Abstract
In order to effectively solve the parameter selection problem of variational mode decomposition (VMD) and accurately extract the bearing fault features, a bearing fault diagnosis method based on multi-feature optimized VMD and fusion index is proposed. Considering the multiple features of fault pulse when the bearing fails, the objective functions and fusion index of information entropy, correlation coefficient, and kurtosis are established, and the parameter optimization problem of VMD is transformed into a multi-objective optimization problem. Firstly, the multi-objective particle swarm optimization (MOPSO) algorithm is used to optimize the three objective functions, and the optimal Pareto frontier solution set of VMD parameter combination is obtained. Secondly, the fusion index is used to evaluate the Pareto frontier solution set, from which the optimal parameter combination of VMD is determined. The bearing fault signal is decomposed by VMD based on the optimal parameter combination, and several intrinsic mode functions (IMFs) are obtained. Then, the fusion index is used to select the optimal IMF, and fault features are extracted. Finally, the analysis results of the simulation signal and actual bearing vibration signals show the effectiveness of the proposed method.
Similar content being viewed by others
Abbreviations
- f(t):
-
Original signal desired for decomposition
- u k(t):
-
kth decomposed IMF
- A k(t):
-
Instantaneous amplitude of uk(t)
- ϕ k(t):
-
Derivative of the instantaneous frequency of uk(t)
- K :
-
Number of IMF
- ω k :
-
Central frequency of the kth IMF
- α :
-
Penalty factor
- λ :
-
Lagrange multiplication operator
- \(v_i^{z + 1}\) :
-
Velocity of ith particle
- \(loc_i^{z + 1}\) :
-
Position of ith particle
- c 1 and c 2 :
-
Learning factors
- it :
-
Number of iterations
- r 1 and r 2 :
-
Random numbers in [0, 1]
- \(p_i^{it}\) :
-
Individual optimal solution
- \(p_g^{it}\) :
-
Global optimal solution
- x :
-
Decision variable
- fun d(x):
-
dth objective function
- RS :
-
Random sequence
- P :
-
Probability distribution of RS
- N :
-
Sampling length
- σ :
-
Standard deviation of uk(t)
- \(ku{r_{{u_k}}}\) :
-
Kurtosis of uk(t)
- \({r_{f{u_k}}}\) :
-
Correlation coefficient between uk(t) and f(t)
- fun :
-
Fusion index
- \({\bar f}\) :
-
Mean value of f(t)
- np :
-
Population number
- w :
-
Inertia weight
- it m :
-
Maximum number of iterations
- s(t):
-
Periodic shock signal
- n(t):
-
Gaussian white noise
- h(t):
-
Oscillating signal with an attenuated amplitude
- C :
-
Attenuation coefficient
- f i :
-
Fault feature frequency of the bearing inner race
- f n :
-
Resonant frequency
- f s :
-
Sampling frequency
- S(df):
-
Sum of envelope spectrum amplitudes of bearing feature frequency and its harmonics
- S:
-
Sum of signal envelope spectrum amplitudes
- R f :
-
Fault feature ratio
- P signal :
-
Target signal power
- P noise :
-
Noise signal power
- F(df):
-
Envelope spectrum amplitude of df
- N(df):
-
Average amplitude of noise bands on both sides of df
- f r :
-
Bearing rotation frequency
- f o :
-
Fault feature frequency of the bearing outer race
- f b :
-
Fault feature frequency of the bearing rolling element
References
L. Zuo, F. J. Xu, C. H. Zhang, T. F. Xiahou and Y. Liu, A multilayer spiking neural network-based approach to bearing fault diagnosis, Reliability Engineering and System Safety, 225 (2022) 108561.
Y. C. Hou, C. Q. Zhou, C. M. Tian, D. Wang, W. T. He, W. J. Huang, P. Wu and D. Z. Wu, Acoustic feature enhancement in rolling bearing fault diagnosis using sparsity-oriented multipoint optimal minimum entropy deconvolution adjusted method, Applied Acoustics, 201 (2022) 109105.
K. H. Chen, Y. T. Lu, R. Q. Zhang and H. Q. Wang, The adaptive bearing fault diagnosis based on optimal regulation of generalized SR behaviors in fluctuating-damping induced harmonic oscillator, Mechanical Systems and Signal Processing, 189 (2023) 110078.
C. López, A. Naranjo, S. L. Lu and K. J. Moore, Hidden Markov model based stochastic resonance and its application to bearing fault diagnosis, J. of Sound and Vibration, 528 (2022) 116890.
Q. Ma, S. Cao, T. Gong and J. H. Yang, Weak fault feature extraction of rolling bearing under strong poisson noise and variable speed conditions, Journal of Mechanical Science and Technology, 36 (2022) 5341–5351.
F. Jiang, K. Ding, G. L. He and C. Y. Du, Sparse dictionary design based on edited cepstrum and its application in rolling bearing fault diagnosis, J. of Sound and Vibration, 490 (2021) 115704.
B. Pang, M. Nazari and G. Tang, Recursive variational mode extraction and its application in rolling bearing fault diagnosis, Mechanical Systems and Signal Processing, 165 (2022) 108321.
M. Singh and R. Kumar, Thrust bearing groove race defect measurement by wavelet decomposition of pre-processed vibration signal, Measurement, 46 (9) (2013) 3508–3515.
H. Ocak, K. A. Loparo and F. M. Discenzo, Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling: A method for bearing prognostics, J. of Sound and Vibration, 302 (4–5) (2007) 951–961.
X. F. Liu, L. Bo and H. L. Luo, Bearing faults diagnostics based on hybrid LS-SVM and EMD method, Measurement, 59 (2015) 145–166.
Z. Wu and N. E. Huang, Ensemble empirical mode decomposition: A noise-assisted data analysis method, Advances in Adaptive Data Analysis, 1 (1) (2009) 1–41.
J. R. Yeh, J. S. Shieh and N. E. Huang, Complementary ensemble empirical mode decomposition: A novel noise enhanced data analysis method, Advances in Adaptive Data Analysis, 2 (2) (2010) 135–156.
M. E. Torres, M. A. Colominas, G. Schlotthauer and P. Flandrin, A complete ensemble empirical mode decomposition with adaptive noise, IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings, Prague, Czech Republic (2011) 4144–4147.
K. Dragomiretskiy and D. Zosso, Variational mode decomposition, IEEE Transactions on Signal Processing, 62 (3) (2014) 531–544.
X. L. Wang, J. C. Shi and J. Zhang, A power information guided-variational mode decomposition (PIVMD) and its application to fault diagnosis of rolling bearing, Digit Signal Process, 132 (2022) 103814.
F. T. Wang, C. X. Liu, T. Zhang, B. S. Dun, Q. K. Han and H. K. Li, Rolling bearing fault diagnosis method based on K value optimization VMD, J. of Vibration, Measurement and Diagnosis, 38 (3) (2018) 540–547.
H. Li, X Wu, T. Liu and Q Chen, Bearing fault feature extraction based on VMD optimized with information entropy, J. of Vibration and Shock, 37 (23) (2018) 219–225.
X. Yan and M. Jia, Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings, Mechanical Systems and Signal Processing, 122 (2019) 56–86.
R. Gu, J. Chen, R. J. Hong, H. Wang and W. W. Wu, Incipient fault diagnosis of rolling bearings based on adaptive variational mode decomposition and Teager energy operator, Measurement, 149 (2020) 106941.
X. Zhang, Q. Miao, H. Zhang and L. Wang, A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery, Mechanical Systems and Signal Processing, 108 (2018) 58–72.
X. Y. Zhou, Y. B. Li, L. Jiang and L. Zhou, Fault feature extraction for rolling bearings based on parameter-adaptive variational mode decomposition and multi-point optimal minimum entropy deconvolution, Measurement, 173 (2021) 108469.
X. Y. Zhang, Y. T. Liang, J. Z. Zhou and Y. Zang, A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM, Measurement, 69 (2015) 164–179.
Z. R. Peng and Z. Liu, Optimal sensor placement of a gear box based on fault diagnosability, J. of Vibration and Shock, 40 (4) (2021) 155–163.
Z. T. Han, Z. Q. Gu, X. K. Ma and W. L. Chen, Multimaterial layout optimization of truss structures via an improved particle swarm optimization algorithm, Computers and Structures, 222 (2019) 10–24.
K. W. Li, L. Liu, J. N. Zhai, T. M. Khoshgoftaar and T. M. Li, The improved grey model based on particle swarm optimization algorithm for time series prediction, Engineering Applications of Artificial Intelligence, 55 (2016) 285–291.
C. A. Coello, G. T. Pulido and M. S. Lechuga, Handling multiple objectives with particle swarm optimization, IEEE Transactions on Evolutionary Computation, 8 (3) (2004) 256–279.
Y. T. Ai, J. Y. Guan, C. W. Fei, J. Tian and F. L. Zhang, Fusion information entropy method of rolling bearing fault diagnosis based on n-dimensional characteristic parameter distance, Mechanical Systems and Signal Processing, 88 (2017) 123–136.
A. Dibaj, R. Hassannejad, M. M. Ettefagh and M. B. Ehghaghi, Incipient fault diagnosis of bearings based on parameter-optimized VMD and envelope spectrum weighted kurtosis index with a new sensitivity assessment threshold, ISA Transactions, 114 (2021) 413–433.
Y. Hu, W. Bao, X. Tu, F. Li and K. Li, An adaptive spectral kurtosis method and its application to fault detection of rolling element bearings, IEEE Transactions on Instrumentation and Measurement, 69 (3) (2020) 739–750.
M. Y. Yu and M. H. Fang, Feature extraction of rolling bearing multiple faults based on correlation coefficient and Hjorth parameter, ISA Transactions, 129 (Part B) (2022) 442–458.
X. Li, X. L. Li, K. Wang and Y. Li, A multi-objective particle swarm optimization algorithm based on enhanced selection, IEEE Access, 7 (2019) 168091–168103.
H. Wang, F. Wu and L. Zhang, Application of variational mode decomposition optimized with improved whale optimization algorithm in bearing failure diagnosis, Alexandria Engineering J., 60 (5) (2021) 4689–4699.
J. Antoni, F. Bonnardot, A. Raad and M. El Badaoui, Cyclostationary modeling of rotating machine vibration signals, Mechanical Systems and Signal Processing, 18 (6) (2004) 1285–1314.
W. P. He, Y. Y. Zi, B. Q. Chen, F. Wu and Z. G. He, Automatic fault feature extraction of mechanical anomaly on induction motor bearing using ensemble super-wavelet transform, Mechanical Systems and Signal Processing, 54 (2015) 457–480.
H. T. Shi, Y. Y. Li, X. T. Bai, K. Zhang and X. M. Sun, A two-stage sound-vibration signal fusion method for weak fault detection in rolling bearing systems, Mechanical Systems and Signal Processing, 172 (2022) 109012.
M. Zhao, J. Lin, Y. H. Miao and X. Q. Xu, Detection and recovery of fault impulses via improved harmonic product spectrum and its application in defect size estimation of train bearings, Measurement, 91 (2016) 421–439.
Y. B. Li, X. Z. Wang, S. B. Si and S. Q. Huang, Entropy based fault classification using the Case Western Reserve University data: A benchmark study, IEEE Transactions on Reliability, 69 (2) (2020) 754–767.
B. Wang, Y. G. Lei, N. P. Li and T. Yan, Deep separable convolutional network for remaining useful life prediction of machinery, Mechanical Systems and Signal Processing, 134 (2019) 106330.
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No: 61463028); and the Natural Science Foundation of Gansu Province (20JR10RA209).
Author information
Authors and Affiliations
Corresponding author
Additional information
Zhen Liu received the Bachelor’s in Mechanical Engineering and Automation from Lanzhou Institute of Technology, Lanzhou, China, in 2017. He received the Master’s in Vehicle Engineering from Lanzhou Jiaotong University, Lanzhou, China, in 2020, where he is currently pursuing the Ph.D. in Mechatronic Engineering. His main research areas include signal processing and fault diagnosis of mechanical equipment.
Zhenrui Peng received the Bachelor’s in Mechanical Engineering from Lanzhou Jiaotong University, Lanzhou, China, in 1995, and the Ph.D. in Control Science and Engineering from Zhejiang University, Hangzhou, China, in 2007. He presided over three projects of the National Natural Science Foundation of China and published over 90 papers up to now, and over 30 papers have been indexed by SCI, EI, and ISTP. His major research fields include fault diagnosis of mechanical equipment, finite element model updating, and structural response reconstruction.
Pei Liu received the Bachelor’s in Industrial Engineering from Lanzhou Jiaotong University, Lanzhou, China, in 2019, where he is currently pursuing the Master’s in Mechanical Engineering. His main research interests include signal processing and fault diagnosis of mechanical equipment.
Rights and permissions
About this article
Cite this article
Liu, Z., Peng, Z. & Liu, P. Multi-feature optimized VMD and fusion index for bearing fault diagnosis method. J Mech Sci Technol 37, 2807–2820 (2023). https://doi.org/10.1007/s12206-023-0508-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-023-0508-4