Bearing Fault Detection Research Articles

A bearing fault detection and remaining useful life prediction method based on a multi-branch residual feature fusion mechanism and optimized weight allocation

Within the context of rapidly progressing industrial sectors, rolling bearings have become a fundamental component across an array of mechanical systems. Their fault detection and remaining useful life (RUL) estimations are vital for ensuring industrial production safety. Yet, the understated characteristics of early-stage, minor faults in bearing degradation often escape detection. Additionally, numerous existing networks overlook the critical information embedded in multi-scale features, consequently diminishing the accuracy of predictions and classifications. The present study proposes MM-InfoGAN (multi-branch residual feature fusion and multi-objective optimization information maximization generative adversarial network), an innovative approach for intelligent fault detection and RUL prediction to address these issues. MM-InfoGAN augments the network’s ability to extract bearing fault characteristics and RUL data, employing a multi-branch residual feature fusion network structure coupled with an attention mechanism. Moreover, it refines the weight allocation strategy for geometric loss and introduces a novel loss function. This function optimizes weight distribution during the GAN’s training phase, expediting the attainment of network equilibrium. The efficacy of the comprehensive MM-InfoGAN model and its integrated modules was substantiated through comparative and ablation experiments conducted on the XJTU-SY dataset and IMS Bearing dataset.

Influences of inclined crack defects on vibration characteristics of cylindrical roller bearings

Crack initiation and propagation directions on the raceway surface of cylindrical roller bearings (CRBs) can generate different forms of excitation patterns and affect the vibration level of CRBs. For inclined crack defects on the raceway surface, the direction of a roller passing through the cracked raceway determines the order and amplitude of time-varying displacement (TVD) excitation and time-varying stiffness (TVS) excitation. In this study, two different excitation modes are proposed to simulate the interactions between the roller and the raceway. Then, the excitation modes are integrated into the dynamic model of CRB and used to study the effects of crack inclination and propagation direction on the vibration characteristics of CRBs. The results show that the bearing vibration acceleration caused by excitation mode I is greater than that caused by excitation mode II. The distribution direction of the inclined crack defect on the CRB raceway has a great influence on its vibration level. It can provide useful guidance for early bearing fault detection and diagnosis.

A Study of Noise Effect in Electrical Machines Bearing Fault Detection and Diagnosis Considering Different Representative Feature Models

As the field of fault diagnosis in electrical machines has significantly attracted the interest of the research community in recent years, several methods have arisen in the literature. Also, raw data signals can be acquired easily nowadays, and, thus, machine learning (ML) and deep learning (DL) are candidate tools for effective diagnosis. At the same time, a challenging task is to identify the presence and type of a bearing fault under noisy conditions, especially when relevant faults are at their incipient stage. Since, in real-world applications and especially in industrial processes, electrical machines operate in constantly noisy environments, a key to an effective approach lies in the preprocessing stage adopted. In this work, an evaluation study is conducted to find the most suitable signal preprocessing techniques and the most effective model for fault diagnosis of 16 conditions/classes, from a low-workload (computational burden) perspective using a well-known dataset. More specifically, the reliability and resiliency of conventional ML and DL models is investigated here, towards rolling bearing fault detection, simulating data that correspond to noisy industrial environments. Diverse preprocessing methods are applied in order to study the performance of different training methods from the feature extraction perspective. These feature extraction methods include statistical features in time-domain analysis (TDA); wavelet packet decomposition (WPD); continuous wavelet transform (CWT); and signal-to-image conversion (SIC), utilizing raw vibration signals acquired under varying load conditions. The noise effect is examined and thoroughly commented on. Finally, the paper provides accumulated usual practices in the sense of preferred preprocessing methods and training models under different load and noise conditions.

A Novel Hybrid Technique Combining Improved Cepstrum Pre-Whitening and High-Pass Filtering for Effective Bearing Fault Diagnosis Using Vibration Data.

Rolling element bearings (REBs) are an essential part of rotating machinery. A localised defect in a REB typically results in periodic impulses in vibration signals at bearing characteristic frequencies (BCFs), and these are widely used for bearing fault detection and diagnosis. One of the most powerful methods for BCF detection in noisy signals is envelope analysis. However, the selection of an effective band-pass filtering region presents significant challenges in moving towards automated bearing fault diagnosis due to the variable nature of the resonant frequencies present in bearing systems and rotating machinery. Cepstrum Pre-Whitening (CPW) is a technique that can effectively eliminate discrete frequency components in the signal whilst detecting the impulsive features related to the bearing defect(s). Nevertheless, CPW is ineffective for detecting incipient bearing defects with weak signatures. In this study, a novel hybrid method based on an improved CPW (ICPW) and high-pass filtering (ICPW-HPF) is developed that shows improved detection of BCFs under a wide range of conditions when compared with existing BCF detection methods, such as Fast Kurtogram (FK). Combined with machine learning techniques, this novel hybrid method provides the capability for automated bearing defect detection and diagnosis without the need for manual selection of the resonant frequencies. The results from this novel hybrid method are compared with a number of established BCF detection methods, including Fast Kurtogram (FK), on vibration signals collected from the project I2BS (An EU Clean Sky 2 project 'Integrated Intelligent Bearing Systems' collaboration between Schaeffler Technologies and the University of Southampton. Safran Aero Engines was the topic manager for this project) and those from three databases available in the public domain-Case Western Reserve University (CWRU), Intelligent Maintenance Systems (IMS) datasets, and Safran jet engine data-all of which have been widely used in studies of this kind. By calculating the Signal-to-Noise Ratio (SNR) of each case, the new method is shown to be effective for a much lower SNR (with an average of 30.21) compared with that achieved using the FK method (average of 14.4) and thus is much more effective in detecting incipient bearing faults. The results also show that it is effective in detecting a combination of several bearing faults that occur simultaneously under a wide range of bearing configurations and test conditions and without the requirement of further human intervention such as extra screening or manual selection of filters.

Joint loss learning-enabled semi-supervised autoencoder for bearing fault diagnosis under limited labeled vibration signals

Rolling bearing is a critical component of machinery that has been widely applied in manufacturing, transportation, aerospace, and power and energy industries. The timely and accurate bearing fault detection thus is of vital importance. Computational data-driven deep learning has recently become a prevailing approach for bearing fault detection. Despite the progress of the deep learning approach, the deep learning performance is hinged upon the size of labeled data, the acquisition of which is expensive in actual implementation. Unlabeled data, on the other hand, are inexpensive. In this research, we develop a new semi-supervised learning method built upon the autoencoder to fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance. Compared with the state-of-the-art semi-supervised learning methods, this proposed method can be more conveniently implemented with fewer hyperparameters to be tuned. In this method, a joint loss is established to account for the effects of labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other well-established baseline methods. Specifically, nearly all emulation runs using the proposed methodology can lead to around 2%–5% accuracy increase, indicating its robustness in performance enhancement.

Automated Variational Nonlinear Chirp Mode Decomposition for Bearing Fault Diagnosis

The variational non-linear chirp mode decomposition (VNCMD) requires initialization of number of modes (NMs) and instantaneous frequency (IF). This paper proposes an automated method for NM selection and IF initialization which works on the scale-space representation based automated boundary detection in magnitude spectrum (MS). The proposed automated VNCMD (AVNCMD) method is applied for bearing fault detection in which the kurtosis based dominant mode selection method is recommended. The instantaneous amplitude (IA) and IF with spectral entropy are computed from the dominant mode. Features are given to feed forward neural network classifier. Methodology is investigated on two datasets for inner race, outer race, and ball race faults detection. The proposed method classifies inner race, outer race, and ball race bearing faults with 97.52% accuracy and classifies inner race and outer race bearing fault with 100% accuracy. Efficacy of the proposed method is compared with the existing methods to justify the superiority.

Evaluation of Bearing Fault Detection on Different _K-Folds using Deep Learning Ensemble Models

One of the most crucial parts of contemporary machinery and industrial equipment is the induction motor. Therefore, it is essential to create a fault diagnosis system that can identify induction motor problems and operating circumstances before they become serious. In this study, an induction motor's defect diagnosis is carried out in three different states, including normal, rotor fault, and bearing fault. The suggested fault diagnostic system is also described, along with a GUI. The experimental findings support the suitability of the suggested approach for rotor and bearing defects in induction motor diagnosis. A GUI for defect diagnostics was also created and used in a real-world setting. We have used Chi-Square method for high score attributes values. For the normal, rotor fault, and bearing fault states of induction motors identified by DBN, CNN, SNN, SVM and RF respectively, the fault detection system's accuracy in the actual world. In the experiment, we find Algorithms model-II, K-Folds (5, 10 & 15) , Accuracy (%), Training loss, Validation loss value for RF-SVM-CNN are 89.2, 0.260013, 0.304936 for k fold 5, 98.4, 0.155960, 0.154133 for k-fold 10 and 98.3, 0.155759, 0.144127 for k- fold 15 respectively.

Feature-Based Bearing Fault Classification Using Taylor–Fourier Transform

This paper proposes a feature-based methodology for early bearing fault detection and classification in induction motors through current signals using the digital Taylor–Fourier transform (DTFT) and statistical methods. The DTFT allows the application of narrow bandwidth digital filters located in the spurious current signal components, wherewith it is possible to gain information to detect bearing issues and classify them using statistical methods. The methodology was implemented in MATLAB using the digital Taylor–Fourier transform for three fault types (bearing ball damage, outer-race damage, and corrosion damage) at different powering conditions: power grid source at 60 Hz and adjustable speed drive applied (60 Hz, 50 Hz, 40 Hz, 30 Hz, 20 Hz, and 10 Hz) in loading and unloading conditions. Results demonstrate a classification accuracy between 93–99% for bearing ball damage, 91–99% for outer-race damage, and 94–99% for corrosion damage.

Co-design Model for Neuromorphic Technology Development in Rolling Element Bearing Condition Monitoring

This paper presents an end-to-end condition monitoring co-design model, from vibration measurement to anomaly detection, where conventional signal processing principles are combined with neuromorphic sensing and computing concepts to enable investigations of the potential improvements offered by brain-like information processing technologies.
 The use of machine learning in condition monitoring became increasingly popular for intelligent fault diagnosis in the last decade, taking advantage of the rapid developments in deep learning.
 However, the high computational cost of training and using deep neural networks prevents the use of such solutions for analysing the bulk of data generated by the resource constrained edge devices, i.e., the condition monitoring sensor systems, as only a minor fraction of data can be transmitted to the cloud or edge servers for analysis.
 There is an untapped potential to process this data and thereby improve intelligent fault diagnosis models using event-triggered sensing, spiking neural networks, and neuromorphic processors that substantially can improve the energy efficiency and capacity of embedded machine learning condition monitoring solutions.
 The proposed co-design model is evaluated on two use-cases involving rolling element bearing failures, one based on a labelled laboratory environment dataset, and one based on a wind turbine drivetrain bearing failure representing a real-world scenario with stochastic changes of machine state and unknown labels of the bearing condition.
 By adjusting co-design parameters, the resulting hybrid conventional/neuromorphic model show a comparable accuracy in detection performance for the laboratory dataset compared to the state-of-the-art reported in the literature.
 Similarly, for the wind turbine drivetrain dataset a bearing fault detection time comparable to that in previous work is obtained.
 This shows the successful implementation of a hybrid conventional/neuromorphic co-design model for condition monitoring applications, offering novel opportunities to investigate performance trade-offs and efficiency improvements enabled by neuromorphic technologies.

Bispectral analysis and information fusion technique for bearing fault classification

The feasibility and effectiveness of data fusion for the fault classification of bearing faults have been very well iterated in the literature. However, all previous endeavors have been limited to time, frequency, and time-frequency domain techniques. The use of higher-order spectral analysis (HOSA), especially Bispectrum and Trispectrum, for fault detection is gaining importance in recent studies due to the many advantages of HOSA. Bispectral features provide a valuable tool for capturing higher-order statistical relationships in signals, making them particularly effective in detecting nonlinearities and distinguishing between Gaussian and non-Gaussian data. Their robustness to noise and ability to reveal hidden information make them advantageous in applications such as vibration analysis, speech recognition, and image processing, where complex signal interactions and nonlinearity play a significant role in data interpretation and pattern recognition. This paper proposes a methodology for the fusion of the data from the vibration and the acoustic sensors for the fault detection of roller element bearings using bispectral features. Higher-order spectral characteristics are derived from vibration and acoustic sensor data, and they are fused using artificial neural networks and various other machine learning algorithms like support vector machine, K nearest neighbor, Naïve Bayes algorithm, and decision tree. This work primarily aims to evaluate the performance of each classifier when applied to the fused data, in contrast to the performance when using individual sensor data alone. The outcomes revealed that, even though the accuracy of the acoustic sensor data was lower in comparison to the vibration sensor data, which exhibited the highest performance of 100% accuracy with nearly all the classifiers, the fused data achieved remarkable results of 100% accuracy with artificial neural networks and decision trees. However, the Naïve Bayes algorithm yielded the lowest accuracy when applied to the fused data. The primary objective of this paper is to demonstrate the application of bispectrum analysis for data fusion and to enhance confidence in fault detection. It achieves this by maintaining the capability to accurately and dependably detect faults, even when a single sensor encounters issues or falls short of anticipated performance standards.

Early Fault Detection of Rolling Bearings Based on Time-Varying Filtering Empirical Mode Decomposition and Adaptive Multipoint Optimal Minimum Entropy Deconvolution Adjusted.

Due to the early formation of rolling bearing fault characteristics in an environment with strong background noise, the single use of the time-varying filtering empirical mode decomposition (TVFEMD) method is not effective for the extraction of fault characteristics. To solve this problem, a new method for early fault detection of rolling bearings is proposed, which combines multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) with parameter optimization and TVFEMD. Firstly, a new weighted envelope spectrum kurtosis index is constructed using the correlation coefficient and envelope spectrum kurtosis, which is used to identify the effective component and noise component of the bearing fault signal decomposed by TVFEMD, and the intrinsic mode function (IMF) containing rich fault information is selected for reconstruction. Then, a new synthetic impact index (SII) is constructed by combining the maximum value of the autocorrelation function and the kurtosis of the envelope spectrum. The SII index is used as the fitness function of the gray wolf optimization algorithm to optimize the fault period, T, and the filter length, L, of MOMDEA. The signal reconstructed by TVF-EMD undergoes adaptive filtering using the MOMEDA method after parameter optimization. Finally, an envelope spectrum analysis is performed on the signal filtered by the adaptive MOMEDA method to extract fault feature information. The experimental results of the simulated and measured signals indicate that this method can effectively extract early fault features of rolling bearings and has good reliability. Compared to the classical FSK, MCKD, and TVFEMD-MOMEDA methods, the first-order correlated kurtosis (FCK) and fault feature coefficient (FFC) of the filtered signal obtained using the proposed method are the largest, while the sample entropy (SE) and envelope spectrum entropy (ESE) are the smallest.

A novel bearing fault diagnosis approach using the Gaussian mixture model and the weighted principal component analysis

The efficient diagnosis of bearing faults requires the extraction of informative features. This paper presents a novel approach that combines Weighted Principal Component Analysis (WPCA) with the Gaussian Mixture Model (GMM) for bearing fault diagnosis. The method employs GMM as a fault classifier, aiming to enhance both efficiency and diagnostic accuracy. The proposed algorithm, Expectation Selection Maximization (ESM), introduces a feature selection step to identify the most relevant features for effective bearing fault detection. Specifically, the suggested algorithm utilizes the conditional entropy divergence indicator, a statistical metric, to quantify the significance of features in detecting bearing faults. To validate the effectiveness of this approach, two distinct case studies are conducted using datasets obtained from the University of Ottawa and Case Western Reserve University (CWRU). These datasets encompass a wide range of bearing working conditions, providing a comprehensive evaluation. Experimental results underscore the merits of the approach, achieving an average accuracy rate of 93% for the University of Ottawa dataset and 80% for the CWRU dataset. Furthermore, the findings highlight the superior performance of the proposed method compared to alternative techniques, as evidenced by the receiver operating characteristic (ROC) curve metric.

Multi-Objective Sparsity Maximum Mode De-Composition: A New Method for Rotating Machine Fault Diagnosis on High-Speed Train Axle Box

Signal decomposition techniques generally have two limitations. First, for adaptive correlated kurtogram (ACK) and variational mode decomposition (VMD), etc., the definition of the decomposition target has no direct relationship with the features of fault impacts, i.e., the decomposition is not guided by the health indices used to characterize bearing faults, resulting in fault impacts cannot be completely separated from vibration data. Second, it is hard to accurately determine the decomposition stop parameter (the number of final output modes), resulting in frequent over- or under-decomposition. All these are not conducive to bearing fault detection in engineering practice. In this paper, a new decomposition method, multi-objective sparse maximum mode decomposition (MOSMMD), is proposed. Firstly, by analyzing the Fourier spectrum of vibration data, MOSMMD constructs multiple finite impulse response filters covering different frequency bands to obtain initial candidate modes. Then, aiming at maximizing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L2</i> / <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L1</i> norm of envelope spectrum (ES), the upper and lower cutoff frequencies of each filter are adjusted adaptively through iterative optimization, and the frequency bands covered by each mode are adjusted accordingly. Finally, by using that fault feature harmonics have periodic natures in ES, the redundant modes are eliminated and only the modes with obvious fault features are output. Compared with VMD and ACK, the decomposition target of MO-SMMD is directly related to the fault features, i.e., cyclostationarity of fault impacts, which makes the extraction of fault impacts more accurate. Moreover, the number of final output modes of MOSMMD is determined adaptively and does not need to be set in advance as an input parameter. Also, MOSMMD can decompose fault modes from vibration data without prior fault information, even when processing concurrent fault signals. Simulation and experiments demonstrate the superiority of the proposed MOSMMD.

Bearing Fault Detection: Feature Selection Algorithm Efficacy Study

Early detection of bearing failures is crucial, requiring a comprehensive diagnostic scheme with relevant features and an effective classifier. Computationally intelligent algorithms (CIA) contribute to enhancing the feature selection process. In this study, 99 classification datasets with classes ranging from 4 to 48 were derived from vibration recordings of Case Western Reserve University. 18 features are extracted in the time domain, of which 12 are statistical features and 6 are time-based frequency features (TBFF). Extracted features are ranked by mutual information, multi-cluster feature selection, and Laplacian scores. The best feature subsets are explored by four CIAs: ant colony optimization, simulated annealing, particle swarm optimization, and wheel-based differential evolution(WBDE) algorithms. The top 4 features of every approach are evaluated with 99 datasets. It was discovered that the feature subset recognized by most of the methodologies is the energy of the 4th derivative, waveform length ratio, sparseness, and mean. This combination results in 92.4% (with 4 features) and 88.94%(with 3 features) accuracy for classifying 48 class data, whereas the deep learning model resulted in 85.6% (with 18 features). Remarkably, it is noted that the feature subset identified by WBDE is identical to the feature subset arrived by voting. Finally, the results are compared to similar research in the literature, and improvements in classification accuracy are revealed.

Piecewise time-delay tri-stable stochastic resonance system and its application in bearing fault diagnosis

Current studies of time-delay based systems are compared to classical tri-stable stochastic resonance (CTSR) system and do not reflect the effect of adding a delay term on unsaturated systems. In this paper, a piecewise delayed tri-stable stochastic resonance (PTTSR) system is proposed. Firstly, the equivalent Langevin for PTTSR system is derived and compared with the output of CTSR and piecewise tri-stable stochastic resonance (PTSR) systems, where the addition of the time-delay term can further improve the output amplitude. Secondly, mean first pass time (MFPT) and output signal-to-noise ratio (SNR) are derived, and the effects of different parameters on MFPT and SNR are investigated. increasing the feedback intensity and time-delay length improved the output SNR. Then, the input period signal is then numerically simulated using the signal-to-noise ratio gain (SNRG) as a measurement, which increases by 2.75 dB for PTTSR system compared to PTSR system. Finally, the three systems are used for bearing fault detection and the system parameters are optimized by genetic algorithm. The results showed that the output amplitude of PTTSR system is more than 12 times that of PTSR system and the SNRG increased by more than 2 dB. This demonstrates the superior performance of PTTSR system in detecting weak signals and provides good feasibility in engineering applications.

Transient-extracting wavelet transform for impulsive-like signals and application to bearing fault detection

Being able to characterize impulsive-like signals and extract their transitory features is difficult due to the presence of noise and irrelevant signal components in real signals. To address these problems, a brand-new time-frequency (TF) analysis technique called the transient-extracting wavelet transform is developed. This method is put forth by first investigating which TF coefficients can represent the fundamental TF properties of impulsive signals, and then designing an extraction operator to get the most related TF coefficients while simultaneously removing the unrelated ones. The signal reconstruction of this method is also analyzed. Additionally, a transient feature extraction approach is suggested for pinpointing the impulse’s occurrence timing, which is essential for correctly identifying the fault type. The analysis shows that the suggested method is more able to analyze impulsive-like data and is an effective bearing defect detector.

GRP-YOLOv5: An Improved Bearing Defect Detection Algorithm Based on YOLOv5.

Currently, most chemical transmission equipment relies on bearings to support rotating shafts and to transmit power. However, bearing defects can lead to a series of failures in the equipment, resulting in reduced production efficiency. To prevent such occurrences, this paper proposes an improved bearing defect detection algorithm based on YOLOv5. Firstly, to mitigate the influence of the similarity between bearing defects and non-defective regions on the detection performance, gamma transformation is introduced in the preprocessing stage of the model to adjust the image's grayscale and contrast. Secondly, to better capture the details and semantic information of the defects, this approach incorporates the ResC2Net model with a residual-like structure during the feature-extraction stage, enabling more nonlinear transformations and channel interaction operations so as to enhance the model's perception and representation capabilities of the defect targets. Additionally, PConv convolution is added in the feature fusion part to increase the network depth and better capture the detailed information of defects while maintaining time complexity. The experimental results demonstrate that the GRP-YOLOv5 model achieves a mAP@0.5 of 93.5%, a mAP@0.5:0.95 of 52.7%, and has a model size of 25 MB. Compared to other experimental models, GRP-YOLOv5 exhibits excellent performance in bearing defect detection accuracy. However, the model's FPS (frames per second) performance is not satisfactory. Despite its small size of 25 MB, the processing speed is relatively slow, which may have some impact on real-time or high-throughput applications. This limitation should be considered in future research and in the optimization efforts to improve the overall performance of the model.

A Wind Turbine Bearing Fault Detection Method Based on Improved CEEMDAN and AR-MEDA

A Wind Turbine Bearing Fault Detection Method Based on Improved CEEMDAN and AR-MEDA

Blind extraction of acoustic signals from rolling bearing composite faults based on ISCA-IMCKD

In production practice, the signal gathered by a sensor often includes strong ambient noise, and its composition is complex. Focusing on the problem that traditional methods are difficult to separate and extract fault frequencies from strong background noise, a novel compound fault blind extraction method based on improved sparse component analysis (ISCA) and improved maximum correlation kurtosis deconvolution (IMCKD)-named ISCA‐IMCKD- is suggested. Initially, the signal that the sensor has collected is shifted into time-frequency area signal by short-time Fourier transform (STFT). In addition, the single source domain characteristic data is screened by improved single source point detection to determine the number of sources. Second, the ISCA method is optimized by using cosine distance improved fuzzy C-means clustering, which is utilized to further process the characteristic data to calculate the mixing matrix. Moreover, the estimated source signal is initially extracted according to the membership degree of clustering results. Finally, the estimated source signal is shifted into the time area by inverse STFT transform, and the IMCKD is employed to enhance the characteristics of the projected source signals. Meanwhile, the initially estimated source signal is completely separated, and the defect frequencies of the composite faults are finally extracted by envelope analysis. Simulation experiments and measured data are employed to certify the viability of the proposed means. The defect detection of rolling bearings is finished while the time cost is significantly saved.

Early Bearing Fault Detection Using EEMD and Three-Sigma Rule Denoising Method

Rotating electrical machines have several physical phenomena. Vibration is one of the important phenomena in the operation of rotating electrical machines. In addition, the vibration signal is considered an important source to have good information on the state of rotating electrical machinery. But this signal is rich in noise, especially under the presence of the bearing fault. This paper proposes a bearing fault diagnosis method based on EEMD and a denoising method based on three-sigma rule. In the first step, the EEMD decomposed the vibration signal into several components called Intrinsic Mode Functions (IMFs). After the calculation of the kurtosis of each IMF component, the signal is reconstructed by choosing components with higher values. To enhance periodic impulses, the three-sigma rule de-noising is applied to the reconstructed signal. As a final step, the envelope spectrum is used to determine the fault characteristic frequency. As a result of testing the bearing with inner race fault and the bearing with outer race, it was verified that the proposed approach suppressed noise effectively and extracted rich fault information from the vibration signals of bearings compared to the EEMD.