Search

Aiming at the difficulty in obtaining the eigenfrequency of the vibration component of rolling bearing faults in a strong background noise environment and the problem of extraction efficiency, the adaptive chirp mode decomposition (ACMD) combined with Improved maximum second-order cyclostationary blind deconvolution (ICYCBD) fault feature extraction algorithm is proposed. Firstly, to improve the signal-to-noise ratio, the original signal is adaptively decomposed using the ACMD method, and the optimal components are selected based on the principle of maximizing the correlation gini coefficient index. Secondly, to improve the accuracy of parameter setting and extraction efficiency, an improved CYCBD method is proposed to estimate the cyclic frequency set of CYCBD using the proposed enhanced energy harmonic product spectrum (EEHPS) method for the optimal components, the envelope spectrum peak factor index is improved by proposing the envelope spectral period pulse factor (EPPF) index, and the filtering length of the CYCBD is selected adaptively using the step search to obtain the optimized filtered signal. Finally, the envelope spectrum analysis is carried out to extract the fault information accurately. The simulation signals and experimental data show that the method can quickly and accurately extract the fault characteristics of rolling bearings under strong background noise, and the comparison with other methods shows the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

This paper addresses challenges in extracting effective information from rolling bearing fault signals and handling strong correlations and information redundancy in high-dimensional feature samples post-extraction. A rolling bearing fault diagnosis method is proposed on the basis of hierarchical discrete entropy (HDE) combined with semi-supervised local Fisher discriminant analysis (SELF). Firstly, hierarchical discrete entropy is extracted from signals preprocessed via variational mode decomposition. We assess entropy stability under different parameters using the coefficient of variation and select optimal parameters accordingly. Secondly, we employ the SELF method to remap the multidimensional feature sample set extracted, performing dimensionality reduction. Finally, a fault diagnosis model classifies the dimensionality-reduced feature samples for fault identification. Experimental results demonstrate that entropy samples extracted via HDE achieve higher diagnostic accuracy after dimensionality reduction with the SELF method. Specifically, accuracy rates of 100 % and 98.2 % are achieved for two types of fault samples, respectively, validating the feasibility and effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Fault mechanism analysis is one of the methods in fault diagnosis, and the dynamic modeling of rolling bearing faults plays a crucial role in studying fault mechanisms. Existing dynamic fault models only consider the impact of fault size and bearing speed on the impact force, providing an incomplete description of the impact force. In order to more accurately describe the dynamic fault model of impact forces, this paper focuses on the deep groove ball bearing with outer race faults. Factors such as defect deformation, speed, and fault size are considered, and an instantaneous impact force excitation function is proposed. Based on this proposed excitation function, a dynamic model for the outer race fault of deep groove ball bearings is established. Finally, through simulation and experimental comparison, the results indicate that the fault characteristic frequencies and their harmonics of the model in this paper are closer to the actual fault characteristic frequencies, reducing the error by 1 to 2 Hz. Therefore, the model proposed in this paper is more effective and accurate, providing a more precise rolling bearing fault model for the study of fault mechanisms. [ABSTRACT FROM AUTHOR]

Feature mode decomposition (FMD) has advantages over the other newer time-frequency methods such as ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) in single channel blind source separation (SCBSS). However, FMD has the defect of needing to determine the precise number of fault sources manually. To solve the above defect of FMD, an adaptive method for determining the number of fault sources based on the shift invariant sparse code (SISC) is proposed. SISC was used to train a set of basis functions from the single channel signal, and the corresponding potential components were reconstructed firstly. Subsequently, the structural similarity of these potential components was used for clustering, and each of the obtained clustering signals represented one kind of fault. Then the number of clustering was determined by minimizing the structural correlation among the clustering signals. It was considered that the source separation had achieved the best effect when the structural difference among the clusters was the largest, and the number of clustering at this time was used as the optimal estimated value, which was used as the modal inputs number of FMD calculation model to realize SCBSS of rolling bearing. Simulation and experimental analysis were carried out to verify the effectiveness of the proposed method, and its superiority was also verified through comparison. [ABSTRACT FROM AUTHOR]

Since bearing fault signal in complex running status is usually characterized as nonlinear and non-stationary, it is difficult to extract accurate affluent features and achieve effective fault identification via conventional signal processing tools. In this article, a rolling bearing fault diagnosis technique based on variational mode decomposition and weighted multidimensional feature entropy fusion is proposed to address this issue, which is mainly composed of three procedures. First, the original signal undergoes the variational model decomposition. Next, the signal features are extracted by weighted multidimensional feature entropy as the input of the diagnosis model. Finally, the classification is performed by a convolutional neural network. The method is applied in simulation and experimental analysis. The experimental results show that the proposed method, which demonstrates strong immunity to noise and robustness, can more effectively and adaptively extract the fault features of rolling bearings and achieve the goal of identifying the rolling bearing fault category and damage degree under variable operating conditions. Meanwhile, this approach exhibits superior accuracy and identification performance to some similar entropy-based hybrid approaches referred to in this article, with a promising prospect in industrial application. [ABSTRACT FROM AUTHOR]

In order to solve the dependence of convolutional neural networks (CNN) on large samples of training data, an intelligent fault diagnosis method based on spectral kurtosis (SK) and attention mechanism is proposed. Firstly, the SK algorithm is used to obtain two-dimensional fast kurtosis graphs from vibration signals, and the two-dimensional fast spectral kurtosis graphs are converted into one-dimensional kurtosis time-domain samples, which are used as the input of CNN. Then the channel attention module (CAM) is added to CNN, and the weight is increased in the channel domain to eliminate the interference of invalid features. The accuracy of fault identification can reach 99.8 % by applying the proposed method on the fault diagnosis experiment of rolling bearings. Compared with the traditional deep learning (DL) method, the proposed method not only has higher accuracy, but also has lower dependence on the number of samples. [ABSTRACT FROM AUTHOR]

As essential equipment in rotating machinery, the fault diagnosis technology of rolling bearings has achieved great success. However, it still suffers from limitations in terms of generalization and noise resistance performance when operating under complex conditions. To accurately identify the fault types of rolling bearings under different loads and nosy environments, a novel intelligent fault diagnosis method is proposed. Firstly, the utilization of dilated convolution expands the network's receptive field, thereby effectively enhancing the scope of fault extraction. Then, by incorporating the Efficient Channel Attention (ECA) in different convolutional layers, the extracted features are adaptively recognized, highlighting important representation information and improving fault diagnosis performance. Finally, the proposed network is utilized for rolling bearing fault diagnosis under diverse operating and noise conditions, and its efficacy is evaluated on various datasets. The experimental results demonstrate that the proposed method exhibits good generalization performance and strong robustness, compared with other methods. [ABSTRACT FROM AUTHOR]

Rolling bearings are the most important components in the transmission system of coal mining machinery, and their operating condition significantly impacts the entire mechanical and electrical equipment. Therefore, the fault diagnosis of rolling bearing can effectively ensure the operation reliability of equipment. Given the strong noise, coal impact, and other interference, the vibration signal of the rolling bearing cannot be effectively decomposed, and the fault identification efficiency is low. According to the method based on vibration analysis, this article proposes a rolling bearing fault diagnosis method based on ensemble local mean decomposition (ELMD) hybrid feature extraction and wavelet neural network. ELMD is used to solve the problem of modal aliasing in local mean decomposition (LMD), which can improve the efficiency of LMD. Quantitatively extracting the mixed features of each component and introducing a wavelet neural network for fault type recognition. The experimental results demonstrate that the proposed method has a high accuracy in fault recognition and is an effective fault diagnosis method. [ABSTRACT FROM AUTHOR]

Traditional feature selection algorithms rarely consider the dynamic misalignment between different time series, and have poor fault tolerance and robustness. In this paper, a fault feature selection method for rolling bearings based on Dynamic Time Warped Related Searches (DTWRS) is proposed. Firstly, the bearing fault feature set is constructed, and the dynamic time warping algorithm is used to calculate the shortest cumulative distance between feature of different faults, and this distance is used as the correlation evaluation standard. Then, two new search rules, dynamic time warping difference and dynamic time warping entropy, are proposed based on the minimum redundancy between bearing fault features and the maximum correlation between fault features and feature categories, use these two search rules to judge the ability of the feature to express the fault, define the quality of the fault feature and sort from good to bad according to the level of ability. Finally, in this order, the number of features is gradually increased and input to the fault classifier, and the sensitive fault feature set is obtained based on the principle of the highest recognition rate and the least number of features. The experimental results show that the fault feature selection method of rolling bearing based on DTWRS can increase the accuracy of fault diagnosis while minimizing the number of features, and improve the efficiency and effect of fault diagnosis. [ABSTRACT FROM AUTHOR]

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). [ABSTRACT FROM AUTHOR]

A typical vibration signal of fault bearing is composed of periodic repetitive transient impulses, multiple vibration disturbance and background noise. Variational mode decomposition (VMD) represents a potential tool for analyzing such signals. However, the reasonable selection of VMD algorithm parameters hinders its application in mechanical signal processing to a certain extent. According to the specific characteristics of rolling bearing fault signal, the composite dimensionless index is constructed as the objective function to ensure the optimal decomposition of VMD. To further enhance the fault characteristics, the tunable Q-factor wavelet transform (TQWT) along with sparse code shrinkage is proposed to denoise the modal components containing periodic impulses, which further highlights the impulses and improves the sparseness of fault signal. Simulation and experimental signal analysis verify the effectiveness and reliability of this method. The results show that the use of optimized VMD and TQWT based sparse code shrinkage dramatically sharpens the impulses from the mixed signal with noise interference and increases the sparseness to a level. [ABSTRACT FROM AUTHOR]

In recent years, many studies have been conducted on remote machine condition monitoring and on-board bearing fault diagnosis. To accurately identify the fault pattern, large amounts of vibration data must be sampled and saved. However, because the bandwidth of the wireless communication is limited, the volume of transmitted data cannot be too large. Therefore, raw data are usually compressed before transmission. All of the previous compression methods use a sample-then-compress framework; however, in this work, we introduce a compression method based on a Compressive Sensing that can simultaneously collect and compress raw data. Additionally, a hybrid measurement matrix is designed for Compressive Sensing and used to compress the data and make it easy to conduct fault diagnosis in the compression domain. This process can significantly reduce the computational complexity of on-board fault diagnosis. The experimental results demonstrate that the proposed compression method is easy to use and the reconstruction process can recover the original signal perfectly. Above all, the compressed signal can preserve the time series information of the original signal, and in contrast to fault diagnosis using the original signal, the accuracy of the fault diagnosis based on conventional methods in the compression domain is not significantly decreased. [ABSTRACT FROM AUTHOR]

Although, deep learning has been successfully used for fault diagnosis of rolling bearing by training large-scale data, the acquisition of large-scale fault data requires a high cost. For small-scale data, the precision of network model will decrease with the deepening of network layers. Aiming at above issue, a convolutional neural network algorithm based on transfer learning model is proposed. First, the overlap sampling of rolling bearing fault signals are used to enhance the datasets, and the transfer learning model is pre-trained on standard-scale dataset to obtain the initial network parameters, that will be used to extract bearing fault features from small-scale dataset. The effects of data scale and fault categories on model accuracy are discussed based on the comparison and verification on public bearing fault dataset. The results show that the proposed method in this paper can achieve high-precision with a small computational cost on fault identification of small-scale fault data, and the method shows popularization value for the analysis of small-scale datasets in other areas. [ABSTRACT FROM AUTHOR]

In an engineering practice, the faults of rolling bearing are mostly represented as being compound and hard to diagnose. For that, intrinsic time-scale decomposition (ITD) algorithm was combined with Auto-correlation Function (AF) to extract the characteristics of compound faults of rolling bearing in aviation engine. Firstly, ITD algorithm was used to decompose acceleration signal into multiple rotational and residual trend component; secondly, rotational components were reconstructed to figure out their AF; finally, characteristic frequency of rolling bearing under compound faults mode was extracted by Hilbert spectrum envelope. To validate the effectiveness of the method, a comparative study on sensor installation positions and vibration acceleration signal of different compound faults has been carried out. The result of study shows that the proposed ITD-AF method is capable to extract compound fault characteristics of rolling bearing in an effective and precise manner and the installation positions of sensors, rotation speed and fault type shows insensitivity to extraction. [ABSTRACT FROM AUTHOR]

The bearing vibration signal is a rich dynamic symptom of bearing wear, and the vibration signal of rolling bearing presents chaotic characteristics. Input and output variables of vibration signal can be constructed through phase space reconstruction, the Input and output variables can be imported into the prediction model for prediction. The prediction accuracy of the extreme learning machine (ELM) model, Kriging model and RBF model are compared, the results show that ELM has higher accuracy, so ELM chaos model is used to predict the future vibration time series data, and the forecasting error can be obtained by comparing the prediction value with the actual values so as to verity the feasibility of the ELM model. The prediction results of the future state of the bearing are processed as the grey-bootstrap method, and the performance reliability prediction of the bearing is realized by the Poisson counting process. The experimental data show that with the deepening of the fault degree, the reliability performance decreases gradually. The reliability performance of the bearing without fault is 100 %, and the reliability performance is 47.56 % when the inner ring faulty size is 0.72 mm. [ABSTRACT FROM AUTHOR]

Aiming at the problem that traditional fast spectral correlation (Fast-SC) cannot effectively extract the fault feature of rolling bearings under strong background noise, we propose to select a band with abundant fault information on the spectral frequency axis by Spectral Gini Index (SGI) and integrate over them to obtain the Improved Enhanced Envelope Spectrum (IEES). The proposed method doesn't rely on the selection of precise fault characteristic frequency, and has a good industrial application prospect. The simulated and experimental results of rolling bearings prove the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Construction of an optimal band-pass filter for effective envelope demodulation spectral (EDS) analysis of rolling element bearing has been studied widely and amount of methods have been arising. However, most of these methods only get the envelope demodulation analysis result of a specific frequency band. In fact, multiple resonance bands might be caused when rolling bearing fails, especially when compound fault arises, and some key components buried in the original signal are often neglected by the above methods such as fast Kurtogram and Autogram algorithms. Therefore, it is particularly necessary to establish a multi-band pass filter algorithm for EDS. In the paper, an adaptive multi-band pass filter method based on signal energy is proposed, and then the square wave envelope analysis method is used for multi-band pass filtered signal to extract the fault characteristic frequency of rolling bearing. In addition, since the phase of the signal retains a lot of useful information of the original signal, the phase information of the multi-band filtered signal is retained and used for signal reconstruction. Not only the early weak fault feature could be extracted, but also the compound fault feature of rolling bearing could also be extracted by the proposed method, which is verified thorough simulation and experiments. [ABSTRACT FROM AUTHOR]

In this paper, relationships between conditional variance statistic and the center frequency as well as the bandwidth of the filter are researched, and we find that conditional variance statistic is suitable for selecting the center frequency of the filter, but undesirable for selecting the bandwidth. Meanwhile, considering that the traditional iterative way to select the optimal resonance frequency band will be affected by the step size, we choose to fix the bandwidth at five times fault characteristic frequency, then Whale Optimization Algorithm (WOA) is utilized to select the optimal center frequency so as to give consideration to both computing efficiency and accuracy of the selection of center frequency. To further suppress the in-band noise, the filtered signal is analyzed by high order energy operator, and the optimal two energy operators are chosen based on Fault Characteristic Index (FCI) for cross-correlation spectrum analysis. Simulation and experimental results indicate that the proposed algorithm can extract the fault feature of rolling bearings under strong background noise effectively. [ABSTRACT FROM AUTHOR]

The high dimensionality data originating from rolling bearing measuring signals with non-linearity and low signal to noise ratio often contains too much disturbance like interference and redundancy for accurate condition identification. A novel manifold learning named Local coordinate weight reconstruction (LCWR) is proposed to remove such disturbance. Due to the different contribution of samples to their manifold structure, weight value is used for the contribution difference. By reconstructing local low-dimensional coordinates according to its weight function about geodesic distance in neighborhood, LCWR targets to reduce reconstruction error, preserve intrinsic structure of the high dimensionality data, eradicate disturbance and extract sensitive features as global low-dimensional coordinates. The experimental results show that the intraclass aggregation and interclass differences of global low-dimensional coordinates extracted via LCWR are better than those of local tangent space alignment (LTSA), locally linear embedding (LLE) and principal component analysis (PCA). The accuracy reaches the highest 96.43% using SVM to identify LCWR based global low-dimensional coordinates, and its effectiveness is testified in diagnosis of rolling bearing fault. [ABSTRACT FROM AUTHOR]

The vibration signal of rolling bearing often has the characteristics of strong noise, nonlinearity and non-stationary, so the accurate fault feature information cannot be obtained directly from the measured vibration signal. Therefore, a fault pattern recognition method for rolling bearing based on complete ensemble local mean decomposition with adaptive noise (CELMDAN) and fuzzy entropy is deeply studied. Firstly, the reason of modal aliasing existing in local mean decomposition (LMD) method is explained. According to the previous methods for modal aliasing processed in other methods, CELMDAN method is proposed. The experiment proves that the proposed CELMDAN method can better handle the vibration signals with nonlinear and non-stationary. Then, the principle and properties of the fuzzy entropy are introduced in detail, and the fault feature of rolling bearing can be reflected. Finally, extreme learning machine (ELM) is introduced as the pattern recognition method based on the effective fault feature of rolling bearing. Combined with the verification of experimental signal, it is proved that the proposed method can extract the fault features of rolling bearing accurately and effectively, and the fault pattern recognition of rolling bearing can be realized. [ABSTRACT FROM AUTHOR]

Extracting the characteristics of rolling bearings in early weak failure stage before the occurring of complete failure has important safety and economic significance in engineering application. The wavelet transform (WT) is the commonly used and effective time-frequency method for fault feature extraction of rotating machinery due to that it could reflect the fault feature in time and frequency domains synchronously. However, WT would not work effectively when the impulsive fault signal is buried by strong background noise, and the situation is particularly serious in the early weak fault stage of rolling bearing. A frequency slice wavelet transform based on wavelet de-noising using neighboring coefficients method is proposed in the paper by combing frequency slice wavelet transform with wavelet de-noising using neighboring coefficient to solve the above problem: Firstly, the vibration signal of rolling bearing is de-noised by wavelet de-noising using the neighboring coefficients method. Then the frequency slice wavelet transform is applied on the de-noised signal, and satisfactory analysis results could be obtained. The effectiveness of the proposed method is verified by the vibration data of rolling bearing accelerated fatigue test. Besides, the analysis result of the same vibration data of rolling bearing accelerated fatigue test using Kurtogram method is also presented in the paper to verify the advantage of the proposed method. [ABSTRACT FROM AUTHOR]

Early fault diagnosis in rolling bearings is crucial to maintenance and safety in industry. To highlight the weak fault features from complex signals combined with multiple interferences and heavy background noise, a novel approach for bearing fault diagnosis based on higher-order analytic energy operator (HO-AEO) and adaptive local iterative filtering (ALIF) is put forward. HO-AEO has better effect in dealing with heavy noise. However, it is subjected to the limitation of mono-components. To solve this limitation, ALIF is adopted firstly to decompose the nonlinear, non-stationary signals into multiple mono-components adaptively. In the next, the resonance frequency band as the optimal intrinsic mode function (IMF) is selected according to the maximum kurtosis. In the following, HO-AEO is utilized to highlight weak fault characteristics of the selected IMF. Finally, the early bearing fault is diagnosed by the energy operator spectrum based on fast Fourier transform (FFT). Comparisons in the simulation indicate that the fourth order HO-AEO shows the best performance in fault diagnosis compared with Teager energy operator (TEO), analytic energy operator (AEO), the second and the third order HO-AEO. The simulated test and experimental results demonstrate that the proposed approach could effectively extract weak fault characteristics from contaminated vibration signals. [ABSTRACT FROM AUTHOR]

The rolling bearing is an essential element widely used in the rotating machinery. Bearing failures are among the main reasons for breakdown of rotating machinery. Therefore, fault detection of bearing is necessary to reduce the probability of breakdown and safety accidents. A novel fault diagnosis method for rolling bearing based on Refined Composite Multiscale Dispersion Entropy (RCMDE) and Improved Support Vector Machine (ISVM) is presented in this paper. The RCMDE is a new irregular index in biomedical signal analysis, which has lower computational cost and more stable results. Therefore, the RCMDE is introduced as fault feature to represent the bearing fault characteristics. After feature extraction, an improved support vector machine based on whale optimization algorithm (WOA) and support vector machine (SVM) is proposed as a fault classifier, which has the advantages of less training samples and good classification effect. The effectiveness of the proposed method in bearing fault diagnosis is verified by using bearing fault experimental data. [ABSTRACT FROM AUTHOR]

Considering the shortcomings of the traditional energy spectrum algorithm applied to the rolling bearing fault diagnosis, which can only represent the tendency of fault feature transformation with a certain scale, but not adjacent scales contained. In this paper, we propose a fault diagnosis method of rolling bearing based on Support Vector Machine, combining energy spread spectrum and genetic optimization. The extracted signal is denoised and decomposed using wavelet packets, the energy spectrums and energy spread spectrums are calculated based on the decomposed different frequency signal components. The genetic algorithm is used to select the important parameters of the Support Vector Machine and bring the determined parameter values into the Support Vector Machine to generate the GA-SVM model. Then, energy spectrums and energy spread spectrums are inputted into GA-SVM as the characteristic parameters for identification. The experimental results show the two new points of energy spread spectrums and GA-SVM improve the diagnostic rate by up to 28.5%, it can effectively improve the fault recognition rate of the rolling bearing. [ABSTRACT FROM AUTHOR]

Aiming at the fault classification problem of the rolling bearing under the uncertain structure parameters work condition, this paper proposes a fault diagnosis method based on the interval support vector domain description (ISVDD). Firstly, intrinsic time scale decomposition is performed for vibration signals of the rolling bearing to get the time-frequency spectrum samples. These samples are divided into a training set and a test set. Then, the training set is used to train the ISVDD. Meanwhile, the dynamic decreasing inertia weight particle swarm optimization is applied to improve the training accuracy of ISVDD model. Finally, the performance of the four interval classifiers is calculated in rolling bearing fault test set. The experimental results show the advantages of the ISVDD model: (1) ISVDD can extend the support vector domain description to solve the uncertain interval rolling bearing fault classification problem effectively; (2) The proposed ISVDD has the highest classification accuracy in four interval classification methods for the different rolling bearing fault types. [ABSTRACT FROM AUTHOR]

In order to monitor, analyze and diagnose the conditions of all kinds of machines, it is often necessary to calculate the probability density function of the sampled vibration signal. A new direct calculation method of probability density from sampled vibration signal based on the linear interpolation method (LIM) is presented in this paper. Two advantages are observed: 1) the time length of each amplitude segment obtained from a sampled vibration signal by the LIM is closer to the original continuous vibration signal, and 2) the calculation results of probability density got by calculating directly the ratio of time length of each amplitude segment to the total time of sampled vibration signal are more correct than those obtained by other existing methods. The applications to sampled simulation and actual vibration signals of a rolling bearing show that the probability density curves obtained by the new direct calculation method are more accurate and smoother than the curves got by other estimating methods used in a lot of famous software. [ABSTRACT FROM AUTHOR]

In order to excavate the relationship between the different features of the vibration signal, and to provide more useful information for the fault diagnosis of rolling bearings, this paper developed a new method of fault diagnosis-health baseline method and introduced the technological process of this method in detail. Through the case study, a health baseline based on two kinds of linear models was constructed. After testing, this method can distinguish the normal state of the rolling bearing, the external ring fault and the rolling element fault, which indicates that the method was feasible and effective for the fault diagnosis of the rolling bearing. [ABSTRACT FROM AUTHOR]

In this paper, a rolling bearing fault detection method based on Local Characteristic-scale Decomposition (LCD) and Teager Energy operator (TEO) is proposed. Vibration signals is related to the bearing fault. However, the vibration signal of rolling bearing is nonlinear and has multiple components, which makes it difficult to analyze the signals by using traditional method such as the fast Fourier transform (FFT). LCD, a recently developed signal decomposition method, is especially capable for dealing with the complex signal by decomposing it into several intrinsic scale components (ISC). Furthermore, to extract fault diagnosis of the components, we used TEO to demodulate each ISC. The energy of fault feature frequencies was extracted as fault vector. The result shows that the method successfully diagnoses bearing fault. [ABSTRACT FROM AUTHOR]

In this paper, the dynamics of rolling bearing with localized defects of the outer ring and rolling element are investigated. In order to study the nonlinear dynamical behaviors of the rolling bearing precisely, a novel dynamic model of the rolling bearing is established based on the Lagrangian approach. By setting 0.2 mm, 0.4 mm and 0.6 mm local defects on the outer ring and rolling element of bearing respectively, the results demonstrate that the amplitude of the rolling bearing is more intense as the local defect size increases, and the acceleration amplitude fluctuation is more significant than the velocity. In addition, in the case of the same defect size, the vibration of the rolling element defect is more intense than the vibration response caused by the outer ring defect. [ABSTRACT FROM AUTHOR]

Rolling bearing's fault mode usually shows compound faults in aero-engine. The compound faults characteristics are more complex than single one, and many signal analysis methods have rather great limitation for compound fault characteristic extraction which leads to the difficulty to monitor the running state of rolling bearing in aero-engine. Based on above analysis, a method of combining wavelet transform with cyclostationary theory, autocorrelation function and Hilbert transform is proposed and applied to extract characteristic frequency of rolling bearing from compound faults mode only according to single-channel vibration acceleration signal of aero-engine. Meanwhile, a consideration is given to the influence of sensor installation position, compound fault types in the extraction of compound faults characteristics. The result indicates that the proposed new method can effectively monitor rolling bearing running state in four different compound fault modes just according to single-channel vibration acceleration signal no matter sensors are installed in horizontal or vertical direction. [ABSTRACT FROM AUTHOR]

The variational mode decomposition (VMD) proposed recently is a kind of time-frequency signal analysis method. VMD has some advantages on signal decomposition such as high precision and noise robustness, but its serious shortcoming is that the number of modes (K) should be given in advance. And if the number is chosen inappropriately, VMD will lead to larger decomposition error. In this paper, the VMD method is introduced and the over- and under-segment characters of VMD are discussed. The cross correlation coefficients can express the similarity between the two signals. Cross correlation coefficients among VMD components and the original signal are used to judge whether over-segment takes place. As a result, the estimation method of VMD parameter K is proposed. Based on the method, the tri-harmonic signal and the vibration signals of ball bearings are analyzed in detail. The results show that the proposed method is feasible and effective. [ABSTRACT FROM AUTHOR]

In order to accurately identify the fault conditions of rolling bearing, this paper presents a fault diagnosis method based on improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and distance evaluation technique. In this method, to effectively extract potential fault-related information, vibration signals of rolling bearing in different fault conditions are decomposed into a set of intrinsic mode functions (IMFs) through improved CEEMDAN. The first eight IMFs containing most fault information are selected for extracting fault features. The original feature set is obtained including energy values, singular values and envelope sample entropy values. Then distance evaluation technique is implemented for selecting sensitive feature set and discarding irrelevant or redundant features. Subsequently, the sensitive feature set is fed into support vector machine (SVM) for automatically identifying rolling bearing fault conditions. The simulation results demonstrate that improved CEEMDAN is able to solve the problem of mode mixing and achieve a numerically negligible reconstruction error. Meanwhile experimental consequences indicate that the proposed method can acquire higher identification accuracy, as well as reduce the classifier computational burden. [ABSTRACT FROM AUTHOR]

Feature extraction of vibration signal is the key factor of machine fault diagnosis. This paper proposes a novel method of capturing shock energy based on multi-scale weight evaluation of high definition time-frequency map. Specifically, the proposed method is conducted by the following steps. First, ensemble empirical mode decomposition (EEMD) preprocessor-based Hilbert-Huang Transform (HHT) is applied to the raw signal for high definition time-frequency map acquisition. Second, an original algorithm named multi-scale binary spectrum was applied to extract impulsive energy features with different frequency characteristics. Then weights of energy can be calculated by dimensionality reduction of each binary spectrum and merged by summation after blank processing. Finally, power spectrum of compound weight of energy can reveal characteristic frequency corresponding to specific fault. In this method, the key point is enhancement of frequency spectrum using higher dimension details. The process of multi-scale binarization and weight summation were aligned and the effectiveness is verified by simulated signal processing and actual case of train bearing experiment. [ABSTRACT FROM AUTHOR]

The vibration signal of rolling bearing is usually complex and the useful fault information is hidden in the background noise, therefore, it is a challenge to identify rolling bearing faults from the complex vibration environment. In this paper, a novel multilayer deep learning convolutional neural network (CNN) method to identify rolling bearing fault is proposed. Firstly, in order to avoid the influence of different characteristics of the input data on the identification accuracy, a normalization preprocessing method is applied to preprocess the vibration signals of rolling bearings. Secondly, a multilayer CNN based on deep learning is designed in this paper to improve the fault identification accuracy of rolling bearing. Simulation data and experimental data analysis results show that the proposed method has better performance than SVM method and ANN method without any manual feature extractor design. [ABSTRACT FROM AUTHOR]

To effectively extract rolling bearing fault feature under variable conditions, a hybrid method based on order tracking and EEMD is proposed in this paper. This method takes the advantages of order tracking, ensemble empirical mode decomposition and 1.5 dimension spectrum. Firstly, order tracking is used to transform the time domain non-stationary vibration signal to angular domain stationary signal. Secondly, ensemble empirical mode decomposition is performed to decompose the angular domain stationary signal into a series of IMFs, and select the IMF in which the largest vibration energy occurs as the characteristic IMF. Thirdly, 1.5 dimension spectrum is further employed to analyze the characteristic IMF, and extract the fault features from background noise. The proposed method is applied to analyze the experimental vibration signals, and the analysis results confirm the effectiveness of the proposed method under variable conditions. [ABSTRACT FROM AUTHOR]

The health state of a rolling bearing keeps changing from a normal state to a slight degradation state followed eventually by a severely degraded state. To make reasonable inspection and maintenance plans, it is necessary to estimate the degradation state and predict the lifetime of a running rolling bearing accurately and in a timely fashion. This paper presents a new method for rolling bearing degradation state estimation and lifetime prediction based on curve similarity recognition. Different from existing methods, this method employs a dynamic time warping algorithm to recognize the curve similarity of those extracted features of rolling bearings in different states of health, which can reflect the intrinsic state of the rolling bearing; it discretizes the bearing degradation state reasonably through curve similarity. Next, the curve similarity is used to train the degradation state estimation model and a support vector machine based lifetime prediction model. Finally, this paper conducts a case study for a rolling bearing with impact degradation and one with wear degradation, respectively. The experimental results indicate that the new proposed method is highly efficient in recognizing the bearing's degradation state and predicting its lifetime. [ABSTRACT FROM AUTHOR]

For rolling bearing diagnosis, the major challenge of signal processing technique is to extract the quasi-periodic impulses which generated by rolling bearing fault, especially when rolling bearing operated in the condition of heavy noise. This paper proposed a new bearing fault diagnosis scheme. First, the Minimum Entropy Deconvolution (MED) is taken to obtain the impulse excitations from the bearing vibration signal. Then, two kinds of morphological filter, named average filter(AVG) and difference filter (DIF), are used as the assisted filtering unit to reduce the random noise in original signal and integrate the positive and negative impulse excitations in MED filtered signal, respectively. At last, the STFT based ridge demodulation analysis is applied to the purified signal, and the bearing fault is easily identified by spectral analysis of the demodulated signal. Two simulated signal are analyzed to test the performance of the proposed scheme. In the first case, the periodic impulse signal adding with random noise is analyzed. The result shows that MED-AVG-DIA is the best scheme for impulse feature extraction. In the second case, the pure impulse signal which filtered by MED is analyzed. The result shows that STFT based ridge demodulation analysis can achieve better demodulation effect than other demodulation methods. The proposed fault diagnosis scheme has been further verified by simulation signal and measured vibration signals of defective bearing. The result shown that the proposed scheme is feasible and effective for the fault diagnosis of rolling bearing. [ABSTRACT FROM AUTHOR]

Healthy status monitoring of train bearing online is very meaningful work. But as traditional diagnosis system does, performing Fourier spectrum with the datum from more than 200 bearings in a marshalling train is an enormous challenge. Here a healthy status monitoring system of train rolling bearing based on Sparse Fast Fourier Transform (SFFT) is proposed. The monitoring system consists two sequential parts. First, extract fault features based on SFFT spectrum and other time-domain parameters. According to train bearing working environment, altogether 7 fault features are extracted in this paper. Another part is constructing a classifier based on BP neural network. Experimental results show that the system proposed here achieves gratifying results comparing with traditional fault diagnosis system [ABSTRACT FROM AUTHOR]

For bearings, radiation noise was an important evaluation index for mechanical property, in particularly mute machinery. Environmental pollution caused by bearing noise has always been the focus in bearing industry. In this paper, slippage of the rolling bearing and its own variable stiffness excitation were considered to accomplish the vibration coupling between the bearing and bearing seat as well as the coupling between bearing vibration and noise by means of combination of dynamic model, FEA model and boundary element method. A perfect coupled vibro-acoustic model of the bearing was built, and its results were compared with the experimental results to verify the reliability of the proposed method. Based on the verified simulation model, the improved design was carried out for the low-noise rolling bearings. Finally, in order to further verify the superiority of the proposed method in this paper, the designed rolling bearing was compared with that of the traditional design method. The results showed that the proposed design method was reliable. [ABSTRACT FROM AUTHOR]

This paper proposes a new rolling bearing fault diagnosis method based on adaptive multiscale fuzzy entropy (AMFE) and support vector machine (SVM). Unlike existing multiscale Fuzzy entropy (MFE) algorithms, the scales of AMFE method are adaptively determined by using the robust Hermite-local mean decomposition (HLMD) method. AMFE method can be achieved by calculating the Fuzzy Entropy (FuzzyEn) of residual sums of the product functions (PFs) through consecutive removal of high-frequency components. Subsequently, the obtained fault features are fed into the multi-fault classifier SVM to automatically fulfill the fault patterns recognition. The experimental results show that the proposed method outperforms the traditional MFE method for the nonlinear and non-stationary signal analysis, which can be applied to recognize the different categories of rolling bearings. [ABSTRACT FROM AUTHOR]

There is no doubt that remaining useful life prediction is important to the health management of modern mechanical equipment. But in most cases, the useful operational information of equipment we can get are limited, one of them is vibration signal. Particle filter is a hybrid prediction method combined with data-driven and model-based two kinds of methods. It can solve prognosis problem with the fitted prediction model only by historical data, and allow the uncertainty management. However, the prediction performance of the method is largely dependent on the prediction model and very sensitive to the initial distribution of the model parameters. These flaws limit the further development of particle filter methods in the prediction. Aiming at the shortcomings of the basic particle filter prediction method, a general prediction framework of particle filter based on degradation rate tracking is proposed in this paper. It turned away from the fitted model, and utilized the statistical rule of degradation rate of historical data to estimate and predict the degradation process of system. The effectiveness of the method proposed is validated with useful life prediction case of rolling bearings. [ABSTRACT FROM AUTHOR]

For the diagnosis of misalignment-rubbing coupling fault of rotor-rolling bearing system caused by misalignment fault, the mechanical model and finite element model of dual-disc rotor system with misalignment-rubbing coupling fault were established based on the nonlinear finite element method, rolling bearing force, equivalent misalignment torque and contact theory in this paper. And then its accuracy was validated by related experiment. According to research on dynamic characteristics of the rotor system with different rubbing stiffness, misalignment angles and rotation rates, it was found that the misalignment-rubbing coupling fault is often characterized by rubbing fault, and that double frequency appeared early, and that peak value increased rapidly. It could be used as a theoretical basis for diagnosing misalignment-rubbing coupling fault of rotor-rolling bearing system. [ABSTRACT FROM AUTHOR]

In order to improve the speed and accuracy of rolling bearing fault diagnosis on small samples, a method based on relevance vector machine (RVM) and Kernel Principle Component Analysis (KPCA) is proposed. Firstly, the wavelet packet energy of the vibration signal is extracted with the wavelet packet transform, which is used as fault feature vectors. Secondly, the dimension of feature vectors is reduced in order to weaken the correlation between the features. The important principal components are selected using KPCA as the new feature vectors under the criterion that the cumulative variance is greater than 95 %. Finally, the faults of rolling bearing are diagnosed through combining KPCA with RVM. Simulation experimental indicates the advantages of the presented method. Moreover, the proposed approach is applied to diagnoses rolling bearing fault. The results show that wavelet packet energy can express rolling bearing fault features accurately, KPCA can reduce the dimension of feature vectors effectively and the proposed method has better performance in the speed of fault diagnosis than the method based on support vector machine (SVM), which supplies a strategy of fault diagnosis for rolling bearing. In this paper, the performance of the proposed method is also compared with other diagnostic methods. [ABSTRACT FROM AUTHOR]

Three simulation experiments are designed to evaluate and compare the performance of three common independent component analysis implementation algorithms -- FastICA, JADE, and extended-Infomax. Experiment results show that the above three algorithms can't separate the mixtures of super-Gaussian and sub-Gaussian precisely, and FastICA fails in recovering weak source signals from mixed signals. In this case an independent component analysis algorithm, which applies genetic algorithm to minimize the difference between joint probability and product of marginal probabilities of separated signals, is proposed. The computation procedure, especially the fitness evaluation when signals are in discrete form, is discussed in detail. The validity of the proposed algorithm is proved by simulation tests. Moreover, the results indicate that the proposed algorithm outperforms the above three common algorithms significantly. Finally the proposed algorithm is applied to separate the mixture of rolling bearing sound signal and electromotor signal, and the results are satisfied. [ABSTRACT FROM AUTHOR]