Faults In Rolling Element Bearings Research Articles

A new signal processing-based approach for detection and localization of defective rolling-element bearing

The signal processing techniques are basically used for the detection of defect in the rotating machines. However, none of the existing approaches consider their localizations especially in gearbox systems where the bearings have the same fundamental characteristic frequencies. In this paper, a novel approach of an analytical Higher-order spectral analysis -based signal processing is investigated to potentially locate the defective rolling-element bearing in the gearbox system. In order to efficiently analyze the vibration signal from bearings for defect detection, experimental studies have shown that the Fast-kurtogram is the most suitable for this purpose. For this reason, we propose a new operation of the Higher-order spectral analysis in order to have both information detection and the localization of the existing defect. This proposed technique offers effective results in terms of detecting and locating the defective bearing.

A simulation-data-driven subdomain adaptation adversarial transfer learning network for rolling element bearing fault diagnosis

In recent years, increasing numbers of deep learning methods for fault diagnosis of rolling element bearings (REBS) have been proposed. However, in industry, the scarcity of available data to monitor the health condition of REBS leads to low recognition accuracy of the trained intelligent diagnostic models. To solve this problem, we propose a simulation-data-driven subdomain adaptation adversarial transfer learning (TL) network (SAATLN). Firstly, a defect vibration model is introduced to simulate vibration signals of different types of REBS faults. And the real signal and simulated signal are used as the target domain and source domain of the TL fault diagnosis methods, respectively. Secondly, SAATLN uses the designed residual squeeze-and-excitation (Re-SE) blocks to extract transfer features between different domains. Meanwhile, it combines adversarial learning and subdomain adaptation to adapt the marginal distribution and conditional distribution discrepancies of high-level features. Also, the local maximum mean discrepancy is introduced as the subdomain adaptation metric criterion. Finally, different transfer tasks are performed on the artificially damaged and run-to-failure REBS data sets. The results demonstrate the effectiveness and superiority of the SAATLN in the simulation-data-driven REBS fault diagnosis.

A Comparative Study to Predict Bearing Degradation Using Discrete Wavelet Transform (DWT), Tabular Generative Adversarial Networks (TGAN) and Machine Learning Models

Prognostics and health management (PHM) is a framework to identify damage prior to its occurrence which leads to the reduction of both maintenance costs and safety hazards. Based on the data collected in condition monitoring, the degradation of the part is predicted. Studies show that most failures are caused by faults in rolling element bearing, which highlights that a bearing is one of the most important mechanical components of any machine. Thus, it becomes important to monitor bearing degradation to make sure that it is utilized properly. Generally, machine learning (ML) or deep learning (DL) techniques are utilized to predict bearing degradation using a data-driven approach, where signals are captured from the machine. There should be a large amount of data to apply either ML or DL techniques, but it is difficult to collect that amount of data directly from any machine. In this study, health assessment is carried out using the correlation coefficient to divide the bearing life into two degradation stages. The raw signal is processed using discrete wavelet transform (DWT), where mutual information (MI) is used to rank and select the base wavelet, after which tabular generative adversarial networks (TGAN) are used to generate the artificial coefficients. Statistical features are calculated from the real data (DWT coefficients) and the artificial data (generated from TGAN). The constructed feature vector is then used as an input to train machine learning models, namely ensemble bagged tree (EBT) and Gaussian process regression with the squared exponential kernel function (SEGPR), to estimate bearing degradation conditions. Both the machine learning models were validated on the publicly available experimental data of FEMTO bearing. Obtained results showed that the developed EBT and SEGPR models accurately predicted the bearing degradation conditions with the average lowest RMSE value of 0.0045 and MAE value of 0.0037.

Localization of defects in rolling element bearings by dynamic classification based on meta-analysis of indicators: supervised real-time OPTICS method

Localization of defects in rolling element bearings by dynamic classification based on meta-analysis of indicators: supervised real-time OPTICS method

A Novel Bearing Faults Detection Method Using Generalized Gaussian Distribution Refined Composite Multiscale Dispersion Entropy

Rolling element bearings are a critical component of rotating machines and the presence of defects in the bearings may eventually lead to machine failure. Hence, early identification of such defects and severity assessment may avoid malfunctioning and breakdown of machines. Vibration signal features are often used to build fault diagnosis and fault classification systems. In this paper, a novel Refined Composite Multiscale Dispersion Entropy (RCMDE) based feature is proposed using a nonlinear mapping approach using the Generalized Gaussian Distribution (GGD)–Cumulative Distribution Function (CDF) with the different shape parameter β. This work combines the GGD Dispersion Entropy (DE) algorithm within the RCMDE framework with a feature selection algorithm, which is then used as input to a Multi-class Support Vector Machine (MCSVM) model for categorizing rolling element bearings fault conditions. The proposed method is validated using Case Western Reserve University (CWRU), Jiangnan University (JNU), and Southeast University (SEU) datasets. The experimental analysis shows that the GGD–RCMDE features are better in terms of classification accuracy, precision, recall and F1–score as compared to existing approaches.

Time domain vibration analysis techniques for condition monitoring of rolling element bearing: A review

Rolling element bearings are very critical components of rotating machines and the presence of defects in the bearing may lead to failure of machines. Rolling Element Bearing (REB) fault detection, diagnosis, prognosis are the key steps of machine failure diagnostics. Under operating condition of the bearing may avoid malfunctioning and breakdown of machines. Although various methods to fault detection and diagnosis of the same have been proposed in the literature, such as the thermograph, visual inspection, ultrasonic test, motor current analysis, acoustic emission analysis, the wear-debris analysis, oil analysis, and the vibration analysis. The vibration-based analysis is proven as a popular among all non-destructive methods due to its merits over the other. Time domain vibration analysis technique is better for the online monitoring, remote area, non human intervention area, and hazard location. This paper reviews time domain vibration analysis techniques for REB fault detection. The collected vibration signals from machinery with the help of appropriate data acquisition system, which incorporates the vibration transducers are in time domain. Various statistical parameters are listed to illustrate them as time domain feature from vibration signals In order to understand various features and terminologies, REB vibration signals (Bearing Data Set) acquired from Bearing Data Center, of Case Western Reserve University (CWRU) are used.

Feature-based performance of SVM and KNN classifiers for diagnosis of rolling element bearing faults

Rolling element bearings (REBs) are vital parts of rotating machinery across various industries. For preventing breakdowns and damages during operation, it is crucial to establish appropriate techniques for condition monitoring and fault diagnostics of these bearings. The development of machine learning (ML) brings a new way of diagnosing the fault of rolling element bearings. In the current work, ML models, namely, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN), are used to classify the faults associated with different ball bearing elements. Using open-source Case Western Reserve University (CWRU) bearing data, machine learning classifiers are trained with extracted time-domain and frequency-domain features. The results show that frequency-domain features are more convincing for the training of ML models, and the KNN classifier has a high level of accuracy compared to SVM.

Use of empirical mode decomposition and K- nearest neighbour classifier for rolling element bearing fault diagnosis

Rolling bearing is widely used in rotary machine; the unexpected failure affects the normal operation of the machine leads to production and financial losses to the industry. Hence, Rolling Element Bearing (REB) fault diagnosis is crucial. In this paper, raw bearing vibration signal is divided into the various intrinsic mode functions (IMFs) using Empirical Mode Decomposition (EMD). Statistical features are extracted from the first three IMFs of each conditions of the bearing. These features were given as inputs to K-NN classifier to classify different condition of the bearing.

Detection of Rolling-Element Bearing Faults in Non-stationary Quasi-Parallel Machinery Using Residual Analysis Augmented by Neural Networks

This work proposes a methodology for the detection of rolling-element bearing faults in quasi-parallel machinery. In the context of this work, parallel machinery is considered to be any group of identical components of a mechanical system that are linked to operate on the same duty cycle. Quasi-parallel machinery can further be defined as two components not identical mechanically, but their operating conditions are correlated and they operate in the same environmental conditions. Furthermore, a new fault detection architecture is proposed wherein a feed-forward neural network (FFNN) is utilized to identify the relationship between signals. The proposed technique is based on the analysis of a calculated residual between feature vectors from two separate components. This technique is designed to reduce the effects of changes in the machines operating state on the condition monitoring system. When a fault detection system is monitoring multiple components in a larger system that are mechanically linked, signals and information that can be gleaned from the system can be used to reduce influences from factors that are not related to condition. The FFNN is used to identify the relationship between the feature vectors from two quasi-parallel components and eliminate the difference when no fault is present. The proposed method is tested on vibration data from two gearboxes that are connected in series. The gearboxes contain bearings operating at different speeds and gear mesh frequencies. In these conditions, a variety of rolling-element bearing faults are detected. The results indicate that improvement in fault detection accuracy can be achieved by using the additional information available from the quasi-parallel machine. The proposed method is directly compared to a typical AANN novelty detection scheme.

Condition monitoring and fault detection in roller bearing used in rolling mill by acoustic emission and vibration analysis

Bearings for rolling elements are essential components of rotating devices and bearing failure can lead to machine failure. As a result, early identification of such defects, as well as the seriousness of damage when the bearing is in use, will aid in the prevention of machine failure and breakdown. Vibration is caused by defective bearings, and these vibration signals may be used to test the bearings. This paper defines the use of acoustic emission to predict fault detection in rolling mill roller bearings in relation to the gradual rise in defect size. The signals acquired by the transducers from the bearings are distorted by other faults and mechanical noise from the machinery, so vibration-based approaches are commonly used in bearing fault diagnosis. A rolling mill machine's condition monitoring involves keeping a close eye on the performance of the roller bearings and detecting bearing faults until they cause any problems. Acoustic emission is a non-destructive testing tool used in structural health control that is gaining interest in the diagnosis of bearing defects. Vibration signals provide a wealth of information about a bearing's operating state. A bearing test rig was designed and developed to investigate various defects in rolling element bearings in a real-world environment. Researchers had previously been unable to create a connection between defect sizes and vibration amplitude despite studying various types of seeded defects with random sizes. The experimental research discussed in this paper focuses on a seeded defect of the same kind that grows in size over time on the outer race of radially loaded cylindrical roller bearings, as well as running the defective bearing at different speeds and loads. Data was collected simultaneously using Acoustic Emission (AE) and vibration probes for better diagnosis. The use of acoustic emission (sound) obtained from the near field region of bearings in good and simulated faulty conditions for fault diagnosis is presented, and it is concluded that the Acoustic Emission (AE) approach is superior to identify faults in roller bearings used in rolling mills over a range of speed and load conditions at gradual increase of defect size.

Rolling Element Bearing Fault Diagnosis for Complex Equipment based on MFMD and BP Neural Network

A new fault feature extraction method for rolling element bearing is put forward in this paper based on modified Fourier mode decomposition (MFMD) and multi-scale permutation entropy, and the fault pattern recognition is studied by combining BP neural network. First, introduce frequency band entropy (FBE) to optimize the boundary frequency search and effective modal component selection of Fourier decomposition. Then, use MFMD to adaptively decompose the original vibration signal to several Fourier intrinsic mode functions (FIMFs) and select effective FIMFs. Next, use multi-scale permutation entropy to quantify the fault features. Finally, input the fault feature vector into the BP neural network for fault diagnosis model training and testing. The method proposed in this paper is applied to the rolling element bearing simulation data and the public bearing fault test data set of Case Western Reserve University to verify the feasibility of the method. The results show that the method proposed in this paper has a high identification accuracy for different types of faults, reaching over 98%. The feasibility and superiority of the rolling element bearing fault diagnosis method based on MFMD and BP neural network are verified, and technical support is provided for the health state assessment of rolling element bearings.

Extracting spatially global and local attentive features for rolling bearing fault diagnosis in electrical machines using attention stream networks

A health diagnosis mechanism of rolling element bearings is necessary since the most frequent faults in rotating electrical machines occur in the bearing parts. Recently, convolutional neural networks (CNNs) have redefined the state-of-the-art accuracy for bearing fault detection and identification, extracting location invariant feature mappings without the need for prior expert knowledge. With the use of convolution operations as the core of the process, CNNs consider the local spatial coherence of the input. However, one major drawback of the convolutional models is the weakness to capture global information about the input vector and to derive knowledge about the statistical properties of the latter. The authors propose a deep learning (DL) model that concatenates the features that are produced from two neural streams. Each consists of an attention mechanism that intends to learn different representations of the input vector, and so finally to produce a feature mapping that contains global and spatial locally information. Simulation results on two famous rolling element bearings fault detection benchmarks show the effectiveness of the method. In particular, the proposed DL model achieves 99.60% in the Case Western Reserve University bearing data set and 99.10% in the Paderborn University bearing data set.

A Combined Short Time Fourier Transform and Image Classification Transformer Model for Rolling Element Bearings Fault Diagnosis in Electric Motors

The most frequent faults in rotating electrical machines occur in their rolling element bearings. Thus, an effective health diagnosis mechanism of rolling element bearings is necessary from operational and economical points of view. Recently, convolutional neural networks (CNNs) have been proposed for bearing fault detection and identification. However, two major drawbacks of these models are (a) their lack of ability to capture global information about the input vector and to derive knowledge about the statistical properties of the latter and (b) the high demand for computational resources. In this paper, short time Fourier transform (STFT) is proposed as a pre-processing step to acquire time-frequency representation vibration images from raw data in variable healthy or faulty conditions. To diagnose and classify the vibration images, the image classification transformer (ICT), inspired from the transformers used for natural language processing, has been suitably adapted to work as an image classifier trained in a supervised manner and is also proposed as an alternative method to CNNs. Simulation results on a famous and well-established rolling element bearing fault detection benchmark show the effectiveness of the proposed method, which achieved 98.3% accuracy (on the test dataset) while requiring substantially fewer computational resources to be trained compared to the CNN approach.

Early detection of bearing faults using minimum entropy deconvolution adjusted and zero frequency filter

A method based on minimum entropy deconvolution with convolution adjustment and zero frequency filter is presented for the identification of weak faults in rolling element bearings. Localized fault present in rolling element bearings causes periodic impulses in the bearing vibration signal. The zero frequency filtering of the bearing vibration signal keeps only the localized disturbances at the impulse locations while attenuating the non-impulsive components of the signal. The effectiveness of zero frequency filtering depends on the strength of impulses present in the measured faulty bearing signal in time domain. In the present work, Minimum entropy deconvolution adjusted is used as a preprocessor to improve the strength of impulses in the measured time-domain bearing signal. The effectiveness of the proposed algorithm is tested with simulated signals for the faulty bearing vibration at different levels of added Gaussian noise. The algorithm is also validated using experimental bearing vibration dataset. Results from the proposed algorithm are compared with the results of the zero frequency filter and local mean subtraction-based technique for rolling element bearings’ fault identification. The proposed algorithm performs better detection in case of a weak fault signal.

Rolling element bearings fault classification based on feature extraction from acceleration data and artificial neural networks

This paper presents the development of an artificial neural network (ANN) model for rolling element bearings fault classification that uses features extracted from acceleration data collected during run-to-failure experiments. The presented approach initially employs a wavelet decomposition method for signal denoising and subsequently relies on a Fourier transform to analyse the acceleration signal in the frequency domain. Several features that correspond to the entire signal range as well as to specific frequency bands are then extracted and used as inputs in the ANN model, which is trained to identify three different operational states, namely, no fault, inner race fault and outer race fault. The developed ANN model is validated using experimental data from the publicly available dataset provided by the Center of Intelligent Maintenance Systems (IMS) of the University of Cincinnati. The results show that the trained ANN model has a classification accuracy of 90.2% in the training data and 100% in the test data.

Rolling element bearing health diagnosis – A comparative study of statistical features

Rolling Element Bearing (REB) fault diagnosis is a widely researched theme. In this work, the raw vibration signal is denoised using Modified Kurtosis Hybrid Thresholding Rule (MKHTR). The denoised signal is subjected to Discrete Wavelet Transforms (DWT) and seventeen statistical features are extracted from the wavelet coefficients. Statistical Features selected using Kernel Fisher Discriminant Analysis (KFDA) are analysed using independent samples test and Mann Whitney U test to distinguish between a healthy and defective REB. Weibull negative log likelihood (WNLL) distinguishes between a healthy and defective REB at the significance level of 0.01 irrespective of the location of the defect. The methodology and outcomes of this study is expected to motivate the researchers to identify the statistical features that distinguish between a healthy and unhealthy REB.

Vibration indicator-based graph convolutional network for semi-supervised bearing fault diagnosis

Since fault diagnosis has entered the big data era, deep learning has been more and more widely studied to diagnose faults of rolling element bearings. Generally, existing methods require labeled data for training before they can be used to recognize faults. However, in real scenarios, massive data are usually unlabeled data rather than labeled ones, because labeling data is always a tough issue and consumes much human labor. In order to fully take advantage of the massive unlabeled data, this paper proposes a vibration indicator-based graph convolutional neural network (VI-GCN) for fault diagnosis. The VI-GCN is applied to a benchmark dataset of bearing faults. Experimental results indicate that it is promising for bearing fault diagnosis when there are few labeled data.

Synchronous chirp mode extraction: A promising tool for fault diagnosis of rolling element bearings under varying speed conditions

As critical components in modern aerospace productions, rolling element bearings (REBs) generally work under varying speed conditions, which brings great challenges to their operating health monitoring. Some novel time–frequency decomposition (TFD) algorithms are established recently to extract nonlinear features from the non-stationary signals effectively, which are promising for realizing fault diagnosis of REBs under varying speed conditions. However, numerous personal experiences must be incorporated and the anti-noise performance of these methods needs to be further enhanced. Given these issues, a synchronous chirp mode extraction (SCME) - based REB fault diagnosis method is proposed for the health monitoring of REBs under varying speed conditions in this study. It mainly consists of following two parts. (a) The shaft rotational frequency (SRF) is initially estimated from the low-frequency band of the vibration signal. Simultaneously, an adaptive refining strategy is incorporated to obtain a suitable bandwidth parameter. (b) A cycle-one-step estimation frame is constructed to extract synchronous modes from the envelope waveform of the vibration signal. Meanwhile, a synchronous mode spectrum (SMS) is generated using the information of the extracted synchronous modes, which is a novel REBs fault diagnosis technique with tacholess and resampling-free. In contrast to the current TFD algorithms, the proposed method needs fewer input parameters and owns a well anti-noise performance because there is no iterative optimization in the procedure of construction of SMS. As a result, the health conditions of REBs are evaluated by detecting the exhibited features in the SMS. Simulations and experiments are conducted to validate the effectiveness of the proposed method in terms of REB fault diagnosis. Analysis results demonstrate that the proposed method outperforms the current TFD algorithm and the conventional order tracking technique for fault diagnosis of REB under varying speed conditions.

Rolling Element Bearing Fault Diagnosis for Complex Equipment Based on FIFD and PNN

The bearing fault feature for complex equipment in early failure period is so weak and susceptible to complicated transmission path and random noise that it’s very difficult to be extracted, so Fast Iterative Filtering Decomposition (FIFD) with Probabilistic Neural Network (PNN) are combined for diagnosing the bearing fault. A bearing simulator was used to collect vibration signals of bearing under different fault locations, and then FIFD was applied to decompose them into several Intrinsic Mode Functions, where their energy entropy as an feature vector was calculated respectively. Finally PNN was used to classify different bearing faults. The bearing fault simulator shows that this method can quickly and accurately identify the different fault locations of bearings.

Numerical investigation of rolling element bearings faults based on spectrogram

Performance evaluation of the rotating machinery faults analysis plays a vital function in reliability. And reliability is one of the key factors for rotating machinery and other types of equipment for quantifying product performance. Rolling bearing elements present in the rotating machinery is directly affected, as is subjected to the unsteady loading over the period of time. The premature failure of this rolling bearing element is maximum, not unusual and the factors are limitless. A small percentage of these rolling element bearings are capable of work for the whole lifespan provided with the operating condition. In this paper, new method of vibration spectrogram based analysis of rolling element bearings faults is studied. For these, the vibration spectral analysis obtained in time and frequency domains are parametrically studied for the different frequency range and converted to spectrogram. For this new technique of signal analysis was numerically investigated using the vibration signals measured on rolling element bearings that are characterized by the local defects, and the results obtained and in accordance within the limits. And these signal processing method will accurate, and locate the defect in rolling element bearings for the exact time frame.