Search

Transient impulses are important information for machinery fault diagnosis. However, the transient features contained in the vibration signals generated by planetary gearboxes are usually immersed by a large amount of background noise and harmonic components. Even mathematical morphology (MM) is an excellent anti-noise signal processing method that can directly extract the geometry of impulse features in the time domain, but the four basic operators of MM can only extract one-way impulses while cannot extract the bidirectional impulses effectively at the same time. To accurately extract the impulse feature information, a novel method for fault detection of planetary gearbox based on an enhanced average (EAVG) filter and modulated signal bispectrum (MSB) is proposed. Firstly, the properties of the extracted impulses based on the four basic operators of MM will be divided into two categories of enhanced average operators. The four EAVG filters consist of the average weighted combination of enhanced average operators, and then the best EAVG filter is selected based on correlation coefficient to implement on the original vibration signal. It allows EAVG filter to extract positive and negative impulses of vibration signal, thereby improving the accuracy of planetary gearbox fault detection. Subsequently, the performance of the EAVG filter is influenced by the length of its structural element (SE), which is adaptively determined using an indicator based kurtosis. Then, the EAVG filter selects the optimal SE length to eliminate the interference of background noise and harmonic components to enhance the impulse components of the vibration signal. However, the nonlinear modulation components that are related to the fault types and severities are not extracted exactly and still remained in the filtered signal by EAVG. Finally, the MSB is utilized to the EAVG filtered signal to decompose the modulated components and extract the fault features. The advantages of EAVG over average (AVG) filter are clarified in the simulation study. In addition, the EAVG-MSB is validated by analyzing the vibration signals of planetary gearboxes with sun gear chipped tooth, sun gear misalignment and bearing inner race fault. The results indicate that the EAVG-MSB is effective and accurate in feature extraction compared with the combination morphological filter-hat transform (CMFH) and average combination difference morphological filter (ACDIF), and the feasibility of the EAVG-MSB are proved for planetary gearbox condition monitoring and fault diagnosis. • EAVG filter is used to extract the positive and negative impulses. • Kurtosis is taken as a novel criterion to optimize the SE length of EAVG. • MSB is used to extract fault feature for planetary gearbox fault detection. • Experimental results prove that the EAVG-MSB outperforms the ACDIF and CMFH. [ABSTRACT FROM AUTHOR]

Highlights • A novel multi-stage noise reduction approach is developed. • EEMD and WT based denoising method is applied. • All IMFs are investigated and utilized for fault feature extraction. • MSB is used to extract fault feature for bearing fault diagnosis accurately. Abstract To extract impulsive feature from vibration signals with strong background noise and interference components for accurate bearing diagnostics. A multi-stage noise reduction method is proposed based on ensemble empirical mode decomposition (EEMD), wavelet thresholding (WT) and modulation signal bispectrum (MSB). Firstly, noisy vibration signals are applied with EEMD to obtain a list of intrinsic mode functions (IMFs) that leverage the desired modulation components to different degrees. Then, a number of initial IMFs in the high frequency range, which are separated by using the mean of the standardized accumulated modes (MSAM) to have more modulation contents, are further denoised by a wavelet thresholding approach. These cleaned IMFs in the high frequency are combined with the low frequency IMFs to construct a pre-denoised signal that maintains the modulation properties of the raw signal. Finally, modulation signal bispectrum (MSB) is used to extract the modulation signature by suppressing further the residual random noise and deterministic interference components. This multi-stage noise reduction method was validated through a simulation study and two experimental fault cases studies of rolling element bearing. The results were more accurate and reliable in diagnosing the bearing inner and outer race defects in comparison with the individual use of the state-of-the-art EEMD and MSB. [ABSTRACT FROM AUTHOR]

Deep learning-based fault diagnosis methods have made tremendous progress in recent years; however, most of these methods are coarse grained and data demanding that cannot find the root causes of mechanical system failures at a finer granularity with limited fault data. Therefore, in this study, we first investigate the few-shot fine-grained fault diagnosis (FSFGFD) problem, with the aim of identifying novel fine-grained faults under different working conditions using only few samples from each class. To address the difficulties of fine-grained fault feature extraction and poor model generalization to unseen few-shot faults in FSFGFD tasks, a novel attention-based deep meta-transfer learning (ADMTL) method is proposed. First, the failure modes under different working conditions are considered as fine-grained faults, and their raw signals are transformed into time–frequency images. Based on this, an attention mechanism is introduced to guide the feature extractor of the ADMTL on what information to learn. The ADMTL then follows a three-stage learning process of pre-training, meta-transfer, and meta-adaptation to achieve fast adaptation to new fine-grained faults using a priori knowledge gained from known faults. Furthermore, a parameter modulation strategy is employed to adaptively update the pre-trained network during the meta-transfer process. The comprehensive experimental results of three case studies demonstrate the superiority of our method over state-of-the-art methods. The proposed method achieves excellent performance with an average accuracy of 99.08%, 95.86%, and 77.74% for FSFGFD tasks when performing meta-transfer within the same machine and between different machines, respectively. [ABSTRACT FROM AUTHOR]

• An enhanced MSB based non-Gaussian noise reduction method is proposed. • An AR model is developed as a pre-filter process unit to reduce the non-Gaussian noise. • The performance of fault feature extraction of the proposed AR-MSB is tested with various data types and bearing fault cases. • AR-MSB has high accuracy in fault feature extraction compared with the conventional MSB and FK. Many methods have been developed for machinery fault diagnosis addressing only Gaussian noise reduction, the major weaknesses of these methods are their performance for non-Gaussian noise suppression. Modulation signal bispectrum (MSB) is a useful signal processing method with significant advantages over traditional spectral analysis as it has the unique properties of Gaussian noise elimination and demodulation. However, it is susceptible to non-Gaussian noise that normally occurs in the practical applications. In view of the deficiency of MSB, in this paper, an autoregressive (AR) modeling filter was developed based on non-Gaussian noise suppression to improve the performance of MSB for machinery fault detection. The AR model was considered as a pre-filter process unit to reduce the non-Gaussian noise. And the order of the AR model, which can affect the performance of the AR filter, was determined adaptively using a kurtosis-based indicator. However, the existing nonlinear modulation components remain in the AR filtered signal. The MSB was then applied to decompose the modulated components and eliminate the Gaussian noise from the filtered signal using AR model for the fault feature extraction accurately. The advantage of the AR model can effectively manage non-Gaussian noise, whereas the MSB can suppress Gaussian noise and is illustrated in the simulation signal. Furthermore, the proposed AR-MSB method was applied to analyze the vibration signals of defective bearings with outer race and inner race faults. By comparison, the proposed approach had a superior performance over conventional MSB and fast kurtogram in extracting fault features and was precise and effective for rolling element bearing fault diagnosis. [ABSTRACT FROM AUTHOR]