Bearings, as universal components, have been widely used in the important position of rotating machinery. However, due to the distribution divergence between training data and test data caused by variable working conditions, such as different rotation speeds and load conditions, most of the fault diagnosis models built during the training stage are not applicable for the detection in the test stage. The models dramatically lead to performance degradation for fault classification. In this paper, a novel bearing fault diagnosis method, domain adaptation by using feature transfer learning (DAFTL) under variable working conditions, is proposed to solve this performance degradation issue. The dataset of normal bearings and faulty bearings are obtained via the fast Fourier transformation (FFT) of raw vibration signals, under different motor speeds and load conditions. Then, marginal and conditional distributions are reduced simultaneously between training data and test data by refining pseudo test labels based on maximum mean discrepancy (MMD) and domain invariant clustering (DIC) in a common space. Ultimately, a transferable feature representation for training data and test data is achieved.With the help of the nearest-neighbor (NN) classifier built on the transferable features, bearing faults are identified in this common space. Extensive experimental results show that DAFTL can identify the bearing fault accurately under variable working conditions and outperforms other competitive approaches.

Transient impulse analysis is an effective way to detect the bearing fault at its early stage. However, it is hard to precisely extract these so-called transient impulses because these collected vibration signals usually are non-stationary, nonlinear, and drowned by heavy background noise. Variational mode decomposition (VMD) can play the role as an adaptive signal processing tool to reveal the weak transient impulses from complex vibration signals. However, its reasonable mode number is difficult to pre-set and this would make the loss of useful transient impulses. To solve this issue, an improved VMD strategy is presented in this paper. For this method, it can not only utilize the advantages of traditional VMD and empirical mode decomposition (EMD) but also adaptively select sensitive intrinsic mode function (IMF) components for fault component analysis by proposed indexed values. EMD is first used to process the collected vibration signal into a series of IMFs, and the so-called useful IMFs are then evaluated by a sensitive IMF evaluation index which is based on the conjoint analysis of relatedness and kurtosis. Afterward, VMD is further improved to effectively decompose the denoised signal reconstructed from these selected useful IMFs of traditional EMD. Finally, the improved VMD is used for incipient fault diagnosis by a defined transient impulse monitoring index and Hilbert envelope analysis. Experiments are performed to demonstrate the effectiveness of the proposed method. The experimental results confirm that the proposed method can accurately extract the features of an incipient fault of a bearing.

With the arrival of the big data era, it has become possible to apply deep learning to the health monitoring of mine production. In this paper, a convolutional neural network (CNN)-based method is proposed to monitor the health condition of the balancing tail ropes (BTRs) of the hoisting system, in which the feature of the BTR image is adaptively extracted using a CNN. This method can automatically detect various BTR faults in real-time, including disproportional spacing, twisted rope, broken strand and broken rope faults. Firstly, a CNN structure is proposed, and regularization technology is adopted to prevent overfitting. Then, a method of image dataset description and establishment that can cover the entire feature space of overhanging BTRs is put forward. Finally, the CNN and two traditional data mining algorithms, namely, k-nearest neighbor (KNN) and an artificial neural network with back propagation (ANN-BP), are adopted to train and test the established dataset, and the influence of hyperparameters on the network diagnostic accuracy is investigated experimentally. The experimental results showed that the CNN could effectively avoid complex steps such as manual feature extraction, that the learning rate and batch-size strongly affected the accuracy and training efficiency, and that the fault diagnosis accuracy of CNN was 100%, which was higher than that of KNN and ANN-BP. Therefore, the proposed CNN with high accuracy, real-time functioning and generalization performance is suitable for application in the health monitoring of hoisting system BTRs.

Rolling bearing is a key component of rotating machinery, and its remaining useful life (RUL) estimation is also a critical technique in prognostics health management activities. In this paper, we propose a two-stage strategy for bearing health monitoring, where the bearing health process is divided into two stages: normal stage and degeneration stage, and a new method is proposed to estimate the bearing RUL by combining a new health indicator (HI) and particle filtering (PF). First, the structural information of the spectrum (SIOS) algorithm is employed to construct the HI called SIOS-based indicator (SIOSI) for bearing degeneration monitoring. Second, the initial degenerate point (IDP) is evaluated by a novel index calculated with self-zero space observer in order to conduct the two-stage division of normal and degeneration stages. Third, after detecting the IDP, the bearing RUL is estimated using the SIOSI and the PF-based algorithm with the help of a degeneration model. The effectiveness of the proposed methodology is validated using vibration data collected from bearing run-to-failure tests. Experimental results have shown that the bearing RUL could be estimated acceptably with the proposed method, and its performance is greatly superior to that presented by L ₁₀ life formula.

Envelope analysis is a widely used method in fault diagnoses of rolling bearings. An optimal narrowband chosen for the envelope demodulation is critical to obtain high detection accuracy. To select the narrowband, the fast kurtogram (FK), which computes the kurtosis of a set of filtered signals, is introduced to detect cyclic transients in a signal, and the zone with the maximum kurtosis is the optimal frequency band. However, the kurtosis value is affected by rotating frequencies and is sensitive to large random impulses which normally occur in industrial applications. These factors weaken the performance of the FK for extracting weak fault features. To overcome these limitations, a novel feature named Order Spectrum Correlated Kurtosis (OSCK) is proposed, replacing the kurtosis index in the FK, to construct an improved kurtogram called Fast Order Spectrum Correlated Kurtogram (FOSCK). A band-pass filter is used to extract the optimal frequency band signal corresponding to the maximum OSCK. The envelope of the filtered signal is calculated using the Hilbert transform, and a low-pass filter is employed to eliminate the trend terms of the envelope. Then, the non-stationary filtered envelope is converted in the time domain into the stationary envelope in the angular domain via Computed Order Tracking (COT) to remove the effects of the speed fluctuation. The order structure of the angular domain envelope signal can then be used to determine the type of fault by identifying its characteristic order. This method offers several merits, such as fine order spectrum resolution and robustness to both random shock and heavy noise. Additionally, it can accurately locate the bearing fault resonance band within a relatively large speed fluctuation. The effectiveness of the proposed method is verified by a number of simulations and experimental bearing fault signals. The results are compared with several existing methods; the proposed method outperforms others in accurate bearing fault feature extraction under varying speed conditions.

In practical applications, the signal measured from a complex mechanical system is usually disturbed by various noises due to the compounded effect of interferences of other machine elements and background noises, especially under varying speed conditions. Resonance-based approaches have been proven to be effective methods to address this problem. However, even if the optimal resonance band is accurately determined, the in-band noise with frequency content in the range covered by the band-pass filter is not eliminated. To avoid missed diagnosis and misdiagnosis of faults in bearings, an iterated SVD (ISVD)-based in-band noise reduction method combined with envelope order spectrum analysis is proposed in this paper. First, the optimal frequency band of a vibrational signal is determined with the help of an enhanced wavelet packet transform kurtogram, in which the kurtosis of each node is calculated based on the envelope spectrum of a signal be reconstructed using the wavelet packet coefficients. The node with the maximum kurtosis value is used to reconstruct the signal. Second, the envelope of a reconstructed signal is calculated by Hilbert transform and the ISVD method is applied to it to reduce the in-band noise. To avoid the destruction of useful information caused by excessive iteration, a threshold is set to determine the number of iterations. After iterative processing, a de-noised signal is reconstructed based on the relationship between the singular value and a frequency component. Finally, the reconstructed signal is resampled and transformed into the fault characteristic order domain where the bearing fault type can be identified from the envelope order spectra. The simulations and experiments were used to validate the efficacy of the proposed method. Compared with the spectral subtraction method, the ISVD method can suppress in-band noise efficiently and beneficial to extract the fault characteristic order under variable speed conditions.