Rolling Bearing Fault Feature Extraction Research Articles

Rolling Bearing Fault Feature Extraction Method based on SSA-VMD and MOMEDA

To address the challenge of extracting bearing fault features, this study proposes a new rolling bearing fault feature extraction method based on the Sparrow Search Algorithm (SSA) to optimize Variational Mode Decomposition (VMD) and Multipoint Optimal Minimum Entropy Deconvolution with Convolution Adjustment (MOMEDA). Firstly, SSA is employed to identify optimal parameters in VMD, followed by the utilization of correlation coefficients and kurtosis to filter relevant Intrinsic Mode Function (IMF) components. Subsequently, MOMEDA is applied to denoise the reconstructed signal, mitigating the interference caused by pulse fault signals. Finally, the envelope spectrum analysis is conducted on the denoised signal. Experimental results demonstrate the efficacy of the proposed method in extracting fault features and mitigating noise interference.

A new approach to adaptive VMD based on SSA for rolling bearing fault feature extraction

Due to the structure of rolling bearings, will have various problems. So the early detection of rolling bearing faults is very important. Consequently, a precise method for extracting fault features is required. In this study, an adaptive variational modal decomposition (VMD) fault feature extraction method is proposed, utilizing the sparrow search algorithm (SSA). Firstly, a novel measurement index called impulse diversity entropy (IDE) is introduced, which better represents internal changes within the mode components. Secondly, the SSA is employed to select the optimal VMD decomposition parameters based on the IDE. Finally, a spectrum analysis is conducted on the mode component with the highest IDE to extract fault features. The experimental results show that this method has an accurate feature extraction ability and obvious advantages over other methods in distinguishing fault and interference frequencies because it is a special signal decomposition 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.

Low-rank and periodic group sparse based signal denoising method for rolling bearing fault feature extraction

Vibration signal analysis is a vital method of achieving rolling bearing fault feature extraction, but the fault impulses contained in the vibration signals are susceptible to interference from noise, making it difficult to extract fault features. In order to effectively extract the fault features of rolling bearings, an adaptive low-rank (LR) and periodic group sparse (AdaLRPGS) denoising method is proposed. Firstly, an AdaLRPGS model is constructed, which is not only an improvement of the classical sparse LR method, but also can effectively enhance the LR and periodic group sparsity of the failure impulses. Secondly, an adaptive period prior matching method is proposed to adaptively match the period of the fault impulses, and the moth flame optimization algorithm is utilized to adaptively search the regularization parameter of the AdaLRPGS model, and then the rule for determining the regularization parameter is summarized in the simulation analysis, which solves the dependence of the AdaLRPGS model on the period prior and regularization parameter. Finally, the solution procedure of the AdaLRPGS model is derived under the framework of the alternating direction method of multipliers. The simulated and measured signals are analyzed using the proposed method and compared with some advanced methods. The results show that the proposed method can extract the fault features of rolling bearings and has significant advantages compared with some advanced methods.

Rolling bearing fault diagnosis based on generalized multiscale mean permutation entropy and GWO‐LSSVM

AbstractFaults in rolling bearings are usually observed through pulses in the vibration signals. However, due to the influence of complex background noise and interference from other machine components present in measurement equipment, vibration signals are typically non‐stationary and often contaminated by noise. Therefore, in order to effectively extract the random variation and non‐linear dynamic variation characteristics of vibration signals, a new method of rolling bearing fault diagnosis based on generalized multiscale mean permutation entropy (GMMPE) and grey wolf optimized least squares support vector machine (GWO‐LSSVM) is put forward in this paper. Based on the multiscale permutation entropy (MPE), the multiscale equalization is firstly used to replace the coarse grained process, and the value of mean is extended to variance to avoid the dynamic mutation of the original signal. Finally, the parameters of LSSVM are optimized by the grey wolf optimization algorithm to achieve accurate identification of fault modes. The results of simulation and experiment show that applying the proposed GMMPE to rolling bearing fault feature extraction is feasible and superior, and the method based on GMMPE and GWO‐LSSVM has better noise robustness, which can effectively achieve rolling bearing fault diagnosis.

Enhanced transfer learning method for rolling bearing fault diagnosis based on linear superposition network

Deep transfer learning is used to solve the problem of unsupervised intelligent fault diagnosis of rolling bearings. However, when the data distribution between two domains is different, the existing deep transfer learning models which only rely on the domain-invariant features are not enough to complete the target domain data learning. To solve this problem, an enhanced transfer learning method based on the linear superposition network is proposed for rolling bearing fault diagnosis. This method improves the structure of the one-dimensional convolutional neural network (1D-CNN) by constructing linear superposition convolution blocks. At the same time, the loss function of transfer learning is constructed by using the pseudo-label of the target domain from the network, which enhances the ability of rolling bearing fault feature extraction. Compared with the traditional feature-based transfer learning methods, the proposed enhanced transfer learning method based on the linear superposition network can make the network place more stress on the feature learning of the target domain. Experimental results on the Paderborn University (PU) dataset show that, compared with the improved deep adaptation network (DAN) model, the proposed method improves the average diagnosis accuracy by 21% on six transfer tasks, showing improved bearing fault diagnostic precision.

Rolling bearing fault feature extraction method based on GWO-optimized adaptive stochastic resonance signal processing

The failure of rolling bearings affects the function and precision of rotating machinery significantly, which has drawn lots of attention in this field. Dealing with the failure of rolling bearings, fault feature extraction is the first and most important problem. In this work, we convert the bearing fault signal into stochastic resonance dynamics equivalently. And, adaptive stochastic resonance is adopted to extract the fault signal feature. In addition, for industrial application of fault signal processing with large amplitude and noise intensity greater than 1, normalized scale transformation is introduced into adaptive stochastic resonance and then solved by fifth-order Runge–Kutta algorithm. Then, to further optimize the solving precision of stochastic resonance model, the scaling coefficient and step size of Runge–Kutta algorithm are chosen with the help of Grey Wolf Optimizer (GWO). Thus, we can obtain a fast convergence speed, high calculation accuracy and effective improvement of signal-to-noise ratio fault feature extraction method for rolling bearing fault signal processing. Finally, a comparation simulation was carried out to demonstrate the efficiency of the proposed method. Compared with Cuckoo Search Optimizer-based stochastic resonance signal processing method, the proposed method achieved a higher signal-to-noise ratio (SNR) to benefit the fault feature extraction. In summary, this work gives out a more practical and effective solution for rolling bearing fault feature extraction in rotating machinery fault diagnosis field.

Fault feature extraction method for rolling bearing based on MVMD and complex Fourier transform

The vibration signals caused by rolling bearing defects in different directions may be different, and the fault diagnosis based on single channel vibration signals may be made incorrectly, and the observation results may be understood wrong. To avoid it, a new rolling bearing fault feature extraction method based on multivariate variational mode decomposition (MVMD) and complex Fourier transform (CFT) were proposed. First, the orthogonally sampled vibration signals were combined into a multivariate signal, and the multivariate signal was decomposed into several intrinsic mode functions (IMFs) using the MVMD. As per this method, a unified mathematical model was used to model vibration signals in two directions, ensuring that fault features were decomposed to the same level. Finally, the CFT was applied to fuse the envelope signals in two directions in order to obtain a clearer and comprehensive amplitude-frequency feature. Simulation and test results verify the feasibility and superiority of the proposed method.

Research on the Sparse Optimization Method of Periodic Weights and its Application in Bearing Fault Diagnosis

The vibration state monitoring signal of rolling bearings usually shows periodic transient impulse characteristics at the time of the fault, but in the fault sprouting stage and actual monitoring, its impulse components are easily disturbed by random pulses, harmonics, background noise, etc., which increases the difficulty of extracting the periodic shock characteristics of the fault. This paper proposed a rolling bearing fault feature extraction method based on sparse coefficient weighting theory and periodic enhancement strategy to effectively extract weak periodic shock features with a low signal-to-noise ratio. In the proposed period weighted sparse wavelet representation (PWSWR) method, firstly, based on the sparse wavelet model, the mean kurtosis (MK) index was introduced as a weight to distinguish the contribution of the wavelet coefficients of each signal component. Secondly, a sparse signal period enhancement strategy was proposed using the improved envelope harmonic product spectrum period estimation method. The strategy is embedded into the sparse representation model to achieve the periodic enhancement of filtered signals. Finally, the envelope detection of the sparse signal was carried out to identify the fault. The results of bearing fault simulation signals and two engineering test signals showed that the proposed method could effectively extract weak fault features of bearings and had certain advantages compared with other sparse methods.

Research on Fault Feature Extraction Method of Rolling Bearing Based on SSA–VMD–MCKD

In response to the problem that nonlinear and non-stationary rolling bearing fault signals are easily disturbed by noise, which leads to the difficulty of fault feature extraction, to take full advantage of the superiority of variational mode decomposition (VMD) in noise reduction, and of maximum correlation kurtosis deconvolution (MCKD) in highlighting continuous pulses masked by noise, a method based on sparrow search algorithm (SSA), VMD, and MCKD is proposed, namely, SSA–VM–MCKD, for rolling bearing faint fault extraction. To improve the feature extraction effect, the method uses the inverse of the peak factor squared of the envelope spectrum as the fitness function, and the parameters to be determined in both algorithms are searched adaptively by SSA. Firstly, the parameter-optimized VMD is used to decompose the fault signal to obtain the intrinsic mode function (IMF) components, from which the optimal mode component is selected, and then the optimal component signal is deconvoluted by the parameter-optimized MCKD to enhance the periodic fault pulses in the optimal component signal, and finally extracts the rolling bearing fault characteristic frequency by envelope demodulation. Experiments on simulated signals and measured data show that the method can adaptively determine the parameters in VMD and MCKD, enhance the fault impact components in the signals, and effectively extract the fault characteristic frequencies of rolling bearings, with a success rate up to 100%, providing a new idea for rolling bearing fault feature extraction.

An adaptive spectrum segmentation-based optimized VMD method and its application in rolling bearing fault diagnosis

Variational mode decomposition (VMD) is a signal decomposition algorithm with excellent denoising ability. However, the drawback that VMD is unable to determine the input parameters adaptively seriously affects the decomposition results. For this issue, an optimized VMD method based on modified scale-space representation (MSSR-VMD) is proposed. Firstly, MSSR is proposed to segment the fault signal spectrum, acquiring modes’ number and the initial center frequency for each mode adaptively. Moreover, a pre-decomposition step is added to the original VMD, which selects a target mode from divided frequency bands. Finally, the penalty factor of the target mode is adjusted during the iterative update of the VMD to achieve accurate extraction for the fault features. MSSR-VMD and other adaptive decomposition algorithms are employed to handle the simulated and experimental signals separately. By comparing the analysis results, the method has certain superiority in rolling bearing fault feature extraction.

Hierarchical dispersion entropy and its application in fault diagnosis of rolling bearing

Aiming at the disadvantage that multi-scale entropy only analyzes the low-frequency components of time series, this paper proposes a rolling bearing fault feature extraction method based on hierarchical dispersion entropy (HDE). Firstly, the HDE is constructed based on the hierarchical operators and dispersion entropy. Secondly, the influence of HDE parameters on entropy stability is studied. Finally, the fault diagnosis method based on HDE, least square support vector machine is applied in rolling bearings. The experiment results show that the proposed method can distinguish different types of the rolling bearing faults. It owns the higher fault diagnosis accuracy than the traditional multi scale entropy methods, such as multi-scale sample entropy (MSE), multi-scale dispersion entropy (MDE).

Rolling bearing fault feature extraction via improved SSD and a singular-value energy autocorrelation coefficient spectrum

It is usually difficult to extract weak fault features from rolling bearing vibration signals under noise pollution. To address this problem, a fault feature extraction approach for rolling bearings using improved singular spectrum decomposition (SSD) and a singular-value energy autocorrelation coefficient spectrum (SVEACS) is proposed. Firstly, to facilitate the determination of the optimal modal parameters in the SSD algorithm, the number of SSD layers is adaptively determined using an improved SSD algorithm based on permutation entropy. Then, the optimal modal components are selected, and the proposed SVEACS is used to determine the order of singular-value noise reduction. Finally, envelope analysis is used to extract the accurate shock characteristics of the denoised signal. The results of the experiments on simulated and real signals indicate that the proposed method can effectively extract the weak characteristics of the vibration signal under strong noise, and accurately diagnose the fault of a rolling bearing.

Research on an ID-PCA Early Fault Detection Method for Rolling Bearings

Since the rolling bearing is complex during the signal acquisition process, there is a certain loss during the process of collecting the vibration signal. This has led to the weakness of the early fault characteristics of the rolling bearing, affecting the accuracy of the rolling bearing fault feature extraction. In response to the above problems, an early fault detection method based on the Improved Deep Principal Component Analysis (ID-PCA) is proposed. The proposed method uses the time-series characteristic information of the vibration signal to establish a model, which solves the problem that the principal component analysis method cannot detect the vibration signal directly. Through the deep decomposition theorem, a multi-layer data processing model is established to fully mine the weak fault features in the vibration signal. It can solve the problem of inaccurate early fault detection results due to weak fault feature information. The reliability of this method is proved theoretically through sensitivity analysis. Finally, through experimental simulation, the accuracy and feasibility of this method are proved from the perspective of practice.

Rolling Bearing Fault Feature Extraction Using Local Maximum Synchrosqueezing Transform and Global Fuzzy Entropy

To achieve good performance of fault feature extraction for a rolling bearing, a new feature extraction method is presented in this paper based on local maximum synchrosqueezing transform (LMSST) and global fuzzy entropy (GFuzzyEn). First, targeting the time-varying features of the vibration signals of the rolling bearing, the LMSST algorithm, which is a newly developed time-frequency method and allows for adaptive mode decomposition, is used to preprocess the vibration signals into a number of mode components. Then, as a modification of FuzzyEn, GFuzzyEn is adopted to evaluate the complexity of these mode components. Compared to FuzzyEn, which focuses mainly on the local characteristics of the short-term physiological time series, the GFuzzyEn emphasizes the global characteristics of the signal considering that the bearing vibration signals' global fluctuation may change as the bearing works under various conditions. Finally, the fault features of the bearing vibration signals are extracted by combining the LMSST and the GFuzzyEn. The experimental analysis shows that the proposed LMSST-GFuzzyEn method can extract rich fault-related information from the bearing vibration data and can achieve good classification performance for rolling bearing fault diagnosis.

Research on rolling bearing fault feature extraction based on entropy feature

In large machinery, the most common element we can use is rolling bearing. When the rolling bearing fails, it is very likely to affect the normal operation of the equipment, or even cause danger. Therefore, it is necessary to monitor and diagnose the bearing fault in advance. The most important step in fault diagnosis is feature extraction. This is the research content of this paper. In this paper, the approximate entropy, the sample entropy and the information entropy are analyzed, and the feature is extracted to diagnose the rolling bearing fault. The specific research contents are as follows: (1) Firstly, the concepts of approximate entropy, sample entropy and information entropy are introduced briefly, and the approximate entropy, sample entropy and information entropy of rolling bearing vibration signals under different fault modes are calculated. The feasibility and shortcomings of the features extracted from these three entropy in the fault characteristics of rolling bearing are analyzed. (2) In order to make up for their defects, a method of fault feature extraction based on approximate entropy, sample entropy and information entropy is proposed, and its feasibility is verified. (3) Simulation experiments are carried out to calculate the accuracy of fault feature extraction based on the joint analysis of approximate entropy, sample entropy and information entropy.

Fault Extraction and Identification on Transmission Components of Mechanical Equipment

In order to solve the problem of nonlinear, nonstationary, complex components and redundant information of rolling bearing vibration signal in single scale, a rolling bearing fault feature extraction method based on wavelet packet decomposition and permutation entropy and sample entropy is proposed. Firstly, wavelet packet decomposition is used to decompose the original signal of rolling bearing into several subbands with different frequencies, and the permutation entropy and sample entropy of signal data at different frequencies are calculated. Secondly, the sample entropy and permutation entropy of different frequency signals after decomposition and reconstruction are extracted to form a high-dimensional feature vector to complete the initial fault feature extraction. Finally, the extracted feature samples are randomly arranged for fault recognition. The experimental data of rolling bearing processed by this method are identified by extreme learning machine. The results show that the method can effectively identify the fault types of rolling bearing, and the classification effect is better than that of the original data set training, and the classification accuracy reaches 99.8.

Application of Entropy Information on Bearing Fault Diagnosis

In order to solve the problem of nonlinear, nonstationary, complex components and redundant information of rolling bearing vibration signal in single scale, a rolling bearing fault feature extraction method based on wavelet packet decomposition and permutation entropy and sample entropy is proposed. Firstly, wavelet packet decomposition is used to decompose the original signal of rolling bearing into several sub bands with different frequencies, and the permutation entropy and sample entropy of signal data at different frequencies are calculated. Secondly, the sample entropy and permutation entropy of different frequency signals after decomposition and reconstruction are extracted to form a high-dimensional feature vector to complete the initial fault feature extraction. Finally, the extracted feature samples are randomly arranged for fault recognition. The experimental data of rolling bearing processed by this method are identified by extreme learning machine. The results show that the method can effectively identify the fault types of rolling bearing, and the classification effect is better than that of the original data set training, and the classification accuracy reaches 99.8

Stochastic resonance in cascaded monostable systems with double feedback and its application in rolling bearing fault feature extraction

Stochastic resonance (SR) has been widely concerned and studied in the field of mechanical fault detection due to the capability of weak signal detection. However, research focused on how to improve the performance of SR system and enable it to process large-parameter signals in engineering practice better. Therefore, from the perspective of feedback control and multi-system synergy, this paper presents a double-feedback cascaded monostable SR (CMSR) system and analyzes the SR phenomenon in the system by using the signal-to-noise ratio as the measurement index. It investigates specifically influence of the coefficients on the system performance. Introducing feedback control and serial structure to a monostable system, consisting of a symmetric quartic potential function, not only alters the response characteristics of the monostable system but also significantly improve the system performance. Compared with the classical bistable SR system with low-pass filtering characteristics, the proposed system can exhibit low-pass filtering or band-pass filtering behavior through different combinations of feedback coefficients, which can better match the frequency characteristic of target signal. Finally, the proposed double-feedback CMSR system is used for extraction of the weak signal features in rolling bearing fault detection, and its superiority and feasibility are verified by comparison with other SR systems.

Rolling bearing fault feature extraction using Adaptive Resonance-based Sparse Signal Decomposition

The existence of periodic impacts in collected vibration signal is the representative symptom of rolling bearing localized defect. Due to the complicacy of the working condition, the fault-related impacts are usually submerged in other ingredients. This article proposes an adaptive Resonance-based Sparse Signal Decomposition (RSSD) for extracting the fault features of rolling bearings. Adaptive RSSD is constructed to fetch the impacts from collected vibration signal, by making RSSD decomposed signal kurtosis value maximum using Lion Swarm Algorithm (LSA). Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA) is further performed to enhance the amplitude and periodicity of impacts contained in RSSD decomposed signal, so that fault feature is highlighted. The superiority and availability of proposed strategy are validated by applying to single fault feature extraction of an experimental dataset and compound faults feature extraction of a locomotive rolling bearing.