Search

In the existing rolling bearing performance degradation assessment methods, the input signal is usually mixed with a large amount of noise and is easily disturbed by the transfer path. The time information is usually ignored when the model processes the input signal, which affects the effect of bearing performance degradation assessment. To solve the above problems, an end-to-end performance degradation assessment model of railway axle box bearing based on a deep residual shrinkage network and a deep long short-term memory network (DRSN-LSTM) is proposed. The proposed model uses DRSN to extract local abstract features from the signal and denoises the signal to obtain the denoised feature vector, then uses deep LSTM to extract the time-series information of the signal. The healthy time-series signal of the rolling bearing is input into the DRSN-LSTM reconstruction model for training. Time-domain, frequency-domain, and time–frequency-domain features are extracted from the signal both before and after reconstruction to form a multi-domain features vector. The mean square error of the two feature vectors is used as the degradation indicator to implement the performance degradation assessment. Artificially induced defects and rolling bearings life accelerated fatigue test data verify that the proposed model is more sensitive to early failures than mathematical models, shallow networks or other deep learning models. The result is similar to the development trend of bearing failures. [ABSTRACT FROM AUTHOR]

During the gear hobbing machine process, the hob performance degradation assessment is significant for optimizing the tool changing frequency and improving machining efficiency. It is challenging to recognize hob wear state through vibration analysis and signal processing. Especially in the condition of intense vibration and noise interference, extracting signal features that reflect the wear state is challenging work. This paper proposes a feature extraction method called Cyclic Statistical Energy (CSE) to obtain the hob wear characteristics by tracking the sensitive frequency band. For the method, the vibration signal model of hob spindle is established first based on the vibration-generation mechanism of the machining process. Then, an index E is proposed to track the wear resonance frequency band of the vibration signal. Furthermore, the cyclic statistical order is analyzed and discussed. The hob performance degradation assessment can be realized by analyzing the energy index E with time variation. The experimental setup has been designed, and the two tests have been conducted in the production line: (1) impact hammer test and (2) hob whole life cutting test. The impact hammer test is set to obtain the modal parameters of the hob. Based on this, the whole life cutting test is designed and realized by which the vibration data of whole life with different wear states can be acquired. The proposed method CSE is successfully applied into online industry experiments test. The results show that the proposed method can give a more accurate performance degradation assessment curve for tool condition monitoring compared with traditional methods such as Wavelet Packet Decomposition (WPD). [ABSTRACT FROM AUTHOR]

The conventional signal processing based methods are difficult to achieve satisfactory results for rolling element bearings (REBs)' weak fault due to the serious influence of interference signal. Intelligent classification technology and the arising popular monitoring technology-performance evaluation assessment (PDA) are the research hotspots of fault diagnosis of REB in recent years, which could resolve the above problem to some extent. Especially the latter could reflect the operating status of the equipment more comprehensively. Effective feature extraction basing on signal processing methods and intelligent algorithm are the two key aspects for the above two technologies which will determine their effectiveness to great extent. Multifractal detrended fluctuation analyses (MDFA) is an effective non-stationary signal processing method which could reveal the multifractality buried in nonlinear and nonstationary vibration signals of REB, and continuous hidden markov model (CHMM) is a mature intelligent algorithm with solid theoretical basis and rich mathematical structure. So a diagnosis method basing on combination of MDFA with CHMM is proposed in the paper, and it could deal with both fault classification and PDA tasks for the diagnosis of REBs. Effectiveness of the proposed method is validated by two different diagnosis experiments, one for fault classification and another for lifecycle performance evaluation of REBs. Compared to state-of-the-art peer methods, the proposed method has the best performance when dealing with fault diagnosis tasks for REBs. [ABSTRACT FROM AUTHOR]

Estimating the remaining useful life (RUL) of components is a crucial task to enhance reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator ( H I ) to infer the current condition of the component, and modelling the degradation process in order to estimate the future behavior. Although many signal processing and data-driven methods have been proposed to construct the H I , most of the existing methods are based on manual feature extraction techniques and require the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the H I . For this purpose, the continuous wavelet transform (CWT) technique was used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model was trained by the healthy operation dataset. Finally, the Mahalanobis distance (MD) between the healthy and failure stages was measured as the H I . The proposed method was tested on a benchmark bearing dataset and compared with several other traditional H I construction models. Experimental results indicate that the constructed H I exhibited a monotonically increasing degradation trend and had good performance in terms of detecting incipient faults. [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]

• 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]

• 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]

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]