Bearing Health Condition Research Articles

Impulses Recovery Technique Based on High Oscillation Region Detection and Shifted Rank-1 Reconstruction—Its Application to Bearing Fault Detection

The health status of bearing is directly related to the safe operation of rotating machinery. Bearing fault detection technology is of great significance to reduce or eliminate safety accidents. Singular value decomposition (SVD), as an effective low-rank approximation tool of data matrix, is widely used in bearing fault detection. The construction of trajectory matrix and the selection of singular value are two important factors that affect the performance of SVD-based fault diagnosis methods. In this paper, a new matrix low-rank approximation tool similar to SVD, shifted rank-1 reconstruction (SR1R), is introduced for fault diagnosis. SR1R uses periodic segment matrix (PSM) as trajectory matrix, and its signal reconstruction does not need to select singular value. In addition, a high oscillation region (HOR) detection method based on variance evaluation is proposed and applied to signal reconstruction of SR1R. The fault impulse detection method combining these two methods is called HOR-SR1R. The proposed method cannot only detect the fault impulses, but also suppress the noise between adjacent fault impulses. By contrast, the traditional SVD cannot eliminate the noise between adjacent fault impulses. The effectiveness of proposed method is validated by simulated signals, wheelset bearing data and open data set. Compared with two SVD-based fault diagnosis methods, Hankel matrix-based SVD and PSM-based SVD, the superiority of the proposed method is highlighted.

Unbalanced Fault Diagnosis Based on an Invariant Temporal-Spatial Attention Fusion Network.

The health status of mechanical bearings concerns the safety of equipment usage. Therefore, it is of crucial importance to monitor mechanical bearings. Currently, deep learning is the mainstream approach for this task. However, in practical situations, the majority of fault samples have the issue of severe class unbalancing, which renders conventional deep learning inapplicable. Targeted at this issue, this paper proposes an invariant temporal-spatial attention fusion network called ITSA-FN for bearing fault diagnosis under unbalanced conditions. First, the proposed method utilizes the invariant temporal-spatial attention representation section, which consists of a pretrained convolutional auto-encoder model, a convolutional block attention module, and a long short-term memory network, to extract independent features and invariant features of spatial-temporal characteristics from input signals. Then, a multilayer perceptron is used to fuse and infer from the extracted features and design a new loss function from the focal loss for network training. Finally, this article validates proposed model's effectiveness through comparative experiments, ablation studies, and generalization performance experiments.

Data-Driven Fatigue Damage Monitoring and Early Warning Model for Bearings

Since the manual extraction of features is not sufficient to accurately characterize the health status of rolling bearings, machine learning algorithms are gradually being used for fault diagnosis of bearings, which can adaptively learn the required features from the input data. In this paper, k -nearest neighbor, support vector machines, and convolutional neural networks are successfully applied to the fault diagnosis of bearings, for the benefit of achieving the detection and early warning of bearing fatigue damage. The original samples are segmented into semioverlapping samples. When using k -nearest neighbor and support vector machines as early warning models, we searched their hyperparameters with random search and grid search, and the results showed that support vector machines could achieve 87.1% of bearing detection accuracy and k -nearest neighbor could achieve 100% of detection accuracy. When convolutional neural networks are used as the early warning model, the accuracy can reach 99.75%.

Intelligent Diagnosis of Rolling Element Bearing Based on Refined Composite Multiscale Reverse Dispersion Entropy and Random Forest.

Rolling bearings are the vital components of large electromechanical equipment, thus it is of great significance to develop intelligent fault diagnoses for them to improve equipment operation reliability. In this paper, a fault diagnosis method based on refined composite multiscale reverse dispersion entropy (RCMRDE) and random forest is developed. Firstly, rolling bearing vibration signals are adaptively decomposed by variational mode decomposition (VMD), and then the RCMRDE values of 25 scales are calculated for original signal and each decomposed component as the initial feature set. Secondly, based on the joint mutual information maximization (JMIM) algorithm, the top 15 sensitive features are selected as a new feature set and feed into random forest model to identify bearing health status. Finally, to verify the effectiveness and superiority of the presented method, actual data acquisition and analysis are performed on the bearing fault diagnosis experimental platform. These results indicate that the presented method can precisely diagnose bearing fault types and damage degree, and the average identification accuracy rate is 97.33%. Compared with the refine composite multiscale dispersion entropy (RCMDE) and multiscale dispersion entropy (MDE), the fault diagnosis accuracy is improved by 2.67% and 8.67%, respectively. Furthermore, compared with the RCMRDE method without VMD decomposition, the fault diagnosis accuracy is improved by 3.67%. Research results prove that a better feature extraction technique is proposed, which can effectively overcome the deficiency of existing entropy and significantly enhance the ability of fault identification.

Bearing fault severity assessment using variable-step multiscale fusion Lempel-Ziv complexity

Abstract Most research on bearing health condition monitoring is devoted to distinguish the defective condition from the healthy condition. In practice, the fault severity assessment is also critical for performing the prognostics and maintenance of bearings. Lempel-Ziv complexity (LZC) has been widely used for the bearing quantitative fault diagnosis. However, the original LZC extracts fault information only at the single scale and often fails to portray the fault features. Then, the multiscale LZC is proposed to more comprehensively extract the fault information. However, multiscale analysis would shorten the length of time series and lead to inaccurate calculation results as the scale factor increases. As such, this paper proposes a novel bearing fault severity assessment method using variable-step multiscale fusion Lempel-Ziv complexity (VSMFLZC) to facilitate the quantitative fault diagnosis of bearings. The variable step length strategy is developed in the proposed method to optimize the coarse-grained procedure. Then, Laplace score is applied to evaluate the features and weights at each scale to obtain the proposed VSMFLZC. By such a fusion algorithm, the sequence can be converted into a single but comprehensive evaluation indicator for the fault severity assessment. The experimental results indicate that the proposed method outperforms the original LZC and multiscale LZC, where the fault features can be more comprehensively extracted and the fault severity assessment of rolling bearing can be successfully realized.

A novel machine learning model for safety risk analysis in flywheel-battery hybrid energy storage system

Flywheel energy storage system (FESS) has been regarded as the most promising hybrid storage technique to manage the battery charging process of electric vehicles. Thanks to properly regulating with the FESS, the battery life can be significantly prolonged. In order to ensure the safety of the hybrid storage system, it is imperative to monitor the mechanical operation condition of the FESS. Because the rolling bearing is a critical mechanical component in the FESS, the performance degradation monitoring and remaining useful life (RUL) prediction of the rolling bearing must be performed. This paper proposes a new machine learning method for the construction of a health indicator to quantitatively evaluate the bearing health status. In this new method, the original feature set is firstly selected through three feature evaluation indicators and the principle component analysis (PCA) is employed to fuse the original feature set as a new health indicator. Then the primary trend of the health indicator is extracted by the empirical mode decomposition (EMD); and the Kriging model-based prediction method is proposed to predict the bearing RUL. The feasibility and superiority of the proposed method is verified through experimental test and analysis result shows that the root mean square error (RMSE) of the prediction is as small as 0.0425.

Fault diagnosis for rolling bearing using a hybrid hierarchical method based on scale-variable dispersion entropy and parametric t-SNE algorithm

Accurate and efficient fault diagnosis for rolling bearing is essential to ensure the reliable and safe operation of mechanical equipment. In this paper, a hybrid hierarchical fault diagnosis method based on scale-variable dispersion entropy (SVDE) and parametric t-distributed stochastic neighbor embedding (Pt-SNE) algorithm, systematically combining the statistics analysis principle and machine learning technique, is proposed. First, an initial evaluation scheme with regard to the health state of bearing is implemented by the SVDE theory blended with the statistical analysis technology. Second, if fault appears, a novel mixed-scale model, integrating series mode with multi-scale factor, is established based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and SVDE for further improvement of feature extraction performance. Subsequently, a Pt-SNE algorithm is provided to reduce the features for higher accuracy and speed of diagnosis. Finally, the obtained low-dimensional representations after reduction can be imported in Softmax classifier for fault recognition. Two vibration datasets are used for bearing fault diagnosis. The experimental results prove the superior performances of the proposed method, and it has better practicability in engineering problems compared with other existing approaches.

Health Condition Identification of Rolling Element Bearing Based on Gradient of Features Matrix and MDDCs-MRSVD

Bearing is a key component in rotary machines, and the performance of the rotary machines mostly depends on the bearing health condition. In order to improve the safety and maintenance plan of the product based on the bearing condition, a monitoring indicator is constructed to identify the health condition of bearings in real time. Firstly, the vibration signal is processed by the proposed Maximal Difference of the Detail Components in Multi-Resolution Singular Value Decomposition (MDDCs-MRSVD) algorithm. Secondly, the features matrix is constructed by selected features to reflect the health condition of bearings. Then, the gradient standard deviation of each sampling time is obtained by the gradient in the amplitude direction of the features matrix. Finally, a monitoring indicator can be constructed to identify healthy stages of bearing. The proposed methods are verified via the tested datasets provided by Intelligent Maintenance Systems, and Xi’an Jiaotong University and the Changxing Sumyoung Technology Co., Ltd. (XJTU-SY). The results indicate that the proposed method is efficient and accurate to monitor and identify the health stages of bearing in real time.

Adaptive Cost Function Ridge Estimation for Rolling Bearing Fault Diagnosis Under Variable Speed Conditions

Rolling bearing health condition evaluation under time-varying operating speed requires information about shaft rotational speed. However, it is not always feasible to install a sensor such as a tachometer or an encoder to collect rotational speed signals due to space limitations or safety considerations. Time-frequency ridge estimation is an alternative approach that directly extracts the fault-related characteristic curves in a time–frequency representation (TFR) without phase reference. The cost function ridge estimation (CFRE) is the most widely used contemporary ridge estimation method. However, there is no explicit principle for the selection of search bandwidth. Moreover, the definitions of weight factor and cost function lack rationality, which causes the CFRE to degrade partially into coarse direct maximum ridge estimation (DMRE) or possibly extract the least frequency-varying curve. A time–frequency ridge estimation method, which is called adaptive CFRE (ACFRE), is developed in this study to address these deficiencies. We improve the original cost function and redefine its mathematical model to better balance searching for peak amplitude and guaranteeing a continuous curve. Numerical simulations and experimental investigations show that the proposed ACFRE is more robust to interferences derived from adjacent curves and noise than CFRE and another well-known ridge estimation approach, fast path optimization (FPO). The proposed method has a smaller root mean square error (RMSE) in estimating bearing characteristics under variable speed conditions.

Continuous Health Monitoring of Rolling Element Bearing Based on Nonlinear Oscillatory Sample Entropy

As a nonlinear measure, sample entropy (SE) can be considered as a suitable parameter for characterizing rolling element bearing health status by measuring complexity of vibration signals. However, in continuous monitoring scenario under noisy condition, all components of a multicomponent bearing signal are not equally sensitive towards change of SE value. As a consequence, a direct application of SE results into inefficient early fault warning and inability to differentiate among different fault types. To deal with this problem, instead of direct utilization of a whole vibration signal, its principal component (PC) sensitive to SE calculation is separated with the help of continuously adjustable parameterized tunable Q factor wavelet transform (TQWT). Since, TQWT uses an oscillation-based bearing PC separation scheme for SE calculation, the newly proposed measure is termed as oscillatory sample entropy (OSE). Due to the biasness of SE algorithm towards bearing PC, proposed OSE can anticipate theoretical concept of complexity change more efficiently with the change of bearing health. Two experimental case studies have shown that proposed OSE can not only overcome the limitations of SE algorithm also demonstrate superiority over approximate entropy (AE) and fuzzy entropy (FE) for continuous monitoring of bearing health.

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder.

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

Bearing fault detection under time-varying speed based on empirical wavelet transform, cultural clan-based optimization algorithm, and random forest classifier

Bearings are massively utilized in industries of nowadays due to their huge importance. Nevertheless, their defects can heavily affect the machines performance. Therefore, many researchers are working on bearing fault detection and classification; however, most of the works are carried out under constant speed conditions, while bearings usually operate under varying speed conditions making the task more challenging. In this paper, we propose a new method for bearing condition monitoring under time-varying speed that is able to detect the fault efficiently from the vibration signatures. First, the vibration signal is processed with the Empirical Wavelet Transform to extract the AM-FM modes. Next, time domain features are calculated from each mode. Then, the features’ set is reduced using the Cultural Clan-based optimization algorithm by removing the redundant and unimportant parameters that may mislead the classification. Finally, an ensemble learning algorithm “Random Forest” is used to train a model able to classify the fault based on the selected features. The proposed method was tested on a time-varying real dataset consisting of three different bearing health states: healthy, outer race defect, and inner race defect. The obtained results indicate the ability of our proposed method to handle the speed variability issue in bearing fault detection with high efficiency.

Time-Frequency Spectral Power Assessment of Rolling Element Bearing Faults Using Adaptive Modified Morlet Wavelet Transform

Objectives: The main objectives of this manuscript are to investigate and diagnose rolling element bearing defects in its inception time. Methods: Vibration signal generated by the induction motor contains a series of frequency components that have rich and viable information about bearing health conditions. Recently, the Maximum Energy Concentration (MEC), measure of time-frequency spectrum has been employed to investigate the small variations in low frequency biomedical signal spectrum. In this paper, the above technique has been modified and applied to study the bearing defects of induction motor using vibration signal and it is termed as Adaptive Modified Morlet Wavelet (AMMW) transform. Initially, this proposed method was validated on two medium frequency synthetic time series signals in terms of MEC measurement at different Signal to Noise Ratio (SNR). Results: The simulated results have depicted that the AMMW method provides excellent timefrequency localization capability over other time-frequency methods like Morlet wavelet transform, modified Morlet wavelet transform, adaptive S-transform and adaptive modified S-transform. Then, this method has been applied to the standard database of vibration signal to determine interquartile power for fault detection purpose and also fault index parameter termed as IFI has been analyzed to detect small variation in vibration signals.

Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network

Remaining Useful Life (RUL) prediction play a crucial part in bearing maintenance, which directly affects the production efficiency and safety of equipment. Moreover, the accuracy of the prediction model is constrained by the feature extraction process and full life data of bearings. In this paper, the life prediction method of faulty rolling bearing with limited data is presented including degradation state model and RUL prediction model. In order to obtain health indication (HI) without human interference in the degradation state modeling stage, the bottleneck structure of Stacked Autoencoder (SAE) is utilized to fuse the four selected features into one HI using Intelligent Maintenance Systems (IMS) bearing dataset as training sample. In RUL prediction model, the Long Short-Term Memory (LSTM) neural network is carried out to establish the model with Standard deviation (Std) input and HI training label. In order to solve the problem of large training error caused by insufficient data in the failure stage of bearing acceleration test, the third-order spline curve interpolation is utilized to enhance the data points. Through parameter analysis, the RMSE and MAE of the test set on the prediction model are 0.032582 and 0.024038, respectively. Furthermore, the effectiveness of the proposed method is further validated by dataset from Case Western Reserve University (CWRU) with different bearing fault degrees. The analysis indicates that the RUL prediction of bearing fault data is consistent with the size of artificial added faults, that is,the more severe the fault the shorter the time of remaining life. The results validate that the proposed method can effectively extract the bearing health state by incorporating feature fusion and establish accurately prediction model for bearing remaining life.

Monitoring the Health Status of Rolling Bearings Based on Adaptive mean-shift

In order to monitor the structural health condition of rolling bearings in real time, an adaptive mean-shift algorithm was proposed to replace the fixed step size in the Mean Shift algorithm with adaptive variable step size. Wavelet packet energy entropy was used to extract the characteristics of rolling bearing vibration signals, and a series of centroids were clustered by adaptive mean-shift after dimensionality reduction. The centroid in normal state was used as the reference centroid to calculate the offsets of all centroids (including reference centroid) and reference centroid. Experiments show that the adaptive mean-shift algorithm converges quickly and has high accuracy. The centroid offset can be used to monitor the structural health effectively.

Intelligent Fault Diagnosis of Rolling-Element Bearings Using a Self-Adaptive Hierarchical Multiscale Fuzzy Entropy.

The fuzzy-entropy-based complexity metric approach has achieved fruitful results in bearing fault diagnosis. However, traditional hierarchical fuzzy entropy (HFE) and multiscale fuzzy entropy (MFE) only excavate bearing fault information on different levels or scales, but do not consider bearing fault information on both multiple layers and multiple scales at the same time, thus easily resulting in incomplete fault information extraction and low-rise identification accuracy. Besides, the key parameters of most existing entropy-based complexity metric methods are selected based on specialist experience, which indicates that they lack self-adaptation. To address these problems, this paper proposes a new intelligent bearing fault diagnosis method based on self-adaptive hierarchical multiscale fuzzy entropy. On the one hand, by integrating the merits of HFE and MFE, a novel complexity metric method, named hierarchical multiscale fuzzy entropy (HMFE), is presented to extract a multidimensional feature matrix of the original bearing vibration signal, where the important parameters of HMFE are automatically determined by using the bird swarm algorithm (BSA). On the other hand, a nonlinear feature matrix classifier with strong robustness, known as support matrix machine (SMM), is introduced for learning the discriminant fault information directly from the extracted multidimensional feature matrix and automatically identifying different bearing health conditions. Two experimental results on bearing fault diagnosis show that the proposed method can obtain average identification accuracies of 99.92% and 99.83%, respectively, which are higher those of several representative entropies reported by this paper. Moreover, in the two experiments, the standard deviations of identification accuracy of the proposed method were, respectively, 0.1687 and 0.2705, which are also greater than those of the comparison methods mentioned in this paper. The effectiveness and superiority of the proposed method are verified by the experimental results.

A novel feature adaptive extraction method based on deep learning for bearing fault diagnosis

Bearing health condition directly affects the reliability of mechanical equipment. Although deep learning (DL) algorithms have achieved great results in the field of bearing fault diagnosis, traditional activation function uses a fixed mathematical formula to achieve non-linear feature transformation, which tend to compress part of the effective fault information and reduce the performance of fault diagnosis. To address this problem, this paper proposes a slope and threshold adaptive activation function with tanh function (STAC-tanh). Establish the relationship between non-linear feature transformation and input signal by automatically adjusting the shape of activation function. Finally, the model can retain valid fault information to improve fault diagnosis performance. Then, combining STAC-tanh and Residual Networks, this paper proposes ResNet-STAC-tanh for bearing fault diagnosis. Experimenting on the two bearing datasets with added noise, the average accuracy of the network reached 90.00% and 90.77%, respectively. The effectiveness of the new method was verified through comparative experiments.

Health Assessment and Remaining Useful Life Prediction of Wind Turbine High-Speed Shaft Bearings

Vibration signals contain abundant information that reflects the health status of wind turbine high-speed shaft bearings ((HSSBs). Accurate health assessment and remaining useful life (RUL) prediction are the keys to the scientific maintenance of wind turbines. In this paper, a method based on the combination of a comprehensive evaluation function and a self-organizing feature map (SOM) network is proposed to construct a health indicator (HI) curve to characterizes the health state of HSSBs. Considering the difficulty in obtaining life cycle data of similar equipment in a short time, the exponential degradation model is selected as the degradation trajectory of HSSBs on the basis of the constructed HI curve, the Bayesian update model, and the expectation–maximization (EM) algorithm are used to predict the RUL of HSSBs. First, the time domain, frequency domain, and time–frequency domain degradation features of HSSBs are extracted. Second, a comprehensive evaluation function is constructed and used to select the degradation features with good performance. Third, the SOM network is used to fuse the selected degradation features to construct a one-dimensional HI curve. Finally, the exponential degradation model is selected as the degradation trajectory of HSSBs, and the Bayesian update and EM algorithm are used to predict the RUL of the HSSB. The monitoring data of a wind turbine HSSB in actual operation is used to validate the model. The HI curve constructed by the method in this paper can better reflect the degradation process of HSSBs. In terms of life prediction, the method in this paper has better prediction accuracy than the SVR model.

Data-driven dictionary design–based sparse classification method for intelligent fault diagnosis of planet bearings

Planet bearings have remained as the challenging components for health monitoring and diagnostics in the planetary transmission systems of helicopters and wind turbines, due to their intricate kinematic mechanisms, strong modulations, and heavy interferences from gear vibrations. To address intelligent diagnostics of planet bearings, this article presents a data-driven dictionary design–based sparse classification (DDD-SC) approach. DDD-SC is free of detecting the weak frequency features and can achieve reliable fault recognition performances for planet bearings without establishing any explicit classifiers. In the first step, DDD-SC implements the data-driven dictionary design with an overlapping segmentation strategy, which leverages the self-similarity features of planet bearing data and constructs the category-specific dictionaries with strong representation power. In the second step, DDD-SC implements the sparsity-based intelligent diagnosis with the sparse representation–based classification criterion and differentiates various planet bearing health states based on minimal sparse reconstruction errors. The effectiveness and superiority of DDD-SC for intelligent planet bearing fault diagnosis have been demonstrated with an experimental planetary transmission system. The extensive diagnosis results show that DDD-SC can achieve the highest diagnosis accuracy, strongest anti-noise performance, and lowest computation costs in comparison with three classical sparse representation–based classification and two advanced deep learning methods.

Remaining Useful Life Prognostics of Bearings Based on a Novel Spatial Graph-Temporal Convolution Network.

As key equipment in modern industry, it is important to diagnose and predict the health status of bearings. Data-driven methods for remaining useful life (RUL) prognostics have achieved excellent performance in recent years compared to traditional methods based on physical models. In this paper, we propose a novel data-driven method for predicting the remaining useful life of bearings based on a deep graph convolutional neural network with spatiotemporal domain convolution. This network uses the average sliding root mean square (ASRMS) as the health factor to identify the healthy and degraded states, and then uses correlation coefficient analysis on the hybrid features of the degraded data to construct a spatial graph according to the strength of the correlation between the obtained features. In the time domain, we introduce historical data as the input to the temporal convolution. After the data are processed by the spatial map and the temporal dimension, we perform the prediction of the remaining useful life. The experimental results show the accuracy of the method.