Incipient Fault Feature Research Articles

Incipient Fault Feature Extraction of Rolling Bearing Based on Optimized Singular Spectrum Decomposition

The incipient fault feature of rolling bearing is difficult to extract from vibration signals for the weak energy and nonstationarity. A method of extracting incipient bearing fault features was proposed in this paper, which based on the optimized singular spectrum decomposition (OSSD) with 1.5-dimensional symmetric differential energy operator (1.5D-SDEO) demodulation. First, the slime mould algorithm (SMA) is used to optimize the input parameter of the singular spectrum decomposition (SSD). Second, the bearing vibrational signal is decomposed into different singular spectrum components (SSC) by the proposed OSSD, and the SSC selected with the largest syncretic impact index (SII). Finally, the selected SSC is demodulated with 1.5D-SDEO, which uses symmetric differential energy operator (SDEO) instead of teager energy operator (TEO) in 1.5-dimensional TEO (1.5D-TEO). Simulation and experimental analysis were conducted to verify the validity of the proposed method. Results demonstrate that the proposed method could provide a new thought on the incipient fault feature extraction of rolling bearings.

Fault detection for rotating machinery using translation-invariant higher-density wavelet packet sliding window block thresholding

The weak incipient fault feature information of mechanical equipment is often submerged in strong background noise, which increases the difficulty of feature extraction. Herein, a novel method called the translation-invariant higher-density wavelet packet sliding window block thresholding is proposed. A higher-density wavelet transform processes one scale function and two wavelet functions, which has an advantage over single wavelet transform in matching various signal feature information. The translation-invariant higher-density wavelet packet transform effectively eliminates the Gibbs phenomenon, and the fine division of frequency bands breaks through the limitations of the higher-density wavelet transform to obtain more comprehensive feature information. At the same time, to accommodate the periodicity of the impact feature signal and the correlation between the decomposition coefficients, a sliding window block thresholding method is proposed. The sliding window is set to independently retain the weak fault features and block thresholding is applied to select the optimal block length and threshold by minimizing the Stein unbiased risk estimator. The results of the simulation and experiment indicate that the proposed method can more effectively reduce the interference of background noise and impurity frequencies, and successfully extract the characteristic frequencies of incipient fault diagnosis.

A Novel Parameter-Adaptive VMD Method Based on Grey Wolf Optimization with Minimum Average Mutual Information for Incipient Fault Detection

Recently, variational mode decomposition (VMD) has attracted wide attention on mechanical vibration signal analysis. However, there are still some dilemmas in the application of VMD, such as the determination of the number of mode decomposition K and quadratic penalty term α. In order to acquire appropriate parameters of VMD, an improved parameter-adaptive VMD method based on grey wolf optimizer (GWO) is developed by taking the minimum average mutual information into consideration (GWOMI). Firstly, the parameters (K, α) are adaptively determined through GWOMI. Then, the vibration signal is decomposed by the developed method and effective modes are extracted according to the maximum kurtosis. Finally, the extracted modes are processed by Hilbert envelope analysis to acquire the incipient fault features. With the simulation and experimental analysis, it is clearly found that the developed method is effective and performs better than some existing ones.

An Adaptive Optimized TVF-EMD Based on a Sparsity-Impact Measure Index for Bearing Incipient Fault Diagnosis

Bearing incipient fault diagnosis is very crucial to the timely condition-based maintenance (CBM), but it is also relatively difficult because of the faint feature and environmental interference. In this article, an adaptive optimized time-varying filtering-based empirical mode decomposition (TVF-EMD) (AO-TVF-EMD) is put forward to extract more explicit and abundant incipient fault features by optimizing the parameter combination in conventional TVF-EMD. First, a novel integrated indicator termed sparsity-impact measure index (SIMI) constructed from dispersion entropy (DE) and envelope characteristic frequency ratio (ECFR) is designed as the parameter selection criterion. This index fully guarantees the optimal sparsity and impact properties of the obtained modes simultaneously, considering both time- and frequency-domain characteristics. Simulation verified that SIMI can not only sensitively characterize the variation of fault feature but also is robust to the environmental disturbance. Subsequently, we employ the Salp swarm algorithm (SSA) to realize the accurate search of parameter combinations where the minimum SIMI is defined as the fitness function. Moreover, comparative analysis in two runs to failure tests of bearings demonstrate that AO-TVF-EMD is more effective to extract incipient fault features than the maximum weighted Kurtosis (MWK) optimized TVF-EMD, the conventional TVF-EMD with fixed parameter, and some other advanced signal processing methods, which highlights the superiority of the proposed method.

Incipient Fault Detection of Rolling Element Bearings Based on Deep EMD-PCA Algorithm

Due to the relatively weak early fault characteristics of rolling bearings, the difficulty of early fault detection increases. For unsolving this problem, an incipient fault detection method based on deep empirical mode decomposition and principal component analysis (Deep EMD-PCA) is proposed. In this method, multiple data processing layers are created to extract weak incipient fault features, and EMD is used to decompose the vibration signal. This method establishes an accurate data mode, which can improve the incipient fault detection capability. It overcomes the difficulties of incipient fault detection, in which weak fault features can be extracted from the background of strong noise. From a theoretical point of view, this paper proves that the Deep EMD-PCA method can retain more variance information and has a good early fault detection ability. The experiment results indicate that the detection rate of Deep EMD-PCA is about 85%, and the failure detection delay time is almost zero. The incipient faults of rolling element bearings can be detected accurately and timely by Deep EMD-PCA. The method effectively improves the accuracy and timeliness of fault detection under actual working conditions and has good practical application value.

Simultaneously Low Rank and Group Sparse Decomposition for Rolling Bearing Fault Diagnosis.

Singular value decomposition (SVD) methods have aroused wide concern to extract the periodic impulses for bearing fault diagnosis. The state-of-the-art SVD methods mainly focus on the low rank property of the Hankel matrix for the fault feature, which cannot achieve satisfied performance when the background noise is strong. Different to the existing low rank-based approaches, we proposed a simultaneously low rank and group sparse decomposition (SLRGSD) method for bearing fault diagnosis. The major contribution is that the simultaneously low rank and group sparse (SLRGS) property of the Hankel matrix for fault feature is first revealed to improve performance of the proposed method. Firstly, we exploit the SLRGS property of the Hankel matrix for the fault feature. On this basis, a regularization model is formulated to construct the new diagnostic framework. Furthermore, the incremental proximal algorithm is adopted to achieve a stationary solution. Finally, the effectiveness of the SLRGSD method for enhancing the fault feature are profoundly validated by the numerical analysis, the artificial bearing fault experiment and the wind turbine bearing fault experiment. Simulation and experimental results indicate that the SLRGSD method can obtain superior results of extracting the incipient fault feature in both performance and visual quality as compared with the state-of-the-art methods.

Sparse Elitist Group Lasso Denoising in Frequency Domain for Bearing Fault Diagnosis

The fault-induced impulse responses of localized bearing fault are usually interfered by the background noise and other harmonic components. They are strongly coupled together and are hard to be separated. It is crucial to develop a fast and reliable method to extract the impulse-based feature for online bearing fault diagnosis in the industry application. In this article, we propose a new sparse elitist group lasso denoising (SEGLD) algorithm in frequency domain to detect the incipient impulse-based fault feature, which is free of utilizing the prior knowledge. We first reveal the sparse characteristics of the bearing fault signals in frequency domain. Then, a tailored denoising model is proposed. To obtain a satisfactory analytical stationary solution, the Douglas-Rachford splitting solver is employed for the denoising model. Moreover, we explore the relationship between the best regularization parameters, the periodic information and the normalization estimated noise of the rolling bearing fault signal. A rule of adaptively selecting the best regularization parameters is demonstrated. Finally, the robustness and effectiveness of the proposed SEGLD algorithm are profoundly verified by the numerical simulation and two evaluation experiments under the conditions of early fault stage and low speed scenario. Also, it is demonstrated that the proposed approach outperforms the state-of-the-art method for extracting the weak fault feature.

Fault Diagnosis of Planetary Gearbox Based on Adaptive Order Bispectrum Slice and Fault Characteristics Energy Ratio Analysis.

The vibration of a planetary gearbox (PG) is complex and mutually modulated, which makes the weak features of incipient fault difficult to detect. To target this problem, a novel method, based on an adaptive order bispectrum slice (AOBS) and the fault characteristics energy ratio (FCER), is proposed. The order bispectrum (OB) method has shown its effectiveness in the feature extraction of bearings and fixed-shaft gearboxes. However, the effectiveness of the PG still needs to be explored. The FCER is developed to sum up the fault information, which is scattered by mutual modulation. In this method, the raw vibration signal is firstly converted to that in the angle domain. Secondly, the characteristic slice of AOBS is extracted. Different from the conventional OB method, the AOBS is extracted by searching for a characteristic carrier frequency adaptively in the sensitive range of signal coupling. Finally, the FCER is summed up and calculated from the fault features that were dispersed in the characteristic slice. Experimental data was processed, using both the AOBS-FCER method, and the method that combines order spectrum analysis with sideband energy ratio (OSA-SER), respectively. Results indicated that the new method is effective in incipient fault feature extraction, compared with the methods of OB and OSA-SER.

Online detection of bearing incipient fault with semi-supervised architecture and deep feature representation

Although researchers have made substantial progress in bearing fault detection and diagnosis recently, incipient fault detection, especially online detection, is still at an initial stage. Generally speaking, online detection of incipient faults is still subject to the following challenges: (1) improving discriminative ability of incipient fault features; (2) adaptive recognition of the distribution inconsistency that exists in online sequential data; (3) achieving automatic detections with avoiding manual adjustment of detection criterion; and (4) reducing false alarm rate. To address these challenges, this paper presents a new approach for bearing incipient fault online detection using semi-supervised architecture and deep feature representation. This approach is simple and effective. First, we extract deep features using stacked denoising auto-encoder from the target bearing's normal state data and an auxiliary bearing's fault state data. Second, we introduce safe semi-supervised support vector machine (S4VM), a kind of semi-supervised classifier, to identify the sequentially arrived data of the target bearing as normal or anomalous. To update the classifier effectively, we use the principal curve to generate synthetic fault data for keeping data classes balanced during online condition monitoring. Finally, we propose a new fault alarm criterion based on S4VM generalization error upper bound to adaptively recognize the occurrence of an incipient fault. The experimental results on three datasets (IEEE PHM Challenge 2012, IMS and XJTU-SY) demonstrate the effectiveness and high reliability of the proposed approach.

A group sparse representation method in frequency domain with adaptive parameters optimization of detecting incipient rolling bearing fault

The periodic impulses are the most important signatures of rolling bearing failure, which are often buried by excessive background noise. It is challenging to extract the incipient periodic impulses in the vibration fault signal. In this paper, we propose a group sparse representation denoising method in frequency domain of extracting the incipient periodic impulses for rolling bearings fault diagnosis. First, we reveal the sparsity within and across groups (SWAG) property of the bearing fault signal in frequency domain. Afterwards, a penalty function promoting SWAG is employed to construct the denoising model in frequency domain. To achieve better feature extraction results, a guided periodic information index is proposed to construct the objective function of Moth-Flame optimization (MFO) algorithm for adaptively optimizing regularization parameters of the proposed denoising model. Lastly, simulation and experimental results indicate that the proposed MFO-SWAG method can accurately maintain the weak fault feature while suppressing the noise effectively. Compared with other state-of-art methods, the proposed method shows better performance of extracting the incipient fault feature of rolling bearings.

Incipient fault diagnosis of rolling bearings based on adaptive variational mode decomposition and Teager energy operator

Extracting incipient fault features of rolling bearings is a hard work as the impact compositions in vibration signals are faint and disturbed by a lot of environmental noise. An adaptive variational mode decomposition and Teager energy operator method (AVMD-TEO) for diagnosing incipient fault of rolling bearings is proposed. Firstly, the minimum average envelope entropy is used as the fitness value to search the optimal parameters of VMD adaptively by grey wolf optimization algorithm. Subsequently, the efficient weighted kurtosis index is introduced to select the efficient modal components for signal reconstruction. Finally, the reconstructed signal is processed by Teager energy operator to enhance the faint transient impact compositions and identify the defect frequency. The superiority of AVMD in parameters selection compared with fixed-parameter VMD and maximum weighted kurtosis optimized VMD is verified by simulated signal analysis. Results from the cases show that the peak signal-to-noise ratio and fault characteristic coefficient obtained by the proposed method are increased by 8% to 229% and 37% to 258% respectively compared with some traditional methods. The proposed AVMD-TEO can effectively reduce signal noise and extract incipient fault feature of rolling bearings.

The Accumulative Component Kurtosis in the SVD Based Denoising of the Fault Diagnosis for Rolling Element Bearing of Generator

Rolling bearings are important load-bearing components that are prone to failure, so it is necessary to reveal their failure mechanisms. As the singular value mainly reflect the energy of the decomposed singular components (SCs), the singular value decomposition (SVD) de-noising tend to preserve the significant-energy SCs and ignoring the neglected one, thus weaken singular has the ability to detect the incipient fault of the mechanical systems. In this paper, accumulative component kurtosis based SVD reconstitution scheme is proposed for mechanical signal denoising to detect the incipient fault of the generator systems. With the kurtosis index, the decomposed SCs can be evaluated and sorted not only according to their energy but also the contribution to the de-noising effect. In this way, the sensitive SCs could be taken into calculation effectively. The advantages of the ACK-SVD over traditional approaches are verified by both simulated signals and real vibration data from the rolling element bearing rig. The results proved the incipient fault feature even with heavy background noise could be extracted successfully.

Periodic feature oriented adapted dictionary free OMP for rolling element bearing incipient fault diagnosis

Abstract To address the troublesome rolling element bearing incipient fault diagnosis task, it is of great importance to extract the periodic impact components embedded in heavy noise usually. The newly developed sparse representation approach, named adapted dictionary free orthogonal matching pursuit (ADOMP), not only provides a more flexible template – Asymmetric Gaussian Chirplet Model (AGCM), but also breaks through the dependence on essential dictionaries for analytic and learning-based sparse representation approaches. Therefore, ADOMP possesses the potential advantages in analyzing bearing incipient fault vibration signals. Considering the significant influence caused by a manual-selected stopping parameter in standard ADOMP, two pieces of prior knowledge are firstly exploited from the vibration signals. Then through establishing a harmonic product spectrum-based kurtosis to directly evaluate the obviousness of extracted periodic features and guide a satisfactory selection for the stopping parameter, the periodic feature oriented ADOMP (PF-ADOMP) is developed. The subsequent refinement by virtue of the exploited time-invariance can further highlight the periodic feature, which is beneficial to the detection of bearing incipient faults. The effectiveness of PF-ADOMP has been validated by analyzing the data from both simulation and bearing life accelerated tests. Meanwhile, the comparisons with respect to the automatic oscillatory behavior-based signal decomposition (Auto-OBSD) method have also been favorably conducted, which show the superiority of the PF-ADOMP in extracting rolling element bearing incipient fault features.

Incipient fault detection of wind turbine large-size slewing bearing based on circular domain

Incipient fault detection of wind turbine large-size slewing bearings is crucial to their high availability and profitable operation. Many studies have been conducted using time-domain, frequency-domain analysis for fault feature extraction. However, they suffer from inherent disadvantages, such as spectrum leakage analysis under variable speed, which make them unsuitable for incipient fault detection. To overcome these shortcomings, a novel incipient weak fault feature extraction method is proposed based on circular domain analysis and piecewise aggregate approximation. A systematic methodology based on circular domain resampling approach is proposed to map the time series signals into angle domain, and eliminate the time attribute. Piecewise aggregate approximation with neighborhood correlation is utilized to reduce the amount of circular-domain signals, and detect the frequency variation of vibration signals when an incipient fault occurs. The application and superiority of the proposed methodology are validated using a wind turbine large-size bearing life-cycle test dataset. Meanwhile, a comparison is conducted between traditional fault features and various circular domain models. Results show that the proposed method has a better performance in detecting incipient faults for wind turbine large-size bearing.

Fractal Lifting Wavelets for Machine Fault Diagnosis

Fault diagnosis is of vital importance in safety and reliable operations of modern electromechanical systems. Advanced signal processing techniques are indispensable for extracting incipient features from measured dynamical signals. For discrete wavelet analysis, shift-invariance and proper frequency-scale configuration are both necessary for effective investigation of incipient fault features. In this paper, a novel fractal lifting scheme is proposed based on redundant second generation wavelet packet decomposition (RSGWPD). Implicit wavelet packets (IWPs), generated via fractal lifting scheme, can realize a novel centralized multiresolution. It is demonstrated that each IWP inherits the property of exact shift-invariance originated from redundant lifting scheme. In addition, a novel concept of nested centralized wavelet packet cluster is introduced for explaining merits provided by sets composed of IWPs. The numerical simulations were employed to validate the benefits of exact shift-invariance in a multiscale analysis of discrete time series. RSGWPD and IWPs are combined to conduct multiscale expansion of vibration measurement. To further explore optimal features, an indicator of spatial-spectral ensemble kurtosis is utilized to select optimal analysis parameters. The proposed technique was successfully applied to case studies of gearbox fault diagnosis as well as bearing fault diagnosis. The comparisons were made between results by the proposed technique and those provided by some other mainstream adaptive signal decomposition methodologies. It is verified that the combination of exact shift-invariance and centralized multiresolution significantly enhances the performance of incipient fault feature extraction of nonstationary vibration signals.

The incipient fault feature enhancement method of the gear box based on the wavelet packet and the minimum entropy deconvolution

ABSTRACTThe amplitude of the vibration signal in the gearbox of the motor driving system is low, resulting in disturbance and vibration noise effect, especially in the early stage of failure. So, it is difficult to extract the characterization of gearbox fault correctly. A method of incipient fault feature enhancement based on the wavelet packet and the minimum entropy deconvolution (MED) is proposed. Firstly, the vibration signal of the gear box containing the incipient fault is decomposed by the wavelet packet, and the decomposed band is reconstructed to eliminate the noise component which is the initial enhancement of the fault feature. After that theMED is used to filter the reconstructed band blind deconvolution to eliminate the influence of the transmission path, so that the feature components of the fault are enhanced again. The combination of WP and MED weakens the influence of the normal components in the original signal, highlights the impact component of the fault, and fully excavates the hidden fault information in the frequency band after the wavelet packet decomposition. Finally, the experimental results are compared and analysed. The experimental results show that the incipient fault feature extracted by this method improves the accuracy of fault diagnosis.

Incipient fault feature extraction of rolling bearings based on the MVMD and Teager energy operator

Aiming at the problems that the incipient fault of rolling bearings is difficult to recognize and the number of intrinsic mode functions (IMFs) decomposed by variational mode decomposition (VMD) must be set in advance and can not be adaptively selected, taking full advantages of the adaptive segmentation of scale spectrum and Teager energy operator (TEO) demodulation, a new method for early fault feature extraction of rolling bearings based on the modified VMD and Teager energy operator (MVMD-TEO) is proposed. Firstly, the vibration signal of rolling bearings is analyzed by adaptive scale space spectrum segmentation to obtain the spectrum segmentation support boundary, and then the number K of IMFs decomposed by VMD is adaptively determined. Secondly, the original vibration signal is adaptively decomposed into K IMFs, and the effective IMF components are extracted based on the correlation coefficient criterion. Finally, the Teager energy spectrum of the reconstructed signal of the effective IMF components is calculated by the TEO, and then the early fault features of rolling bearings are extracted to realize the fault identification and location. Comparative experiments of the proposed method and the existing fault feature extraction method based on Local Mean Decomposition and Teager energy operator (LMD-TEO) have been implemented using experimental data-sets and a measured data-set. The results of comparative experiments in three application cases show that the presented method can achieve a fairly or slightly better performance than LMD-TEO method, and the validity and feasibility of the proposed method are proved.

Application of improved wavelet total variation denoising for rolling bearing incipient fault diagnosis

When incipient fault appear in the rolling bearing, the fault feature is too small and easily submerged in the strong background noise. In this paper, wavelet total variation denoising based on kurtosis (Kurt-WATV) is studied, which can extract the incipient fault feature of the rolling bearing more effectively. The proposed algorithm contains main steps: a) establish a sparse diagnosis model, b) represent periodic impulses based on the redundant wavelet dictionary, c) solve the joint optimization problem by alternating direction method of multipliers (ADMM), d) obtain the reconstructed signal using kurtosis value as criterion and then select optimal wavelet subbands. This paper uses overcomplete rational-dilation wavelet transform (ORDWT) as a dictionary, and adjusts the control parameters to achieve the concentration in the time-frequency plane. Incipient fault of rolling bearing is used as an example, and the result shows that the effectiveness and superiority of the proposed Kurt- WATV bearing fault diagnosis algorithm.

Higher‐order correlation–based multivariate statistical process monitoring

AbstractAs shallow architecture is inefficient in terms of computational elements, some incipient fault features can be characterized through the composition of many nonlinearities, ie, with deep network. In this paper, a novel approach is developed for multivariate statistical process monitoring based on higher‐order correlations. First, the correlations among monitoring variables can be learned by a multilayer learning framework hierarchically: The higher the number of layers to be stacked, the more nonlinear and abstract features can be characterized. Second, 3 monitoring statistics, SRE, M2, and C, are presented to monitor whether the process is remaining in control, and they are instructive for the identification of fault types. Moreover, only normal data are used in training phase; this can avoid the unbalance problem of different types of fault data. These capabilities of the proposed approach are illustrated with two industrial benchmarks, Tennessee Eastman process and Metal Etch process.

Weak fault feature extraction of rolling bearings based on globally optimized sparse coding and approximate SVD

Abstract Fault feature extraction is crucial to condition monitoring and fault prognostics. However, when fault is in the initial stage, it is often very weak and submerged in the strong noise. This makes the fault feature very difficult to be extracted. In this paper, we propose a novel method based on sparse representation theory. It is inspired by the traditional K-SVD based de-noising method and can penetrate into the underlying structure of the signal. It learns sparse coefficients and dictionary from the noisy signal itself. The coefficients are globally optimized based on an l 1 -regularized least square problem solving method, which can locate the impulse coordinates more accurately compared with orthonormal matching pursuit (OMP) applied in the traditional K-SVD. The dictionary learning is based on an approximation of singular value decomposition (SVD). With the learned dictionary, we can capture the higher-level structure of the signal. Combining the sparse coefficients and the learned dictionary, we can de-noise the signal effectively and extract the incipient weak fault features of rolling bearings. The results of processing both simulated and experimental signals are illustrated and both validate the proposed method. All the experimental data are also processed by SpaEIAD, wavelet shrinkage, and fast kurtogram for comparison.