Bearing Fault Signal Research Articles

Fault diagnosis of rotating mechanical bearing based on adaptive noise-complete ensemble empirical modal decomposition and time-reallocated multisynchronous compression transform

Due to the noise interference in the original vibration signals measured from vibration sensors, it is necessary to noise reduce the signals before extracting fault features from them. This paper proposes a fault feature extraction method combining the adaptive noise-complete ensemble empirical modal decomposition (CEEMDAN) and the time-reallocated multisynchronous compression transform (TMSST), which first decomposes the original signal, then combines the relevant index values of the decomposed signal to filter the optimal signal components, and finally uses the TMSST to extract the fault features from the reconstructed signal. In this paper, a set of simulated signal data and two sets of experimental data are used to evaluate the performance of the method, and the results show that the method works well for rolling bearing fault signal identification.

Enhancement of bearing fault detection using an alternative analytic energy operator and sparse Bayesian step-filtering

The bearing fault signal is a kind of weak signal, so it is easy to be submerged by background noise. As such, signature extraction is facing a great challenge; hence, an effective signature extraction method plays an essential role in bearing fault extraction. In this paper, a new method for bearing fault detection based on an alternative analytic energy operator and sparse Bayesian step-filtering (SBSF) was applied. The SBSF technique can remove much background noise from the raw signal and enhance the characteristics related to the bearing fault. Besides, it has also a high calculation efficiency. Afterward, an improved analytic energy operator, the symmetric high-order analytic energy operator (SHO-AEO), which is an enhanced demodulation technique that outperforms the conventional demodulation technique, was applied to detect bearing fault signatures from filtered signals. The proposed energy measure is formed using the original signal, its Hilbert transform, and its high-order derivatives. Unlike traditional energy operators, it includes the information of the real and imaginary parts of the analytic signal. As a demodulation technique, it is also tailored to extract both the amplitude and frequency modulations from the filtered signal. Furthermore, compared with the previous energy operators, it provides better anti-noise capability. Hence, the proposed fault detection method of combining the SHO-AEO and SBSF not only has high computational efficiency but also provides much better noise handling potential. Through simulated and real tests, this proposed method is demonstrated to be robust against various noise levels and to detect the bearing fault signature.

Fault diagnosis of rolling bearing using marine predators algorithm-based support vector machine and topology learning and out-of-sample embedding

The long-term safe operation of rotating machinery is closely related to the stability of rolling bearings. This paper proposes a rolling bearing fault diagnosis method based on refined composite multiscale fuzzy entropy (RCMFE), topology learning and out-of-sample embedding (TLOE), and the marine predators algorithm based-support vector machine (MPA-SVM). First, the RCMFE algorithm is used to extract the features of the original rolling bearing fault signal and to construct the original high-dimensional fault feature set. Then, TLOE is used to reduce the dimensionality of the high-dimensional fault feature set. The low-dimensional sensitive fault features are extracted to construct a low-dimensional fault feature subset. Finally, fault-type discrimination is performed using the MPA-SVM. The Case Western Reserve University dataset and data from fault diagnosis experiments performed on 1210 self-aligning ball bearings were used to verify the proposed method. The results demonstrate the effectiveness of the fault diagnosis method, which can diagnose bearing faults with up to 100% accuracy.

An improved local characteristic-scale decomposition to restrict end effects, mode mixing and its application to extract incipient bearing fault signal

Empirical mode decomposition (EMD) adaptively decomposes a signal into a linear combination of waveforms embedded in the signal and has been successfully applied to many engineering areas including mechanical fault diagnosis. Local characteristic-scale decomposition (LCD) defines a new baseline signal and then conducts the sifting process to achieve decomposition. LCD utilizes the inherent instantaneous amplitude/frequency/phase information and morphological features of signals leading to a set of powerful adaptive signal filters. However, LCD suffers from the problems of end effects and mode mixing inheriting from the sifting process. This paper proposes an improved LCD (ILCD) method to reduce the two problems. First, the equivalent filter and equivalent impulse response of LCD are analyzed and compared with EMD and intrinsic time-scale decomposition (ITD). Furthermore, the ILCD deals with the problem of end effects based on support vector regression (SVR) boundary condition processing method and resolves the problem of mode mixing using complementary partial noise assisted method (CPNAM). Simulation case studies are used to verify the improvements of the proposed method. Finally, the ILCD is applied to extract bearing fault signals for an experimental bearing under variable speed condition and a practice case of wind power bearing. The analysis results from the applications demonstrate that the proposed algorithm is effective and robust in extracting incipient bearing fault signals.

Blind source extraction based on EMD and temporal correlation for rolling element bearing fault diagnosis

Purpose Fault diagnosis methods based on blind source separation (BSS) for rolling element bearings are necessary tools to prevent any unexpected accidents. In the field application, the actual signal acquisition is usually hindered by certain restrictions, such as the limited number of signal channels. The purpose of this study is to fulfill the weakness of the existed BSS method. Design/methodology/approach To deal with this problem, this paper proposes a blind source extraction (BSE) method for bearing fault diagnosis based on empirical mode decomposition (EMD) and temporal correlation. First, a single-channel undetermined BSS problem is transformed into a determined BSS problem using the EMD algorithm. Then, the desired fault signal is extracted from selected intrinsic mode functions with a multi-shift correlation method. Findings Experimental results prove the extracted fault signal can be easily identified through the envelope spectrum. The application of the proposed method is validated using simulated signals and rolling element bearing signals of the train axle. Originality/value This paper proposes an underdetermined BSE method based on the EMD and the temporal correlation method for rolling element bearings. A simulated signal and two bearing fault signal from the train rolling element bearings show that the proposed method can well extract the bearing fault signal. Note that the proposed method can extract the periodic fault signal for bearing fault diagnosis. Thus, it should be helpful in the diagnosis of other rotating machinery, such as gears or blades.

A sparse measurement matrix based method for feature enhancement of bearing fault signal

In the process of bearing signal acquisition, the overloaded data often causes great pressure on the equipment. In order to solve this problem, compressed sensing theory is used to collect signals, and the measurement matrix is sparsed into a sparse measurement matrix and a base measurement matrix. The fusion of the sparse dictionary and the measurement matrix expands the selections of the measurement matrix and improves the reconstruction accuracy. For the phenomenon of the local aggregation of matrix energy caused by the initialization of the sparse measurement matrix, the method of segmented reconstruction is proposed to solve it. Then, in view of the situation that the useful information in the reconstructed signal is polluted by a lot of noise, a new wavelet threshold denoising method is proposed, which is fused with the empirical wavelet transform (EWT), and the margin index and the peak-to-peak value are used as sensitive parameters to adjust the threshold, the effect of denoising and fault feature enhancement are performed simultaneously. Through two-step strategy, the effective acquisition of bearing signals and the enhancement of fault features are realized. The performance of this method is verified by simulation and actual bearing data and the results are encouraging.

A new fault diagnosis method based on adaptive spectrum mode extraction

Variational mode decomposition provides a feasible method for non-stationary signal analysis, but the method is still not adaptive, which greatly limits the wide application of the method. Therefore, an adaptive spectrum mode extraction method is proposed in this article. The proposed method is mainly composed of spectral segmentation, mode extraction, and feedback adjustment. In the spectral segmentation part, considering the lack of robustness of classical scale space in a strong noise environment, this article proposes a method of fault feature mapping, which solves over-decomposition of variational mode decomposition guided by classical scale space. In the mode extraction part, for insufficient self-adaptability of the single penalty factor in the variational mode decomposition method, this article proposes a method of spectral aggregation factor, which solves multiple penalty factors that conform to different intrinsic modal functions. In the feedback adjustment part, this article proposes the method of transboundary criterion, which makes the result of variational mode decomposition within a preset range. Finally, using dispersion entropy and kurtosis indicators, intrinsic modal function components containing fault frequencies are extracted for envelope spectrum analysis to extract fault characteristic frequencies. In order to verify the effectiveness of the proposed method, the proposed method is applied to simulation signals and bearing fault signals. Comparing the decomposition results of different methods, the conclusion shows that the proposed method is more advantageous for the fault feature extraction of rolling bearings.

Derivative and enhanced discrete analytic wavelet algorithm for rolling bearing fault diagnosis

In order to effectively analyze the fault signals of non-linear and non-stationary rolling bearings and obtain high-precision fault diagnosis results of rolling bearings, the derivative and enhanced discrete analytic wavelet algorithm for rolling bearing fault diagnosis is studied. The morphological spectrum of fault signal is obtained by multi-scale morphological opening operation. The morphological spectrum entropy is calculated from the morphological spectrum curve to describe the morphological characteristics of different signals of rolling bearing. The morphological features of the obtained signals are decomposed by approximate analytic complex wavelet transform, rearrangement of wavelet packet subspace and cross-combination of wavelet packet subspace. The derivative and enhanced discrete analytic wavelet algorithm is used to diagnose rolling bearing faults. The experimental results show that the algorithm can accurately diagnose the fault of rolling bearings, and can completely diagnose 10 specific faults of rolling bearings. The error of diagnosing the diameter of pits is less than 0.1%. It can be applied to the actual fault diagnosis of rolling bearings.

Effect of Magnets Asymmetry on Stray Magnetic Flux Based Bearing Damage Detection in PMSM

In this paper, it is shown that stray magnetic flux is a highly reliable condition monitoring variable which is rich in motor health related information and it is superior to motor current. It is well-known that the magnetic field distribution in permanent magnet (PM) rotors exhibit asymmetry due to magnet manufacturing process. It is shown that, in addition to the clear characteristic bearing signatures, the magnet imperfections induce multiple new bearing fault signatures in the stray magnetic flux. Different than current, the signatures in stray flux are more immune to noise, consistent and independent of load and speed. It is also shown that the stray flux-based detection method can locate the faulty bearing. To justify the proposed approach, comparative simulations and experiments are carried out on a surface mounted PM synchronous motor (PMSM) and an interior permanent magnet motor (IPM) with outer raceway bearing fault and different degree of magnet field asymmetry.

Fault Diagnosis of Subway Traction Motor Bearing Based on Information Fusion under Variable Working Conditions

Under the variable working condition, the fault signal of the rolling bearing contains rich characteristic information. In view of the problem that the traditional fault diagnosis method of the rolling bearing depends on the prior knowledge and expert experience too much and the low recognition rate of some faults with the single signal, one method of rolling bearing fault diagnosis based on information fusion under the variable working condition is proposed. Firstly, one test and multi‐information acquisition system of the rolling bearing is built. Secondly, the metro traction motor bearing nu216 is selected as the research object, and to prefabricate the defects, the data of acoustic emission and vibration acceleration signals during the test of the bearing is acquired. Then, the original signal is processed and extracted by the wavelet packet decomposition, and the normalized feature information is fused by the convolution neural network. Finally, the two‐dimensional convolution neural network model is established to diagnose the bearing fault of the metro traction motor under different conditions. The test results show that the intelligent fault diagnosis method of the subway traction motor bearing based on information fusion under variable working conditions can accurately identify the fault type of the bearing, while the load and speed change. When the neural network training set and the test set cover the same working conditions, the accuracy can reach 100%.

Match-Extracting Chirplet Transform With Application to Bearing Fault Diagnosis

As a typical nonstationary signal, rolling bearing fault signals exhibit dynamic characteristics and low signal-to-noise ratio, which lead to fuzzy spectrograms from traditional time–frequency analysis (TFA) methods. It is a challenging task to accurately represent its instantaneous frequency (IF) trajectory. To solve this problem, this article proposes a TFA method which is called match-extracting chirplet transform for analyzing multicomponent dynamic signals. It generates a time–frequency (TF) representation of high energy concentration by constructing a basis function that matches the chirp rate with the original signal at any TF point. A matching extraction operator is built to extract the best matching ridges on the IF trajectory to further improve the quality of the spectrum. The proposed method can effectively characterize the dynamic characteristics of multicomponent signals and reduce the energy divergence. Meanwhile the algorithm retains signal reconstruction and can be used to recover significant components by adaptively searching modal ridges. Numerical verification shows that this method has a better performance in TF location and noise robustness. Finally, the validity of this method in mechanical fault diagnosis is verified by applying it to actual bearing signals.

An Improved k-Value Symmetrical Difference Analytic Energy Operator With HTFIF and L-KCA for Bearing Fault Diagnosis

The opportune fault detection of the rolling element bearings can avoid serious equipment accidents or even casualties. However, the early fault features of the bearings are weak and often submerged in heavy background noise and interferences. This paper proposes a novel approach for bearing fault diagnosis based on the hard thresholding fast iterative filtering (HTFIF), IMF selection index integrating L- kurtosis, correlation coefficient and autocorrelation function impulse harmonic to noise ratio (L-KCA), and improved k-value symmetrical difference analytic energy operator (k-SDAEO). As an adaptive and fast time-frequency analysis method, HTFIF is first adopted to process the bearing vibration signal and obtain a series of IMFs. After that, an alternative fusion index L-KCA is developed to select the sensitive IMF. Finally, a novel k-SDAEO with strong noise robustness is presented to process the selected IMF. With this method, the weak bearing fault signatures can be identified from the energy spectrum. The performance of the proposed method comparing to the traditional methods are investigated by numerical simulation and experimental studies. The results show that the proposed method has better fault feature extraction capability and higher efficiency, which can be implemented in the on-line and real-time fault detection.

The Enhancement of Weak Bearing Fault Signatures by Stochastic Resonance with a Novel Potential Function

As the critical parts of wind turbines, rolling bearings are prone to faults due to the extreme operating conditions. To avoid the influence of the faults on wind turbine performance and asset damages, many methods have been developed to monitor the health of bearings by accurately analyzing their vibration signals. Stochastic resonance (SR)-based signal enhancement is one of effective methods to extract the characteristic frequencies of weak fault signals. This paper constructs a new SR model, which is established based on the joint properties of both Power Function Type Single-Well and Woods-Saxon (PWS), and used to make fault frequency easy to detect. However, the collected vibration signals usually contain strong noise interference, which leads to poor effect when using the SR analysis method alone. Therefore, this paper combines the Fourier Decomposition Method (FDM) and SR to improve the detection accuracy of bearing fault signals feature. Here, the FDM is an alternative method of empirical mode decomposition (EMD), which is widely used in nonlinear signal analysis to eliminate the interference of low-frequency coupled signals. In this paper, a new stochastic resonance model (PWS) is constructed and combined with FDM to enhance the vibration signals of the input and output shaft of the wind turbine gearbox bearing, make the bearing fault signals can be easily detected. The results show that the combination of the two methods can detect the frequency of a bearing failure, thereby reminding maintenance personnel to urgently develop a maintenance plan.

Prognosis of Wind Turbine Gearbox Bearing Failures using SCADA and Modeled Data


 
 
 Predictive maintenance and condition monitoring systems for wind turbines have seen increased adoption to minimize downtime, reducing operation and maintenance costs. On today’s wind power plants, the integrated supervisory control and data acquisition (SCADA) system provides low- frequency operational data that can be leveraged to quantify a wind turbine’s health. The aim of this study is to utilize machine-learning techniques to predict axial cracking failures in wind turbine gearbox bearings up to 1 month ahead of time. The failures are assumed to have occurred when the investigated bearing was replaced. While current SCADA systems show the overall condition of a wind turbine, often they do not allow for the investigation of specific gearbox bearings’ health. To enrich bearing fault signatures, additional data are computed through physics-based models using gearbox design information. Based on SCADA data, modeled data, and bearing failure log data from an actual wind plant, the performances of different machine-learning models on unseen data are then evaluated using industry-standard metrics such as precision, recall, and F1 score. Results show the overall system performance enhancement in predicting bearing failure when modeled data are included with SCADA data. The reduction in terms of false alarms is about 50%, and improvement in terms of precision and F1 score is about 33% and 12% respectively, based on the best modeling case in this study.
 
 

Sparse representation of parametric dictionary based on fault impact matching for wheelset bearing fault diagnosis

Wheelset bearing is one of the crucial rotating elements in the train bogie. Detection of wheelset bearing defect comes with many challenges due to complex wheel/rail excitation and the horrible working condition. The parametric dictionary sparse representation provides a practical path to detect the weak fault of wheelset bearing. However, the parametric dictionary obtained by the classical correlation filtering algorithm (CFA) is hard to match the analyzed signal’s underlying fault impact characteristic. A novel parametric dictionary design algorithm named fault impact matching algorithm (FIMA) combining Orthogonal matching pursuit (OMP) is proposed to address the problem in this paper. The core of the FIMA mainly comprises two stages: partial segmentation and global analysis. Two indexes, correlation function (CF) and kurtosis, are used to comprehensively evaluate the partial and global matching degree between the Laplace wavelet and the signal. The proposed method’s effectiveness is verified by the fault simulation analysis and the practical wheelset bearing fault signals (outer and inner race fault). Some comparison studies demonstrate that the proposed method outperforms the CFA–OMP, the K-SVD–OMP and some time–frequency decomposition methods, such as EWT and VMD, in detecting the bearing weak defects.

Fault Diagnosis of Spindle Device in Hoist Using Variational Mode Decomposition and Statistical Features

By analyzing nonlinear and nonstationary vibration signals from the spindle device of the mine hoist, it is a challenge to overcome the difficulty of fault feature extraction and accurately identify the fault of rotor-bearing system. In response to this problem, this paper proposes a new approach based on variational mode decomposition (VMD), SVM, and statistical characteristics such as variance contribution rate (VCR), energy entropy (EE), and permutation entropy (PE). Comparisons have gone to evaluate the performance of rolling bearing defect by using EMD (Empirical Mode Decomposition), MEEMD (Modified Ensemble EMD), BP (Back Propagation) network, single or multiple statistical characteristics, and different motor loads. The experiment was carried out on the mechanical failure simulator of the main shaft device of the hoist, which verified the reliability and effectiveness of the method. The results show that the diagnosis method is suitable for feature extraction of bearing fault signals, with the highest diagnosis accuracy. It can provide a good practical reference for the fault diagnosis of mechanical equipment of the hoist spindle device and has certain practical value.

A new approach to health condition identification of rolling bearing using hierarchical dispersion entropy and improved Laplacian score

Since bearing fault signal under complex running status is usually manifested as the characteristics of nonlinear and non-stationary, which implies it is difficult to extract accurate affluent features and achieve effective fault identification via conventional signal processing tools. In this article, a hybrid intelligent fault identification scheme, the combination of hierarchical dispersion entropy and improved Laplacian score, is proposed to address this problem, which is mainly composed of three procedures. First, the particle swarm optimization–based optimized hierarchical dispersion entropy is adopted to excavate multilevel fault symptoms from low-frequency and high-frequency components, which can both solve the shortcoming of missing of high-frequency feature information existing in the recently presented multiscale dispersion entropy and artificial parameter selection issue of hierarchical dispersion entropy. Second, an improved feature selection strategy based on improved Laplacian score is proposed to select the sensitive features to establish a low-dimensional feature data set by incorporating the weight coefficient into Laplacian score. Finally, the established low-dimensional feature data set is fed to a Softmax classifier to automatically identify different health conditions of rolling bearing. The efficacy of the proposed method is validated by two experimental cases. Results show that our approach is highly effective in recognizing different fault categories and severities of rolling bearing. Meanwhile, our approach exhibits higher accuracy and better identification performance than some similar entropy-based hybrid approaches and other identification methods reported in this article.

A fast iterative filtering decomposition and symmetric difference analytic energy operator for bearing fault extraction

The fault vibration signals extracted from defective bearings are generally non-stationary and non-linear. Besides, such signals are extremely weak and easily buried by inevitable background noise and vibration interferences. Thus, the development of methods capable of detecting their hidden information in a fast and reliable way is of high interest in bearing fault detection. An alternative bearing fault extraction method based on fast iterative filtering decomposition (FIFD) and symmetric difference analytic energy operator (SD-AEO) is proposed in this work. The FIFD method performs excellently in suppressing mode mixing and produce a meaningful decomposition for a higher level of noise. More importantly, unlike other mode decomposition techniques, the FIFD has high computational efficiency, so we can speed up the calculations significantly. After decomposing the signal into a group of intrinsic mode functions (IMFs), a criterion based on the product of kurtosis and permutation entropy (PeEn) is proposed to choose the IMFs embedding richer bearing fault impulses. Subsequently, an enhanced demodulation technique, SD-AEO, is employed to detect the bearing fault signatures from the selected IMF. The simulated and real signals verify the efficiency of the proposed method.

An MCM-Enhanced Compressive Sensing for Weak Fault Feature Extraction of Rolling Element Bearings under Variable Speeds

The compressive sensing (CS) theory provides a new slight to the big-data problem led by the Shannon sampling theorem in rolling element bearings condition monitoring, where the measurement matrix of CS tends to be designed by the random matrix (RM) to preserve the integrity of signal roughly. However, when the signal to be analyzed is infected with strong noise, not only does the signal become insufficiently sparse, but the randomness of the measurement matrix will bring down the sensing efficiency, resulting in the loss of fault feature. Thus, a sensing-enhanced CS scheme based on a series of modes after VMD decomposition is proposed under this paper. The core of this scheme is as follows: (1) the principal mode of VMD with better sparsity replaces the raw signal for compressive sensing; (2) all these modes contain the time-frequency characteristics of the raw signal; (3) a new measurement matrix called mode-circulant matrix (MCM) is defined by circulating the mode matrix, and when the amount of samples is shrunk, the sensing efficiency can be enhanced greatly. Besides, considering the fault signal of rolling bearings under variable speed, there is a need to use order tracking to overcome the nonstationarity of the signal before applying CS theory. The analysis results of simulation and experiment prove that the VMD- and MCM-based CS can successfully extract the weak fault feature of rolling bearings with operating speed changing.

A typical stochastic resonance in Landau-type potential field

Considering the significant influence of the asymmetric structure of the one-dimensional potential field on the stochastic resonance (SR), the research is extended to the two-dimensional asymmetric potential field. The Brownian particles moving in the Landau-type potential field served as the research object. According to the linear response theory and probability flow method, the analytical formula for the spectrum power amplification (SPA) of the physical system concerning the driving frequency is derived. When the SPA is used as a measurement index, the theoretical analysis shows that an atypical SR phenomenon occurs in the system. The reason is that as the noise intensity increases, the response mode changes due to the asymmetric structure of the Landau-type potential field. Moreover, the linear responses and the SPA are inversely proportional to the driving frequency. The conclusions of the theoretical analysis are verified by numerical simulation. Finally, the Landau-type potential system is applied to the bearing fault signal detection. The experimental results show that the Landau-type potential system can effectively diagnose the faults of the inner and outer ring of the bearings, which proves the application value of the Landau-type potential system.