Faults In Rolling Element Bearings Research Articles

Graph-Based Feature Engineering for Enhanced Machine Learning in Rolling Element Bearing Fault Diagnosis

Graph-Based Feature Engineering for Enhanced Machine Learning in Rolling Element Bearing Fault Diagnosis

Encoder signal-based optimized Savitzky-Golay and adaptive spectrum editing for feature extraction of rolling element bearing under low-speed and variable-speed conditions

Feature extraction of rolling element bearings (REB) under variable-speed conditions is always one of the hot and difficult points in the field of fault diagnosis. Based on the encoder signal with the advantages of low noise, and direct correlation with machine dynamics, an optimized Savitzky-Golay and adaptive spectrum editing are proposed for REB feature extraction under low-speed and variable-speed conditions. Firstly, the estimated features of the instantaneous angular speed (IAS) and interference components are studied. Secondly, based on the proposed multipoint mean ratio indicator and parametric decomposition structure, an adaptive SG filter is proposed to remove the speed trend component. Thirdly, an adaptive spectrum editing scheme with no transition band and low computational cost advantages is proposed to detect REB fault based on the combination of the cyclic dislocation scheme, the Gaussian function and the Pearson theory. Simulation and experiments are used to verify the effectiveness of the proposed scheme.

Rolling Element Bearing Fault Diagnosis Based on Multi-objective Optimized Deep Auto-encoder

Abstract Bearing fault diagnosis holds significant importance, with widespread attention focused on enhancing its accuracy and efficiency. Existing diagnostic methods based on deep learning and transfer learning typically tackle this issue by introducing new function modules and diagnostic strategies, such as attention mechanism, adversarial domain adaptation, etc. However, most studies do not consider the structure and hyperparameters optimization of the network to improve the diagnostic performance of the network itself. To address this limitation, a novel multi-objective optimized deep auto-encoder (MODAE) is proposed in this paper. The optimal network structure and hyperparameters is determined by a multi-objective particle swarm optimization algorithm. Crucially, the method is based on a data-driven approaches to automatically search for network structures with stronger generalization and feature extraction capabilities to address engineering problems in different scenarios. Finally, this method is examined in both multi-fault classification diagnosis and transfer diagnosis scenarios, demonstrating strong self-adaptability through experimental results. In comparison with typical deep learning fault diagnosis methods, the proposed method demonstrates higher diagnostic accuracy and superior generalization ability.

A Generalised Intelligent Bearing Fault Diagnosis Model Based on a Two-Stage Approach

This paper introduces a two-stage intelligent fault diagnosis model for rolling element bearings (REBs) aimed at overcoming the challenge of limited real-world vibration training data. In this study, bearing characteristic frequencies (BCFs) extracted from a novel hybrid method combining cepstrum pre-whitening (CPW) and high-pass filtering developed by the authors’ group are used as input features, and a two-stage approach is taken to develop an intelligent REB fault detect and diagnosis model. In the first stage, various machine learning (ML) methods, including support vector machine (SVM), multinomial logistic regressions (MLR), and artificial neural networks (ANN), are evaluated to identify faulty bearings from healthy ones. The best-performing ML model is selected for this stage. In the second stage, a similar evaluation is conducted to find the most suitable ML technique for bearing fault classification. The model is trained and validated using vibration data from an EU Clean Sky2 I2BS project (An EU Clean Sky 2 project ‘Integrated Intelligent Bearing Systems’ collaborated between Schaeffler Technologies and the University of Southampton. Safran Aero Engines was the topic manager for this project) and tested on datasets from Case Western Reserve University (CWRU) and the US Society for Machinery Failure Prevention Technology (MFPT). The results show that the two-stage model, using an SVM with a polynomial kernel function in Stage-1 and an ANN with one hidden layer and 0.05 dropout rate in Stage-2, can successfully detect bearing conditions in both test datasets and perform better than the results in literature without the requirement of further training. Compared with a single-stage model, the two-stage model also shows improved performance.

Adaptive bearing fault diagnosis using reference frequency and modified scalogram

Previous studies on the diagnosis of natural faults in rolling element bearings have primarily concentrated on detecting an increase in the frequency amplitude across a broad frequency spectrum within the measured signal when a fault occurs in the bearing. However, this study introduces an adaptive method centered on the conspicuous distinction in frequency amplitude between the shaft and bearing fault frequencies as the bearing fault progresses. Specifically, we propose a bearing fault diagnosis approach leveraging the shaft frequency amplitude as a constant reference independent of prevailing conditions, as it consistently maintains a relatively steady level regardless of the presence of bearing faults. Moreover, we devised a modified scalogram to enhance the diagnostic performance for bearing faults by consistently and prominently visualizing information pertinent to faults. We comprehensively assessed fault diagnosis accuracy between a convolutional neural network employing the scalogram and one employing the modified scalogram to verify the diagnostic performance of the adaptive method. This analysis yielded accuracies of 93.6% and 99.3%, respectively. Furthermore, the relationship between the bearing fault diagnosis results and the visualized fault-related information in the scalogram and modified scalogram was analyzed using gradient-weighted class activation mapping, providing evidence supporting improved fault diagnosis performance using the adaptive method.

Automatic Feature Extraction Based on Envelope Analysis and its Application in Rolling-Element Bearing Fault Detection

Bearing fault diagnosis is essential for the maintenance, durability, and reliability of rotating machines. It can minimize economic losses by removing unplanned downtime in the industry due to the failure of rotary machines. In bearing fault detection, developing fault features extraction techniques that can successfully applicable for various fault severity and different operating conditions is still a critical issue. In the current work, the feature extraction technique is a combination between pre-processing algorithms and envelope analysis method. In the pre-processing stage, the autoregressive (AR) model is used to filter the original signal and remove the deterministic vibration sources, as well as maintain the signal representing the condition of the bearing without contaminating noises. Then, the most suitable frequency band is selected based on the spectral kurtosis (SK) analysis. This band contains the signature frequencies of the roller bearing. After that, envelope analysis is employed for detecting faults at different severity. Finally, the features represented the peaks at fundamental fault frequencies are automatically selected from the envelope spectrum. By analyzing all diagnoses results, it is found that the presented method effectively extracts the features at calculated resonance bearing frequencies and proves the significance of the enhancements in a pre-filtering stage in the overall detection performance. Also, it can benefit from these features in the fault classification fields at different speeds because it is independent of speed variation.

Research progress on bearing fault diagnosis with signal processing methods for rolling element bearings

As a prerequisite for rotating machinery to operate effectively, rolling element bearings play an essential role. The focus of condition monitoring has initially been on defect identification, then on its measurement, and eventually on automatic defect prediction. The improvement in signal processing has made this breakthrough possible. The quality of characteristics taken from the bearing signals strongly impacts how effective these techniques are. Aiming to provide the researchers with the option to choose and implement the optimum signal analysis method, the authors have described numerous signal processing techniques used to diagnose faults in rolling element bearings. The research study examines several important studies and explains their relevance to locating rolling bearing defects. It analyzed recent research, ones from the past, and developments in the field of diagnosing bearing defects. The main goal of the research is to investigate different vibration signal processing and analysis methods for locating and evaluating bearing faults. After that, each of these subjects is rigorously analyzed in order to draw conclusions, spot new trends, and pinpoint areas that still need more research. This article is meant to serve as a guide for those who operate in the condition monitoring domain.

Incipient fault feature extraction of rolling element bearings based on SOSO boosting technique and improved energy operator

The incipient fault features of rolling element bearings (REBs) are easily overwhelmed by environmental noise and vibration interference. Therefore, this paper proposes a novel fault feature extraction method for REBs based on a SOSO (Strengthen-Operate denoising-Subtract-Strengthen) boosting technique. Firstly, an improved fast non-local mean filtering (IFNLM) algorithm is proposed by improving the similarity measure and kernel function while reducing the amount of weight calculation based on distance symmetry. Secondly, a SOSO_IFNLM boosting filtering structure is constructed to reduce the noise of the original vibration signal and enhance the early faint fault pulse. Finally, a k-value improved symmetric higher-order frequency-weighted energy operator (k-SHFWEO) is proposed to detect the bearing fault features from denoised signals. The effectiveness and feasibility of the proposed SOSO_IFNLM-k-SHFWEO method are numerically and experimentally investigated. The results demonstrate that the proposed method has better fault feature extraction capability for early weak faults of REBs and higher efficiency compared to other popular methods.

An optimized extreme learning machine‐based novel model for bearing fault classification

AbstractThis work addresses the rolling element bearing (REB) fault classification problem by tackling the issue of identifying the appropriate parameters for the extreme learning machine (ELM) and enhancing its effectiveness. This study introduces a memetic algorithm (MA) to identify the optimal ELM parameter set for compact ELM architecture alongside better ELM performance. The goal of using MA is to investigate the promising solution space and systematically exploit the facts in the viable solution space. In the proposed method, the local search method is proposed along with link‐based and node‐based genetic operators to provide a tight ELM structure. A vibration data set simulated from the bearing of rotating machinery has been used to assess the performance of the optimized ELM with the REB fault categorization problem. The complexity involved in choosing a promising feature set is eliminated because the vibration data has been transformed into kurtograms to reflect the input of the model. The experimental results demonstrate that MA efficiently optimizes the ELM to improve the fault classification accuracy by around 99.0% and reduces the requirement of hidden nodes by 17.0% for both data sets. As a result, the proposed scheme is demonstrated to be a practically acceptable and well‐organized solution that offers a compact ELM architecture in comparison to the state‐of‐the‐art methods for the fault classification problem.

Instantaneous-Angular-Speed-Based Synchronous Averaging Tool for Bearing Outer Race Fault Diagnosis

Synchronous averaging (SA) is a powerful signal processing tool to enhance the feature of interesting periodic events by suppressing non-synchronous components. However, the features related to the rolling element bearing (REB) fault may not be effectively enhanced by SA under random slip conditions. To address this issue, two instantaneous angular speed (IAS)-based synchronous averaging frameworks are proposed in this study. Then, an improved negentropy indicator is proposed to characterize the richness of the REB fault information. Additionally, based on the estimation feature of the IAS signal, the effects of the encoder resolution and structure damping factor on the waveform related to the faulty REB are studied, respectively. Simulation and experiment results show that the proposed schemes can be used to enhance the feature of the REB fault under random slip conditions.

Signal-to-Image: Rolling Bearing Fault Diagnosis Using ResNet Family Deep-Learning Models

Rolling element bearings (REBs) are the most frequent cause of machine breakdowns. Traditional methods for fault diagnosis in rolling bearings rely on feature extraction and signal processing techniques. However, these methods can be affected by the complexity of the underlying patterns and the need for expert knowledge during signal analysis. This paper proposes a novel signal-to-image method in which the raw signal data are transformed into 2D images using continuous wavelet transform (CWT). This transformation enhances the features extracted from the raw data, allowing for further analysis and interpretation. Transformed images of both normal and faulty rolling bearings from the Case Western Reserve University (CWRU) dataset were used with deep-learning models from the ResNet family. They can automatically learn and identify patterns in raw vibration signals after continuous wavelet transform is used, eliminating the need for manual feature extraction. To further improve the training results, squeeze-and-excitation networks (SENets) were added to improve the process. By comparing results obtained from several models, we found that SE-ResNet152 has the best performance for REB fault diagnosis.

A Novel Method for Bearing Fault Diagnosis under Variable Speed Based on Envelope Spectrum Fault Characteristic Frequency Band Identification.

Rolling element bearing (REB) vibration signals under variable speed (VS) have non-stationary characteristics. Order tracking (OT) and time-frequency analysis (TFA) are two widely used methods for REB fault diagnosis under VS. However, the effect of OT methods is affected by resampling errors and close-order harmonic interference, while the accuracy of TFA methods is mainly limited by time-frequency resolution and ridge extraction algorithms. To address this issue, a novel method based on envelope spectrum fault characteristic frequency band identification (FCFBI) is proposed. Firstly, the characteristics of the bearing fault vibration signal's envelope spectrum under VS are analyzed in detail and the fault characteristic frequency band (FCFB) is introduced as a new and effective representation of faults. Then, fault templates based on FCFB are constructed as reference for fault identification. Finally, based on the calculation of the correlation coefficients between the envelope spectrum and fault templates in the extended FCFB, the bearing fault can be diagnosed automatically according to the preset correlation coefficient criterion. Two bearing VS experiments indicate that the proposed method can achieve satisfactory diagnostic accuracy. The comparison of OT and TFA methods further demonstrates the comprehensive superiority of the proposed method in the overall consideration of accuracy, diagnostic time, tachometer dependency, and automatic degree.

Continuous monitoring of rolling element bearing health by nonlinear weighted squared envelope-based fuzzy entropy

Fuzzy entropy (FE) can be regarded as an effective measure for nonlinear characterization of rolling element bearing (REB) health condition by quantifying the complexity of vibration signals. However, during continuous monitoring operation under heavy noise, transient impulses corresponding to a REB fault get submerged under unnecessary random noise components. As a consequence, FE algorithm not only fails to detect a REB fault at the earliest point of inception but also performs poorly in monitoring the development of the incepted fault in an efficient manner. Aiming at solving the aforementioned limitations of FE in continuous monitoring of REB health, background noise associated with collected vibration signals is eliminated by weighting the corresponding square envelope signal. Due to the utilization of weighted squared envelope signal, the proposed measure is termed as weighted square envelope-based FE (WSEFE). One simulated case and two different run-to-failure experimental cases are used for validation. The comparison results demonstrate that the proposed WSEFE not only overcomes the limitations of original FE but also performs better than conventional permutation entropy and advanced FE-based measure multiscale FE (MFE) in continuous monitoring of REB health.

Fault diagnosis of rolling element bearing using continuous wavelet transform and K- nearest neighbour

Rotating machines are a common class for machineries in industries and one of the root cause of failure of these machines are faults in rolling element bearing (REB). Therefore, to prevent machinery performance degradation and malfunctioning, an effective bearing fault diagnosis technique is vital. So, the use of different machine learning techniques proposes a new method of diagnosing REB defects. Machine learning (ML) method namely K-nearest neighbour (KNN) is used to classify different types of REB faults. In this article, vibration signals are acquired from a customized test rig for three conditions of deep groove ball bearings: Normal (N), defect on Inner Race (IR) and defect on Outer Race (OR) at different loads and maximum speed. Continuous Wavelet Transform (CWT) has been applied to the acquired signal and Seventeen Time Frequency Domain (TFD) statistical features were extracted from CWT coefficients. KNN classifier is trained using these TFD. The classification accuracy on test data i.e., 83.3% reveals that KNN can be effectively used to classify different conditions of REB.

Intelligent Fault Diagnosis of Industrial Bearings Using Transfer Learning and CNNs Pre-Trained for Audio Classification

The training of Artificial Intelligence algorithms for machine diagnosis often requires a huge amount of data, which is scarcely available in industry. This work shows that convolutional networks pre-trained for audio classification already contain knowledge for classifying bearing vibrations, since both tasks share the need to extract features from spectrograms. Knowledge transfer is realized through transfer learning to identify localized defects in rolling element bearings. This technique provides a tool to transfer the knowledge embedded in neural networks pre-trained for fulfilling similar tasks to diagnostic scenarios, significantly limiting the amount of data needed for fine-tuning. The VGGish model was fine-tuned for the specific diagnostic task by handling vibration samples. Data were extracted from the test bench for medium-size bearings specially set up in the mechanical engineering laboratories of the Politecnico di Torino. The experiment involved three damage classes. Results show that the model pre-trained using sound spectrograms can be successfully employed for classifying the bearing state through vibration spectrograms. The effectiveness of the model is assessed through comparisons with the existing literature.

Dynamics Analysis and Deep Learning-Based Fault Diagnosis of Defective Rolling Element Bearing on the Multi-Joint Robot

Industrial robots typically perform a variety of tasks and occupy critical positions in modern manufacturing fields. When certain failures occur in the internal structures of robots, it tends to result in significant financial loss and the consumption of human resources. As a result, timely and effective fault diagnosis is critical to ensuring the safe operation of robots. Deep learning-based methods are currently being widely used by researchers to address some shortcomings of traditional methods. However, due to realistic factor limitations, few researchers take the failure pattern of rotating machinery and the location of fault joints into account at the same time, so the fault types of multi-joint robots are not thoroughly investigated. In this case, we proposed a dynamic simulation method that considers the effects of bearing failures at various faulty joint locations and makes it possible to investigate more possible failure cases of multi-joint robots. In addition, we used LSTM and DCNN to perform staged fault diagnosis tasks, allowing us to gradually locate faulty joints and investigate detailed failure forms. According to the experimental results, distinguishable vibration signals corresponding to various fault states are successfully obtained, and our implemented algorithms are validated for their advanced performance in diagnosis tasks via comparative experiments.

Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification

Vibration signals captured with an accelerometer carry essential information about Rolling Element Bearings (REBs) faults in rotating machinery, and the envelope spectrum has proven to be a robust tool for their diagnosis at an early stage of development. In this paper, Cepstrum Pre-Whitening (CPW) has been applied to REBs’ signals to enhance and extract health-state condition indicators from the preprocessed signals’ envelope spectra. These features are used to train some of the state-of-the-art Machine Learning (ML) algorithms, combined with time-domain features such as basic statistics, high-order statistics and impulsive metrics. Before training, these features were ranked according to statistical techniques such as one-way ANOVA and the Kruskal–Wallis test. A Convolutional Neural Network (CNN) has been designed to implement the classification of REBs’ signals from a Deep Learning (DL) point of view, receiving raw time signals’ greyscale images as inputs. The different ML models have yielded validation accuracies of up to 87.6%, while the CNN yielded accuracy of up to 77.61%, for the entire dataset. In addition, the same models have yielded validation accuracies of up to 97.8%, while the CNN, 90.67%, where signals from REBs with faulty balls have been removed from the dataset, highlighting the difficulty of classifying such faults. Furthermore, from the results of the different ML algorithms compared to those of the CNN, frequency-domain features have proven to be highly relevant condition indicators combined with some time-domain features. These models can be potentially helpful in applications that require early diagnosis of REBs faults, such as wind turbines, vehicle transmissions and industrial machinery.

Application of Improved Robust Local Mean Decomposition and Multiple Disturbance Multi-Verse Optimizer-Based MCKD in the Diagnosis of Multiple Rolling Element Bearing Faults

Rolling element bearings are an important joint in mechanical equipment and have a high engineering application value. To solve the problem of the difficulty in extracting periodic fault pulses due to complex noise interference and the interference of transmission paths in rolling element bearing fault characteristic signals, a novel hybrid fault diagnosis method based on complementary complete ensemble robust local mean decomposition with adaptive noise (CCERLMDAN) combined with multiple disturbance multi-verse optimizer (MDMVO)-based Maximum correlated Kurtosis deconvolution (MCKD) is proposed in this paper, and applied in different rolling element bearing fault conditions. Firstly, the CCERLMDAN method adaptively decomposes the fault vibration signal into multiple product functions (PF), and then selects the PF with the most fault information through the sensitive index (SI). Finally, the MDMVO method adaptively selects the best parameter combination of the MCKD method and then uses MCKD to perform a deconvolution operation on the selected PF, highlighting the periodic fault pulse excited by the bearing fault. The field-measured vibration signals of rolling element bearing faults are applied to verify the proposed method. The final results show that the method effectively improves the fault diagnosis accuracy of rolling element bearings, and both CCERLMDAN and MDMVO methods achieve a better performance than the original method.

Proportional Selection Scheme: A Frequency Band Division Tool for Rolling Element Bearing Diagnostics

The cyclic spectral coherence analysis has been proved to be a useful tool to reveal the hidden periodic or repetitive patterns, and how to determine an optimal demodulation band is crucial for characterizing the fault characteristic of the rolling element bearing (REB). Thus, a proportional selection scheme based on a bottom-up strategy is proposed in this study, which can determine an optimal demodulation band and realize bearing fault feature extraction under the conditions of poor frequency resolution and a lower signal-to-noise ratio (SNR). First, compared with conventional frequency division structures, such as the 1/3-binary tree structure, the finer frequency band groups with the same bandwidth in each division level can be obtained automatically and strictly under poor frequency resolution conditions. Second, the richness of the REB fault information of each divided frequency band can be evaluated by the improved diagnostic feature indicator under a lower SNR condition. By using the scheme, the fault characteristic of the REB can be exposed. The efficacy of the proposed scheme is supported by simulations and experiments under some tough conditions

Enhanced demodulation band selection based on Operational Modal Analysis (OMA) for bearing diagnostics

Vibration time signals emitted by a defective rolling element bearing are often used to determine its health condition. For real-world measurements these fault signals may be weak compared to the remaining content in the measured signal causing increased difficulties to fault detection. One way of enhancing the fault detection is by demodulation at a filtered frequency band in which the Signal-to-Noise-Ratio (SNR) of the fault signal is high. In the present paper, we propose a method that uses the resonances obtained from Operational Modal Analysis (OMA) as center frequencies for the filter bands as it is assumed that the characteristic bearing fault frequencies modulate resonances or carrier frequencies close to them. An indicator is used to determine which of the resonances from the OMA enhance the fault signal the most and this selection is dependent on the bandwidth as well. The presented method is applied on signals from two experimental cases, an experimental test rig of a planetary gearbox and a wind turbine gearbox, and is compared to the Fast Kurtogram and Log-Cycligram to assess its performance for band selection. The results show that the presented method determines a suited band for band pass filtering which enhances the fault detection at the two complex use cases.