Rolling Bearings Research Articles

A Collaborative Domain Adversarial Network for Unlabeled Bearing Fault Diagnosis

At present, data-driven fault diagnosis has made significant achievements. However, in actual industrial environments, labeled fault data are difficult to obtain, making the industrial application of intelligent fault diagnosis models very challenging. This limitation even prevents intelligent fault diagnosis algorithms from being applicable in real-world industrial settings. In light of this, this paper proposes a Collaborative Domain Adversarial Network (CDAN) method for the fault diagnosis of rolling bearings using unlabeled data. First, two types of feature extractors are employed to extract features from both the source and target domain samples, reducing signal redundancy and avoiding the loss of critical signal features. Second, the multi-kernel clustering algorithm is used to compute the differences in input feature values, create pseudo-labels for the target domain samples, and update the CDAN network parameters through backpropagation, enabling the network to extract domain-invariant features. Finally, to ensure that unlabeled target domain data can participate in network training, a pseudo-label strategy using the maximum probability label as the true label is employed, addressing the issue of unlabeled target domain data not being trainable and enhancing the model’s ability to acquire reliable diagnostic knowledge. This paper validates the CDAN using two publicly available datasets, CWRU and PU. Compared with four other advanced methods, the CDAN method improved the average recognition accuracy by 7.85% and 5.22%, respectively. This indirectly proves the effectiveness and superiority of the CDAN in identifying unlabeled bearing faults.

Rolling element bearing fault diagnosis under time-varying speed conditions based on improved wavelet packet transform and envelope order tracking

Abstract Rolling element bearings (REBs) are crucial components of rotating machinery and play an important role in industrial production. Failure of REBs can lead to significant economic losses and catastrophic accidents. In order to ensure their safe and stable operation, we propose a novel approach called EOT-IWPT which combines the envelope order tracking (EOT) with an improved wavelet packet transform algorithm (IWPT) for diagnosing failures in REBs under time-varying speed conditions. First, the time- domain vibration signal is resampled at constant angle intervels according to the phase of the rotating shaft to obtain the angle-domian signal. Next, the resampled signal is decomposed to sub-band signals using IWPT. Third, the squared envelope spectra (also called envelope order spectra) of the last layer wavelet packet coefficients are obtained by the Hilbert transform and the Fourier transform. Finally, the diagnostic results can be easily determined based on the squared envelope spectra. The procedure and performance of the proposed approach are illustrated and evaluated through simulation analysis, proving that the proposed method can effectively extract the fault features. Furthermore, experimental analysis results indicate that the proposed method outperforms both EOT-WPT and SK-EOT-BPF.

Bearing fault diagnosis based on enhanced Canberra distance feature in SDP image

Abstract Feature enhancement is important in mechanical equipment fault diagnosis. A limited set of characteristic parameters is insufficient for diagnosing bearing signals with multiple fault types. The presence of noise increases the difficulty of extracting fault features from images. To address the challenge of diagnosing rolling bearing faults in complex environments, this study presents an enhanced weighted image fusion framework aimed at enhancing fault features within the images, which enables accurate diagnosis of bearing faults using a limited number of features. The proposed method encompasses four distinct stages. In the first stage, a symmetrized dot pattern method is employed to transform one-dimensional time-series data into two-dimensional images, visualizing the signal in a 2D format. In the second stage, image binarization and an improved weighted fusion method are utilized to simplify subsequent processing and enhance the image features. The third stage involves extracting the image’s contrast and maximum singular value to improve the Canberra distance calculation. Finally, the enhanced Canberra distance is used for classifying bearing faults. Performance testing of the image feature enhancement is conducted on various datasets containing rolling bearings. Comparative experiments with alternative enhancement methods demonstrate the superiority of the proposed improved weighted image fusion framework. Comparative experiments with the original Canberra distance validate the effectiveness of the enhanced Canberra distance. Additionally, experiments conducted in noisy environments confirm the robustness of the proposed approach. Furthermore, the image feature enhancement method is applied to other bearing datasets, and the experimental results demonstrate its effectiveness in enhancing fault feature representation and achieving accurate diagnosis of rolling bearings.

Method for enhancing fault feature signals of rolling bearings in gas turbine engines

Aiming at the problem that the weak fault signal of rolling bearings in gas turbine engines (GTEs) is affected by environmental noise, which leads to the difficulty of effective information extraction and easy to ignore, the characterization method for cyclic extraction of main bearing fault feature components in GTEs is proposed. The proposed method begins by subjecting raw vibration signals to wavelet packet decomposition and correlating correlation coefficient and kurtosis values for each node component. These values are then normalized and amalgamated into a comprehensive parameter denoted as P. Subsequently, a confidence interval is established to categorize node components into three groups: high signal-to-noise ratio signals, low signal-to-noise ratio signals, and high-noise signals. Then, the high signal-to-noise ratio signals are continuously filtered according to the feature component cyclic extraction criterion until the termination condition is reached. Finally, all high signal-to-noise ratio signals are reconstructed, followed by envelope demodulation to extract subtle bearing fault characteristics. The findings underscore the efficacy of this approach in extracting fault features within the intricate transmission path of rolling bearings, offering a robust solution for the intricate signal processing and diagnosis of complex rolling bearing faults in GTEs.

Development of linear bearing equipment for modal testing of low-frequency weakly damped spacecraft structures

This article presents the results of a study of the bearing capacity and dissipative properties of an aerostatic linear bearing developed at JSC RESHETNEV for modal testing of complex structures. When selecting equipment for modal testing, the main condition is the requirement to minimize the distortions introduced into the determined dynamic characteristics: frequencies of natural vibration modes, the vibration modes themselves, as well as modal masses and damping coefficients. In other words, all equipment used for ground-based modal testing should ideally have zero added mass, stiffness and friction. The main systems containing elements that create dissipative forces that affect the determination of damping coefficients are systems for weight compensation and vibration excitation on natural modes. The weight compensation system usually contains either elastic elements or a system of guides with rolling or sliding bearings. If the former bring additional rigidity and mass to the test object, the latter bring mass and friction (dry or viscous), which increases the error in determining the dynamic characteristics. The excitation of vibrations on natural modes, in most cases, is carried out by electrodynamic vibrators consisting of a magnetization coil (or permanent magnet) and a movable coil moving in a magnetic gap. The movable coil is oriented in the magnetic gap using a special system containing either elastic elements or a linear guide bearing. Vibrators with elastic coil suspension elements cannot be used for modal tests of extended structures with low rigidity. The problem of creating an ideal bearing to replace classic linear (sliding or roller) ones arose during preparation for modal tests of the wing of a solar battery of a spacecraft (SC). Aerostatic bearings (supports) have virtually zero friction and sufficient load-bearing capacity, in which compressed air acts as a lubricant, eliminating physical contacts of the interacting surfaces. To confirm the possibility of using aerostatic bearings in equipment for conducting modal tests of extended structures with low frequencies of natural oscillations, comparative tests of a roller and aerostatic bearing were carried out. During the tests, optimal air flow parameters (nozzle diameter, operating pressure and gap) were selected, which ensure the required load-bearing capacity for radial forces and torques (bending and torsion). A comparative assessment of dissipative properties was carried out when measuring the attenuation parameters of single-mass harmonic oscillators, which include aerostatic and roller linear bearings. With a nozzle diameter of 0.6 mm, a working gap of 40 μm and a bearing input pressure of 1.0 bar, the logarithmic decrement of oscillations of the harmonic oscillator with an aerostatic bearing was 0.084, which is more than 28 times lower than the logarithmic decrement of oscillations of an oscillator with a roller bearing. The conducted studies confirmed the possibility of using the developed aerostatic bearing in test systems used in modal tests of large-sized transformable spacecraft structures.

Rolling bearing fault diagnosis method based on wavelet packet logarithmic energy map

Aiming at the fault diagnosis problem of rolling bearings, a diagnosis method based on wavelet packet logarithmic energy map is proposed. Firstly, a new wavelet packet node logarithmic energy formula is improved and proposed to overcome the shortcomings of cumbersome parameter determination and strong subjectivity in the traditional wavelet packet energy formula, improve the recognition of high-frequency faults and the distinction of low-frequency fault categories, so as to fully extract the initial time-frequency domain features; secondly, the Gram angle and field idea is used to realize the conversion from one-dimensional features to two-dimensional image features, so as to construct the logarithmic energy map feature based on wavelet packet, which further considers the spatial information between adjacent features, thereby optimizing the initial time-frequency domain features and improving the significance of the obtained features. On this basis, the residual network is used to improve the accuracy of fault diagnosis classification results. Finally, through the simulation verification of the standard rolling bearing data set of Case Western Reserve University, it can be seen that the fault diagnosis model constructed by the proposed method has high diagnostic accuracy and strong generalization ability.

Remaining Useful Life of the Rolling Bearings Prediction Method Based on Transfer Learning Integrated with CNN-GRU-MHA

To accurately predict the remaining useful life (RUL) of rolling bearings under limited data and fluctuating load conditions, we propose a new method for constructing health indicators (HI) and a transfer learning prediction framework, which integrates Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Multi-head attention (MHA). Firstly, we combined Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) to fully extract temporal and spatial features from vibration signals. Then, the Multi-head attention mechanism (MHA) was added for weighted processing to improve the expression ability of the model. Finally, a new method for constructing Health indicators (HIs) was proposed in which the noise reduction and normalized vibration signals were taken as a HI, the L1 regularization method was added to avoid overfitting, and the model-based transfer learning method was used to realize the RUL prediction of bearings under small samples and variable load conditions. Experiments were conducted using the PHM2012 dataset from the FEMTO-ST research institute and XJTU-SY dataset. Three sets of 12 migration experiments were conducted under three different operating conditions on the PHM2012 dataset. The results show that the average RMSE of the proposed method was 0.0443, indicating high prediction accuracy under variable loads and small sample conditions. Three different operating conditions and two sets of four migration experiments were conducted on the XJTU-SY dataset, and the results show that the average RMSE of the proposed method was 0.0693, verifying the good generalization of the model under variable load conditions. In summary, the proposed HI construction method and prediction framework can effectively reduce the differences between features, with high stability and good generalizability.

Sinkhorn divergence-based contrast domain adaptation for remaining useful life prediction of rolling bearings under multiple operating conditions

Under multiple operating conditions, the degradation characteristics of rolling bearings show diverse distributions. Domain adaptation (DA) achieves effective alignment between source and target domains by extracting domain-invariant features. However, in the prediction of remaining useful life (RUL) for bearings, numerous DA methods overlook mutual information from target-specific data and encounter potential challenges such as the vanishing gradient problem during the alignment of data distributions, leading to limited performance. To address these challenges, a novel method called Sinkhorn Divergence-based Contrast Domain Adaptation (SD_CDA) is proposed to predict RUL under multiple operating conditions. Firstly, an adversarial training framework is constructed to initially extract domain-invariant features. Subsequently, the cross-domain temporal mixup strategy is proposed for the data augment, which obtains positive samples to serve contrastive learning. Then self-supervised momentum contrast (MoCo) is employed to extract mutual information from target-specific data, preserving its specificity. Finally, Sinkhorn divergence is introduced to further align the fine-grained structure of the source domain and target domain, and enhance the transfer ability of the model. The experimental results demonstrate the superiority and effectiveness of the proposed method under multiple operating conditions.

Wind Turbine Bearing Failure Diagnosis Using Multi-Scale Feature Extraction and Residual Neural Networks with Block Attention

Wind turbine rolling bearings are crucial components for ensuring the reliability and stability of wind power systems. Their failure can lead to significant economic losses and equipment downtime. Therefore, the accurate diagnosis of bearing faults is of great importance. Although existing deep learning fault diagnosis methods have achieved certain results, they still face limitations such as inadequate feature extraction capabilities, insufficient generalization to complex working conditions, and ineffective multi-scale feature capture. To address these issues, this paper proposes an advanced fault diagnosis method named the two-stream feature fusion convolutional neural network (TSFFResNet-Net). Firstly, the proposed method combines the advantages of one-dimensional convolutional neural networks (1D-ResNet) and two-dimensional convolutional neural networks (2D-ResNet). It transforms one-dimensional vibration signals into two-dimensional images through the empirical wavelet transform (EWT) method. Then, parallel convolutional kernels in 1D-ResNet and 2D-ResNet are used to extract multi-scale features, respectively. Next, the Convolutional Block Attention Module (CBAM) is introduced to enhance the network’s ability to capture key features by focusing on important features in specific channels or spatial areas. After feature fusion, CBAM is introduced again to further enhance the effect of feature fusion, ensuring that the features extracted by different network branches can be effectively integrated, ultimately providing more accurate input features for the classification task of the fully connected layer. The experimental results demonstrate that the proposed method outperforms other traditional methods and advanced convolutional neural network models on different datasets. Compared with convolutional neural network models such as LeNet-5, AlexNet, and ResNet, the proposed method achieves a significantly higher accuracy on the test set, with a stable accuracy of over 99%. Compared with other models, it shows better generalization and stability, effectively improving the overall performance of rolling bearing vibration signal fault diagnosis. The method provides an effective solution for the intelligent fault diagnosis of wind turbine rolling bearings.

KAN-HyperMP: An Enhanced Fault Diagnosis Model for Rolling Bearings in Noisy Environments

Rolling bearings often produce non-stationary signals that are easily obscured by noise, particularly in high-noise environments, making fault detection a challenging task. To address this challenge, a novel fault diagnosis approach based on the Kolmogorov–Arnold Network-based Hypergraph Message Passing (KAN-HyperMP) model is proposed. The KAN-HyperMP model is composed of three key components: a neighbor feature aggregation block, a feature fusion block, and a KANLinear block. Firstly, the neighbor feature aggregation block leverages hypergraph theory to integrate information from more distant neighbors, aiding in the reduction of noise impact, even when nearby neighbors are severely affected. Subsequently, the feature fusion block combines the features of these higher-order neighbors with the target node’s own features, enabling the model to capture the complete structure of the hypergraph. Finally, the smoothness properties of B-spline functions within the Kolmogorov–Arnold Network (KAN) are employed to extract critical diagnostic features from noisy signals. The proposed model is trained and evaluated on the Southeast University (SEU) and Jiangnan University (JNU) Datasets, achieving accuracy rates of 99.70% and 99.10%, respectively, demonstrating its effectiveness in fault diagnosis under both noise-free and noisy conditions.

Deep learning-based fault classification of rolling bearings under noisy conditions using CEEMD-VMD-IMF with magnitude scalogram images

Deep learning-based fault classification of rolling bearings under noisy conditions using CEEMD-VMD-IMF with magnitude scalogram images

COMPUTER DIAGNOSTICS OF THE CONDITION OF SHIP ROLLING BEARINGS DURING THEIR OPERATION

The results of statistical processing of vibration signals obtained during diagnostics of ship power plants during the operation process are offered. A distinctive feature of monitoring the technical condition of elements of ship power plants is the uncertainty in the fixation and duration of extreme loads. The peculiarity of computer vibration diagnostics of rotary mechanisms is determined, which is that, in particular, physical measurements of vibration signals require their use in mathematical models of the physical state of the bearing. Calculations of statistical characteristics of vibration signals in the time domain, such as standard deviation (Std), asymmetry (Skewness), kurtosis (Kurtosis), full range of oscillations (Peak2Peak), root mean square value (RMS), cross factor (CrestFactor), form- factor (ShapeFactor), impulse factor (ImpulseFactor), marginal factor (MarginFactor), energy (Energy). The variety of diagnostic signals leads to the need to merge indicators of different dimensions without losing available information into a single generalizing indicator, for which the method of principal components is used in the work. The methodology of statistical processing and practical implementation of diagnostics of vibration signals during the analysis of damage evolution of rolling bearings of turbochargers of marine power plants are described. A new computer information parameter of vibration diagnostics based on the analysis of the first principal component in the time domain and spectral excess in the frequency domain has been identified and experimentally confirmed. The use of new diagnostic parameters makes it possible not only to judge the degree of damage to the rolling bearing, but also to observe the dynamics of the development of the defect and make a relative forecast of the working life of the rolling bearing. A real practical situation is considered - computer diagnostics of vibration signals of ship rolling bearings of a point defect of an external defect of a rolling bearing ring. Determining the applicability of the principal component method to other types of defects showed their potential for vibrodiagnosis of defects located on the inner ring of the bearing and when the ball falls out of the holder.

Enhanced rolling bearing fault diagnosis using DBO-VMD-KELM

Abstract To enhance the extraction of fault signal characteristics from rolling bearings and enhance fault classification precision, this paper presents an approach for diagnosing rolling bearing faults, integrating Variational Mode Decomposition (VMD) and Kernel Extreme Learning Machine (KELM). Furthermore, the Dung Beetle Optimizer (DBO) algorithm is employed to optimize VMD and KELM, addressing the challenge of determining critical parameters effectively. Initially, VMD is employed to break down the fault data from rolling bearings, and the pivotal parameters [k, α] of VMD are globally fine-tuned via the DBO algorithm, with the minimum envelope entropy serving as the optimization criterion. The ideal components of the decomposed intrinsic mode function (IMF) are then determined by comparing their minimal arranged entropy. Nine time-domain indicators are then computed to create the feature vector. Finally, in the KELM diagnostic model, the constructed feature vector is input, and DBO is combined with KELM for optimization to achieve the final fault diagnosis. Simulation results show that the fault diagnosis rate of KELM is 92%, and the fault diagnosis rate of KELM optimized by DBO is 99%, effectively identifying the fault categories of rolling bearings.

WCNN-RSN: a novel fault diagnosis method for rolling bearing using multimodal feature fusion

Abstract Fault diagnosis of rolling bearings is significant for the safe operation of engineering equipment. Many intelligent diagnostic methods have been successfully developed. However, it is often susceptible to noisy environments. Therefore, the paper proposes a rolling bearing fault diagnosis method based on multimodal information fusion in time and time–frequency domains by combining an improved 1D-convolutional neural network (CNN) with ResNet50 wavelet improved CNN-ResNet (WCNN-RSN). The algorithm employs the Multi-Head Attention (MHA) mechanism to complementarily fuse fault features in different scales, achieving fault diagnosis by fully extracting fault features. The experimental results show that the diagnostic effect of WCNN-RSN is better than that of the comparison methods under noise interference, which proves that the proposed method possesses good anti-noise and generalization ability.

A fractional-derivative kernel learning strategy for predicting residual life of rolling bearings

In the field of mechanical equipment maintenance, accurately estimating the remaining useful life (RUL) of rolling bearings is crucial for ensuring reliable equipment operation. However, prevalent deep learning methods face challenges such as limited sample sizes, and “black-box” mechanisms. To enhance the accuracy and interpretability of rolling bearing RUL prediction, a novel fractional-derivative kernel mean p-power error filtering algorithm (FrKMPE) is introduced. A comprehensive analysis of convergence for this method in terms of both mean error and mean square error criteria is provided. By combining the memory properties of fractional-derivative with the adaptability of kernel method, it can effectively capture features of non-stationary signals and sensitively monitor changes of rolling bearing health states (HSs). The effectiveness of the FrKMPE is validated through its application to the prediction of RUL using the IEEE PHM 2012 challenge dataset and the XJTU-SY dataset. Experimental results demonstrate that the proposed FrKMPE outperforms existing kernel adaptive filtering and deep learning methods in rolling bearing RUL prediction. The proposed method has advantages in dealing with complex nonlinear data and improving prediction accuracy, and provides a new perspective and solution for rolling bearing RUL prediction.

An Optimization Approach for Enhancing Energy Efficiency, Reducing CO2 Emission, and Improving Lubrication Reliability in Roller Bearings using ABC Algorithm

Friction and energy waste pose significant challenges in various industrial processes. Lubrication plays a crucial role in reducing friction and optimizing energy consumption. This study focuses on analyzing, simulating and calculation the oil film thickness, friction levels, energy losses, and CO2 emissions. The objective is to optimize lubrication conditions to enhance performance, improve energy consumption, and maximize lubrication efficiency for rolling bearings in a centrifugal fan. The simulation utilizes ANSYS CFX software, MATLAB programming. The optimal oil viscosity grade is determined based on two objectives by using artificial bee colony algorithm (ABC): minimizing energy consumption (thus reducing CO2 emission) and achieving the optimal oil film thickness and viscosity ratio. The findings reveal that, under the current lubrication conditions and normal fan operation, energy losses due to oil friction amount to 36.3 MWh per year, with CO2 emissions resulting from power losses reaching 18,750 kilograms per year. By transitioning to the optimized oil grade, energy savings of 1.08 MWh per year and a corresponding reduction of 557 kilograms in CO2 emissions per year can be achieved.

Extraction and classification of vibration features of rolling element bearing with increasing the rotational speed

Machinery components degrade over time due to continuous use. A reliable prognosis framework can improve machinery health by monitoring the behavior of its parts and providing warnings before critical failures occur. Bearings, which are essential components of rotating machinery, help maintenance personnel assess the machine’s condition during continuous wear. In this study, vibration data from roller bearings under various conditions and faults were collected. The Vibration analysis technique was employed to detect and classify different faults in bearings based on the characteristics of the vibration signals generated by the machinery. Faults can be detected, diagnosed, and classified by analyzing bearing vibration signatures using techniques such as frequency analysis, time-domain analysis, spectral analysis, and kurtogram classifiers. This enables appropriate maintenance actions to be taken in time, preventing further damage or failures.

Domain reinforcement feature adaptation methodology with correlation alignment for compound fault diagnosis of rolling bearing

In the long-term operation process, rolling bearings often have multiple single faults or cascade faults, which are coupled with each other to form the compound fault. The complex coupling components of compound fault lead to difficultly building a correlation between compound fault feature and fault class. Moreover, for the transfer learning based on domain adaptation, compound fault feature of source domain is pretty different from that of target domain, thus knowledge of source domain is hard to be transferred into the cross-domain unsupervised learning process of target domain. To solve above mentioned problems well, this paper proposes a domain reinforcement feature adaptation methodology with correlation alignment (CA-DRFA) to complete the cross-domain compound fault diagnosis of bearings. Specifically, a deep reinforcement learning model is improved by being combined with the domain adversarial training way, and meanwhile the correlation alignment metrics is adopted to enhance the generalization performance in feature alignment. In addition, a laboratory experiment and an engineering application are performed to demonstrate that CA-DRFA outperforms other popular cross-domain fault diagnosis methods in cross cutting condition and speed transfer tasks. Overall, CA-DRFA is able to implement cross-domain compound fault diagnosis with high accuracy, and effectively reduce the cost of labeling samples.

PeriodNet: Noise-Robust Fault Diagnosis Method Under Varying Speed Conditions.

Rolling bearings are critical components in modern mechanical systems and have been extensively equipped in various rotating machinery. However, their operating conditions are becoming increasingly complex due to diverse working requirements, dramatically increasing their failure risks. Worse still, the interference of strong background noises and the modulation of varying speed conditions make intelligent fault diagnosis very challenging for conventional methods with limited feature extraction capability. To this end, this study proposes a periodic convolutional neural network (PeriodNet), which is an intelligent end-to-end framework for bearing fault diagnosis. The proposed PeriodNet is constructed by inserting a periodic convolutional module (PeriodConv) before a backbone network. PeriodConv is developed based on the generalized short-time noise resist correlation (GeSTNRC) method, which can effectively capture features from noisy vibration signals collected under varying speed conditions. In PeriodConv, GeSTNRC is extended to the weighted version through deep learning (DL) techniques, whose parameters can be optimized during training. Two open-source datasets collected under constant and varying speed conditions are adopted to assess the proposed method. Case studies demonstrate that PeriodNet has excellent generalizability and is effective under varying speed conditions. Experiments adding noise interference further reveal that PeriodNet is highly robust in noisy environments.

Research on magnetic fluid precise localized lubrication thrust cylindrical roller bearing with low-friction micro-vibration and high load-bearing capacity

Abstract As the magnetic field that is difficult to be distributed in the existing magnetic fluid thrust cylindrical roller bearing structure, it is more difficult for the magnetic fluid to be evenly distributed inside the bearing raceway with the axial localized lubrication, which seriously affects the engineering application of the magnetic fluid bearing. To solve the magnetic field control problem that the magnetic fluid is uneasy to be accurately localized and adsorbed, a new type of magnetic fluid thrust cylindrical roller bearing is designed in this study, which shows good characteristics of low-friction, micro-vibration and high load-bearing capacity. The seat-ring is set as an annular raceway that can be used for magnetic fluid storage and matching with the roller lubrication system, and an annular permanent magnet is designed as an external magnetic field source to be placed below the annular raceway to adsorb the magnetic fluid on the friction surface. The structure design of the axial magnetic fluid localized lubrication bearing is reasonable, which is especially suitable for precision instruments with strict operating-conditions and precision-lubrication.