Search

• Proposed a semantic construction method using adaptive resonance demodulation, which improves the interpretability of semantic features. • Proposed a semantic-induced zero-shot diagnosis framework to identify unknown compound faults using single fault samples of railway bearings. For the challenges of diverse compound faults and low identification accuracy of railway bearings, a new zero-shot diagnosis model based on adaptive resonance demodulation semantic is proposed for the compound fault diagnosis of railway bearings. The model adopts adaptive resonance demodulation to identify the optimal resonance frequency band rich in fault information in bearing signals, and constructs the single and compound fault semantics of samples without separating the compound fault signals, thus improving the interpretability of semantic features. Moreover, spatial Euclidean distance is used to measure the similarity of features and semantics in the mapping space, which enables the identification of unknown compound faults by single faults. Verification through railway bearing data shows that this model effectively improves the compound fault identification accuracy under zero samples and is better than the comparison models. The research results can provide theoretical reference for the research and application of railway bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

• ORS is developed to be installed on the rotating shaft for vibration measurements. • The developed ORS largely improves the SNR of vibration collections than OHS. • The FFT-based fault diagnosis theory for the rolling bearing is presented. • ORS can achieve easier and more robust Hilbert envelope analysis for diagnosis. • Results validate the performance of ORS for early rolling bearing fault diagnosis. The traditional on-house sensing (OHS) accelerometer for vibration measurements causes poor signal-to-noise ratio (SNR) and complicated fault modulations, which increases the difficulty and complexity for early bearing fault diagnosis. To overcome these challenges, this paper develops a wireless triaxial on-rotor sensing (ORS) system to largely improve the SNR and deduces fast Fourier transform (FFT) and Hilbert envelope analysis for accurate early rolling bearing fault diagnosis, which largely improves accuracy and efficiency for early fault diagnosis. First, the development of the ORS system for wireless vibration measurements is given. Second, the theoretical diagnostic relationships between dynamic ORS signals and rolling bearing faults are derived for FFT and Hilbert envelope analysis for the first time. Finally, the induction motor tests with outer and inner race faults successfully validate that both simple FFT and Hilbert envelope analysis can achieve more robust early rolling bearing fault diagnosis compared to OHS measurements. [ABSTRACT FROM AUTHOR]

• The proposed method extends the cyclic frequency range to Fs /2. • The designed scale factor in CWT can help locate important frequency bands. • TKEO is improved to process the single-carrier signal in the frequency domain. • The developed method can enhance the fault features effectively. • Induction motor tests validate the superiority of the method for early fault detection. The cyclostationary analysis techniques have been extensively explored for the purpose of fault detection in rotating machinery. However, there are still huge challenges because of both limited detection frequency range and low fault identification accuracy. This paper proposes an improved cyclostationary method to enhance incipient fault features. Firstly, the continuous wavelet transform is used to accurately locate important frequency bands, and the fault modulation mechanism or fast kurtogram can be adopted to design the optimal wavelet transform scale factor. Secondly, the Teager-Kaiser energy operator is improved to be used in the frequency domain for the weak fault feature enhancement. Finally, fault features are presented in the cyclic frequency domain through spectral coherence and enhanced envelope spectrum. The proposed method is verified through both numerical simulation and experiments, including incipient half-broken rotor bar, and rolling bearing outer race faults in induction motors. [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]

• A method to accurately calculate the blade characteristic frequency is proposed. • It relies on the physical relationship between the BPF and fundamental frequency. • Blade vibrations are separated using VKF with parameters optimization. • A framework for blade early diagnosis based on unsupervised learning is verified. Blade fault is a catastrophic failure of gas turbines. In order to improve the reliability of blade during operation, condition monitoring is one of the effective methods. However, there always exist two problems with blade monitoring: 1) challenges in warning of the occurrence of blade failure in advance and 2) difficulties finding the location after blade failure. In this article, we solve these problems by excavating the characteristics of blade-related signals in broadband casing vibration with advanced signal processing methods and machine learning technology. First, a novel method--Sparse Harmonic Product Spectrum (SHPS)--is proposed to accurately calculate blade passing frequency from gas turbine broadband casing vibration. The SPHS relies on Fourier transform, and its calculation utilizes the physical relationship between fundamental frequency and blade passing frequencies. Combining Vold-Kalman filter with adaptive parameter optimization process (AVKF), the blade-related vibration can be separated from casing vibration even in strong noise. Analysis of simulated casing vibration signal is used to verify the effectiveness and superiority of proposed method. Based on blade-related vibration, we build a gas turbine blade condition model in an unsupervised learning manner. The model can excavate potential blade failures earlier and more accurately than conventional threshold methods. Then, three coefficients are constructed according to the blade-related vibration characteristics to identify the blade fault location in multi-stage system. Moreover, the effectiveness of the proposed blade diagnosis framework is verified using actual industrial gas turbine blade fracturing failure data. [ABSTRACT FROM AUTHOR]

• A NFE is proposed to quantify the fault information distribution in the SCoh. • A WCES from the SCoh with normalized weight is proposed as fault detector. • WCES can effectively extract fault information distributed in multiple bands. • WCES delivers superior bearing diagnostic performance than SES, EES and IES. Enhanced envelope spectrum (EES) and improved envelope spectrum (IES) generated from spectral coherence (SCoh) are proven to be more robust fault detection tools than squared envelope spectrum (SES). However, EES cannot effectively detect the fault-induced components under strong interference noise and IES can only capture the information of a fault-sensitive resonance spectral frequency band. To overcome these problems, weighted combined envelope spectrum (WCES) from SCoh is proposed as a novel fault detector. WCES integrates the fault components distributed in multiple resonance frequency bands using normalized feature energy and removes the envelope spectrum slices with less fault information to exclude disturbance noises. The performance of WCES is validated using simulations and experiments and compared with the advanced envelope spectra. The results demonstrate that WCES can effectively detect bearing faults under strong interference noise and multiple resonances compared with the SES, EES and IES, and has potential application value in bearing diagnostics. [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]