Weighted low-rank sparse model via nuclear norm minimization for bearing fault detection

Du, Zhaohui; Chen, Xuefeng; Yang, Boyuan; Zhai, Zhi; Yan, Ruqiang

doi:10.1016/j.jsv.2017.03.044

Cited by 34 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Zhu and Fan [19,20] developed an optimal Laplace wavelet, tunable Q-factor wavelet transform, single-side Morlet wavelet basis combined with split variable augmented Lagrangian shrinkage algorithm (SALSA) to extract impulse components and transient features. Du [21] proposed a nuclear norm minimization that uses a weighted low-rank sparse model for bearing fault detection. Cui [22,23] introduced composite dictionary multi-atom matching and a matching pursuit algorithm based on an adaptive impulse dictionary for gear-box and bearing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Incipient Fault Diagnosis of Rolling Bearings Based on Impulse-Step Impact Dictionary and Re-Weighted Minimizing Nonconvex Penalty Lq Regular Technique

Liang

2017

Entropy

View full text Add to dashboard Cite

Abstract:The periodical transient impulses caused by localized faults are sensitive and important characteristic information for rotating machinery fault diagnosis. However, it is very difficult to accurately extract transient impulses at the incipient fault stage because the fault impulse features are rather weak and always corrupted by heavy background noise. In this paper, a new transient impulse extraction methodology is proposed based on impulse-step dictionary and re-weighted minimizing nonconvex penalty Lq regular (R-WMNPLq, q = 0.5) for the incipient fault diagnosis of rolling bearings. Prior to the sparse representation, the original vibration signal is preprocessed by the variational mode decomposition (VMD) technique. Due to the physical mechanism of periodic double impacts, including step-like and impulse-like impacts, an impulse-step impact dictionary atom could be designed to match the natural waveform structure of vibration signals. On the other hand, the traditional sparse reconstruction approaches such as orthogonal matching pursuit (OMP), L1-norm regularization treat all vibration signal values equally and thus ignore the fact that the vibration peak value may have more useful information about periodical transient impulses and should be preserved at a larger weight value. Therefore, penalty and smoothing parameters are introduced on the reconstructed model to guarantee the reasonable distribution consistence of peak vibration values. Lastly, the proposed technique is applied to accelerated lifetime testing of rolling bearings, where it achieves a more noticeable and higher diagnostic accuracy compared with OMP, L1-norm regularization and traditional spectral Kurtogram (SK) method.

show abstract

Section: Introductionmentioning

confidence: 99%

Incipient Fault Diagnosis of Rolling Bearings Based on Impulse-Step Impact Dictionary and Re-Weighted Minimizing Nonconvex Penalty Lq Regular Technique

Liang

2017

Entropy

View full text Add to dashboard Cite

show abstract

“…Recently, the sparse and low-rank physical meaning has been successfully applied to vibration signal denoising and fault diagnosis [7], [8]. Du et al [9] proposed a weighted low-rank sparse model for bearing fault diagnosis. Zhang et al [10] extended this model to the fault diagnosis of highspeed aero-engine bearings by improving the construction of the matrix using k-means clustering.…”

Section: Introductionmentioning

confidence: 99%

The sparse and low-rank interpretation of SVD-based denoising for vibration signals

Zhao

Wang

Wong

et al. 2020

2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

Self Cite

View full text Add to dashboard Cite

Vibration signal denoising is one of the most important steps in condition monitoring and fault diagnosis, and SVD-based methods are a vital part of advanced signal denoising due to their non-parametric and simple properties. The relationships between SVD-based denoising and other advanced signal processing methods are very significant and can help speed up the development of SVD-based denoising methods. There is limited prior work into the sparse and low-rank meaning of SVD-based denoising. In this paper, we build the relationships among SVDbased denoising, sparse l0-norm minimization, sparse weighted l1-norm minimization, and weighted low-rank model, when the dictionary is designed by left and right singular matrices in sparse minimization. Using the derived conclusion, we establish weighted soft singular value decomposition (WSSVD) for vibration signal denoising. Finally, we perform one experimental study to verify the effectiveness of WSSVD considering impulse interference and amplitude fidelity.Index Terms-Sparse and low-rank, SVD-based denoising, vibration signal processing

show abstract

“…In [35], Zhang et al proposed a novel convex penalty regularization method called Kurtosis-based weighted sparse decomposition (Kur-WSD) on the basis of the L1-norm method to detect the inner fault of an alternating current motor. In [36], Du et al propose a rigorously weighted low-rank sparse detection framework to explore the physical/internal mechanisms of bearing faults and implement fault diagnosis of a wind turbine.…”

Section: Introductionmentioning

confidence: 99%

Weak Fault Detection for Gearboxes Using Majorization–Minimization and Asymmetric Convex Penalty Regularization

Liang

2018

Symmetry

View full text Add to dashboard Cite

It is a primary challenge in the fault diagnosis community of the gearbox to extract the weak fault features under heavy background noise and nonstationary conditions. For this purpose, a novel weak fault detection approach based on majorization-minimization (MM) and asymmetric convex penalty regularization (ACPR) is proposed in this paper. The proposed objective cost function (OCF) consisting of a signal-fidelity term, and two parameterized penalty terms (i.e., one is an asymmetric nonconvex penalty regularization term, and another is a symmetric nonconvex penalty regularization term).To begin with, the asymmetric and symmetric penalty functions are established on the basis of an L1-norm model, then, according to the splitting idea, the majorizer of the symmetric function and the majorizer of the asymmetric function are respectively calculated via the MM algorithm. Finally, the MM is reintroduced to solve the proposed OCF. As examples, the effectiveness and reliability of the proposed method is verified through simulated data and gearbox experimental real data. Meanwhile, a comparison with the state of-the-art methods is illustrated, including nonconvex penalty regularization (NCPR) and L1-norm fused lasso optimization (LFLO) techniques, the results indicate that the gear chipping characteristic frequency 13.22 Hz and its harmonic (2f, 3f, 4f and 5f) can be identified clearly, which highlights the superiority of the proposed approach.

show abstract

Weighted low-rank sparse model via nuclear norm minimization for bearing fault detection

Cited by 34 publications

References 30 publications

Incipient Fault Diagnosis of Rolling Bearings Based on Impulse-Step Impact Dictionary and Re-Weighted Minimizing Nonconvex Penalty Lq Regular Technique

Incipient Fault Diagnosis of Rolling Bearings Based on Impulse-Step Impact Dictionary and Re-Weighted Minimizing Nonconvex Penalty Lq Regular Technique

The sparse and low-rank interpretation of SVD-based denoising for vibration signals

Weak Fault Detection for Gearboxes Using Majorization–Minimization and Asymmetric Convex Penalty Regularization

Contact Info

Product

Resources

About