Rolling Element Fault Research Articles

An intelligent fault diagnosis method for rolling bearings based on feature transfer with improved DenseNet and joint distribution adaptation

Mechanical intelligent fault diagnosis is an important method to accurately identify the health status of mechanical equipment. Traditional fault diagnosis methods perform poorly in the diagnosis of rolling bearings under complex conditions. In this paper, a feature transfer learning model based on improved DenseNet and joint distribution adaptation (FT-IDJ) is proposed. With this model, we apply it to implement rolling bearing fault diagnosis. A lightweight DenseNet model is firstly proposed to extract the transferable features of the raw vibration signal. Furthermore, the parameters in the DenseNet are constrained by the domain adaptive regularization term and pseudo label learning. The marginal distribution discrepancy and the conditional distribution discrepancy of the learned transferable features are reduced by this way. The proposed method is validated by the diagnosis experiments with CWRU and Jiangnan University rolling bearing datasets. The experimental results showed that the proposed FT-IDJ can classify common rolling bearing faults such as inner ring fault, outer ring fault and rolling element fault. Also, it has higher classification accuracy than DAN and other eight methods, which demonstrates its effectively learning transferable features from auxiliary data.

VMD based trigonometric entropy measure: a simple and effective tool for dynamic degradation monitoring of rolling element bearing

Early identification of rolling element defects is always a topic of interest for researchers and the industry. For early fault identification, a simple and effective dynamic degradation monitoring method using variational mode decomposition (VMD) based trigonometric entropy measure is developed. First, vibration signals are obtained and are further decomposed using VMD to obtain various frequency modes. Second, a trigonometric entropy measure is developed to monitor the dynamic change occurring in the health of bearing. Third, trigonometric entropy measure of various VMD modes is computed. Fourth, the variance of measure is computed and two modes having the highest variance are selected for principal component analysis (PCA). Thereafter, PCA of selected measures is carried out. Finally, dynamic degradation monitoring is carried out by observing the trend in the principal component having the highest diverse information. The testing of newly developed VMD based trigonometric entropy measure is carried out on the two different types of data set. One is from XJTU-SY Bearing datasets and another is from the Centre for Intelligent Maintenance Systems. The experimental study reveals that the proposed method is capable of raising the alarm about the initiation of defects at a very early stage. Compared to existing indicators such as kurtosis, RMS, and Shannon entropy, the proposed method is superior while carrying out defect degradation monitoring.

Localization of Rolling Element Faults Using Improved Binary Particle Swarm Optimization Algorithm for Feature Selection Task

The accurate localization of the rolling element failure is very important to ensure the reliability of rotating machinery. This paper proposes an efficient and anti-noise fault diagnosis model for rolling elements. The proposed model is composed of feature extraction, feature selection and fault classification. Feature extraction is composed of signal processing and signal noise reduction. Signal processing is carried out by local mean decomposition (LMD), and signal noise reduction is performed by product function (PF) selection and wavelet packet decomposition (WPD). Through the steps of signal noise reduction, high-frequency noise can be effectively removed, and the fault information hidden under the noise can be extracted. To further improve the effectiveness of the diagnostic model, an improved binary particle swarm optimization (IBPSO) is proposed to find the most important features from the feature space. In IBPSO, cycling time-varying inertia weight is introduced to balance exploitation and exploration and improve the capability to escape from local solutions, and crossover and mutation operations are also introduced to improve exploration and exploitation capabilities, respectively. The main contributions of this research are briefly described as follows: (1) The feature extraction process applied in this research can effectively remove noise and establish a high-accuracy feature set. (2) The proposed feature selection algorithm has higher accuracy than the other state-of-the-art feature selection algorithms. (3) In a strong noise environment, the proposed rolling element fault diagnosis model is compared with the state-of-the-art fault diagnosis model in terms of classification accuracy. Experimental results show that the model can maintain high classification accuracy in a strong noise environment. Therefore, it can be proved that the fault diagnosis model proposed in this paper can be effectively applied to the fault diagnosis of rotating machinery.

Enhanced bearing fault detection using multichannel, multilevel 1D CNN classifier

Electric motors are widely used in many industrial applications on account of stability, solidity and ease of use. Mechanical bearing faults have the highest statistical occurrence percentage among all of the motor fault types. Accurate and advance detection of the bearing faults is critical to avoid unpredicted breakdowns of electric motors. Through early detection of bearing faults, it would be possible to solve the problem at a lower cost by repairing and/or replacing relevant parts. Most of the fault detection works in the literature attempted to detect binary {healthy, faulty} motor fault case based on a single input. In this study, we propose an enhanced performance bearing fault diagnosis system based on multichannel, multilevel 1D-CNN classifier processing vibration data collected from multiple accelerometers mounted on bearings in a test bed. Effectiveness and feasibility of the proposed method are validated by applying it to the benchmark IMS bearing vibration dataset for inner race and rolling element faults and comparing the results with the conventional single-axis data-based fault detection.

Nonlinear Dynamic Modeling and Vibration Analysis of Faulty Rolling Bearing Based on Collision Impact

Abstract This study proposes a new nonlinear dynamic model of rolling bearing faults based on a collision impact system. The dynamic model accounts for the collision impact system consisting of the rolling elements and localized faults according to the nonlinear Hertzian contact. First, considering the impact of the rolling element and fault structure, the collision impact system between rolling element and localized fault is established, and the vibration responses of the collision impact system can be obtained. Second, the overall rolling bearing is treated as a mass-spring model, and the contact between the rolling element and raceway is treated as a nonlinear spring that conforms to the Hertzian contact deformation theory. Third, according to the Lagrange equation, overall potential energy, overall kinetic energy, elastic potential energy, and kinetic energy of the collision impact system are used to describe the vibration characteristics. Considering the impact of collision impact systems, a nonlinear dynamic model of rolling bearing faults is established. The simulated acceleration results based on the nonlinear dynamic model are compared to experimental results. The comparison indicates that the numerical model can be used to predict the vibration characteristics of rolling bearings faults effectively.

Investigations of Antifriction bearing defects using Vibration Signatures

Antifriction bearing failure is a major factor in the failure of rotating machinery. As a fatal defect is detected, it is common to shut down the machinery as soon as possible to avoid catastrophic damages. Performing such action typically results in substantial time and economic losses. Therefore it is important to monitor the conditions of antifriction bearings and to know the details of the severity of defects before they cause serious catastrophic consequences. The vibration monitoring technique is the most suitable method to analyze various defects in bearing. This technique can provide early information about progressing malfunctions. Time-domain analysis and frequency domain analysis have been employed to identify different defects in bearing running at three different speeds. Defect-free and defective bearing are used for testing. Time-domain and frequency-domain signals acquired for both good and defective bearings Time waveform indicated the severity of vibration in defective bearings. The frequency spectrum is used to identify the amplitudes corresponding to fault frequencies and enables to predict of the defect presence. The roller bearing is considered for analysis. Three types of defects namely outer race, inner race, and rolling element defect are considered. Experimental data of both defect-free and defective bearings are processed to show the effectiveness of the fault diagnosis using this method. In fault monitoring and diagnostics of bearings, real-time processing and fast on line fault indication are becoming increasingly important. Towards this goal, attention has focused on a search for the use of effective signal processing and signatures extracting methods to realize immediate fault detection.

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

Preventive maintenance of modern electric rotating machinery (RM) is critical for ensuring reliable operation, preventing unpredicted breakdowns and avoiding costly repairs. Recently many studies investigated machine learning monitoring methods especially based on Deep Learning networks focusing mostly on detecting bearing faults; however, none of them addressed bearing fault severity classification for early fault diagnosis with high enough accuracy. 1D Convolutional Neural Networks (CNNs) have indeed achieved good performance for detecting RM bearing faults from raw vibration and current signals but did not classify fault severity. Furthermore, recent studies have demonstrated the limitation in terms of learning capability of conventional CNNs attributed to the basic underlying linear neuron model. Recently, Operational Neural Networks (ONNs) were proposed to enhance the learning capability of CNN by introducing non-linear neuron models and further heterogeneity in the network configuration. In this study, we propose 1D Self-organized ONNs (Self-ONNs) with generative neurons for bearing fault severity classification and providing continuous condition monitoring. Experimental results over the benchmark NSF/IMS bearing vibration dataset using both x- and y-axis vibration signals for inner race and rolling element faults demonstrate that the proposed 1D Self-ONNs achieve significant performance gap against the state-of-the-art (1D CNNs) with similar computational complexity.

Rolling Element Fault Diagnosis Based on VMD and Sensitivity MCKD

In order to improve the diagnosis accuracy and solve the weak fault signal of rolling element of rolling bearings due to long transmission path, a novel fault diagnosis method based on variational mode decomposition (VMD) and maximum correlation kurtosis deconvolution (MCKD), namely VMD-MCKD-FD is proposed for rolling elements of rolling bearings in this paper. In the proposed VMD-MCKD-FD, the vibration signal of rolling element of rolling bearings is decomposed into a series of Intrinsic Mode Functions (IMFs) by using VMD method. Then the number of modes with outstanding fault information is determined by Kurtosis criterion in order to calculate the deconvolution period T. The periodic fault component of reconstructed signal is enhanced by using sensitivity MCKD method. Finally, the power spectrum of the reconstructed signal is analyzed in detail in order to obtain the fault frequency and diagnose the rolling element fault of rolling bearings. The simulation signal and actual vibration signal are selected to verify the effectiveness of the VMD-MCKD-FD method. The experimental results show that the VMD-MCKD-FD method can effectively diagnose the rolling element fault of rolling bearings and obtain better fault accuracy.

Spectrum analysis of rolling element bearing faults

The health status of these bearings efficiently and effectively can be monitor using the spectrum analysis. The rolling element bearings are of two types rolling and sliding rolling element bearings, and these Sliding rolling bearings are of two types, linear and journal rolling bearings. The combination of both roller and ball can be referred to as rolling element bearings and can be widely used in many applications. The usage can be wide a range because of the permit rotary motion of shafts, starting from aircraft gas turbines, power transmissions, electric motors, bicycles, roller skates and many more. As the rolling element bearings have many advantages, compared with other types of bearings. As they are commonly referred to as antifriction bearings because the amount of lubrication required is less. In this paper, a new dimension is added for the spectrum analysis of rolling element bearing faults detection, analysis and diagnosis. Her the rolling element bearing faults are studied in comparison with three major factors like the time domain, frequency domain and spectrum plot obtained for the rolling element faults. The spectrum obtained from the normal and inner, outer race faults are consider mapping the spectrum analysis in more effective way.

A comprehensive evaluation of the effect of defect size in rolling element bearings on the statistical features of the vibration signal

A defective rolling element bearing produces a specific vibration pattern that can be used as a diagnostic tool in predictive maintenance. Defect growth from an incipient fault to a fully developed fault alters the vibration pattern significantly. Changes in the statistical features of the acceleration as the defect grows can provide useful information in degradation assessment. The purpose of this paper is to study the trend of the important statistical features in terms of defect size. A physical model with the ability of modeling naturally developed defects has been used for the simulation of the generated vibrations in the rolling element bearings. Defects on the outer race, inner race and rolling element have been considered separately. The vibration signals have been obtained numerically from the model and their statistical features have been calculated for different defect sizes. The behavior of the statistical features including rms, peak, crest factor, kurtosis and level crossing rate have been studied thoroughly and simple relations between the defect size and vibration features have been proposed. Level crossing rate is introduced as a useful feature in the condition monitoring of rolling element bearings. Experimental data of a bearing with a natural defect have been measured using an accelerometer in a test and used to validate the results.

Research on Rolling Bearing Fault Diagnosis Using Improved Majorization-Minimization-Based Total Variation and Empirical Wavelet Transform

Bearings are among the most widely used core components in mechanical equipment. Their failure creates the potential for serious accidents and economic losses. Vibration signature analyses are the most common approach to assess the viability of bearings due to its ease of measurement and high correlation with structural dynamics. However, the collected vibration signals of rolling bearings are usually nonstationary and are inevitably accompanied by noise interference. This makes it difficult to extract the feature frequency for the failed bearing and affects the diagnosis accuracy. The majorization-minimization-based total variation (TV-MM) denoising algorithm effectively removes the noise interference from the signal and highlights the related feature information. The value of its main parameter λ determines the quality of the denoising effect. However, manually selecting parameters requires professional experience in a process that it is time-consuming and laborious, while the use of genetic algorithms is cumbersome. Therefore, an improved particle swarm algorithm (IPSO) is used to find the optimal solution of λ. The IPSO utilises the mutation concept in genetic algorithms to reinitialise the particles with a certain probability after each update. In addition, the empirical wavelet transform (EWT) is an adaptive signal processing method suitable for processing nonlinear and nonstationary signals. Therefore, this paper presents an ensemble analysis method that combines the IPSO, TV-MM, and EWT. First, IPSO is used to optimise the denoising parameter λ. The TV-MM under this parameter effectively removes the background noise interference and improves the accuracy of the subsequent modal decomposition. Then, the EWT is used for the adaptive division to produce a set of sequences. Finally, Hilbert envelope demodulation is performed on each component to realise fault diagnosis. The results from simulations and signals received from defective bearings with outer race fault, inner race fault, and rolling element fault demonstrate the effectiveness of the proposed method for fault diagnosis of rolling bearings.

Wavelet Resonance Demodulation Method and Its Application in Fault Diagnosis of Railway Bearings

Resonance demodulation method other than other diagnosis methods, such as AR model method and wavelet transform method, is adopted by engineers to diagnose the faults of rotating machinery, but its effectiveness depends to a great extent on how to choose the center frequency and the bandwidth of the filter. Here a new resonance demodulation method based on wavelet is presented, which applies time-frequency transform on the acceleration signals collected and extracts the time-energy signal from the time-frequency spectrum instead of filtering the original acceleration signals and then extracting the envelope. The key part of the method is that a criterion in terms of the minimum of kurtosis factor is proposed and the time-energy signal, which is equivalent to envelope, can be automatically derived from the time-frequency spectrum according to the criteria. The method is applied to the analysis of vibration signals of rolling bearings with outer-race inner ring faults and rolling element faults, and the results show that it performs effectively in fault diagnosis of freight car rolling bearings and performs more effectively than conventional fault diagnosis methods, say, demodulated resonance technology, to extract the fault characteristic.

Rolling Bearing Fault Diagnosis Based on Adaptive Multiparameter-Adjusting Bistable Stochastic Resonance

The weak-signal detection technologies based on stochastic resonance (SR) play important roles in the vibration-based health monitoring and fault diagnosis of rolling bearings, especially at their early-fault stage. Aiming at the parameter-fixed vibration signals in practical engineering, it is feasible to diagnose the potential rolling bearing faults through adaptively adjusting the SR system parameters, as well as other generalized parameters such as the amplitude-transformation coefficient and scale-transformation coefficient. However, extant adaptive adjustment methods focus on the system parameters, while the adjustments of other adjustable parameters have not been fully studied, thus limiting the detection performance of the adaptive SR method. In order to further enhance the detection performance of adaptive SR methods and extend their application in rolling bearing fault diagnosis, an adaptive multiparameter-adjusting SR (AMPASR) method for bistable systems based on particle swarm optimization (PSO) algorithm is proposed in this paper. This method can produce optimal SR output through adaptively adjusting multiparameters, thus realizing fault feature extraction and further fault diagnosis. Furthermore, the influence of algorithm parameters on the optimization results is discussed, and the optimization results of the Langevin system and the Duffing system are compared. Finally, we propose a weak-signal detection method based on the AMPASR of the Duffing system and employ three diagnosis examples involving inner ring fault, outer ring fault, and rolling element fault diagnoses to demonstrate its feasibility in rolling bearing fault diagnosis.

Signal Processing for Enhancing Impulsiveness Toward Estimating Location of Multiple Roller Defects in a Taper Roller Bearing

Abstract Rolling element defect identification is a difficult task. The reason being that defect on the rolling element has both rotational as well as revolutionary motion. To identify rolling element defect in a taper roller bearing, a novel signal processing scheme is proposed which results in a substantial increase in kurtosis and impulse factor of the vibration signal. The scheme constitutes a series of operations. In the beginning, the raw signal is decomposed by ensemble empirical mode decomposition (EEMD) and inverse filtering (INF). The above two stages of signal processing extract hidden impulses which are suppressed in the noise present in the experimental data. In the third stage of processing, continuous wavelet transform (CWT) using adaptive wavelet is applied to the preprocessed signal to produce a 2D map of the CWT scalogram. This transformation results in a higher coefficient in the region of impulse produced due to the defect. Finally, time marginal integration (TMI) of the CWT scalogram is carried out for defect localization. The defect frequency was evaluated with an accuracy of 97.81% and defect location was identified with an accuracy of 92%.

Fault diagnosis for rolling element bearing using variational mode decomposition and l1 trend filtering

In order to extract the faint fault features of bearings in strong noise background, a method based on variational mode decomposition and l1 trend filtering is proposed in this study. In the variational model, the mode number κ is determined difficulty, thus l1 trend filtering is applied to simplify the frequency spectrum of the original signals. In this case, this parameter can be defined easily. At the same time, a criterion based on kurtosis is used to adaptively select the regularization parameter of l1 trend filtering. The combined approach is evaluated by simulation analysis and the vibration signals of damaged bearings with a rolling element fault, an outer race fault and an inner race fault. The results demonstrate that the hybrid method is effective in detecting the three bearing faults. Moreover, compared with another approach based on multiscale morphology and empirical mode decomposition, the proposed method can extract more bearing fault features.

Bearing fault diagnosis in rotating machinery based on cepstrum pre-whitening of vibration and acoustic emission

In this study, an experimental system was built to acquire vibration and acoustic emission (AE) signals from faulted bearings methodology based on cepstrum pre-whitening (CPW), tested for vibration signals, and was applied for both types of signals to compare and enhance results on machining condition monitoring. The methodology was applied to 9 vibration and 9 AE signals from the experimental system database. For the 18 analyzed signals, in 5 the identification of fault components was easily made, in 12 the fault identification was possible, and in 1 the identification was not completed. The comparison between vibration and AE from 9 tests of experimental system results in 6, vibration has a better result than AE, specifically in the inner race and rolling element faults, for the remaining 3 tests that correspond to outer race fault, AE has a better result.

Study of Vibrational Response of a Rotary System with Defective Rolling Element Bearing

Study of Vibrational Response of a Rotary System with Defective Rolling Element Bearing

Complementary ensemble local means decomposition method and its application to rolling element bearings fault diagnosis

Local means decomposition is an adaptive and nonparametric time–frequency decomposition method for nonstationary and nonlinear signals. However, in practice, local means decomposition is susceptible to mode mixing phenomena and produces different scale oscillations in one mode or similar scale oscillations in different modes, rendering the decomposition results difficult to interpret in terms of physical meansing. The noise-assisted ensemble local means decomposition method not only effectively resolved mode mixing but also generated a new problem, which tolerates residual noise in signal reconstruction. Targeting these shortcomings, this article proposes complementary ensemble local means decomposition, a novel noise-assisted time–frequency analysis method. First, an ensemble of white noise is added to the original signal via complementary positive and negative pairs. Second, local means decomposition is applied to decompose the noisy signals into a series of product functions, and the final results are obtained by averaging. The simulation results confirm that complementary ensemble local means decomposition offers an innovative improvement over ensemble local means decomposition in terms of eliminating residual noise. The superiority of the proposed method was further validated on fault signals obtained from faulty railway bearings (rolling element and outer race fault signals).

An Incorrect Data Detection Method for Big Data Cleaning of Machinery Condition Monitoring

The presence of incorrect data leads to the decrease of condition-monitoring big data quality. As a result, unreliable or misleading results are probably obtained by analyzing these poor-quality data. In this paper, to improve the data quality, an incorrect data detection method based on an improved local outlier factor (LOF) is proposed for data cleaning. First, a sliding window technique is used to divide data into different segments. These segments are considered as different objects and their attributes consist of time-domain statistical features extracted from each segment, such as mean, maximum and peak-to-peak value. Second, a kernel-based LOF (KLOF) is calculated using these attributes to evaluate the degree of each segment being incorrect data. Third, according to these KLOF values and a threshold value, incorrect data are detected. Finally, a simulation of vibration data generated by a defective rolling element bearing and three real cases concerning a fixed-axle gearbox, a wind turbine, and a planetary gearbox are used to verify the effectiveness of the proposed method, respectively. The results demonstrate that the proposed method is able to detect both missing segments and abnormal segments, which are two typical incorrect data, effectively, and thus is helpful for big data cleaning of machinery condition monitoring.

A Hybrid Time-Frequency Analysis Method for Railway Rolling-Element Bearing Fault Diagnosis

The health condition of rolling-element bearings is important for machine performance and operating safety. Due to external interferences, the impulse-related fault information is always buried in the raw vibration signal. To solve this problem, a hybrid time-frequency analysis method combining ensemble local mean decomposition (ELMD) and the Teager-Kaiser energy operator (TKEO) is proposed for the fault diagnosis of high-speed train bearings. The ELMD method is a significant improvement over local mean decomposition (LMD) for addressing the mode-mixing problem. The TKEO method is effective for separating amplitude-modulated (AM) and frequency-modulated (FM) signals from a raw signal. But it is only valid for monocomponent AM-FM signals. The proposed time-frequency method integrates the advantages of ELMD and TKEO to detect localized defects in rolling-element bearings. First, a raw signal is decomposed into an ensemble of PFs and a residual component using ELMD. A novel sensitive parameter (SP) is introduced to select the sensitive PF that contains the most fault-related information. Subsequently, the TKEO is applied to extract both the amplitude and frequency modulations from the selected PF. The experimental results of rolling element and outer race fault signals confirmed that the proposed method could effectively recover fault information from raw signals contaminated by strong noise and other interferences.