Search

Slope entropy (SlE) is an effective nonlinear dynamic analysis method, which has been used in mechanical fault diagnosis field. However, SlE only analyzes the time series on a single scale with much important information on other scales being ignored. Inspired by the multiscale analysis, the multiscale slope entropy (MSlE) is developed to extract the multiscale features of time series. Nevertheless, MSlE is susceptible to the loss of important information of original time series due to insufficient coarse-graining. In this paper, a novel algorithm termed refined time-shift multiscale slope entropy (RTSMSlE) is further proposed for enhancing the performance of MSlE. RTSMSlE changes the original coarse-grained computation and effectively improves the nonlinear analysis performance of MSlE, which has higher discriminating power and is less affected by mutant signals. After that, a novel fault diagnosis method for rotating machinery is proposed based on the RTSMSlE and DBO–SVM classifier. The effectiveness and superiority of the proposed fault diagnosis method is verified via the simulated signals and the measured data analysis with comparison to the MSlE, refined time-shift multiscale sample entropy (RTSMSE), refined time-shift multiscale fuzzy entropy (RTSMFE), refined composite multiscale sample entropy (RCMSE) and refined composite multiscale dispersion entropy (RCMDE). The analysis results show that the proposed method provides better diagnostic effect and more stable performance in analyzing the vibration signals of rotating machinery than the compared methods. [ABSTRACT FROM AUTHOR]

Insufficient training data often leads to overfitting, posing a significant challenge in diagnosing faults in mechanical devices, particularly rotating machinery. To address this issue, this paper introduces a novel approach employing a graph neural network (GNN) with one-shot learning for fault diagnosis in rotating machinery. Firstly, the Short-Time Fourier Transform (STFT) is utilized for data preprocessing to convert the one-dimensional data into two-dimensional pictures. Subsequently, Feature extraction a convolutional neural network (CNN) is utilized to perform feature extraction. By introducing the adjacency matrix to explore the spatial information within data, a graph neural network (GNN) method is proposed to achieve the fault classification of rotating machinery with small sample. The method utilizes GNN to process structural information between, transferring the distance metric from Euclidean space to non-Euclidean space. Classification accuracy is thereby improved based on information processing in non-Euclidean space.Experiments were implemented on two datasets to verify the proposed method, including an open dataset of the rolling bearing and an experimental rig of the rotate vector (RV) reducer in an industrial robot. Siamese Net, Matching Net, and sparse auto-encoder with random forest (SAE + RF) wereemployed as the comparisons to further prove the effectiveness of the proposed method. Results indicate that the proposed method outperforms all the comparative methods in both rotating machineries. [ABSTRACT FROM AUTHOR]

In rotating machinery, the condition of rolling bearings is paramount, directly influencing operational integrity. However, the literature on the fault evolution of rolling bearings in their nascent stages is notably limited. Addressing this gap, our study establishes an innovative nonlinear dynamic model for early fault evolution of rolling bearings based on collision impact. Firstly, considering the fault evolution characteristics, the influence of the rolling element and fault structure, the dynamic model of early fault evolution between the rolling element and the local fault is established. Secondly, according to the Hertzian contact deformation theory, a nonlinear dynamic model of rolling bearings expressed as mass-spring is established. Thirdly, the energy contribution method is used to integrate the fault evolution model and the nonlinear dynamic model of the rolling bearing. A nonlinear dynamic model of early fault evolution of the rolling bearing is proposed by using the Lagrangian equation. Comparing the simulation results of the nonlinear dynamic with the experimental results, it can be seen that the numerical model can effectively predict the evolution process and vibration characteristics of the fault evolution of rolling bearings in the early stage. [ABSTRACT FROM AUTHOR]

Current unsupervised domain adaptation methods for intelligent fault diagnosis focus on learning domain-invariant representations under covariate shift assumption. However, the covariate shift assumption is usually unsatisfied when each fault class in different domains consists of multiple modes with skewed proportions, which is common in industrial scenarios. Imbalanced data from multiple modes cause the presence of within-domain class imbalance and between-domain label distributional shift. This paper introduces a novel subpopulation shift that further considers the domain shift from a subpopulation perspective, i.e., that covariate shift and label distributional shift across domains are caused by shifts in the multiple modes. To address this issue, a label propagation-based unsupervised domain adaptation is proposed based on a realistic expansion assumption. We apply the theoretical analysis of the proposed method with a bi-level optimization strategy adapted from meta-learning. Using joint optimization of a teacher model and a student model, the label propagation-based model-agnostic meta-learning (LPMAML) not only propagates supervision information from the source to the target but also adjusts the teacher's strategy throughout the student's learning process. To alleviate the noise caused by label distributional shift, we integrate a sampling-based alignment method that aligns the empirical label distributions across the two domains into LPMAML. Experimental results on three bearing datasets show that the proposed method has impressive generalization ability under covariate, label distributional, and subpopulation shifts. The proposed method offers consistent improvements to unsupervised domain adaptation (UDA) methods. Compared with the vanilla UDA methods, the average diagnosis accuracies of the proposed method on the label distributional shift benchmark and subpopulation shift benchmark are improved by 8.21% and 7.63%, respectively. [ABSTRACT FROM AUTHOR]

Mechanical system fault diagnosis is essential to save costs and ensure safety. Generally, rotating machinery operates in nonstationary cases, which makes fault features complex and difficult to identify. However, existing fault diagnosis methods have the following limitations. (1) Consider only time or frequency domain features fusion. (2) Extract the fusion features representation only in the Euclidean domain. Based on that, a novel method based on multisensory time-frequency features fusion and graph attention network is proposed for rotating machinery fault diagnosis under the nonstationary case. First, the multi-sensor time series are converted into multi-sensor time-frequency maps by image-to-matrix, matrix concatenation, and matrix-to-image operations. Then, simple linear iterative clustering is applied to make the superpixels in the multi-sensor time-frequency maps into nodes and form graphs based on color and texture features. Finally, the graph attention network with residual connection is applied to distinguish the rotating machinery's health status. The proposed method is verified using gearbox test rig data and bearing public data, respectively. The experimental results indicate that the proposed method can provide more reliable and accurate fault diagnosis results for rotating machinery than other methods. [ABSTRACT FROM AUTHOR]

Rotating machinery is critical functional part of industrial mechanical equipment, and health status of rotating machinery is closely related to equipment stability, reliability and safety. Vibration signals for health prediction are often collected under operating conditions with variable loads and speeds, which makes health prediction more challenging. STFT-based time-frequency representation methods are widely used for the health prediction of rotating machinery. However, these methods lack specific learning mechanisms to effectively distinguish the time-frequency representations at different time points and frequency bands and highlight important feature information. To vanquish the weakness, this paper develops a novel dynamic adaptive time-frequency attention residual network (TFARNet) for rotating machinery intelligent health prediction. Firstly, a new adaptive STFT time-frequency attention (TFA) unit is developed to recalibrate time-frequency features, thereby enhancing important information and suppressing redundant information. Secondly, the TFA unit is inserted into the residual network, by stacking multiple residual blocks and TFA units to establish TFARNet and efficiently learn more discriminative features. Thirdly, label smoothing regularization and dynamic learning rate are employed to accelerate model convergence and optimize the model training process. Finally, three cases are carried out to evaluate the developed method. Compared with the other seven health prediction methods, the developed method can achieve higher prediction accuracy. [ABSTRACT FROM AUTHOR]

Ball bearings play a pivotal role in rotating machinery, making it crucial to detect their wear condition in real time for preventive maintenance. This paper proposes a novel method, involving one-dimensional convolutional neural network (1DCNN) and lubricating oil, which is sensitive to early abnormal wear, to intelligently predict the wear condition of ball bearings. To achieve that, an industrial-level gas turbine is used in the test to simulate the practical working conditions. During the machine's operation, the lubricating oil is sampled at different time intervals for spectral oil analysis (SOA), which is later utilized as the input data set. The 1DCNN model is then constructed and fine-tuned to extract its wear characters, and finally outputs a one-dimensional time-sequence feature vector of the SOA data, providing wear information for the upcoming hours. The predicted results have shown that the 1DCNN model can effectively predict the trend of wear condition with higher accuracy of over 97% and better generalization performance compared with the BP neural networks. Additionally, the validation test results have also verified the reliability of the 1DCNN model, which can be useful for manufacturing industries in reducing costly maintenance fees by early detection of potential failure. [ABSTRACT FROM AUTHOR]

Rolling bearing fault diagnosis based on convolutional neural network is greatly effective for bearing maintenance, and it is of great significance for ensuring the safe operation of rotating machinery. However, the traditional convolutional neural network models only focus on the single-scale feature and ignore the multi-scale deep information, which results in low performance for conducting the complex fault diagnosis problem. Aiming at this problem, we propose an improved fault diagnosis method of rolling bearings based on multi-scale attention convolutional neural network. In the first stage, a one-dimensional convolutional neural network model integrating feature extraction and fault intelligence classification is established. Subsequently, a multi-scale structure with serial layer skipping connection is constructed to extract multi-scale features in different reception fields, and the "Concat" operator is used to fuse the extracted features of each layer with SE attention mechanism in order to obtain more important feature information. And then, the fault samples are input into the network model to realize the end-to-end fault diagnosis of rolling bearings result from the nonlinear fitting ability of deep learning. Extensive experiments on two well-known rolling bearing datasets validate that the proposed method not only achieves higher fault diagnosis accuracy on the fault data sets under constant load conditions, but also exhibits strong fault identification and transfer diagnosis ability on the fault data sets under variable load conditions. [ABSTRACT FROM AUTHOR]

Time series is a popular data type that is collected from various machines for fault diagnosis. Although most time-series models for fault diagnosis reflect local relations well, they cannot extract the global patterns that contain valuable information that can be used to recognize faults. To reflect the global structural information of a time series, many recent studies have used a graph constructed by visibility algorithms (VAs) that convert a time series into a graph. However, applying the VAs to high-frequency time series—which the machines typically generate—is challenging because the computational burden of the VAs increases with the length of a time series. Therefore, we propose a novel graph-based fault diagnosis framework for high-frequency time series. First, we propose an efficient VA (EVA) that extracts essential data points to characterize a time series and constructs a graph from a high-frequency time series. Not only do the EVAs convert a given time series faster into a graph than the VAs, but the resulting graphs also characterize the time-series structure with simplicity and clarity by selecting essential data points. Then, we adopt a graph convolutional network to analyze the resulting graphs and diagnose faults. We verified the characteristics of the EVAs and the fault diagnosis performance of the proposed framework using toy time series and public rotating machinery datasets, respectively. The results demonstrated that, compared to the VAs, the EVAs are efficient in terms of computational cost, and the proposed framework is effective for fault diagnosis. [ABSTRACT FROM AUTHOR]

For a variety of production and development processes, there is a need for precise and reliable measurements of rotating machinery or objects. In this article, an alternative approach is introduced to assess both rotational and translational movements in a rotor by employing the technique known as "visual encoder." This methodology combines principles of computer vision with visual components, operating analogously to conventional optical encoders. Non-contact measurements provided by visual encoders offer several advantages, including the ability to withstand free movements and oscillations along the rotation axis, as well as application in hostile environments, such as high-temperature conditions that might pose challenges for conventional measurement methods. The proposed method incorporates translational motion tracking into rotational velocity measurement using cost-effective conventional equipment. Experimental tests demonstrate that the developed system exhibited high precision and robustness under various operating conditions, successfully operating even at rotational frequencies close to the sampling rate. The results validate the developed technique as a viable alternative for measuring rotation and translational movement in rotor applications. [ABSTRACT FROM AUTHOR]

In the context of rotating machinery maintenance, this study examines diagnostic, prognostic and health management (PHM) techniques, where a set of signal processing and supervised machine learning processes are used in a precise strategy that allows us to diagnose the condition of a gas turbine and also to predict its remaining useful life (RUL), to make appropriate maintenance decisions. Using a database of historical vibration signals, partial failure due to misalignment is diagnosed by Fast Fourier Transform (FFT) analysis. This partial failure can evolve into a total failure, leading to the cessation of production and higher maintenance costs. Predictive maintenance can improve its ability to predict failure phenomena using data-driven degradation modeling. On this basis, a total failure of a gas turbine can be avoided. A set of temporal and frequency health indicators are extracted at each operating cycle to be analyzed, filtered, and improved using statistical techniques such as normalization methods and correlation analysis. Additionally, the rolling average is used based on window functions and monotonicity to choose the best and most reliable indicators. Before fitting the decay curves of the selected health indicators using an exponential regression model, they were combined into a single indicator by applying the principal component analysis (PCA) technique to facilitate the adjustment process. The results showed good performance after testing the exponential model to predict the RUL on the test data. [ABSTRACT FROM AUTHOR]

The intelligent fault diagnosis model has made a significant development, whose high-precision results rely on a large amount of labeled data. However, in the actual industrial environment, it is very difficult to obtain a large amount of labeled data. It will make it difficult for the fault diagnosis model to converge with limited labeled industrial data. To address this paradox, we propose a novel unsupervised domain adaptation framework (M-Net) for fault diagnosis of rotating machinery, which only requires unlabeled industrial data. The M-Net will be pretrained using the labeled data, which can be accessed through the labs. In this stage, we propose a multi-scale feature extractor that can extract and fuse multi-scale features. This operation will generalize the features further. Then, we will align the distribution of the labeled data and unlabeled industrial data using the generator model based on multi-kernel maximum mean discrepancy. This will reduce the distribution distance between the labeled data and the unlabeled industrial data. For now, the unsupervised domain adaptation problem has shifted to a semi-supervised domain adaptation problem. The results, obtained through experimental comparison, demonstrate that the M-Net can achieve an accuracy of over 99.99% with labeled data and a maximum transfer accuracy of over 99% with unlabeled industrial data. [ABSTRACT FROM AUTHOR]

Bearings represent crucial components within rotating machinery, and unexpected failures can lead to significant damage and unplanned breakdowns. This paper introduces a novel approach to diagnose bearing faults under variable working conditions, leveraging the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and sequential backward selection (SBS). CEEMDAN automatically selects intrinsic mode functions (IMFs) from vibration and current signals to establish a comprehensive set of health indicators. Subsequently, the SBS algorithm identifies the most pertinent indicators for different bearing failure modes. The accuracy of the proposed method is evaluated on both vibration and electrical signals using data from a dedicated test bench at the Signal and Industrial Process Analysis Laboratory (LASPI). Results demonstrate the effectiveness of the proposed method in accurately identifying and classifying bearing faults across various working conditions, utilizing both types of signals. This approach holds promise for real-world industrial applications, offering a reliable method for condition monitoring and diagnostics in bearing systems. [ABSTRACT FROM AUTHOR]

Deep learning-based methods are widely applied to fault diagnostics, which depend on adequate samples. However, fault samples are often limited and even not available in industrial applications. To solve this problem, an optimal transport strategy-based meta-attention network (OTS-MAN) is proposed for the fault diagnosis by exploiting the fault knowledge learned from few source domains to diagnose the target domain with zero sample. Firstly, a new meta-attention network is built to mine discriminative features of each class from the source domain. Then, an optimal transport strategy is designed to align the feature distribution of each category between known fault in the source domain and unknown fault in the target domain. Finally, the similarity scores are obtained to assess the health status of the target domain. The proposed OTS-MAN is trained only with known source domain data and can diagnose unknown faults without previous access to target domain data. The validity of the proposed method is implemented through using two cases. The results indicate that the OTS-MAN has a better fault diagnosis accuracy than existing methods, and its noise immunity is also improved. [ABSTRACT FROM AUTHOR]

With the development of complex and intelligent mechanical products, the reliability of rotating machinery equipment increasingly gains much attention. As essential parts of rotating machinery equipment, bearing failures are becoming one of the leading root causes of mechanical failures. The critical problem of the bearing fault diagnosis is the method based on mechanical vibration signals. However, an accurate fault diagnosis is constantly challenged due to the nonlinearity and non-stationarity of vibration signals. This work investigates the fault diagnosis of bearing based on vibration signals, and an image-based deep learning method is proposed, in which vibration signals in the time domain are transformed into intrinsic mode functions (IMFs), and uncorrelated IMFs are removed. Rest IMFs reconstruct signals, which are transferred into symmetrized dot pattern (SDP) images. The fault diagnosis is then formulated as an image classification problem and solved with deep learning networks. In this work, the parameters of SDP are selected by optimizing an image similarity to improve the classification accuracy. The presented method is demonstrated with an experimental fault diagnosis of rolling bearings, and results show that the accuracy of the proposed method can be up to 99%. [ABSTRACT FROM AUTHOR]

Most transfer learning-based fault diagnosis methods learn diagnostic information from the source domain to enhance performance in the target domain. However, in practical applications, usually there are multiple available source domains, and relying on diagnostic information from only a single source domain limits the transfer performance. To this end, a non-uniformly weighted multisource domain adaptation network is proposed to address the above challenge. In the proposed method, an intra-domain distribution alignment strategy is designed to eliminate multi-domain shifts and align each pair of source and target domains. Furthermore, a non-uniform weighting scheme is proposed for measuring the importance of different sources based on the similarity between the source and target domains. On this basis, a weighted multisource domain adversarial framework is designed to enhance multisource domain adaptation performance. Numerous experimental results on three datasets validate the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Background: Multi-faults in rotating machines are critical and create an unfavourable working environment. Research on multi-faults is still in the early stages, and models are trained at constant speeds, which are not efficient under different types of uncertain speed conditions. Methodology: This paper proposes developing a multi-fault diagnosis system that can work irrespective of speed conditions. Vibration signatures were acquired from the different experimental multi-fault conditions under an uncertain operating environment. STFNet (Segmented Time-frequency Network) was applied to extract fault information and to create an intelligent multi-fault classification model. Results and validation: Rigorous testing of the proposed STFNet model was done under various uncertain speed conditions like constant, continuously accelerated, continuously decelerated and fluctuating speed, and a maximum accuracy of 97.87 % was achieved. The performance of the proposed model was compared with the existing algorithms and was validated on another bearing multi-fault dataset. Conclusion: As per the industrial requirement, the proposed approach will be very helpful for diagnosing multi-faults under various uncertain speed conditions. [ABSTRACT FROM AUTHOR]

Purpose: Fault diagnosis for wind turbines can effectively reduce the impact of failures, ensuring the safe and reliable operation of machinery equipment significantly and avoiding significant maintenance costs. However, the features of composite faults in wind turbines are coupled under the influence of multiple vibration sources. Particularly, slight fault signals are generally covered by noise and strong fault signals, making them difficult to identify effectively Methods: An early composite fault diagnosis algorithm named Continuous Spectral Kurtosis Deconvolution (CSKD) is proposed in this paper by analyzing the phenomenon of multiple spectral kurtosis maxima in the fast kurtosis graph under the composite fault condition. According to the maximum spectral kurtosis in the fast kurtosis graph and its corresponding frequency and frequency resolution, a band-pass FIR filter model is established for deconvolution processing to obtain significant fault signals. The obtained fault signals are removed by the narrow-band band-stop filter to achieve the purpose of significantly decoupling the composite fault. Results: The proposed algorithm is verified by a typical model simulation and engineering application, with the composite fault of the inner and outer rings of the large-scale wind turbine bearing. Results show that the proposed algorithm can realize the decoupling of large-scale rotating machinery composite fault signals and extract slighter signal features in the early composite faults effectively. Conclusion: Results show that the proposed algorithm is able to provide a solution for composite fault diagnosis of wind turbines. The method can be extended to further consider more complex and practical cases. [ABSTRACT FROM AUTHOR]

Purpose: Every Deep Learning (DL) model generates features, which basically consist of particular properties. This leads to the problem of loss of important features as the algorithms applied in the pre-trained DL models are tested on particular data, which is of a different classification problem. This paper addresses the data imbalance problem and the loss of important feature problems in DL models applied to condition monitoring of Machines. Methods: The acquired vibration signal for different conditions are divided into segments using the Average Frequency Band Decomposition (AFBD) approach. The two- dimensional image data set is developed using the time frequency approach. The four pre-reliable deep neural networks used in this approach for feature extraction are Alex Net, ResNet-18, Inception-ResNet-v2, and NASNet Mobile. The extracted features from the following networks are then fused using the Serial Based Feature Fusion (SBFF) method. Before providing fused features for classification, important features are selected using the Univariate Feature Selection (UFS) technique. The hyper-parameter tuning of the classifiers is done using the Grid Search (GS) Optimization Technique. The data imbalance problem has been solved using the Affine Image Transform (AFT), which generates augmented images based on rotations. Results: For validation of the proposed methodology, Case Western Reserve University (CWRU) benchmark data set is used. The experimental results and analysis shows, the highest achieved efficacy in the proposed technique is 99.7%. Conclusion: The developed technique is able to provide a solution for unplanned failures of Induction Motors. It is also able to detect multiple faults such as bearing and rotor faults with a high efficacy. [ABSTRACT FROM AUTHOR]

In the process of rotating machinery fault diagnosis (RMFD), the lack of feature conditions leads to the problem of low accuracy of traditional rule-based reasoning methods FD. This paper proposed a knowledge graph (KG)-driven device FD method and applied it to RMFD. First, we proposed a multi-level KG construction method to get multi-source data based on each level and analyzed the levels that affected the system state. A single-level KG was constructed through data features, and a multilevel KG with a stereostructure was built using a multi-source data fusion model as data support for FD. Second, we proposed an approach based on multilevel KG and Bayes theory to detect the system state and located the source of faults by combining the KG reasoning based on relational paths, then used the relationships between the structures of rotating mechanical equipment for fault cause reasoning and used the KG as a knowledge base for a reason using machine learning. Finally, the proposed method was validated using a steelworks motor as an example and compared with other ways, such as rule-based FD. The results show that under the condition of missing input features, the accuracy of the proposed method reaches 91.1%, which is significantly higher than other methods and effectively solves the problem of low diagnostic accuracy. [ABSTRACT FROM AUTHOR]

Rolling bearings, as integral components of rotating machinery, play a crucial role in ensuring the safe and stable operation of equipment. However, due to the inherent imbalance in the collected actual data, the accuracy of fault diagnosis is significantly compromised. An enhanced relative generative adversarial network (ERGAN) data augmentation model is proposed to improve fault diagnosis capability in imbalanced datasets. This paper introduces a relative loss function with a gradient penalty to enhance training stability and effectively address the mode collapse issue. Additionally, the generator and discriminator are reconstructed using one-dimensional convolutional layers and spectral normalization layers, which improves the quality of generated samples and effectively avoid gradient issues. Finally, an improved deep convolutional diagnostic model (DCNN) is established using variable convolutional kernels for fault classification. Experimental results demonstrate that, compared to other methods, this approach exhibits superior performance in imbalanced fault diagnosis tasks. [ABSTRACT FROM AUTHOR]

Bearing is the key component of rotating machinery, so the rapid and accurate fault diagnosis of bearing is of great significance. As one of the most commonly used diagnostic ways, vibration analysis has been explored by many scholars. However, vibration signals are underutilized in most studies and the fault information is not sufficiently extracted, which will lead to the failure of achieving expected diagnostic accuracy. This paper proposes a multilevel feature fusion of multi-domain vibration signals method for bearing fault diagnosis. Vibration signals are converted into time domain, frequency domain and time–frequency domain for fault diagnosis to realize the full use of vibration signals. The bilinear model and multi-head attention are applied to the fine-grained fusion of features extracted from multi-domain vibration signals. Experiments are conducted on Paderborn bearing data set to verify the effectiveness of proposed method. Results show that the accuracy of proposed method is greatly improved, which is much higher than the other methods. [ABSTRACT FROM AUTHOR]

Purpose: Thrust bearings play a critical role in high-speed rotating machinery, such as turbines, pumps, compressors, and turbogenerators, by transferring axial loads between the collar and the bearing pads. The lubricating fluid prevents contact, friction, and wear between solid parts and acts as a cooling medium. The purpose of this study is to evaluate the first- and second-order bearing coefficients of an inclined pad hydrodynamic thrust bearing, which have not been previously investigated, to improve the accuracy of modeling thrust bearings. Methods: In the analysis of thrust bearing systems, the lubricating fluid film is modeled as a massless spring-damper system. The finite perturbation method for the governing Reynolds equation is used to calculate the dynamic coefficients of the thrust bearing. This is done using the finite difference method (FDM) in polar coordinates. Results: This study investigates the influence of misalignment, rotating speed, and mesh size on the bearing coefficients of the thrust bearing. The results show that misalignment angle and film thickness have a clear effect on the dynamic coefficients, while changing the rotational speed has no effect on the damping coefficients. The study also investigates the axial force and moments and dynamic coefficients of an inclined pad thrust bearing. Conclusion: This study concludes that evaluating the first- and second-order bearing coefficients of the thrust bearing using the finite perturbation method can improve the accuracy of modeling thrust bearings. The study also highlights the significant influence of misalignment and film thickness on the dynamic coefficients of the thrust bearing. The results presented in this study provide valuable data that can be used as input for rotor dynamics analyses in high-speed rotating machinery. [ABSTRACT FROM AUTHOR]

Background: Hirth couplings are frequently used in the aero-engines turbine. The assembled stiffness of the Hirth couplings is significance to the design of the rotor system as it is outstandingly different from the continuous rotor structure. The decreasing of the axial pressing force to the rotor system of fifth-generation aero-engines can dramatically weaken the assembled stiffness of the Hirth coupling, which affect the rotor dynamics and even result in the rubbing faults. Purpose: This paper focuses on the theoretical study on the rubbing characteristics of the noncontinuous rotor blade casing system caused by the stiffness weakening of the Hirth couplings. Methods: A novel analytical model of the Central Tie Rod Rotor-blade-Casing (CTRRBC) coupling system considering the Hirth couplings is derived through the Timoshenko theory and Hamilton variational principle. Then the no rubbing condition, the single-blade rubbing condition and four-blade rubbing condition of the non-continuous rotor system are calculated by using the Newmark-β method. Results: The study results obtained by applying the analytical model are shown that (1) a decrease the assembled stiffness of the Hirth couplings lead to the significant amplitude amplification phenomenon of the rotor, blade and casing. (2) four-blade rubbing levels are related to the non-continuous rotor whirl, the rubbing happens on the blade located at the right end of the rotor whirl, nearest the casing, becomes more severe, vice versa. (3) Increasing the axial pressing force reaches the 60 kN, the rubbing responses of the non-continuous rotor blade system are similar to continuous structure (integral rotor). Conclusion: These results reveal the nonlinear rubbing faults characteristics of the central tie rod rotor blade casing coupling system with the Hirth couplings connection. Nonlinear effects are highlight and the multi-frequency components of system are contributed to diagnose the rubbing faults of noncontinuous rotating machinery. [ABSTRACT FROM AUTHOR]

Recent advances in sensor technology and computing capabilities have enabled the creation of data-driven models that can support real-time decision making. Such a decision aid can allow for predictive maintenance (PdM) to be undertaken on a much greater scale in manufacturing plants. PdM includes data-driven prognostics and health management (PHM). A key element in developing prognostic models involves the acquisition of high-quality data, traditionally achieved through feature extraction methods to distill meaningful insights from extensive and noisy datasets. However, such methods may not handle noisy data well or address measurement errors adequately, potentially resulting in extracted features that inadequately represent the degradation process as a machine approaches failure or fault. Also, effects of sensor types on the feature extraction and prediction model have not been much explored yet. To overcome this limitation, we proposed a solution which involves dynamic feature extraction where a statistical penalty is introduced to mitigate the influence of noisy statistical features within a monotonic trend. Subsequently, the features extracted using this method are utilized to construct a health indicator (HI). Leveraging historical HI values, a probabilistic regression model may be used to forecast the time to failure (TTF) of rotating machinery with uncertainty propagation. To validate the proposed method, acceleration data were collected from rotating machinery for several run-to-failure cases. The proposed method is demonstrated to provide excellent forecasts of TTF for both accelerometer types. [ABSTRACT FROM AUTHOR]

In order to precisely diagnose the fault type of rotating machinery, a fault diagnosis method for rotating machinery based on improved multiscale attention entropy and random forests is proposed in this study. Firstly, a nonlinear dynamics technique without hyperparameters namely multiscale attention entropy is proposed for measuring signal complexity by extending attention entropy to multiple time scales. Secondly, aiming at the insufficient coarse-graining of multiscale attention entropy, composite multiscale attention entropy is exploited to extract the features of rotating machinery faults. Then, t-distributed stochastic neighbor embedding is used to overcome the feature redundancy problem by reducing the dimension of the extracted features. Finally, the reduced-dimensional features are inputted into the random forests model to complete fault pattern recognition of rotating machinery. The results of the experiment indicate that the proposed method achieves the optimal diagnostic performance on two different fault datasets respectively, showing an extremely competitive advantage in comparison with conventional diagnosis models. Meanwhile, the proposed method is adopted to the actual hydropower unit without misjudgment, which verifies its strong adaptability. The research proposes a novel method for detecting faults in rotating machinery such as hydropower units. [ABSTRACT FROM AUTHOR]

This study presents an enhanced envelope detection technique implemented on a field-programmable gate array (FPGA) to diagnose bearing faults in rotating machinery. Bearing faults frequently result in machinery breakdowns, incurring substantial downtime and maintenance expenses. In our approach, we employ the Teager energy operator (TEO) to extract the vibration signal envelope. Subsequently, we subject the envelope signal to the fast Fourier transform (FFT) to generate the envelope spectrum of the vibration signal. Finally, we further refine the envelope spectrum using TEO for a second time, resulting in a pronounced fault peak that facilitates early fault detection. We evaluate the effectiveness and performance of the proposed method using two distinct types of bearing vibration signals, one being simulated and the other measured. Our findings reveal that the suggested approach outperforms traditional envelope detection methods, leading to a substantially enhanced fault diagnosis capability. For instance, when we assess the characteristic frequency ratio (FCFR) for faults in the inner and outer rings of the bearing using the proposed method, we observe that the FCFR values are significantly elevated, ranging from 160 to 330% higher compared to the analysis performed by the TEO and HT methods. Consequently, this indicates that the proposed approach has the ability to detect faults at an earlier stage than other methods. Furthermore, the FPGA-based implementation makes it suitable for critical industrial applications where rapid fault detection is essential to prevent catastrophic failures. [ABSTRACT FROM AUTHOR]

The important part of mechanical equipment is rotating machinery, used mostly in industrial machinery. Rolling element bearings are the utmost dominant part in rotating machinery, so even small defects in these components could result in catastrophic system failure and enormous financial losses. Hence, it is crucial to create consistent and affordable condition monitoring and fault diagnosis systems that estimate severity level and failure modes and to create an appropriate maintenance strategy. The studies reveal that the fault diagnostic system focuses on single fault diagnosis of the shaft-bearing system. However, in real scenarios, the occurrence of a single fault is very unlikely. Thus, multifault diagnosis of the shaft-bearing system is of greater significance. This paper aims at steadily and broadly summarizing the development of the intelligent multifault diagnostic and condition monitoring systems. In addition, there is a rapid development of application of Internet of things, cloud computing and artificial intelligence techniques for fault diagnosis. In this paper, we summarize the study of various fault diagnostic system built on the architecture and application of these cutting-edge technologies for predictive maintenance of mechanical equipment. [ABSTRACT FROM AUTHOR]

This study has developed new features necessary for condition monitoring and diagnosis of rotating machinery. These features are developed using the phase change of vibration signal, which is characteristic of blade rubbing fault. These developed features are intended to identify the fault's correct condition and severity of the rotating machinery. The difference between normal and blade rubbing fault was compared through experiments. The experimental model was produced to simulate a blade rubbing fault. The data were acquired through the experimental model and calculated using the developed features. Fault detection was confirmed by using genetic algorithm and machine learning that failure detection was possible using the developed features, it is expected that such study can evaluate the health of the rotating machinery. [ABSTRACT FROM AUTHOR]

Blade rubbing faults cause detrimental impact on the operation of aeroengines. Most of the existing studies on blade rubbing in the shaft-disk-blade-casing (SDBC) system have overlooked the elastic deformation of the blade, while some only consider the whirl of the rotor, neglecting its spin. To address these limitations, this paper proposes a dynamic model with large rotation for the SDBC system. The model incorporates the spin and whirl of the rotor, enabling the realistic reproduction of multi-blade rubbing faults. To verify the accuracy of the SDBC model with large rotation and demonstrate its capability to effectively consider the rotational effects such as the centrifugal stiffening and gyroscopic effects, the natural characteristics and dynamic responses of the proposed model are compared with those obtained from reported research and experimental results. Furthermore, the effects of the rotating speed, contact stiffness, and blade number on the dynamic characteristics of the SDBC system with multi-blade rubbing are investigated. The results indicate that the phase angle between the rotor deflection and the unbalance excitation force increases with the increasing rotating speed, which significantly influences the rubbing penetration of each blade. The natural frequency of the SDBC system with rubbing constrain can be observed in the acceleration response of the casing and the torsional response of the shaft, and the frequency is related to the contact stiffness. Moreover, the vibration amplitude increases significantly with the product of the blade number under rubbing, and the rotating frequency approaches the natural frequency of the SDBC system. The proposed model can provide valuable insight for the fault diagnosis of rubbing in bladed rotating machinery. [ABSTRACT FROM AUTHOR]

Purpose: This paper proposes a Low-Frequency Adaptation-Deep Neural Network (LFA-DNN) architecture for the classification of shaft imbalance in rotatory machinery. Additionally, a Low-Frequency Adaptation-Convolution Autoencoder (LFA-CA) is proposed to address the issue of industrial noise in the signals. The paper also proposes a deep neural network-based domain adaptation approach to tackle the problem of domain shift in the feature spaces of different datasets due to fluctuating operating conditions. Methods: The LFA-DNN architecture is designed to extract low-frequency features from vibrational data and diagnose the presence of imbalance. The LFA-CA is specifically designed to extract signal features and reconstruct them. Domain adaptation is proposed to adapt the feature spaces of classes of one dataset to another dataset with different operating conditions. The proposed methodology is evaluated on a dataset collected experimentally with varying amounts of mass unbalance. Results: The proposed LFA-DNN and LFA-CA architectures are effective in classifying shaft imbalance faults and denoising the signals, respectively. The proposed domain adaptation approach successfully reduces the Maximum Mean Discrepancy (MMD) between feature space distributions, thereby improving the accuracy of the model in real-world industrial settings. Conclusions: The proposed methodology is effective in detecting and diagnosing shaft imbalance faults in industrial rotating machinery, despite the challenges of fluctuating operating conditions and industrial noise in the signals. The domain adaptation approach is effective in reducing the domain shift problem and improving the accuracy of the model. This paper provides a comprehensive approach to tackle the problem of shaft imbalance faults, which can enhance the overall product quality and the safety of workers in industrial settings. [ABSTRACT FROM AUTHOR]

Purpose: Due to the influence of external factors such as noise, the operating conditions of rotating machinery in actual operation are not constant, and it is difficult to obtain high diagnostic accuracy using differently distributed training data and test data for fault diagnosis. Methods: To solve the problem of fault diagnosis under variable working conditions, we come up with a fault diagnosis approach on the account of Inception V1 module with self-attention mechanism for domain adversarial transfer network (IS-DATN). First, a feature extractor based on the Inception V1 module and the self-attention mechanism is constructed to learn domain-invariant features from the training data of the source and target domains; then, the feature extractor and the domain discriminator are trained using an adversarial training strategy to optimize the performance of both, and the labeled classifier is trained to enable accurate fault identification; finally, the test data are fed into the model, and the labeled classifier can accurately assign the unlabeled target domain data to each category, which enables fault diagnosis under variable running requirements. Results and Conclusion: The experiments in this article use the Case Western Reserve University and Laboratory self-test rolling bearing dataset and show that the presented approach can reduce the domain distribution differences, and obtain 95.43% diagnostic accuracy in case of a large difference in working conditions and 100% diagnostic accuracy in case of similar working conditions, compared with other methods, the proposed method has better transfer effect and higher diagnostic accuracy. [ABSTRACT FROM AUTHOR]

The vibration signal of rotating mechanical equipment contains a large amount of information that can be used for the fault diagnosis of rotating mechanical equipment. However, the vibration information is distributed in multiple dimensions, and a single-scale analysis cannot effectively reflect its damage characteristics, reducing the accuracy of fault diagnosis. Accordingly, an improved hierarchical fluctuation dispersion entropy (MHFDE) method based on the improved hierarchical processing is proposed. MHFDE can simultaneously mine low- and high-frequency features in the time series, avoiding information omission. Comparison results of the simulated signals show that the proposed method has the advantages of high stability and accurate measurement of complexity. In combination with the multi-cluster feature selection (MCFS) and kernel limit learning machine (KELM) optimized by whale optimization algorithm (WOA), a rotating machinery damage recognition method based on MHFDE-MCFS and WOA-KEM was proposed. Three sets of typical rotating machinery datasets are used to verify the effectiveness of the proposed method. The results show that this method can not only accurately and stably identify the damage types of the three selected machinery but also have a higher accuracy of damage recognition compared with the existing feature extraction methods. [ABSTRACT FROM AUTHOR]

Fault diagnosis is an important technology for performing intelligent manufacturing. To simultaneously maintain high manufacturing quality and low failure rate for manufacturing systems, it is of great value to accurately locate the fault element, evaluate the fault severity and find the fault root cause. In order to effectively and accurately perform fault diagnosis for rotating machinery, a novel feature selection method named unified discriminant manifold learning (UDML) is proposed in this research. To be specific, the local linear relationship, the distance between adjacent points, the intra-class and inter-class variance are unified in UDML. Based on these, the local structure, global information and label information of high-dimensional features are effectively preserved by UDML. Through this dimension reduction method, homogeneous features become more concentrated while heterogeneous features become more distant. Consequently, mechanical faults could be diagnosed accurately with the help of proposed UDML. More importantly, local linear embedding algorithm, locality preserving projections algorithm, and linear discriminant analysis algorithm could be regarded as a special form of UDML. Moreover, a novel weighted neighborhood graph is constructed to effectively reduce the interference of outliers and noise. The corresponding model parameters are dynamically adjusted by the gray wolf optimization algorithm to find a subspace that discovers the intrinsic manifold structure for classification tasks. Based on the above innovations, a fault diagnosis method for rotating machinery is proposed. Through experimental verifications and comparisons with several classical feature selection algorithms, rotating machinery fault diagnosis can be more accurately performed by the proposed method. [ABSTRACT FROM AUTHOR]

The vibration signals of rotating machinery usually contain various natural oscillation modes, exhibiting multi-scale features. This paper proposes a Multi-Branch one-dimensional deep Convolutional Neural Network model (MBCNN) that can extract multi-scale features from raw data hierarchically, thereby improving the diagnostic accuracy of gearbox faults in noisy environments. Meanwhile, the algorithms for multi-branch generation and algorithms of the convolution and pooling for each branch are deducted. The MBCNN integrates multiple branches with interrelated convolution kernels of different widths, and each branch can extract the high-level features of the signal. The network parameters of each branch are adjusted by the loss function, which makes the features of the branches complementary. Through the design of MBCNN, the local, global, deep layer and comprehensive information can be obtained from the raw data. On the widely used Case Western Reserve University Bearing Dataset, this paper conducted a performance comparison between the proposed MBCNN and other baselines including the shallow learning methods, 1D-CNN, and multi-scale feature learning methods. Moreover, our gearbox dataset was conducted on a fault diagnosis platform, and a series of experiments were conducted to verify the effectiveness and superiority of the MBCNN. The results indicate that the MBCNN can identify the faults in the gearbox with an accuracy of higher than 92%, and the average validation time per sample is less than 3.2 ms. In a noisy environment, the diagnostic accuracy can reach 90%. The proposed MBCNN provides an effective and intelligent detection method to identify the faults of rotating machinery in the manufacturing processes. [ABSTRACT FROM AUTHOR]

Traditional rolling bearing fault diagnosis approaches require a large amount of fault data in advance, while some specific fault data is difficult to obtain in engineering scenarios. This imbalanced fault data problem seriously affects the accuracy of fault diagnosis. To improve the accuracy under imbalanced data conditions, we propose a novel data augmentation method of Enhanced Generative Adversarial Networks with Data Selection Module (EGAN-DSM). Firstly, a network enhancement module is designed, which quantifies antagonism between the generator and discriminator through loss value. And the module determines whether to iteratively enhance the networks with weak adversarial ability. Secondly, a Data Selected Module (DSM) is constructed using Hilbert space distance for screening generated data, and the screened data is mixed with original imbalanced data to reconstruct balanced data sets. Then, Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN) is used for fault diagnosis. Finally, the method is verified by data measured on a rotating machine experimental platform. The results show that our method has high fault diagnosis accuracy under the condition of imbalanced data. [ABSTRACT FROM AUTHOR]

As an important part of rotating machinery, the failure of bearings will cause serious vibration and noise of mechanical equipment, which will affect the normal operation of the equipment and even lead to economic losses and casualties. To accurately and efficiently diagnose the working state and fault category of bearings, a new fault diagnosis method for rolling bearings based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), weighted permutation entropy (WPE) and adaptive chaotic particle swarm optimization back propagation (BP) neural network (ACPSO-BP) was proposed. CEEMDAN and WPE were used to extract fault features and optimize the feature vector by mean domain specification principles. ACPSO optimizes the convergence speed and recognition accuracy of the BP neural network by introducing an adaptive tent mapping interval. The experimental results on bearing data from Western Reserve University and actual wind turbine data show that the proposed diagnosis method can achieve high fault recognition accuracy with a small number of training samples. [ABSTRACT FROM AUTHOR]

The manuscript proposes a fault diagnosis method based on graph neural network (GNN) with one-shot learning to effectively diagnose rolling bearings under variable operating conditions. In this proposed method, the convolutional neural network is utilized for feature extraction, reducing loss in the process. Subsequently, GNN applies an adjacency matrix to generate codes for one-shot learning. Experimental verification is conducted using open data from Case Western Reserve University Rolling Bearing Data Center, where four different working conditions with six types of typical faults are selected as input signals. The classification accuracy of the proposed method reaches 98.02%. To further validate its effectiveness, traditional single-learning neural networks such as Siamese, Matching Net, Prototypical Net and (Stacked Auto Encoder) SAE are introduced as comparisons. Simulation results that the proposed method outperforms all chosen methods. [ABSTRACT FROM AUTHOR]

In the current industrial production process, fault data of rotating machinery are often difficult to obtain, and a small amount of fault data can lead to insufficient training of the model and reduced diagnostic accuracy. In addition, the generative adversarial network as a data generation model has the disadvantage of unstable training leading to poor quality of generated data. To address the shortcomings mentioned above, this paper proposed a rotating machinery fault diagnosis method based on the self-attention gradient penalty Wasserstein generative adversarial network under small samples. First, the Wasserstein distance with gradient penalty and self-attention mechanism was introduced into the generative adversarial network model to construct the self-attention gradient penalty Wasserstein generative adversarial network (SA-WGAN-GP) to solve the problems of poor quality of simulation data and unstable training. Then, a convolutional variational autoencoder (Con-VAE)-based sample screening strategy was constructed to realize the screening of high-quality simulation data. Finally, the original data and the screened simulation data were fed into the classifier to achieve fault diagnosis. Experimental validation was performed on Case Western Reserve University and laboratory self-test rolling bearing data. The experimental results show that the method can generate higher-quality simulation data and obtain higher diagnostic accuracy compared with other small-sample methods. [ABSTRACT FROM AUTHOR]

Purpose: The global interest of developing monitoring system is increasing due to the continuous challenges in reliability and accuracy. Automatic fault detection and diagnosis of rotating machinery play an important role for the high efficiency and reliability of modern industrial systems. The key point of having high accurate automatic model for fault detection and diagnosis is obtaining defect features and choosing a representative approach for the model. Methods: In this paper, a model is developed based on Mel Frequency Cepstral Coefficients (MFCC) and gammatone cepstral coefficients (GTCC) that are computed for the input signal frames. Additionally, two global representations (feature concatenation and feature statistics) are adopted to feed Support Vector Machine (SVM) and a temporal representation is used with Long Short-Term Memory (LSTM) and Echo State Network (ESN) classification models. To generalize the proposed model, the experiments are evaluated based on two different datasets (PHM09 and DDS), where the PHM09 contains samples of helical and spur gears while the DDS contains samples from parallel and plenary gearboxes. Results: The results show that the proposed SVM model based on feature concatenation can effectively detect faults from gears and outperforms the other existing methods in the state-of-the-art studies. Conclusion: Base on the result of this paper, a global representation by concatenating frame-based features outperforms global statistical and time-series feature representations. [ABSTRACT FROM AUTHOR]

Background: Deep learning-based fault diagnosis techniques are promising approaches that can eliminate the need for advanced skills in signal processing and diagnostic expertise. Purpose: The sparse filtering method is an unsupervised learning method whose parameters play a vital role in obtaining more accurate and reliable results. Thus, their appropriate selection is necessary to obtain more accurate diagnosis of faults in rotating machinery by adaptively collecting the features of the vibration signal. Method: In this paper, a novel unsupervised learning method called general normalized sparse filtering (GNSF) based on Wasserstein distance with maximum mean discrepancy (MMD) has been proposed for fault diagnosis. Initially, the objective function of generalized l r - p / q norm is optimized to compute the feature sparsity that enhances the regularization performance of the sparse filtering. Whereas, clustering of features is done by Wasserstein distance with MMD highlights the contribution of different features in fault clustering. Conclusion: Using GNSF based on Wasserstein distance with MMD, a new intelligent fault diagnosis method is planned and applied to the centrifugal pump and Pelton wheel vibration data under harsh/defect-induced operating conditions. Even with a lesser number of training samples, the proposed approach can successfully identify the various health conditions of the centrifugal pump and Pelton wheel. For instance, at 5% of training samples, the proposed fault identification scheme obtained 99.95% and 99.91% of accuracy. The results confirm the capabilities and effectiveness of the proposed method in terms of efficiency and computation time even for fewer training samples. [ABSTRACT FROM AUTHOR]

Fault diagnosis is an essential process for the health maintenance of rotating machinery. With the development of AI technology, many deep learning-based methods have been applied to fault diagnosis to enhance the intelligence level of equipment maintenance. Such methods normally need a large amount of labeled data for model training. However, label acquisition is a difficult task that requires extensive human labor. To address these issues, a fault diagnosis method based on feature extraction via an unsupervised graph neural network is proposed in this paper. In the proposed method, the K-nearest neighbor approach is adopted to construct a fault graph from the collected signals, thereby providing extra relationship information for fine feature mining. Then, the GraphSAGE model is trained on the constructed graph in an unsupervised way, that is, it does not need labeled data, to extract features of each signal sample. Based on the extracted features, some traditional classifiers are adopted to identify the fault types. The proposed model is evaluated on a rolling bearing dataset provided by the University of Paderborn and a motor rotor dataset collected by a constructed motor rotor system. Compared with some traditional deep learning-based fault diagnosis methods, the proposed model can achieve more accurate diagnoses even when there are only a few labeled samples. [ABSTRACT FROM AUTHOR]

To abstract the fault features from multivariate vibration signals of the rotating machinery under different speeds, an improved multivariate multiscale fuzzy distribution entropy (IMMFDE) is proposed. Based on multivariate empirical mode decomposition, the IMMFDE can determine the maximum scale adaptively, meanwhile eliminate the frequency aliasing and avoid the loss of potentially useful information in the multiscale process. The trait of IMMFDE is verified by calculating the sequences and their amplitude spectrums at each scale of the simulated multivariate signals. Further, the fault diagnosis method is proposed for the rotating machinery under different speeds based on IMMFDE. In the method, the statistical parameters and IMMFDE are calculated as fault feature set; then, support vector machine is used for fault diagnosis. Applying the method to two types of the rotating machinery multi-fault diagnosis under different speeds, the results show the proposed method can obtain better fault diagnosis results. [ABSTRACT FROM AUTHOR]

The importance of the quality of life of rotating machinery increases the Bearing fault diagnosis. Deep learning models (DL)-based databases become increasingly smart in the field of fault diagnostics, the latest research has widely used CNNs (convolutional neural networks). This paper proposes a new way to diagnose bearing failures with CNN with Bilinear LSTM. Traditional CNNs are however not easy to detect defects due to the fixed geometry of complex fault diagnosis with different working conditions. Our primary and secondary classifiers at specified layers replace primitive shape convolutions with reconfigurable convolutions, resulting in classification results with stringent feature time-frequency incompatibility and a larger receptive field. To acquire more adaptive knowledge and insight into the proposed approach, we employ the CWRU (Case Western Reserve University) opensource dataset to compare classification accuracy. The bearing dataset has been subjected to comprehensive experiments and evaluations in order to confirm the efficacy of the suggested technique's diagnostic performance in a variety of settings. By comparing multiple perspectives on the same dataset with related tasks, the proposed method's superiority is proved. To limit the effect of noise and avoid temporal oscillations, degraded index sequences are matched with a CNN. Current and previous inspection data are fed into a new CNN-BiLSTM model, which is then used to predict the useful time and compatible power values of bearing RULs. When it comes to output, go with the lifetime percentage. The proposed method has been tested by accelerating bearing operation to failure, and the results show that the method has advantages in predicting RUL more accurately. The results of the experiments suggest that the proposed core distance measurement method is a viable new tool for intelligent rolling bearing diagnosis. The BiLSTM technique is more diagnostic than some generic models, according to experimental results using the 48 K and 12 K CWRU datasets, with overall accuracy of 99.80% and 98.3%, respectively. [ABSTRACT FROM AUTHOR]

Identification of multiple mechanical faults from vibration signals has always been one of the most challenging tasks in the field of condition monitoring and fault diagnosis. This study proposes a new fault-oriented vibration signal decomposition method, called adaptive feature mode decomposition (AFMD), to identify multiple localized faults in rotating machines interfered by strong periodic harmonics in a robust and effective manner. The autoregressive model is first introduced as a preprocessing technique for initially reducing deterministic components of the raw signal. Then, for signal decomposition, an adaptive finite impulse response (FIR) filter bank is designed utilizing the blind deconvolution theory. The filter coefficients of the FIR filter bank are iteratively updated to make each filtered sub-signal infinitely approach their deconvolution objective functions based on the correlated kurtosis. Meanwhile, the filter length is adaptively determined using the developed evaluation indicator termed as the weighted squared envelope harmonic-to-noise ratio. Finally, several decomposed modes focusing on fault signatures can be acquired automatically, using the newly proposed mode selection strategy that considers signal similarity across multiple domains. The proposed AFMD method can significantly reduce the likelihood of incorrect diagnoses, as demonstrated by two simulated and two experimental datasets with multiple localized bearing and gear faults. The analysis results show that the proposed method outperforms over the state-of-the-art feature mode decomposition and the most popular variational mode decomposition in multi-fault feature extraction and weak fault detection, when interfered by strong periodic harmonics as well as other background noise. [ABSTRACT FROM AUTHOR]

The intelligent maintenance of rotating machinery is inseparable from the real-time condition detection and fault diagnosis system. The traditional blind source fault diagnosis method has low efficiency and high misdiagnosis rate, so this paper introduces the VS-Harmogram method with prior parameters. First, the Fourier spectrum should be re-cut by power spectral density and the information in each frequency band can be sequentially extracted. Secondly, the window width of power spectral density is gradually increased to expand the variability of the sweep frequency. Finally, the harmonic spectral kurtosis of each component should be calculated using the prior parameters of the rotating equipment. A variable spectral segmentation Harmogram (VS-Harmogram) with multiple sets of boundaries would be constructed. The validity of the method can be verified by using the fault signals of rolling bearings in rotating equipment. [ABSTRACT FROM AUTHOR]

Ball bearings are the most critical components of rotating machinery in oil and gas companies. Typical research has focused on bearing failure detection based on bearing failure frequencies derived from the velocity spectrum. However, most bearing failures are caused by improper or insufficient lubrication. The current research utilizes a case study demonstrating when ball bearings must be replaced or relubricated due to poor lubrication conditions. Poor lubrication is the cause of natural frequency excitation in bearings, where rapid bearing damage is typically induced by poor lubrication film. According to experimental data in this study, the bearing failed due to natural frequency excitation. In addition, when analyzing a signal with the velocity spectrum, high frequencies are displayed. Bearing failure is detected without bearing failure frequencies using the natural frequencies of the bearing in the velocity spectrum signal. Moreover, an experimental investigation of the bearing failure of a liquid ring compressor was conducted utilizing a VIBXPERT II vibration analyzer and the Omni trend software. The velocity spectrum is derived based on a fast Fourier transform from a time signal. After lubricating natural frequencies must be disappeared from the velocity spectrum otherwise, the bearing is failed and must be changed. [ABSTRACT FROM AUTHOR]

Introduction: Intelligent diagnostics is the most important issue in the predictive maintenance of industrial rotating machinery. Analytical diagnostics tools have been proved effective. However, these techniques are unable to be adaptively implemented for diverse machines with various defect modes. Deep diagnostics tools have been demonstrated efficient, but they exploit massive data with a high computational cost and time that is impractical for online condition monitoring. Furthermore, the health signals may be acquired under unknown operational conditions in real machines. These are the major challenges for previous diagnostics methods and make them infeasible in real-world applications. Therefore, a novel technique is proposed in this research to solve mentioned problems. Purpose: The main novelty of this method is to fuse information of various processing functions and to apply an efficient feature bank for performing an efficacious feature learning method based on the multidomain strategy. The other novelty of this rese arch is to select multi-distribution transferable features for the diagnostics of rotating machinery under unseen working conditions. The Mean Squared Error (MSE) function for the improvement of diagnostics accuracy and the transferable feature space with semi-definite dimension between the source and target machines with different working conditions for the improvement of diagnostics speed are minimized jointly via single-layer and multi-layer perceptron neural networks. To complement a real diagnostics approach, we also introduce a noise-robust pattern for the actual environment via applying the mean discrepancy function between source and multitarget domains for transferable features learning with the purpose of independency of failure distribution and robustness-to-noise with unknown operational conditions. Materials and methods: This approach is verified by two case studies of machinery vibration data sets for the robustness analysis of multi-fault diagnosis problems under various operational conditions for the sensitivity analysis. Conclusion: Results indicate that the proposed algorithm achieves good performance in comparison with the state-of-the-arts methods for unseen working conditions. [ABSTRACT FROM AUTHOR]

Recently, rotating machinery has been widely applied in various mechanical systems such as hydroelectric and nuclear power plants. When mechanical systems are operated, the main rotor is rotated to manufacture the product. If a fault occurs in the rotor, then the system is damaged. Thus, to avoid malfunction of the system and rotor damage, vibration issues because of bending, misalignment, and imbalance should be considered. In this regard, a smart structure-based active bearing system is extensively researched and developed to control rotor vibration. This system can continuously improve the noise, vibration, and harshness performance under various operating conditions by controlling the dynamic characteristics of the active bearing. This study focused on the effect of rotor motion control by quantifying the active bearing force and phase when an active bearing was applied in a simple rotor model. A simple rotor with two active bearing systems was modeled based on lumped-parameter modeling. In the rotor model, the active bearing, which had two piezoelectric actuators and rubber grommets placed in both the x- and y-directions, was located on both sides to control the vibration. The interaction between the rotor and the active bearing system was considered to quantify the force and phase of this system. Furthermore, through simulation, the motion control effect was validated when an active bearing was applied in the rotor model. [ABSTRACT FROM AUTHOR]

The evolution of pressure-sensitive paint (PSP)-based surface pressure measurement technology for rotating machinery is significant for flow mechanism analysis and blade design. Considering the challenges of reducing motion blur and improving signal-to-noise ratio (SNR) in the application of PSP technology for the rotating machinery, an accumulated imaging method with phase-locking based on the periodic characteristics of the rotor flow field has been proposed in this study, which is capable of capturing the phase-averaging pressure on the rotor blade surface. The motion blur is reduced by pulse acquisition of PSP luminescent, and the SNR is improved by accumulating luminescent signals of the same phase multiple times, which can address the challenge. Single PSP luminescence acquisition time and accumulation number are the two most crucial parameters for measurement accuracy, and the constraints of the parameters are discussed in detail according to the principle of PSP. The PSP measurement system for rotating machinery based on the proposed method has been established, and the method is successfully applied to the rotating blade surface pressure measurement of a transonic axial fan. Besides, the proposed method can also be applied to the temperature measurement of the rotating blades based on temperature-sensitive paint. The results offer a technical foundation for the pressure measurement of rotating machinery. [ABSTRACT FROM AUTHOR]