Bearing Fault Signal Research Articles

An enhanced spline-based time-varying filtering method and fast MKurtgram for bearing fault identification under random impulsive environment

In certain engineering problems, the presence of random impulsive components can heavily corrupt a signal. Thus, random impulsive components are also known as random impulsive noise or non-Gaussian noise. Commonly used signal processing tools in fault diagnosis may perform poorly under such operational conditions. To this end, an alternative approach integrating time-varying filtering with fast MKurtgram (FMK) is proposed as a solution. The FMK is developed based on the fast kurtogram (FK). The FMK addresses a major drawback of the FK, which is vulnerable to random impulsive noise, thus FMK exhibits good performance in impulsive environments. However, the FMK may produce inaccurate estimates of the bandwidth and center frequency when random impulsive noise is relatively intensive. To alleviate this, a spline-based time-varying filtering (TVF) method is designed in this work. This spline-based TVF method is highly effective in eliminating a large amount of Gaussian noise, as well as attenuating the energy of the impulsive components. After undergoing this pre-treatment, the FMK can estimate both bandwidth and center frequency more precisely. The proposed approach is demonstrated to be effective through the simulated and real bearing fault signals.

Generalized adaptive singular spectrum decomposition and its application in fault diagnosis of rotating machinery under varying speed

Rotating machinery fault signals often consist of multiple components with time varying frequencies under variable speed conditions. Spectral overlap exists among these components, making it difficult to independently separate the features of the components. Singular spectrum decomposition (SSD), a singular spectrum analysis-based signal decomposition method, has shown its great potential in suppressing background noise and extracting fault-related components in complex background noise environments. However, SSD is a frequency domain decomposition method with equivalent filtering characteristics, and it is susceptible to the mode mixing when processing signals with spectral overlap. Moreover, the choice of a key parameter in the iteration decomposition process of SSD, the embedding dimension, is determined using an empirical formula, which might cause suboptimal decomposition outcomes. To address these issues, this paper proposes a generalized adaptive singular spectrum decomposition (GASSD) method, which combines generalized demodulation with improved embedding dimension selection for SSD. GASSD incorporates SSD into the framework of adaptive generalized demodulation to separate specific frequency domain features. Firstly, for an effective generalized demodulation analysis, a region block synchronous ridge extraction method is proposed to accurately estimate the instantaneous frequency ridges from the time-frequency plane, which helps construct proper demodulation phase functions. Secondly, to achieve optimal analysis of SSD, a Gini moderation decomposition index is designed to improve the construction of the trajectory matrix by determining an appropriate embedding dimension. Finally, the reliability of the proposed method is demonstrated by analyzing wind turbine generator bearing fault signals and rotor rubbing fault signals.

Motor Bearing Fault Diagnosis in an Industrial Robot Under Complex Variable Speed Conditions

Abstract Motor bearing is the key vulnerable part of the servomotor in an industrial robot, which is always arranged at the joint that is the main load area. In the movement process of the robot, motor bearing bears a great impact due to the frequent movement of joints, which is easily damaged. The fault characteristic information of a bearing in these complex conditions shows strong nonstationary characteristics. Early nonstationary fault signals are often weak and submerged in background noise. The nonstationary signal processing method using computed order analysis and the weak signal enhancement method using adaptive stochastic resonance both show good performances for the above problems. Inspired by these, a hybrid diagnosis strategy for motor bearing under these speed conditions is proposed. Firstly, the nonstationary fault signals of the motor bearing are transformed into stationary angular signals via computed order analysis. Then, the fault modes are identified via resonance demodulation and variational mode decomposition in the order spectrum. Finally, adaptive stochastic resonance is used to extract the fault features reflecting the bearing operation state. Two types of typical speed conditions are considered, which are representative of the joint. Numerical simulation analysis and experiments verify the effectiveness of the diagnosis method.

An alternative bearing fault detection strategy for vibrating screen bearings

The transformation of the mining machinery industry is oriented towards the adoption of highly sophisticated technologies, with the aim of enhancing operational efficiency. Specifically, there is a focus on improving the nature and quality of operations carried out, such as vibrating screen. Vibrating screens, being one of the pivotal machines, have gained extensive utilization in mining processing plants. However, the demanding working conditions can lead to potential failures in certain components of vibrating screens. Bearings are one of the components that are susceptible to faults. Moreover, owing to the unique working environment and structure of vibrating screens, the signals extracted from defective bearings in vibrating screens exhibit greater complexity and distinctiveness, including (i) vibration interference related to the unbalanced shafts, (ii) cyclic impulses produced by the damaged bearing, (iii) non-cyclic random impulsive noise owing to pieces of coal falling into the deck, and (iv) inevitable noise from environmental conditions. To address this issue, an alternative procedure for bearing fault detection from vibrating screens served in the coal industry is proposed in the work. The strategy for bearing fault signature extraction covers three main steps: (a) a new fast resampled iterative filtering (FRIF) method is utilized to remove the vibration interference produced by the unbalanced shafts and simultaneously eliminate large amounts of background noise; (b) a signal processing method based stable distribution is designed to cancel the random impulses (impulsive noise); and (c) an improved energy operator demodulation technique is proposed to identify the bearing fault characteristics from the purified signal. The proposed strategy is validated using simulated and real tests.

Rapid learning of bearing signal pattern using CfCs promoted by a self-attention mechanism

Deep learning is helpful for improving the fault recognition ability of bearings, but this kind of model relies on a large number of training samples and computing resources. In this paper, an algorithm termed a closed-form continuous-depth neural network (CfC) assisted by an information compression-interaction (ICI) module and spatial conjunction attention (SCA) module (CfC-ISCA) is proposed. The ICI module extracts the main features of input signals, the SCA module is designed for positioning target features and capturing more useful features, and the CfC module is used to further fuse features and achieve rapid learning of samples. This algorithm can learn bearing fault signal patterns rapidly and has excellent fault identification ability under small sample conditions. Some public datasets are used to validate the model performance. The test results show that the proposed CfC-ISCA algorithm has comprehensive advantages in fault signal recognition, consumption of computing resources and fast learning compared to comparative methods.

Complementary Ensemble Empirical Mode Decomposition and Maximum Correlated Kurtosis Deconvolution for Wind Turbine Bearing Fault Feature Extraction

Wind turbine bearing fault signals exhibit characteristics such as nonlinearity, non-stationarity, and susceptibility to external noise interference, making it challenging to extract fault features and identify them accurately. In light of these issues, this paper proposes a fault signal feature extraction method that combines complementary ensemble empirical mode decomposition (CEEMD) and maximum correlated kurtosis deconvolution (MCKD). CEEMD is utilized to decompose the signals, reducing mode mixing and eliminating residual auxiliary noise in the decomposition process, thereby obtaining linear and stationary signals that enhance the significance of the features. MCKD is employed to increase the kurtosis value of the fault signals, facilitating the extraction of continuous transient impacts from weak fault signals. Finally, a Convolutional Neural Network (CNN) is employed to validate that the method enhances fault characteristics and improves the accuracy of fault signal recognition.

Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis

This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR).

Rolling bearing weak fault detection using transient structure‐optimal VMD and adaptive group sparse coding

AbstractRolling bearings are essential parts in machine equipment and detecting damage in the early stage is crucial for ensuring the safe production and machine life. However, it is difficult to extract weak fault features under strong background noise, discrete harmonic frequency interference and non‐stationary service conditions. This investigation proposes a hybrid fault diagnosis approach utilizing transient structure‐optimal variational mode decomposition (TS‐OVMD) and adaptive group sparse coding (AGSC) for addressing the formidable problem. According to the singular value structure between transient signal and the interference signal, this work investigates the singular value shrinkage (SVS) technique to adaptively obtain the independent components number. Then, we present a transient structure measure (TSM) to adaptively optimize the balance factor. This measure index systematically quantifies the typical characteristics of the bearing fault signal, which can maximize the fault information representation and effectively reduces the useful information loss caused by improper selection of VMD parameters. Finally, a sparse coding model called AGSC is furthermore designed to enhance the fault impulses readability and suppress residual noise based on the sparsity within group property and the TSM. The proposed approach is verified using experimental data and is found to be superiority comparison with the state‐of‐the‐art method.

Deep Learning Network Based on Improved Sparrow Search Algorithm Optimization for Rolling Bearing Fault Diagnosis

In recent years, deep learning has been increasingly used in fault diagnosis of rotating machinery. However, the actual acquisition of rolling bearing fault signals often contains ambient noise, making it difficult to determine the optimal values of the parameters. In this paper, a sparrow search algorithm (LSSA) based on backward learning of lens imaging and Gaussian Cauchy variation is proposed. The lens imaging reverse learning strategy enhances the traversal capability of the algorithm and allows for a better balance of algorithm exploration and development. Then, the performance of the proposed LSSA was tested on the benchmark function. Finally, LSSA is used to find the optimal modal component K and the optimal penalty factor α in VMD-GRU, which in turn realizes the fault diagnosis of rolling bearings. The experimental results show that the model can achieve a 96.61% accuracy in rolling bearing fault diagnosis, which proves the effectiveness of the method.

A Rolling Bearing Fault Feature Extraction Algorithm Based on IPOA-VMD and MOMEDA.

Since the rolling bearing fault signal captured by a vibration sensor contains a large amount of background noise, fault features cannot be accurately extracted. To address this problem, a rolling bearing fault feature extraction algorithm based on improved pelican optimization algorithm (IPOA)-variable modal decomposition (VMD) and multipoint optimal minimum entropy deconvolution adjustment (MOMEDA) methods is proposed. Firstly, the pelican optimization algorithm (POA) was improved using a reverse learning strategy for dimensional-by-dimensional lens imaging and circle mapping, and the optimization performance of IPOA was verified. Secondly, the kurtosis-square envelope Gini coefficient criterion was used to select the optimal modal components from the decomposed components of the signal, and MOMEDA was used to process the optimal modal components in order to obtain the optimal deconvolution signal. Finally, the Teager energy operator (TEO) was employed to demodulate and analyze the optimally deconvoluted signal in order to enhance the transient shock component of the original fault signal. The effectiveness of the proposed method was verified using simulated and actual signals. The results showed that the proposed method can accurately extract failure characteristics in the presence of strong background noise interference.

Early Fault Detection of Rolling Bearings Based on Time-Varying Filtering Empirical Mode Decomposition and Adaptive Multipoint Optimal Minimum Entropy Deconvolution Adjusted.

Due to the early formation of rolling bearing fault characteristics in an environment with strong background noise, the single use of the time-varying filtering empirical mode decomposition (TVFEMD) method is not effective for the extraction of fault characteristics. To solve this problem, a new method for early fault detection of rolling bearings is proposed, which combines multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) with parameter optimization and TVFEMD. Firstly, a new weighted envelope spectrum kurtosis index is constructed using the correlation coefficient and envelope spectrum kurtosis, which is used to identify the effective component and noise component of the bearing fault signal decomposed by TVFEMD, and the intrinsic mode function (IMF) containing rich fault information is selected for reconstruction. Then, a new synthetic impact index (SII) is constructed by combining the maximum value of the autocorrelation function and the kurtosis of the envelope spectrum. The SII index is used as the fitness function of the gray wolf optimization algorithm to optimize the fault period, T, and the filter length, L, of MOMDEA. The signal reconstructed by TVF-EMD undergoes adaptive filtering using the MOMEDA method after parameter optimization. Finally, an envelope spectrum analysis is performed on the signal filtered by the adaptive MOMEDA method to extract fault feature information. The experimental results of the simulated and measured signals indicate that this method can effectively extract early fault features of rolling bearings and has good reliability. Compared to the classical FSK, MCKD, and TVFEMD-MOMEDA methods, the first-order correlated kurtosis (FCK) and fault feature coefficient (FFC) of the filtered signal obtained using the proposed method are the largest, while the sample entropy (SE) and envelope spectrum entropy (ESE) are the smallest.

Transient fault extraction for wind turbine generator bearing based on Bayesian biorthogonal sparse representation using adaptive redundant lifting wavelet dictionary

Aiming at the problem that it is difficult to detect effective transient impact characteristics of wind turbine generator bearing fault signals due to non-stationary and strong noise, a fault diagnosis method based on adaptive redundant lifting wavelet dictionary and Bayesian biorthogonal sparse representation (SR) algorithm is proposed. First, a Bayesian model is integrated into the biorthogonal matching pursuit (MP) algorithm to improve the use of dictionary atoms in the effective support set. Then, an adaptive redundant lifting wavelet is used to construct a dictionary matching the transient characteristics of the signal. Finally, the SR algorithm is established by integrating the Bayesian biorthogonal MP model and adaptive redundant lifting wavelet dictionary. Simulation and experimental results show that the proposed method can improve the accuracy of signal reconstruction of transient components and effectively extract bearing fault features, thus verifying the effectiveness and robustness of the method.

Extraction and diagnosis of rolling bearing fault signals based on improved wavelet transform

As the continuous growth of the machinery industry, the importance of rolling bearings as key connecting parts in machinery movement is also increasing. However, the extraction and diagnosis of rolling bearing fault signals are difficult, and how to use modern transform analysis methods to raise the extraction efficiency and diagnostic accuracy becomes the focus. For this, a rolling bearing fault signal extraction and diagnosis model is designed based on empirical wavelet transform. The diagnostic model is optimized by using support vector machine and quantum genetic algorithm to design a rolling bearing fault signal extraction and diagnosis model based on improved empirical wavelet transform-support vector machine. The test results show that the research method can obtain four component signals showing different anomalies when generating time domain diagrams. Only five component peaks are generated and one group is extracted as output when generating component peaks. The abnormal amplitude of envelope spectrum basically reaches 0.40×10-6 or above. The judgment accuracy of component diagnosis reaches 98.12%. The above results show that the research method has better fault signal extraction ability and better diagnostic accuracy when performing fault signal diagnosis, which can provide new technical support for rolling bearing fault signal extraction and diagnosis.

Diagnosis of bearing fault signals based on empirical standard autoregressive power spectrum signal decomposition method

Signal decomposition is an essential tool for the time–frequency analysis of bearing fault signals. Methods for extracting effective fault characteristic information from bearing vibration signals have received increasing attention from researchers. This paper proposes a novel signal decomposition method, called empirical standard autoregressive power spectrum decomposition (ESARPSD), to diagnose bearing faults. First, the normalized autoregressive power spectrum of the bearing fault signal is obtained and its bounds are derived using the lowest minima principle. The decomposed component signals are then filtered through a zero-phase filter bank. Each decomposition component is then demodulated and the respective envelope spectrum is observed to determine the corresponding fault frequency. Zero-phase filter banks are used to deal with the problems of noise interference, which makes decomposition difficult, and frequency aliasing, which occurs when the signal-to-noise ratio is low. Moreover, through normalized autoregressive power spectrum and resonance demodulation techniques, adaptive signal decomposition can accurately separate the target high-frequency vibration signals and detect the fault frequency. The accuracy and performance of the proposed ESARPSD method were validated using simulated signals and actual experimental data. The results demonstrate that this method can effectively decompose bearing fault signal and identify all fault characteristics.

Angle domain cepstral comb and notch liftering—A method to separate concurrent gear and bearing faults under variable speed conditions

In recent years, in particular because of the importance of wind turbines in renewable power generation, there is now a demand for signal processing techniques to cope with the variable speed. It is also important to distinguish between gear and bearing faults which are both critical in wind turbine monitoring. This paper describes a pair of interrelated techniques, which make use of the fundamental differences between gear and bearing fault signals to separately diagnose them, even when both are present at the same time, andfor speed variations up to ± 20%. The signals are order tracked to the (rotation) angle domain, after which the real cepstrum is calculated. The deterministic gear signals appear only at discrete quefrencies, which can be extracted by comb liftering, which results in signals virtually independent of speed and speed variation, and which are very close to the static transmission error (STE) of each gear. For bearing faults, the discrete quefrency components are instead removed by a comb notch lifter, leaving a signal dominated by the bearing fault information. The paper gives numerous examples from gear test rigs with concurrent gear faults (root crack and developing pitting) and bearing faults, separating and diagnosing the two types of fault sources while excluding background noise.

A rolling bearing fault diagnosis method based on Markov transition field and multi-scale Runge-Kutta residual network

In order to address the problem that one- dimensional convolutional neural networks is difficult to extract the local correlation information and mine multi-scale information of rolling bearing fault signals under variable working conditions, a novel fault diagnosis method for rolling bearings based on Markov transition field (MTF) and multi-scale Runge–Kutta residual attention network (MRKRA-Net) is proposed in this paper. Firstly, the original signal is encoded into a two-dimensional image using the MTF method. Then, a multi-scale network is constructed using pre-activation Runge–Kutta residual blocks to extract multi-level features. Secondly, a feature-guided attention mechanism is designed and embedded into the network model to enhance its generalization ability. Finally, the MRKRA-Net model is validated on two different bearing datasets, and the results show that compared with other popular intelligent fault diagnosis methods, MRKRA-Net has higher fault diagnosis accuracy and stronger robustness under both given and variable working conditions.

Local time-reassigned synchrosqueezing transform and its application in bearing fault characteristic extraction

Rolling bearing fault signals and other types of impulse signals present transient broadband and fast time-varying characteristics in the time–frequency plane, which makes accurately locating the time–frequency trajectory of the signal a challenging task. In this paper, a new time–frequency analysis method is proposed to achieve a high energy-concentrated time–frequency representation for impulsive-like signals. At first, the points on the time–frequency ridges are detected to construct a fixed point set as the reassignment target of the fuzzy energy. Then the local blurred energy is directly assigned to the nearest ridge according to the reassignment direction of time–frequency points. The proposed method ensures a high concentration of energy and supports perfect signal reconstruction. The results of numerical validation prove that the new time–frequency analysis method has excellent noise robustness and energy concentration capability. Finally, the application of bearing fault diagnosis under multiple operating conditions confirms the excellence in the fault diagnosis field.

A reinforcement neural architecture search convolutional neural network for rolling bearing fault diagnosis

The complexity of machinery makes accurate identification of rolling bearing fault signals difficult. Convolutional neural networks (CNNs) have made some progress, but they rely on the expertise of the network designer and the iterative process of optimizing numerous parameters. Therefore, there is an urgent need to develop a method that reduces the threshold for designing CNNs for a given task. In this article, we propose a reinforcement neural architecture search CNN to address this problem. Firstly, we design a neural architecture search algorithm that can generate different types of sub-networks specifically for fault diagnosis tasks. Secondly, we execute a reinforcement learning-based search strategy to discover promising sub-networks. Furthermore, we enhance the performance of the sub-network by improving the optimizer and training parameters. We conduct extensive experiments using two different types of datasets and verify that the proposed method’s fault classification capability is superior to existing methods.

Multilevel Feature Extraction Method for Adaptive Fault Diagnosis of Railway Axle Box Bearing

Railway axle box bearing fault signal contains high Q-factor resonance and low Q-factor transient shock components with periodic transient shock features that can characterize bearing faults. However, extracting fault features is usually difficult due to noise, transmission paths, and high-amplitude accidental shocks. Therefore, to address the abovementioned problems, the multilevel feature extraction method for adaptive fault diagnosis of railway axle box bearing was proposed. This paper used the maximum second-order cyclostationary blind convolution (CYCBD) to weaken the influence of disturbances, enhancing weak transient shock components. Resonant sparse decomposition(RSSD) is used for the selection of quality factor Q due to its excellent fault feature separation property. Considering the strict fault frequency component periodicity in the envelope spectrum, the envelope spectrum multipoint kurtosis (ESMK) is proposed as a metric. The Q factor is optimized using the gray wolf optimization algorithm (GWO) to obtain an adaptive sparse decomposition method (GWO-RSSD) for extracting bearing transient fault shocks to eliminate the signal effects of high-amplitude disturbance shocks and background noise. The simulation results and measured signal analysis of railway axle box bearing show that ESMK can effectively measure periodic transient shocks under strong shock interference compared with the MED-RSSD method. Thus, GWO-RSSD can adaptively separate the optimal low-Q resonance components, verifying the methods’ effectiveness and superiority.

Missing signal imputation for multi-channel sensing signals on rotary machinery by tensor factorization

Multi-channel sensor fusion can be challenging for real-time machinery fault identification and diagnosis when a substantial amount of missing data exists. Usually, some (or even all) sensors may not function correctly during real-time data acquisition due to sensor malfunction or transmission issues. Additionally, multi-channel sensor fusion yields a large volume of data. Imputation of missing entries can also be challenging with a large volume of data, which can predominantly affect the accuracy of machinery fault diagnosis. However, how to impute a substantial amount of missing data for machinery fault identification is an open research question. In light of the above challenges, this paper proposes constructing time-domain tensors based on heterogeneous sensor signals. Subsequently, the fully Bayesian CANDECOMP/PARAFAC (FBCP) factorization method is adopted for missing data imputation of diverse bearing faults signals. To validate the effectiveness of this proposed method, a machinery fault simulator was used to collect diverse bearing fault signals by incorporating both acoustics and vibration sensors. A varying percentage of continuous missing signal scenarios are introduced at the random locations among different acoustics and vibration channels to construct incomplete tensors. Subsequently, the FBCP method was leveraged to complete the incomplete tensors and calculate estimated tensors. To evaluate the performance of continuous missing data imputation, relative standard errors are computed based on the estimated and actual time-domain tensors. Experimental results show that this proposed method can effectively impute a substantial portion of continuous missing data from diverse bearing fault scenarios.