Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review

Zhang, Shen; Zhang, Shibo; Wang, Bingnan; Habetler, T.G.

doi:10.1109/access.2020.2972859

Cited by 553 publications

(342 citation statements)

References 163 publications

(176 reference statements)

Supporting

Mentioning

328

Contrasting

Unclassified

Order By: Relevance

“…Symmetry 2020, 12, x FOR PEER REVIEW 3 of 23 component analysis. In particular, the application of deep learning methods has attracted considerable interest from the industry and academia [16,17]. For bearing fault detection, Ni et al [18] proposed a method based on random matrix theory to evaluate the degradation of the rolling bearing system and increase the production safety.…”

Section: Design and Analysis Of A Dcab Systemmentioning

confidence: 99%

Bifurcation and Nonlinear Behavior Analysis of Dual-Directional Coupled Aerodynamic Bearing Systems

Wang

Lin

2020

Symmetry

View full text Add to dashboard Cite

Dual-directional coupled aerodynamic bearing (DCAB) systems have received considerable attention over the past few years. These systems are primarily used to solve air lubrication problems in high-precision mechanisms and equipment that run at a high rotational speed and require high rigidity and precision. DCABs have the advantages of axial and radial thrust and provide high rigidity, dual-directional support, and high load-carrying capacity. In DCAB systems, the nonlinearity of the air film pressure and dynamic problems, such as critical speed, unbalanced air supply, or poor design, can cause the instability of the rotor-bearing system and phenomena such as nonperiodic or chaotic motion under certain parameters or conditions. Therefore, to investigate what conditions lead to nonperiodic phenomena and to avoid irregular vibration, the properties and performance of the DCAB system were explored in detail by using three numerical methods for verifying the accuracy of the numerical results. The rotor behavior was also studied by analyzing the spectral response, the bifurcation phenomenon, Poincaré maps, and the maximum Lyapunov exponent. The numerical results indicate that chaos occurs in the DCAB system for specific ranges of the rotor mass and bearing number. For example, when the rotor mass (mr) is 5.7 kg, chaotic regions where the maximum Lyapunov exponents are greater than 0 occur at bearing number ranges of 3.96–3.98 and 4.63–5.02. The coupling effect of the rotor mass and bearing number was also determined. This effect can provide an important guideline for avoiding an unstable state.

show abstract

Section: Design and Analysis Of A Dcab Systemmentioning

confidence: 99%

Bifurcation and Nonlinear Behavior Analysis of Dual-Directional Coupled Aerodynamic Bearing Systems

Wang

Lin

2020

Symmetry

View full text Add to dashboard Cite

show abstract

“…Despite the wide application, rolling bearings are prone to a variety of premature failures caused by many reasons, such as fatigue, lack of lubrication, or overload. The occurrence of failures in the bearing will introduce potential damages to the machinery, resulting in performance degradation in the system [1]- [3]. Therefore, fault diagnosis of rolling bearing is of significance to ensure the reliability of the machinery, enabling detecting and troubleshooting the potential failures as early as possible [4].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Multiscale Weighted Permutation Entropy for Rolling Bearing Fault Diagnosis

et al. 2020

View full text Add to dashboard Cite

Fault diagnosis of rolling bearing is of great importance to ensure high reliability and safety in the industrial machinery system. Entropy measures are useful non-linear indicators for time series complexity analysis and have been widely applied in bearing fault diagnosis in the past decade. In this paper, an improved entropy measure is proposed, named Adaptive Multiscale Weighted Permutation Entropy (AMWPE). Then, a new rolling bearing fault diagnosis method is developed based on the AMWPE and multi-class SVM. For comparison, an experimental bearing dataset is analyzed using the AMWPE and conventional entropy measures, and then multi-class SVM is adopted for fault type classification. Further, the robustness of different entropy measures against noise is studied by analyzing noisy signals with various Signal-to-Noise Ratios (SNRs). The experimental results have demonstrated the effectiveness of the proposed method in bearing fault diagnosis under different fault types, severity degrees, and SNR levels. INDEX TERMS Fault diagnosis, rolling bearing, entropy measure, support vector machine. YU ZHANG received the B.Eng. degree from the

show abstract

“…Most current diagnostic algorithms are evaluated on Case Western Reserve University (CWRU) bearing dataset. The accuracy of REB fault diagnosis on CWRU bearing dataset is already overly saturated [30]. The highest accuracy of 99.99% has been yielded by Wen et.…”

Section: Introductionmentioning

confidence: 99%

Input Feature Mappings-Based Deep Residual Networks for Fault Diagnosis of Rolling Element Bearing With Complicated Dataset

et al. 2020

View full text Add to dashboard Cite

Most rolling element bearing (REB) fault diagnosis algorithms are evaluated on the Case Western Reserve University (CWRU) bearing dataset for its popularity and simplicity. However, the diagnosis accuracy on CWRU bearing dataset is overly saturated; it is nearly up to 100%. In this study, an input feature mappings (IFMs)-based deep residual network (ResNet) is proposed to conduct detailed and comprehensive fault diagnosis on REB with complicated bearing dataset. Firstly, a new data preprocessing method named as a signal-to-IFMs method is proposed to automatically extract features from raw signals without predefined parameters. Then, a deep ResNet is used as the fault classifier to learn the discriminative features from IFMs and identify the faults of REB. Finally, the proposed model is evaluated on the artificial, real, and mixed damages of the Paderborn university bearing dataset. The proposed method yields the average testing accuracies of 99.7%, 99.7%, and 99.81% in artificial, real, and mixed bearing damages, which outperforms other methods. INDEX TERMS Rolling element bearing, fault diagnosis, signal-to-input feature mappings, deep residual networks.

show abstract

Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review

Cited by 553 publications

References 163 publications

Bifurcation and Nonlinear Behavior Analysis of Dual-Directional Coupled Aerodynamic Bearing Systems

Bifurcation and Nonlinear Behavior Analysis of Dual-Directional Coupled Aerodynamic Bearing Systems

Adaptive Multiscale Weighted Permutation Entropy for Rolling Bearing Fault Diagnosis

Input Feature Mappings-Based Deep Residual Networks for Fault Diagnosis of Rolling Element Bearing With Complicated Dataset

Contact Info

Product

Resources

About