Fault Diagnosis Of Rolling Element Bearings Research Articles

A novel deep learning model for fault diagnosis of rolling-element bearing based on convolution neural network and recurrent neural network

Rolling bearings are critical components that are incredibly prone to failure in the operation of mechanical equipment. Due to the complexity of the actual working conditions, multiple types, positions and scales of bearings are problematic to accurately and completely classify using conventional classification methods. In this study, a novel end-to-end deep learning framework consisting of a one-dimensional convolutional neural network (1D-CNN) and a module fused by long short-term memory (LSTM) and gated recurrent unit (GRU) is proposed to diagnose bearing failures, thus solving the problem of the poor accuracy of traditional fault identification. First, 1D-CNN is used to extract local features from bearing data thanks to its excellent local feature extraction capabilities. Second, global features are extracted from bearing data using LSTM and GRU, and classification is performed with Softmax. Finally, the proposed model is evaluated using Case Western Reserve University and the University of Cincinnati data, with accuracy rates of 99.99% and 99.83%, respectively. The experimental results indicate that the proposed model has good feasibility and performance.

Dynamic response of rolling element bearing with compound fault considering defect-rolling-element interaction

Dynamic modelling of rolling element bearing (REB) is a significant method to explore the vibration mechanism generated by fault, and it is the theoretical basis of fault diagnosis of REBs. Aiming at the complexity of defect-rolling-element interaction under radial load, the whole contact process of rolling element (RE) passing over defective area of outer or inner ring is analysed in detail. The impact force excitation function is derived by rotation and revolution velocity of RE. A four degree-of-freedom (DOF) dynamic model of REB with compound fault of both inner and outer raceway surface is developed by considering the time-varying displacement, impact force excitative and elastohydrodynamic lubrication (EHL) condition, and the novelty of the model is that the improved impact force excitation function is used. The experimental validation is carried out on test tig of Machinery Fault Simulator. The change of impact force with shaft speed and defect size is analysed. It is shown that the simulation results of the proposed model are closer to experimental results. A mapping method from defect-rolling-element-defect (DRED) behaviour to time is proposed to study the vibration characteristics of DRED behaviour, the results show that the amplitude of vibration will decrease when the same RE collides with inner and outer raceway defects simultaneously. When the same RE collides with inner and outer raceway defect successively, the amplitude of vibration will reach the maximum during the inner raceway defect rolling over each RE once. The proposed model can be used in practical application to study the influence of compound defects on vibration response of REB.

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.

An improved spectral amplitude modulation method for rolling element bearing fault diagnosis

An improved spectral amplitude modulation method for rolling element bearing fault diagnosis

Automatic Transmission Bearing Fault Diagnosis Based on Comprehensive Index Method and Convolutional Neural Network

Rolling-element bearing fault diagnosis has some problems in the applied environment, such as low signal-to-noise ratio, weak feature extraction, low efficiency of feature learning and the complex structure of diagnosis models. A fault diagnosis method based on the comprehensive index method, complete ensemble empirical mode decomposition with adaptive noise independent component analysis (CEEMDANICA) and two-dimensional convolutional neural network (TDCNN) is proposed. Firstly, the original vibration signal of the bearing is preprocessed by CEEMDANICA, and the ICA components with different frequencies are obtained. Secondly, the ICA components are selected as the sample set by using multiscale permutation entropy, correlation coefficient, kurtosis and box dimension. Finally, the sample set are trained and tested by a DCNN model to realize the fault diagnosis of different bearing fault types. In order to verify the reliability of the method, a bearing fault vibration monitoring platform for an electric vehicle two-speed automatic transmission was built to collect the bearing vibration signals of multiple fault types under different working conditions. The diagnostic accuracy of several deep learning models is compared. The results show that the proposed method can realize the single and compound fault diagnosis of rolling-element bearings in an automatic transmission, with a high degree of accuracy.

Rolling element bearing fault diagnosis using supervised learning methods- artificial neural network and discriminant classifier

Rolling element bearing fault diagnosis using supervised learning methods- artificial neural network and discriminant classifier

Interpretable fault diagnosis with shapelet temporal logic: Theory and application

Shapelets are discriminative subsequences of sequential data that best predict the target variable and are directly interpretable, which have attracted considerable interest within the interpretable fault diagnosis community. Despite their immense potential as a data mining primitive, currently, shapelet-based methods ignore the temporal properties of shapelets. This paper presents a shapelet temporal logic, which is an expressive formal language to describe the temporal properties of shapelets. Moreover, an incremental algorithm is proposed to find the optimal logic expression with formal and theoretical guarantees, and the obtained logic expression can be used for fault diagnosis. Additionally, a case study on rolling element bearing fault diagnosis shows the proposed method can diagnose and interpret faults with high accuracy. Comparison experiments with other logic-based and shapelet-based methods illustrate the proposed method has better interpretability at the cost of computation efficiency.

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 novel signal denoising method using stationary wavelet transform and particle swarm optimization with application to rolling element bearing fault diagnosis

In this paper, a novel signal denoising method based on Stationary Wavelet Transform and Particle Swarm Optimization Algorithm (SWT-PSO) is proposed. The threshold values for wavelet denoising are selected using the meta-heuristic algorithm of particle swarm optimization such that the denoised signal has maximum weighted kurtosis. In many faulty rotating machinery elements such as rolling element bearings and gears, impact-type vibration signals are produced. Such impact type vibration signals have a high value of kurtosis. The proposed SWT-PSO scheme can be used for the enhancement of fault signature in rotating machinery by increasing the kurtosis of such signals. The proposed algorithm has been applied on simulated as well as experimental defective rolling element bearing signal. Vibration signals from rolling element bearing with inner race and outer race defects are acquired by accelerometers on a Machinery Fault Simulator (MFS) setup. Then the proposed methodology is applied successfully to denoise the signals at various noise levels. Further, Spectrum envelope of the denoised vibration signal is used to obtain the characteristic defect frequencies. The developed methodology is finally compared with widely used Minimum Entropy Deconvolution (MED) algorithm. It has been demonstrated that the proposed algorithm has better capability of extracting the impulsive characteristic as well as preserving the signal geometrical structure than compared to MED.

Bearing fault diagnosis under class unbalanced data based on deep learning

There is a huge difference in the number of operating samples and failure samples in industrial production. If the diagnostic model is trained through deep learning under an unbalanced data set, it will make the model recognize the faulty samples as normal samples. Aiming at this problem, an adaptive focus loss function mechanism is proposed. It can avoid over-learning large-scale samples during small-batch imbalance training. At the same time, to improve the generalization ability of fault samples, a pre-training data enhancement mechanism is proposed. By using the rolling element bearing fault diagnosis data set, the effectiveness of the two mechanisms is verified. The two mechanisms can not only complete training tasks under unbalanced data and improve generalization ability.

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.

A novel fault diagnostic system for rolling element bearings using deep transfer learning on bispectrum contour maps

Transfer learning using Convolution Neural Networks (CNNs) has improved the state of the art results in many research studies. Rolling element bearing fault diagnosis is a domain that has been researched extensively using different data mining and machine learning techniques. In this paper, we prove that deep CNNs, when trained on Bispectrum images of fault signals using transfer learning, provide highly accurate and reliable results for fault diagnosis that are at par with the state of the art results. These transfer learning based models are able to quickly learn patterns from visual features of a vibration signal’s bispectrum, eliminating the need for manual feature extraction. In this paper, four pretrained networks – Alexnet, VGG-19, GoogLeNet, ResNet-50 – have been fine tuned on bispectrum images prepared from vibration signals of machine ball bearing elements. Each network has been trained with 3 optimizers – Stochastic Gradient Descent (SGD), Adaptive Moment Estimation (Adam) and Adamax. These models are able to obtain high classification accuracy within a few epochs. We also visualise and analyze the feature maps associated with intermediate convolution layers for one of these models.

Modulation signal bispectrum with optimized wavelet packet denoising for rolling bearing fault diagnosis

Transient impulses caused by local faults are critical informative indicators for rolling element bearing fault diagnosis. The methods for accurately extracting transient impulses while suppressing strong background noise and interference components have received extensive studies. In this article, a novel fault diagnosis scheme based on optimized wavelet packet denoising and modulation signal bispectrum is proposed, which takes advantage of the transient impulse enhancement of wavelet packet denoising and the demodulation ability of modulation signal bispectrum to diagnose bearing faults more accurately. First, the measured signals are decomposed into a series of time–frequency subspaces using wavelet packet transform. An optimal threshold value is selected based on the proposed threshold criterion by considering unbiased autocorrelation of envelope and Gini index of the transient impulses. Subsequently, the subspaces are denoised by the wavelet packet denoising with the optimized threshold value, and the master subspaces that containing the fault-related transient impulses are selected based on the Gini index indicator. Finally, the modulation signal bispectrum is utilized to further purify the signal and extract the modulation components contained in the transient impulses, and the suboptimal modulation signal bispectrum slices are selected based on the characteristic frequency intensity coefficient. The modulation signal bispectrum detector is then obtained by averaging the suboptimal modulation signal bispectrum slices to determine the type of the bearing faults. The proposed wavelet packet denoising-modulation signal bispectrum is validated based on the simulation and experimental studies. Compared with the variational mode decomposition and Teager energy operator, fast kurtogram as well as conventional modulation signal bispectrum, the proposed wavelet packet denoising-modulation signal bispectrum method has superior performance in extracting the fault feature of the incipient defects on different bearing components.

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.

Application of an information fusion scheme for rolling element bearing fault diagnosis

This study addresses the high level of misdiagnoses and low reliability of individual rolling element bearing fault diagnosis methods by proposing a fault diagnosis scheme with enhanced diagnosis accuracy that combines the results of two individual diagnosis methods based on an improved information fusion method. The proposed scheme applies variational mode decomposition in conjunction with a support vector machine for conducting fault diagnosis in the frequency domain, which achieves high fault diagnosis precision for learned fault conditions. Meanwhile, good generalization ability is achieved for identifying the operational conditions of bearings in the time domain by integrated mathematical morphology and correlation analysis. Subsequently, conflicts arising between evidences derived from the individual detection results are measured comprehensively using a novel strategy, and the evidences are then combined based on the Dempster–Shafer theory (DST) to enhance the information fusion effect. The effectiveness of the proposed information fusion method is verified by means of a numerical example in comparison with other fusion methods based on DST. The experimental application of the proposed information fusion fault diagnosis scheme demonstrates the complementary advantages of the two individual methods for significantly improving the diagnosis accuracy relative to the accuracies of the individual methods alone.

An optimized adaptive PReLU-DBN for rolling element bearing fault diagnosis

Rolling element bearings are critical components in industrial rotating machines. Faults and failures of bearings can cause degradation of machine performance or even a catastrophe. Therefore, it is significant to perform bearing fault diagnosis accurately and effectively. Deep Learning based approaches are promising for bearing diagnosis. They can extract fault information efficiently and conduct accurate diagnosis. However, the structure of deep learning networks is often determined by trial and error, which is time consuming and lacks theoretical guidance. Besides, the traditional deep learning approaches have low diagnosis accuracy and learning efficiency. To address these problems, this paper proposes a rolling element bearing fault diagnosis approach based on principal component analysis and adaptive deep belief network with Parametric Rectified Linear Unit activation layers. In the proposed approach, particle swarm optimization is integrated to obtain an optimal DBN structure with high accuracy and convergence rate. Experiments on tapered roller bearings and comparison studies with state-of-the-art methods are conducted to demonstrate the effectiveness and accuracy of the proposed approach.

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.

Fault diagnosis of rolling element bearing using autonomous harmonic product spectrum method

Maintenance planning plays a critical role in the process industry, where any unplanned maintenance may lead to a significant loss. Condition monitoring happens to aid maintenance planning and has become an inherent part of the maintenance activity. Physical parameters such as vibration, acoustic emission, current, etc., are used for condition monitoring, out of which vibration is the most preferred parameter and is widely used in the industry. Vibration data is measured near to bearings, which themselves are monitored for their condition, and hence rolling element bearing (REB) is the focus of this study. REBs are monitored for the presence of a fault in them as well as for their severity. Fault diagnosis of REB using harmonic product spectrum (HPS) is proposed in this study. The proposed methodology's novelty lies in the signal pre-processing step, whose output is fed to the HPS method, which is used for defective raceway identification. The efficacy of HPS is assessed with parameter optimized Variational mode decomposition (VMD) and classical bandpass filtering method as pre-processors. It is observed that the HPS delivers better diagnostic results with the VMD method than the bandpass filtering method. Non-dominated sorting particle swarm optimization algorithm is deployed for parameter optimization of VMD. HPS combined with VMD as pre-processor forms an autonomous HPS(AHPS) algorithm, whose input is measured signal and output is defect frequency. The process is so designed that a raw signal, when fed to the algorithm, delivers the result as identification of a defective raceway. Unlike previously developed methods, the proposed method needs no manual intervention. Results obtained from simulated signals and signals recorded through experiments validate that the proposed methodology can be used effectively for fault diagnosis of REB.

Blind source extraction based on EMD and temporal correlation for rolling element bearing fault diagnosis

Purpose Fault diagnosis methods based on blind source separation (BSS) for rolling element bearings are necessary tools to prevent any unexpected accidents. In the field application, the actual signal acquisition is usually hindered by certain restrictions, such as the limited number of signal channels. The purpose of this study is to fulfill the weakness of the existed BSS method. Design/methodology/approach To deal with this problem, this paper proposes a blind source extraction (BSE) method for bearing fault diagnosis based on empirical mode decomposition (EMD) and temporal correlation. First, a single-channel undetermined BSS problem is transformed into a determined BSS problem using the EMD algorithm. Then, the desired fault signal is extracted from selected intrinsic mode functions with a multi-shift correlation method. Findings Experimental results prove the extracted fault signal can be easily identified through the envelope spectrum. The application of the proposed method is validated using simulated signals and rolling element bearing signals of the train axle. Originality/value This paper proposes an underdetermined BSE method based on the EMD and the temporal correlation method for rolling element bearings. A simulated signal and two bearing fault signal from the train rolling element bearings show that the proposed method can well extract the bearing fault signal. Note that the proposed method can extract the periodic fault signal for bearing fault diagnosis. Thus, it should be helpful in the diagnosis of other rotating machinery, such as gears or blades.