Search

Highlights • A subspace-based minimum volume ellipsoid model is proposed for performance degradation assessment of aero-engine bearings. • The multimodal homologous features are modelled by subspaces. • The proposed model is validated by run-to-failure tests of aero-engine bearings. • The proposed model outperforms traditional method. Abstract Performance degradation assessment is an important concept in prognostics and health management (PHM) of complex engineering systems. In this study, a novel method utilizing subspace-based minimum volume ellipsoid (SMVE) for bearing performance degradation assessment is proposed. The statistical features extracted from vibration signals are seen as multimodal homologous features in time, frequency and wavelet modalities, thus it needs to consider the differences in variance for the homologous features as well as covariance among them. The subspaces are used to model the homologous features of different frequency bands since they can capture the dynamic information. Based on subspaces, the proposed SMVE model covering most or all of the normal data by a unique ellipsoid with minimum volume considers variance of each dimension adaptively. A performance degradation index is designed based on the SMVE. The proposed method is applied on the vibration signals acquired in run-to-failure tests of aero-engine bearings and common bearings. By comparison with the commonly used time-domain features and traditional minimum volume ellipsoid method, the results demonstrate the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

The operation conditions are always non-stationary in the operation of rotating machinery. It is the key to realize the fault diagnosis of rotating machinery under different operation conditions by extracting the features which are irrelevant to the operation conditions and contain fault information. Nuisance attribute projection (NAP) is compensation technique to eliminate the influence of interference information in the feature space which has been used in speaker recognition and face recognition. In this paper, the rolling bearing vibration signals under different operation conditions are used to verify the nuisance removing ability of (NAP) in the feature space. Above all, after NAP are applied to the simulation and measured signals under different rotating speeds and loads, the comparisons between the original features and NAP features have shown that NAP can effectively eliminate the effect of nuisance attributes through projection. Moreover, it is verified that the information of fault pattern and fault degree are retained in the features after projection by analyzing the measured signals of different fault pattern and simulation signals of different fault degree under various rotating speeds, respectively. Furthermore, it is confirmed that the NAP can get rid of the nuisance attributes by analyzing twelve bearing tests of whole life under different operation conditions and channels. On the other hand, a feature selection method based on ranking mutual information (RMI) is used in this paper to select the features of more monotonous in bearing performance degradation assessment. The application sequences of RMI and NAP are studied for their influence on the bearing performance degradation index in the last part since the different sequence may affect the assessment results. The comparison results have shown that NAP should be used before feature selection in rotating machinery fault diagnosis. [ABSTRACT FROM AUTHOR]

Linear Brownian motion with constant drift is widely used in remaining useful life predictions because its first hitting time follows the inverse Gaussian distribution. State space modelling of linear Brownian motion was proposed to make the drift coefficient adaptive and incorporate on-line measurements into the first hitting time distribution. Here, the drift coefficient followed the Gaussian distribution, and it was iteratively estimated by using Kalman filtering once a new measurement was available. Then, to model nonlinear degradation, linear Brownian motion with adaptive drift was extended to nonlinear Brownian motion with adaptive drift. However, in previous studies, an underlying assumption used in the state space modelling was that in the update phase of Kalman filtering, the predicted drift coefficient at the current time exactly equalled the posterior drift coefficient estimated at the previous time, which caused a contradiction with the predicted drift coefficient evolution driven by an additive Gaussian process noise. In this paper, to alleviate such an underlying assumption, a new state space model is constructed. As a result, in the update phase of Kalman filtering, the predicted drift coefficient at the current time evolves from the posterior drift coefficient at the previous time. Moreover, the optimal Kalman filtering gain for iteratively estimating the posterior drift coefficient at any time is mathematically derived. A discussion that theoretically explains the main reasons why the constructed state space model can result in high remaining useful life prediction accuracies is provided. Finally, the proposed state space model and its associated Kalman filtering gain are applied to battery prognostics. [ABSTRACT FROM AUTHOR]

Bearing-supported shafts are widely used in various machines. Due to harsh working environments, bearing performance degrades over time. To prevent unexpected bearing failures and accidents, bearing performance degradation assessment becomes an emerging topic in recent years. Bearing performance degradation assessment aims to evaluate the current health condition of a bearing through a bearing health indicator. In the past years, many signal processing and data mining based methods were proposed to construct bearing health indicators. However, the upper and lower bounds of these bearing health indicators were not theoretically calculated and they strongly depended on historical bearing data including normal and failure data. Besides, most health indicators are dimensional, which connotes that these health indicators are prone to be affected by varying operating conditions, such as varying speeds and loads. In this paper, based on the principle of squared envelope analysis, we focus on theoretical investigation of bearing performance degradation assessment in the case of additive Gaussian noises, including distribution establishment of squared envelope, construction of a generalized dimensionless bearing health indicator, and mathematical calculation of the upper and lower bounds of the generalized dimensionless bearing health indicator. Then, analyses of simulated and real bearing run to failure data are used as two case studies to illustrate how the generalized dimensionless health indicator works and demonstrate its effectiveness in bearing performance degradation assessment. Results show that squared envelope follows a noncentral chi-square distribution and the upper and lower bounds of the generalized dimensionless health indicator can be mathematically established. Moreover, the generalized dimensionless health indicator is sensitive to an incipient bearing defect in the process of bearing performance degradation. [ABSTRACT FROM AUTHOR]

Bearing is the most critical component in rotating machinery since it is more susceptible to failure. The monitoring of degradation in bearings becomes of great concern for averting the sudden machinery breakdown. In this study, a novel method for bearing performance degradation assessment (PDA) based on an amalgamation of empirical mode decomposition (EMD) and k-medoids clustering is encouraged. The fault features are extracted from the bearing signals using the EMD process. The extracted features are then subjected to k-medoids based clustering for obtaining the normal state and failure state cluster centres. A confidence value (CV) curve based on dissimilarity of the test data object to the normal state is obtained and employed as the degradation indicator for assessing the health of bearings. The proposed outlook is applied on the vibration signals collected in run-to-failure tests of bearings to assess its effectiveness in bearing PDA. To validate the superiority of the suggested approach, it is compared with commonly used time-domain features RMS and kurtosis, well-known fault diagnosis method envelope analysis (EA) and existing PDA classifiers i.e. self-organizing maps (SOM) and Fuzzy c-means (FCM). The results demonstrate that the recommended method outperforms the time-domain features, SOM and FCM based PDA in detecting the early stage degradation more precisely. Moreover, EA can be used as an accompanying method to confirm the early stage defect detected by the proposed bearing PDA approach. The study shows the potential application of k-medoids clustering as an effective tool for PDA of bearings. [ABSTRACT FROM AUTHOR]

To effectively assess different fault locations and different degrees of performance degradation of a rolling bearing with a unified assessment index, a novel state assessment method based on the relative compensation distance of multiple-domain features and locally linear embedding is proposed. First, for a single-sample signal, time-domain and frequency-domain indexes can be calculated for the original vibration signal and each sensitive intrinsic mode function obtained by improved ensemble empirical mode decomposition, and the singular values of the sensitive intrinsic mode function matrix can be extracted by singular value decomposition to construct a high-dimensional hybrid-domain feature vector. Second, a feature matrix can be constructed by arranging each feature vector of multiple samples, the dimensions of each row vector of the feature matrix can be reduced by the locally linear embedding algorithm, and the compensation distance of each fault state of the rolling bearing can be calculated using the support vector machine. Finally, the relative distance between different fault locations and different degrees of performance degradation and the normal-state optimal classification surface can be compensated, and on the basis of the proposed relative compensation distance, the assessment model can be constructed and an assessment curve drawn. Experimental results show that the proposed method can effectively assess different fault locations and different degrees of performance degradation of the rolling bearing under certain conditions. [ABSTRACT FROM AUTHOR]

• Definition of key-spectrum coined MKSFS and a new entropic index coined MKSFS-FE. • Proposal of an integrated framework via MKSFS, MKSFS-FE and statistical properties. • The dynamic fault alarm and identification strategy for online scenarios. • The health state segmentation and pattern analysis strategy for offline scenarios. • Validation of the framework through eighteen sets of bearing degradation signals. Dynamic health monitoring (DHM) and performance degradation assessment (PDA) is critical for mechanical bearings throughout their long in-service life. For this issue, it is currently rare to find a framework with interpretable and automatic approaches developed from pure signal processing techniques and statistical theories. Therefore, an integrated framework via key-spectrum entropy and statistical properties for bearing DHM and PDA is developed in this paper, which integrates the proposed key spectrum, key-spectrum entropy, joint statistical alarm and fault identification strategy, health phase segmentation strategy, and three-dimensional (3D) key spectrums. First, a Kurtosis-Energy metric is defined to extract the key spectrum, which is reconstructed by two wavelet-decomposed sub-bands where the interference components are suppressed. A new health index (HI) of key-spectrum entropy is then defined to quantify the bearing degradation process. Second, a joint statistical alarm and fault identification strategy via updated HIs and key spectrum is proposed to form a DHM methodology for implementing bearing dynamic fault detection and recognition. Third, a health phase segmentation strategy and 3D key spectrums are developed to form a PDA methodology for implementing bearing health phase assessment and degradation pattern analysis. Comprehensive evaluations and comparisons on eighteen sets of bearing degradation vibration signals demonstrate the validity of the proposed framework, as well as its great practical application prospects. [ABSTRACT FROM AUTHOR]

Bearing performance degradation assessment is a key step of condition-based maintenance. In this paper, a novel indicator of bearing performance degradation assessment is presented based on the mathematical morphology (MM) theory for higher efficiency. Because the traditional mathematical morphology particle (MMP) is unable to exactly describe the bearing's performance degradation, we extended its definition to the general space to address the limited ability of the former definition. On the basis of the innovative definition, we used the morphology erosion operation instead of the morphology open operation to calculate the general mathematical morphology particle (GMMP) of the bearing's whole life data. The analysis of the simulation and practical application demonstrated that the proposed index is feasible and effective to indicate the performance degradation of the bearing. [ABSTRACT FROM AUTHOR]

• DBN without the classification output layer is selected as the feature self-extraction model to avoid the participation of human experience, and save time and effort to a certain extent; • SVDD is selected as the degradation index to build the model, and SSA is used to solve the problem that its parameters are not easy to determine, and expounding the principle of SSA-SVDD; • Two sets of bearing whole-life cycle experimental data were selected to verify the effectiveness of the method. The degradation index constructed by the method in this paper can effectively evaluate the performance degradation process of rolling bearings under different situations, and accurately detect the occurrence of early weak faults of rolling bearings. • The model can be constructed with the data under normal conditions, which overcomes the difficulty of obtaining fault samples during the operation of actual bearing equipment, and has a good guiding significance for the performance monitoring of bearing equipment. Rolling bearing performance degradation assessment (PDA) based on vibration signal is critical to intelligent maintenance. However, there are two problems in existing methods: 1) degradation signals are needed as building model, 2) feature extraction is dependent on experience and operation parameters. Aiming at these challenges, a PDA method based on deep belief network (DBN) and improved support vector data description (SVDD) is proposed in this paper. The normalized amplitude spectrum under normal state is used as the training sample of DBN without the classified output layer, which is used as the automatic feature extraction model. Then, the SVDD which requires appropriate penalty parameter C and kernel parameter σ is employed to fuse these features into performance indicator (PI), and the sparrow search algorithm (SSA) is introduced into the parameters optimization process of SVDD. The results applied in two experiment datasets show that the proposed method can detect the occurrence of incipient degradation and reflect the whole bearing performance degradation. And the advantages over other methods have been shown. In addition, the anti-noise capability, compared with RMS, is discussed, and the results show that the proposed method is better than RMS to some extent, which is worth being researched further in principle. [ABSTRACT FROM AUTHOR]

• A sparse representation degradation modeling methodology is proposed. • The sparsity property of square envelope spectra of fault transients is investigated. • The monotonicity property of a health index is enhanced based on an optimization degradation model. • Optimized weights can be sparsely located at fault characteristic frequencies and their harmonics. Performance degradation assessment (PDA) is an intersection technology of machine condition monitoring, degradation evaluation, and fault diagnosis in condition-based maintenance (CBM). A commonly used strategy of PDA is to use a health index (HI) to detect an incipient fault for machine condition monitoring and subsequently to track monotonic performance degradation trajectories. Sparse representation, as a classical signal processing method, has been widely studied for machine fault diagnosis while its extension to PDA is seldom reported. Based on the sparsity property of fault signals in the frequency domain, a novel sparse representation degradation modeling methodology that integrates sparse representation and monotonic degradation modeling is proposed in this paper to enrich PDA. At first, the sparsity property of square envelope spectra is thoroughly investigated. Based on the sparse representation theory, a HI is designed as the sum of weighted atoms. Besides, the amplitudes of square envelope spectra are used as a dictionary. Then, a sparse representation degradation model is proposed to realize the monotonicity property of a HI and the sparsity of weight coefficients. Experimental verification shows that HIs constructed from the proposed methodology are more suitable to PDA compared to existing HIs. Moreover, a prominent advantage of the proposed sparse degradation modeling is that no prior knowledge and complicated signal processing algorithms are required. Moreover, optimized weights are sparsely located at informative frequency bands for subsequent fault diagnosis, which provides informative frequencies for many blind fault diagnostic scenarios. [ABSTRACT FROM AUTHOR]

Slurry pumps are commonly used in oil-sand mining for pumping mixtures of abrasive liquids and solids. These operations cause constant wear of slurry pump impellers, which results in the breakdown of the slurry pumps. This paper develops a prognostic method for estimating remaining useful life of slurry pump impellers. First, a moving-average wear degradation index is proposed to assess the performance degradation of the slurry pump impeller. Secondly, the state space model of the proposed health index is constructed. A general sequential Monte Carlo method is employed to derive the parameters of the state space model. The remaining useful life of the slurry pump impeller is estimated by extrapolating the established state space model to a specified alert threshold. Data collected from an industrial oil sand pump were used to validate the developed method. The results show that the accuracy of the developed method improves as more data become available. [ABSTRACT FROM AUTHOR]

Based on the traditional theory of singular value decomposition (SVD), singular values (SVs) and ratios of neighboring singular values (NSVRs) are introduced to the feature extraction of vibration signals. The proposed feature extraction method is called SV–NSVR. Combined with selected SV–NSVR features, continuous hidden Markov model (CHMM) is used to realize the automatic classification. Then the SV–NSVR and CHMM based method is applied in fault diagnosis and performance assessment of rolling element bearings. The simulation and experimental results show that this method has a higher accuracy for the bearing fault diagnosis compared with those using other SVD features, and it is effective for the performance assessment of rolling element bearings. [ABSTRACT FROM AUTHOR]

Abstract: Bearing performance degradation assessment is crucial to realize condition-based maintenance. In this paper, a new method for it is proposed based on lifting wavelet packet decomposition and fuzzy c-means. Feature vectors are composed of the node energies of lifting wavelet packet decomposition. Normal and final failure data are used as training samples to build assessment model utilizing fuzzy c-means, and the subjection of tested data to normal state is defined as the degradation indicator, which has intuitionistics explanation related to degradation degree. Results of its application to accelerated bearing life test show that this indicator can reflect effectively performance degradation of bearing. And after discussing the influence of outliers in training set, a robust strategy is proposed. [Copyright &y& Elsevier]

Abstract: Bearing performance degradation assessment is one of the most important techniques in proactive maintenance aiming to realize equipment''s near-zero downtime and maximum productivity. In this paper, we propose a new robust method for it based on improved wavelet packet decomposition (IWPD) and support vector data description (SVDD). A health index is designed based on general distance. Node energies of IWPD are used to compose feature vectors. Based on feature vectors extracted from normal signals, a SVDD model fitting a tight hypersphere around them is trained, the general distance of test data to this hypersphere is used as the health index. Research results of its application in a bearing accelerated life test show that this health index can reflect effectively bearing performance degradation comparing with many other parameters. [Copyright &y& Elsevier]