Abstract
In this study, a multi-level state classification method based on support vector data description (SVDD) is proposed to detect bearing preload state. Firstly, a three-category classification support vector data description algorithm is proposed to establish the three-state non-aliasing hypersphere model, which can combine the kernel principal component analysis (KPCA) and membership degree. Then, by classifying the first-level training sample model of uniform and non-uniform preload states, the second-level training sample model of non-uniform preload states is established based on SVDD algorithm. Moreover, the balanced multi-label propagation classification criterion is defined that can be used to identify the preload state level based on the training sample model. Finally, a preload state detection system is developed, which can accurately simulate uniform/non-uniform preload states for spindle bearings. The experimental results demonstrate that the proposed algorithm can effectively classify the preload states of spindle bearings with average accuracy higher than 94%.
Similar content being viewed by others
Abbreviations
- a1–3 :
-
The spherical center coordinates of three hyperspheres
- C:
-
Penalty factors
- F 1–3 :
-
The force applied on bearing
- N 1–3 :
-
The number of samples of three categories, respectively
- P:
-
Preload state feature set
- R 1–3 :
-
The radius of three hyperspheres
- S 1–3 :
-
Support vector set
- Y:
-
Principal feature set
- A:
-
Lagrange multiplier
- λ:
-
Lagrange multiplier
- xi, yj, zk :
-
The class I, class II and class III sample datasets
- ξ:
-
Slack variable
- θ:
-
Inclination angle
- Δh:
-
The difference between the highest point and the lowest point on the bearing spacer
References
C. Ma, X. S. Mei, J. Yang and H. Shi, Thermal characteristics analysis and experimental study on the high-speed spindle system, International Journal of Advanced Manufacturing Technology, 79 (2015) 469–489.
A. Matsubara, S. Tsujimoto and D. Kono, Evaluation of dynamic stiffness of machine tool spindle by non-contact excitation tests, CIRP Annals-Manufacturing Technology, 64 (2015) 365–368.
S. E. Deng, Y. S. Wang and X. N. Li, Experimental study on the relationship between bearing preload and system natural frequency, Journal of Aerospace Power, 25(8) (2010) 1883–1887.
J. D. Li, Y. S. Zhu, Q. Q. Xiong and K. Yan, Research on axial dynamic stiffness of fix-pressure spindle, Journal of Xi’an Jiaotong University, 48(10) (2014) 1–6.
F. Du, B. T. Li, J. Zhang, Q. M. Zhu and J. Hong, Ultrasonic measurement of contact stiffness and pressure distribution on spindle-holder taper interfaces, International Journal of Machine Tools & Manufacture, 97(10) (2015) 18–28.
Y. C. Shin, Y. C. Huang and J. A. Chao, Diagnosis of ball screw preload loss by vibration signals through the Hilbert-Huang transform and multiscale measure, Applied Mechanics & Materials, 58–60 (2011) 636–641.
Z. R. Wang, Y. L. Wang, C. Y. Chen, C. C. Zhou, Y. Ou and H. T. Feng, A study on fault diagnosis of ball screw preload loss based on vibration signals, Vibration and Shock, 37(12) (2018) 201–206.
P. C. Tsai, C. C. Cheng and Y. C. Hwang, Ball screw preload loss detection using ball pass frequency, Mechanical Systems and Signal Processing, 48(1–2) (2014) 77–91.
Y. C. Huang, Y. S. Chen, S. L. Sun and K. H. Peng, Prognostic diagnosis of hollow ball screw pretension on preload loss through sensed vibration signals, Lecture Notes in Electrical Engineering, 234 (2013) 959–966.
Y. F. Zhang, X. H. Li, S. A. Wang and Y. H. Sun, Investigation assembly state of spindle bearing based on improved maximum correlated kurtosis deconvolution and support vector machine, Journal of Vibroengineering, 20(2) (2018) 963–977.
D. M. J. Tax and R. P. W. Duin, Support vector domain description, Pattern Recognition Letter, 20(11/13) (1999) 1191–1199.
Z. Q. Jiang, X. Feng, X. Z. Feng and L. G. Li, A study of SVDD-based algorithm to the fault diagnosis of mechanical equipment system, PhysicsProcedia, 33 (2012) 1068–1073.
H. C. Wang, Fault diagnosis of rolling element bearings compound faults based on sparse no-negative matrix factorization-support vector data description, Journal of Vibration and Control, 24(2) (2016) 272–282.
A. Cherni, F. Theljani and K. Laabidi, Fault diagnosis for three-phase asynchronous machine using a modified SVDD, International Conference on Control, Automation and Diagnosis (ICCAD) (2017) 158–163.
M. C. Chen, C. C. Hsu, B. Malhotra and M. K. Tiwari, An efficient ICA-DW-SVDD fault detection and diagnosis method for non-Gaussian processes, International Journal of Production Research, 54(17) (2016) 5208–5218.
G. X. Huang, H. F. Chen, Z. L. Zhou, Y. Feng and K. Guo, Two-class support vector data description, Pattern Recognition, 44(2) (2011) 320–329.
NSK, Super Precision Bearings, Catalog No. E1254, NSK Ltd., Japan (2019).
O. Taouali, I. Jaffel, H. Lahdhiri, M. Faouzi and H. Messaoud, New fault detection method based on reduced kernel principal component analysis, International Journal of Advanced Manufacturing Technology, 85(5–8) (2016) 1547–1552.
Z. H. Wu, Y. F. Lin, S. Gregory, H. Y. Wan and S. F. Tian, Balanced multi-label propagation for overlapping community detection in social networks, Journal of Computer Science and Technology (English Version), 27(3) (2012) 468–479.
NSK, Rolling Bearings, Catalog No. E1102, NSK Ltd., Japan (2013).
Acknowledgments
This work was supported by the National Key Research and Development Program of China (No. 2018YFB2000504) and Major Technology Projects of Shaanxi province of China (No. 2018zdzx01-02-01) and Fundamental Research Funds for the Central Universities and National Science (No. xzd012019032). The authors express their gratitude for their support.
Author information
Authors and Affiliations
Corresponding author
Additional information
Xiaohu Li is an Associate Professor of the School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, China. He received his B.S. degree in Department of Mechanical Engineering in 1999. He received his M.S. degree in 2004, and Ph.D. degree in 2010 in School of Mechanical Engineering in Xi’an Jiao-tong University, respectively. His main research interests include intelligent spindle, electromechanical system optimization control and hydraulic servo control, etc.
Rights and permissions
About this article
Cite this article
Li, X., Zhang, Y., Han, Y. et al. Preload state detection for precision spindle bearings based on multi-level classification. J Mech Sci Technol 34, 4393–4403 (2020). https://doi.org/10.1007/s12206-020-1004-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-020-1004-8