Rolling Bearings Research Articles

A novel simulation-assisted transfer method for bearing unknown fault diagnosis

Abstract Supervised data-driven bearing fault diagnosis methods rely on completed datasets of faults, which can be challenging for signals collected in real engineering. Recognizing unknown faults using a data-driven approach is particularly difficult, as purposefully modeling these faults is complex. To address this challenge, this study proposes a new simulation-assisted transfer bearing unknown fault diagnosis method for realizing unknown compound fault diagnosis of rotating machinery. Firstly, finite element method is used to obtain the compound fault data that does not exist in the historical data, and wavelet packet transform is performed on the simulated and measured signals to enhance the detailed features of the signals. Then, a deep convolutional feature fusion network based on hybrid multi-wavelet spatial attention is constructed to fuse the time-frequency information processed by different wavelet bases. Finally, by integrating the concepts of intra-class splitting and transfer learning, the model is fine-tuned using simulation data to recognize unknown compound faults of rolling bearings. The method validates the simulated signals’ feasibility and the unknown faults’ diagnostic validity under the publicly available rolling bearings dataset. Compared to the comparison methods, the method’s accuracy increased by 2.86%, 2.61%, 5.41%, 4.77%, and 7.07%, respectively.

Digital twin-assisted intelligent fault diagnosis for bearings

Abstract Data-driven intelligent fault diagnosis methods generally require a large amount of labeled data and considerable time to train network models. However, obtaining sufficient labeled data in practical industrial scenarios has always been a challenge, which hinders the practical application of data-driven methods. A digital twin (DT) model of rolling bearings can generate labeled training dataset for various bearing faults, supplementing the limited measured data. This paper proposes a novel DT-assisted approach to address the issue of limited measured data for bearing fault diagnosis. First, a dynamic model of bearing with damages is introduced to generate simulated bearing acceleration vibration signals. A DT model is constructed in Simulink, where the model parameters are updated based on the actual system behavior. Second, the structural parameters of the DT model are adaptively updated using least squares method with the measured data. Third, a Vision Transformer (ViT) -based network, integrated with short-time Fourier transform, is developed to achieve accurate fault diagnosis. By applying short-time Fourier transform at the input end of the ViT network, the model effectively extracts additional information from the vibration signals. Pre-training the network with an extensive dataset from miscellaneous tasks enables the acquisition of pre-trained weights, which are subsequently transferred to the bearing fault diagnosis task. Experiments results verify that the proposed approach can achieve higher diagnostic accuracy and better stability.

A method to develop a high-fidelity gearbox thermal model based on limited temperature measurements

This paper presents a method to create a high-fidelity gearbox thermal model. A hybrid analytical-empirical model is presented, it is based on the thermal network approach and experiments are used to determine some unknown parameters of the model. A test campaign was led on a four stages helical gear unit and consisted of cooling measurements, no-load tests and loaded tests. These experiments were performed under different rotational speeds and loads. The results show that the developed thermal model provides an accurate prediction of the thermal behavior of different components of the gearbox (namely rolling element bearings and oil) by only using few thermal sensors. These results are corroborated by power losses measurements which demonstrate that the model can estimate the gear unit efficiency.

Thermal infrared imaging for conveyor roller fault detection in coal mines.

As a key mechanism of belt conveyor, the health status and working state of its parts have a profound impact on whether the belt conveyor can run normally and safely. In the composition of the standard belt conveyor, the number of rollers is numerous and scattered. At the same time, under the complex environment of the work site, the fault detection of each roller is particularly difficult. In order to solve the above problems, a diagnosis method based on thermal infrared image features is proposed to detect the faults of each roller mechanism in the belt conveyor. Firstly, the position of the idler is identified based on the YOLOv4 identification method, and then the sticking resistance and bearing damage of the idler are detected based on the temperature difference discrimination method. In this paper, the target recognition method based on YOLOv4 is used to identify the position of the roller, and the recognition accuracy is 93.8%, which meets the requirements of the project. The infrared image obtained by the dual-spectrum camera is used to distinguish the fault of the idler in the coal mine. The temperature of the bearing and surface of the normal roller increases rapidly within 10 minutes of operation, and the temperature changes slightly after 10 minutes of operation. The bearing damaged idler has a greater friction effect at the bearing, so the temperature at the bearing rises faster, and there is a temperature difference of about 7°C between the bearing and the normal roller. The surface temperature of the idler in the blocking state is also fast for about 20 minutes, and there will be a temperature difference of about 8°between the surface of the idler and the normal roller. In this paper, it is determined that the temperature rise coefficients of the roller surface and bearing under normal conditions are 24% 28% and 18% 22% respectively. It is determined that the threshold value of the temperature rise coefficient in the blocking state and the damaged state is 30% and 25% respectively, that is, when the surface temperature rise coefficient of the roller is detected to be more than 30%, it is determined that the card resistance fault occurs, when the temperature rise coefficient at the roller bearing is detected > 25%, the bearing damage fault is judged.

A coarse and fine-grained deep multi view subspace clustering method for unsupervised fault diagnosis of rolling bearings

Abstract To address the issue of insufficient characterization of fault features in inherent vibration data that affects the performance of unsupervised learning-based fault diagnosis, a coarse and fine-grained deep multi view subspace clustering method (CFG-DMVSC) for unsupervised fault diagnosis of rolling bearings is proposed. The proposed method designs a convolutional autoencoder network based on the Gramian angular field transformation for multi-signal analysis domains. A multi-view coarse-grained self-expressive method based on information entropy is designed to handle differences in information across different views. Furthermore, a fine-grained common and independent information separation loss function based on mutual information is proposed to ensure compactness among multiple views. Both the Case Western Reserve University rolling bearing dataset and privately built bearing fault test bench data demonstrate that, compared to existing methods, the proposed method can perform coarse and fine-grained division in multi-view subspaces, achieving better clustering diagnosis performance on the extracted common information among views.

Fourth-stable stochastic resonance and its application to weak fault signal detection of rotating machinery

Weak characteristic extraction is vital for weak fault signal detection of machinery. Stochastic resonance (SR) is able to transfer noise energy into weak fault characteristic frequency excited by a defect of machines. However, the potential function in SR is vital to enhance weak fault characteristic frequency and determines the capability of SR to improve the signal-to-noise ratio (SNR) of a noisy signal. Now, common potential functions include monostable, bistable and even tri-stable potentials but fourth-stable SR has not been studied and applied to detect early fault characteristic frequency. In this paper, thus, we would investigate the behaviors of SR with a fourth-stable potential subject to additive noise, in which the approximate theoretical expression of the power done by SR is derived to demonstrate the fourth-stable Sr Then, a SR method with the fourth-stable potential is proposed to enhance weak fault characteristic frequency, in which these system parameters are adjusted by using SNR as the objective function and using genetic algorithms adaptively. In this paper, thus, Finally, the proposed method is verified by using a simulated signal with noise and two early fault experiment of rolling element bearings with different levels of defects on the outer and inner races. Moreover, the proposed method is compared with wavelet denoising and fast kurtogram methods. The comparisons indicate that the proposed method has the better performance for enhancing weak fault characteristic frequency or weak useful signals than other two methods and is available to weak fault signal detection of machinery.

Multi-graph attention fusion graph neural network for remaining useful life prediction of rolling bearings

Abstract Graph neural network (GNN) has the proven ability to learn feature representations from graph data, and has been utilized for the tasks of predicting the machinery remaining useful life (RUL). However, existing methods only focus on a single graph structure and cannot integrate the correlation information contained in multi-graph structures. To address these issues, a multi-graph structure GNN prediction method with attention fusion (MGAFGNN) is proposed in this paper for GNN-based bearing RUL prediction. Specifically, a multi-channel graph attention module is designed to effectively learn the similar features of node neighbors from different graph data and capture the multi-scale latent features of nodes through the nonlinear transformation. Furthermore, a multi-graph attention fusion module (MGAFM) is proposed to extract the collaborative features from the interaction graph, thereby fusing the feature embeddings from different graph structures. The fused feature representation is sent to the long short-term memory network to further learn the temporal features and achieve RUL prediction. The experimental results on two bearing datasets demonstrate that MGAFGNN outperforms existing methods in terms of prediction performance by effectively incorporating multi-graph structural information.

Fault diagnosis algorithm based on GADF-DFT and multi-kernel domain coordinated adaptive network

To address the problems of low detection accuracy of rolling bearings under different loads and the difficulty of effectively identifying the lack of labelled data, a rolling bearing fault diagnosis method combining GADF-DFT image coding and Multi-kernel domain coordinated adaptation network is proposed. Firstly, the vibration signal is converted into a two-dimensional image using GADF coding technology, and then the GADF image is converted into the frequency domain using discrete Fourier transform to extract deeper feature information. Combined with the multi-source domain adaptive method, the public feature extraction module is used to initially achieve feature mining of the image; the MK-MMD algorithm of the domain-specific adaptive module reduces the difference in feature distribution between the source and target domains; and the final classification difference minimization module reduces the problems caused by the classification errors that may be generated by the different domain classifiers due to the fact that the data samples are located near the category boundaries. The test uses the Case Western Reserve University dataset and divides the dataset with different operating conditions as the source and target domains, and the test results show that the proposed model demonstrates its effectiveness in responding to the complex operating condition changes in rolling bearing fault detection in multiple operating condition migration tasks, good adaptability and robustness, and is able to achieve accurate fault diagnosis under different operating conditions.

Investigation of the Electrical Impedance Signal Behavior in Rolling Element Bearings as a New Approach for Damage Detection

The opportunities of impedance-based condition monitoring for rolling bearings have been shown earlier by the authors: Changes in the impedance signal and the derived features enable the detection of pitting damages. Localizing and measuring the pitting length in the raceway direction is possible. Furthermore, the changes in features behavior are physically explainable. These investigations were focused on a single bearing type and only one load condition. Different bearing types and load angles were not considered yet. Thus, the impedance signals and their features of different bearing types under different load angles are investigated and compared. The signals are generated in fatigue tests on a rolling bearing test rig with conventional integrated vibration analysis based on structural borne sound. The rolling bearing impedance is gauged using an alternating current measurement bridge. Significant changes in the vibration signals mark the end of the fatigue tests. Therefore, comparing the response time of the impedance can be compared to the vibration signal response time. It can be shown that the rolling bearing impedance is an instrument for condition monitoring, independently from the bearing type. In case of pure radial loads, explicit changes in the impedance signal are detectable, which indicate a pitting damage. Under combined loads, the signal changes are detectable as well, but not as significant as under radial load. Damage-indicating signal changes occur later compared to pure radial loads, but nevertheless enable an early detection. Therefore, the rolling bearing impedance is an instrument for pitting damage detection, independently from bearing type and load angle.

Contrast learning with hard example mining for few-shot fault diagnosis of rolling bearings

Contrast learning with hard example mining for few-shot fault diagnosis of rolling bearings

Transformer-based novel framework for remaining useful life prediction of lubricant in operational rolling bearings

Accurate prediction of the remaining useful life (RUL) of lubricants in rolling bearings is crucial for maintaining efficient operation of rotating machinery and ensuring timely lubricant replacement. We propose a comprehensive framework that integrates the temporal variation transfer function (TVTF), harmonic-sideband Matrix, and the harmonic frequency transformer (HarFT), a transformer-based model. This approach effectively utilizes vibration characteristics to enhance the accuracy of lubricant degradation prediction in rolling bearings. Validation with rolling bearings experiencing lubrication failure confirms that our framework significantly outperforms alternative methods in RUL prediction. The proposed framework excels in extracting and analyzing harmonic components from vibration responses, enabling detection of minute status variations due to lubricant degradation. By applying explainable artificial intelligence (XAI), it is possible to ascertain the rationale behind the RUL predicted by the HarFT model, facilitating evidence-based decisions. Our research provides a novel strategy for lubricant RUL assessment in rolling bearings, thereby improving reliability and maintenance efficiency in industrial applications.

Local damage detection in rolling element bearings based on a single ensemble empirical mode decomposition

A Single Ensemble Empirical Mode Decomposition (SEEMD) is proposed to locate the damage in rolling element bearings. The SEEMD method eliminates the need for adding or subtracting noise repeatedly to process signals, unlike other techniques that rely on multiple ensembles. The SEEMD requires a single sifting process of a modified raw signal to reduce the computation time significantly. The other advantage of the SEEMD method is its success in dealing with non-Gaussian or non-stationary perturbing signals. In SEEMD, a fractional Gaussian noise (FGN) is initially added to the raw signal to emphasize the signal's high frequencies. Then, a convoluted white Gaussian noise is multiplied on the resulting signal, changing its spectral content, which helps in extracting the weak periodic signal. Finally, the obtained signal is decomposed using a single sifting process. The proposed methodology is applied to the raw signals obtained from the mining industry. These signals are difficult to analyze since cyclic impulsive components are obscured by noise and other interference. Based on the results, the proposed method can effectively detect the fault where the signal of interest (SOI) has been extracted with good quality.

A Review of the Intelligent Condition Monitoring of Rolling Element Bearings

A Review of the Intelligent Condition Monitoring of Rolling Element Bearings

Theoretical Evaluation of Lubrication Performance of Thrust-Type Foil Bearings in Liquid Nitrogen

The development of reusable liquid rocket turbopumps has gradually highlighted the disadvantages of rolling bearings, particularly the contradiction between long service life and high rotational speed. It is critical to explore a feasible bearing scheme offering a long wear life and high stability to replace the existing rolling bearings. In this study, liquid nitrogen is adopted to simulate the ultra-low temperature environment of liquid rocket turbopumps, and theoretical evaluations of the lubrication performance of thrust-type foil bearings in liquid nitrogen are conducted. A link-spring model for the bump foil structure and a thin-plate finite element model for the top foil structure are established. The static and dynamic characteristics of the bearings are analyzed using methods including the finite difference method, the Newton–Raphson iteration method, and the finite element method. Detailed analysis includes the effects of factors such as rotational speed, fluid film thickness, thrust disk tilt angle, and the friction coefficient of the bump foil interface on the static and dynamic characteristics of thrust-type foil bearings. The research results indicate that thrust-type foil bearings have a good load-carrying capacity and low frictional power consumption. The adaptive deformation of the foil structure increases the fluid film thickness, preventing dry friction due to direct contact between the rotor journal and the bearing surface. When faced with thrust disk tilt, the direct translational stiffness and damping coefficient of the bearing do not undergo significant changes, ensuring system stability. Based on the results of this study, the exceptional performance characteristics of thrust-type foil bearings make them a promising alternative to rolling bearings for the development of reusable liquid rocket turbopumps.

An Intelligent diagnosis method for rolling bearings based on Ghost module and adaptive weighting module

An Intelligent diagnosis method for rolling bearings based on Ghost module and adaptive weighting module

Fault Diagnosis Method of Bearings Based on SCSSA-VMD-MCKD

To tackle the issue of detecting early, subtle faults in rolling bearings in the presence of noise interference, the SCSSA-VMD-MCKD method is suggested. This method optimizes the Variational Mode Decomposition (VMD) and Maximum Correlated Kurtosis Deconvolution (MCKD) by integrating the sine-cosine and Cauchy Mutation Sparrow Search Algorithm (SCSSA). The approach aims to effectively diagnose faults in rolling bearings by leveraging the strengths of VMD and MCKD in noise reduction and highlighting fault frequencies. The method utilizes the SCSSA algorithm to autonomously search for parameters in both VMD and MCKD, using the EnvelopeCrest Factor Ec as a fitness function. Firstly, SCSSA is employed to optimize the decomposition mode number K and penalty factor α in the VMD algorithm. Secondly, the parameters in the MCKD algorithm are optimized, and MCKD is used for deconvolution to enhance the impulsive characteristics of the best modal component. Finally, the signal is further analyzed after deconvolution. The results demonstrate that this algorithm can effectively identify subtle fault signals in bearing signals and diagnose fault frequencies in noisy environments. The accuracy of fault diagnosis can reach nearly 99%.

A multi-domain adversarial transfer network for cross domain fault diagnosis under imbalanced data

In the intelligent fault diagnosis of rolling bearings, transfer learning methods extend the applicability of models to diverse working scenarios. However, real-world scenarios often suffer from data imbalance, which reduces diagnostic accuracy. To address this issue, this paper proposes a multi-domain adversarial transfer (MDAT) framework to enhance cross-domain fault diagnosis accuracy for rolling bearings under imbalanced data conditions. First, an enhanced information generation method is introduced to produce realistic and useable synthetic data to mitigate data imbalance. Subsequently, an adversarial multi-domain adaptation module is designed to learn invariant features across multiple domains. Finally, a domain reweighting method is proposed to improve domain alignment and enhance domain confusion. The effectiveness of the proposed method was validated through two case studies on rolling bearing fault diagnosis. The results demonstrated that MDAT achieved cross-domain diagnosis accuracies of 89.2% and 99.0% under imbalanced data conditions, confirming the effectiveness and superiority of the MDAT framework.

Fault Diagnosis and Prediction of Remaining Useful Life (RUL) of Rolling Element Bearing : A review state of art

Fault diagnosis of rolling element bearings is a critical aspect of machine maintenance and reliability. Bearings are extensively used in various industrial applications, and their failure can lead to costly downtime and equipment damage. Rotating machinery under continuous overload conditions can indeed significantly degrade bearing life and lead to various other issues. To identify issues in rolling element bearings (REB), several techniques and methods are employed. Diagnosing faults in ball bearings while simultaneously estimating the Remaining Useful Life (RUL) of the bearing is a crucial aspect of predictive maintenance. This can be achieved through a combination of signal processing techniques, machine learning methods, and RUL prediction models. The estimation of a bearing Remaining Useful Life (RUL) is of significant importance in predictive maintenance strategies to avoid unexpected failures, reduce downtime, and optimize maintenance costs. This literature review aims to explore the methodologies, techniques, and advancements in predicting the remaining useful life of bearings.

Short-Time Variance Providing Evidential Reference Frequency for Lock-in Amplifier in Fault Diagnosis of Rolling Bearings

Short-Time Variance Providing Evidential Reference Frequency for Lock-in Amplifier in Fault Diagnosis of Rolling Bearings

A shunted-swin transformer for surface defect detection in roller bearings

Although surface defect detection for roller bearings has received much attention in smart industrial manufacturing, most existing approaches employed the existing Convolution or Transformer models without modification to detect the defects. Such applications are undesirable because the classification models lack the necessary spatial relationship between multiple objects within an image. To develop a specialized model to detect bearing defects, we expand the applicability of the Swin Transformer. This paper presented a shunted-window Transformer (sSwin), which replaces the shifted-window mechanism with the shunted large–small windows. In sSwin, the self-attention heads can capture multi-scale token granularity features within the same self-attention layer. Also, a proposed local connection module enhances the boundary interaction of adjacent value tokens. As a result of the different-scale receptive fields of tokens within one attention layer, the model can bring significant performance gain on the defective detection tasks. The experiment demonstrates that sSwin-T outperforms the classical Swin-T by +2.8% APb and +1.9% APm, and Swinv2-T by +1.0% APb and +1.1% APm on COCO. It also surpasses them by +1.1% APb and +3.4% APb on the private bearing dataset with Cascade Mask-RCNN 3x.