP images were used to train convolutional neural network (C N N), and obtain the rotor fault diagnosis model. Test study showed that the proposed method has higher diagnosis accuracy than other fault diagnosis methods do; its diagnosis performance is good in strong noise environment; the parametric optimization SDP analysis based on BAS algorithm amplifies characterization differences of rotor faults with different types and severities, and improves fault diagnosis accuracy. © 2023 Chinese Vibration Engineering Society. All rights reserved.

引用

页码：81 / 88

页数：7

共 22 条

[1] GAO Y, LIU X Y, HUANG H Z, Et al., A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems [J], ISA Transactions, 108, pp. 356-366, (2021)
[2] LEI Y G, YANG B, JIANG X W, Et al., Applications of machine learning to machine fault diagnosis: a review and roadmap, Mechanical Systems and Signal Processing, 138, (2020)
[3] YAN Renwu, LIN Chuan, GAO Shuoxun, Et al., Fault diagnosis and analysis of circuit breaker based on wavelet ti me-frequency representations and convolution neural network [J], Journal of Vibration and Shock, 39, 10, pp. 198-205, (2020)
[4] WANG Chongyu, ZHENG Zhaoli, LIU Tianyuan, Et al., Research on detection method of steam turbine rotor unbalance and misalignment fault based on convolution neural network [J], Proceedings of the CSEE, 41, 7, pp. 2417-2427, (2021)
[5] YAN X A, SHE D M, XU Y D, Et al., Deep regularized variational autoencoder for intelligent fault diagnosis of rotor-bearing system within entire life-cycle process [J], Knowledge-Based Systems, 226, (2021)
[6] JIAO J Y, ZHAO M, LIN J, Et al., A comprehensive review on convolutional neural network in machine fault diagnosis [J], Neurocomputing, 417, pp. 36-63, (2020)
[7] TAO H F, WANG P, CHEN Y Y, Et al., An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks, Journal of the Franklin Institute, 357, 11, pp. 7286-7307, (2020)
[8] LIANG P F, DENG C, WU J, Et al., Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network [J], Measurement, 159, (2020)
[9] GLOWACZ A., Fault diagnosis of electric impact drills using thermal imaging, Measurement, 171, (2021)
[10] ZHU X X, HOU D N, ZHOU P, Et al., Rotor fault diagnosis using a convolutional neural network with symmetrized dot pattern images, Measurement, 138, pp. 526-535, (2019)

← 1 2 3 →