Abstract
In considering that variational modal decomposition (VMD) can fulfill the self-adaptive separation of complex signals, the paper has applied VMD to the identification of rotor–stator rubbing fault and position in aero-engine. The paper has proposed a method combing autocorrelation function (AF), variational modal decomposition (VMD) and k-nearest neighbor (KNN) classification algorithm. To reduce noise and reinforce the characteristics of faults, the method firstly calculates the autocorrelation function of vibration acceleration signals from casing. Secondly, the autocorrelation function is decomposed by VMD algorithm to obtain the intrinsic modal functions of different frequency bands. Thirdly, calculates the normalized energy of intrinsic modal components and carry out cluster analysis on the normalized energy set by k-means clustering. Finally, the normalized energy obtained are inputted into KNN classifier as characteristic vectors to identify rotor–stator rubbing fault and rubbing positions. The result indicates that the proposed AF-VMD-KNN method has the recognition rate of rubbing faults as high as over 94% in terms of different dates, rotation speeds and rubbing severity with training and testing samples randomly divided.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig1_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-021-00357-z/MediaObjects/42417_2021_357_Fig12_HTML.png)
Similar content being viewed by others
References
Zhou W, Qiu N et al (2018) Dynamic analysis of a planar multi-stage centrifugal pump rotor system based on a novel coupled model. J Sound Vib 434:237–260
Wenjie Z, Yuhua C et al (2020) A novel axial vibration model of multistage pump rotor system with dynamic force of balance disc. J Vib Eng Technol 8(05):673–683
Corral-Hernández JA, Antonino-Daviu JA (2016) Influence of the start-up system in the diagnosis of faults in the rotor of induction motors using the discrete wavelet transform. Proc Comput Sci 83:807–815
Ren Z, Zhou S et al (2015) Crack fault diagnosis of rotor systems using wavelet transforms. Comput Electr Eng 45:33–41
Yan X, Zhang C, Liu Y (2021) Multi-branch convolutional neural network with generalized shaft orbit for fault diagnosis of active magnetic bearing-rotor system. Measurement 171:108778
Zhiyi H, Haidong S et al (2020) An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE. Adv Eng Inf 46:101150
Yang Y, Jie T et al (2021) Rub-impact investigation of a single-rotor system considering coating effect and coating hardness. J Vib Eng Technol 9(03):491–505
Tiancheng Z, Shuqian C et al (2019) Analysis and experiment of coupled bending and torsional vibration of a rub-impact dual-rotor system. J Aerosp Power 34(03):643–655
Xiaolong W, Guiji T (2015) Rubbing feature extraction using morphological component analysis and reassigned scale spectrum. Electr Mach Control Appl 42(01):51–56
Bingxi Z, Dawei Ji et al (2020) Rubbing fault diagnosis of rotor system based on combined feature space in time and time-frequency domain. J Xi’an Jiaotong Univ 54(01):75–84
Zhigang W, Hongchao W et al (2016) Early rub-impact fault diagnosis of turbine rotors based on morphological component analysis. Chin J Constr Mach 14(06):545–547
Zeng M, Yang Y et al (2015) Normalized complex Teager energy operator demodulation method and its application to fault diagnosis in a rubbing rotor system. Mech Syst Signal Process 50–51:380–399
Yu M, Feng Z, Huang J, Zhu L (2016) Aero-engine rotor-stator rubbing position identification based on casing velocity signal. J Vibroeng 18(4):2123–2124
Gao Sheng Wu, Yinong JZ (2019) Static and dynamic rubbing positions identification of cryocooler based on wavelet packet analysis and support vector machine. J Infrared Millim Waves 38(05):627–632
Zheng J, Tong J et al (2019) Partial ensemble approach to resolve the mode mixing of extreme-point weighted mode decomposition. Digit Signal Process 89:70–81
Dragomiretskiy K, Zosso D (2014) Variational mode decomposition. IEEE Trans Signal Process 62(3):531–544
Yonghe W, Cao Huai Lu, Ziqian. (2019) Application of variational mode decomposition and particle swarm optimization support vector machine method in fault diagnosis of rotor rubbing. J Shenyang Ligong Univ 38(04):45–51
Yan X, Jia M (2019) Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings. Mech Syst Signal Process 122:56–86
Jingbo G, Junxian S et al (2020) An integrated method based on hybrid grey wolf optimizer improved variational mode decomposition and deep neural network for fault diagnosis of rolling bearing. Measurement 162:107901
Dibaj A, Hassannejad R et al (2021) Incipient fault diagnosis of bearings based on parameter-optimized VMD and envelope spectrum weighted kurtosis index with a new sensitivity assessment threshold. ISA Trans 114
Yan Z, Junchao Z et al (2018) Rub-impact fault diagnosis of rotating machinery based on VMD and Hilbert spectrum. J Vib Meas Diag 38(2):381–386
Yonghe W, Qingtao J, Huai C (2020) PSO-based optimization of VMD and SVM rotor touch recognition. J Shenyang Ligong Univ 39(04):42–47
Tingting H (2013) Research on k-means clustering algorithm. J Huangshan Univ 15(05):17–19
Jiawei L, Qi Li et al (2018) A discrete hidden Markov model fault diagnosis strategy based on k-means clustering dedicated to PEM fuel cell systems of tramways. Int J Hydrog Energy 43(27):12428–12441
Zhao L, Peng T et al (2015) Fault condition recognition based on multi-scale texture features and embedding prior knowledge k-means for antimony flotation process. IFAC PapersOnLine 48(21):864–870
Jinyu G, Xin W, Yuan Li (2018) Application of KNN in fault isolation of chemical production process. Appl Res Comput 35(04):1117–1121
Li Yuan Wu, Jie WG (2015) K-nearest neighbor imputation method and its application in fault diagnosis of industrial process. J Shanghai Jiaotong Univ (Chin Ed) 49(06):830–836
Jianghua Ge, Qi L et al (2018) Fault diagnosis method of gearbox supporting tension machine and KNN-AMDM decision fusion. J Vib Eng 31(06):1093–1101
Bide Z, Ting M, Tao W (2020) Research on adaptive k-value weighted KNN algorithm for power transformer fault diagnosis. Hubei Electr Power 44(02):6–12
Dongcui W, Yunfei D, Chenxuan Z (2019) A fault diagnosis method for gearbox based on neutrosophic k-nearest neighbor. J Vib Shock 38(20):148–153
Acknowledgements
This work was supported by National Natural Science Foundation of China [Grant number: 51605309], Natural Science Foundation of Liaoning Province [Grant number: 2019-ZD-0219] , Aeronautical Science Foundation of China [Grant number: 201933054002] and Department of Education of Liaoning Province [Grant number: JYT19042].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest in preparing this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, W., Yu, M. & Fang, M. Research on Identification and Localization of Rotor–Stator Rubbing Faults Based on AF-VMD-KNN. J. Vib. Eng. Technol. 9, 2213–2228 (2021). https://doi.org/10.1007/s42417-021-00357-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42417-021-00357-z