Bearing Fault Identification Research Articles

Enhanced hierarchical symbolic dynamic entropy and maximum mean and covariance discrepancy-based transfer joint matching with Welsh loss for intelligent cross-domain bearing health monitoring

Domain adaptation (DA) as a critical and valuable tool is devoted to minimizing the distribution discrepancy across domains, which has been successfully utilized in intelligent bearing health monitoring. In particular, transfer joint matching (TJM) is a promising transfer learning strategy, especially when the domains differ considerably. In the TJM, the maximum mean discrepancy (MMD) is usually employed to assess the discrepancy of distributions in reproducing kernel Hilbert space (RKHS). However, the MMD has been proved to lose some useful statistical information in the RKHS. Hence, an improved TJM approach, called maximum mean and covariance discrepancy-based transfer joint matching with Welsh loss (MMCD-WTJM), is proposed in this article. In MMCD-WTJM, maximum mean and covariance discrepancy (MMCD) instead of MMD is incorporated into the TJM to match more statistical information in RKHS. Meanwhile, the Welsh loss function is incorporated into the TJM to enhance the stability of the model. Besides, we develop enhanced hierarchical symbolic dynamic entropy (EHSDE) to extract a more useful feature representation. Eventually, a novel hybrid cross-domain bearing fault identification based on EHSDE and MMCD-WTJM is developed. The analysis results of eight transfer bearing fault identification tasks demonstrate that the developed approach has an excellent capacity in intelligent bearing health monitoring under varying operation conditions and different machines. Compared with the existing entropy-based fault feature extraction approaches and domain adaptation-based transfer fault diagnosis methods, the presented bearing health monitoring scheme has remarkable strengths in recognition accuracy.

Fault diagnosis of wind turbine bearing based on CNN-XGBoost

When a wind turbine bearing fails, because the fault signal shows the characteristics of instability and non-linearity,it is difficult to extract the fault features artificially, resulting in a lower accuracy of the wind turbine bearing fault classification. In order to realize the automatic extraction of wind turbine bearing faults and improve the accuracy of fault classification, this paper proposes a wind turbine bearing fault identification method based on the combination of convolutional neural network and limit gradient lifting algorithm. First, convert the original bearing fault signal into a grayscale image. Then, the gray image is input to the convolutional neural network to automatically extract the feature of the fault. Finally, the limit gradient boosting algorithm optimized by the grid search algorithm is used as a classifier to classify the fault. The simulation results show that the method used in this paper can achieve a high rate of correctness of wind turbine bearing fault identification, indicating that this method is effective for wind turbine bearing fault diagnosis.

Bearing Fault Identification Based on Deep Convolution Residual Network

Bearings are important parts in industrial production and are related to the normal operation of mechanical equipment. For bearing fault identification， traditional method often includes feature extraction, which involves professional prior knowledge and is time-consuming. This paper proposes the deep convolution residual network (DCRN) to identify the bearing fault. Based on the end-to-end learning characteristics of deep neural networks, this method can directly use raw data for training, and does not require feature extraction. Moreover, under the effect of skip connection, DCRN can exert the powerful fitting ability of deep neural network. In this paper, by stacking residual blocks, three different architecture of DCRN are designed and all three achieve very high accuracy, respectively 99.60%, 99.71% and 99.81%. Compared with other methods, DCRN have better generalization performance.

Order-Based Identification of Bearing Defects under Variable Speed Condition

Condition monitoring of rotating machinery plays an important role in reducing catastrophic failures and production losses in the 4.0 Industry. Vibration analysis has proven to be effective in diagnosing rotating machine failures. However, identifying bearing defects based on vibration analysis remains a difficult task, especially in non-stationary operation conditions. This work aims to automate the process of identifying bearing defects under variable operating speeds. Based on an order analysis technique, three frequency domain features: Spectrum peak Ratio Outer (SPRO), Spectrum peak Ratio Inner (SPRI), and Spectrum peak Ratio Rolling element (SPRR) are updated to perform with non-stationary signals. The updated features are extracted from vibration data of a real ball bearing system. They are retained to build a predictive multi-kernel support vector machine (MSVM) classification model. Therefore, the effectiveness of the proposed features is evaluated based on the performance of the constructed classifier. The updated features deployed have proven their effectiveness in identifying bearing: outer race, inner race, ball, and combined defects under variable speed conditions.

Bearing defect identification via evolutionary algorithm with adaptive wavelet mutation strategy

The vibration signals obtained from the bearings are associated with nonlinear and nonstationary characteristics, which hinder the fault identification of the bearing. A scheme of fault identification is proposed to identify the faults in bearing in this paper. The vibration signal first pre-processed by wavelet packet transform, followed by Hilbert-Huang transform, decomposes the reconstructed signal into the IMFs. The L-moment criterion is used to select a prominent IMF. The prominent IMF is further utilized to extract the features from the processed signal. The dataset prepared from features trains the SVM model. A novel optimization technique viz 'Diversity driven multi-parent evolutionary algorithm with adaptive wavelet mutation' is proposed to optimize the SVM parameters to increase its efficiency. The efficacy of the proposed algorithm is tested against benchmark functions; obtained results proved its effectiveness. The overall accuracy of built SVM is found to be 100% with suitable regularization and kernel parameter values.

Bearing defect identification by swarm decomposition considering permutation entropy measure and opposition-based slime mould algorithm

An intelligent defect identification scheme has been proposed to identify the taper roller bearing defects through the extreme learning machine (ELM) model. The raw vibration signal from the bearing test rig is decomposed into different modes by Swarm decomposition (SWD) method to remove noise. The permutation entropy (PE) is taken as a measurement index to select the prominent mode. Features sensitive to defect conditions are extracted from prominent mode using a filter-based relief algorithm. The ranking of fault features is done on the score values. An opposition-based slime mould algorithm is investigated for finding the optimal parameters (weight connecting the input layer with output layer; and biases in hidden neurons) of ELM. Using optimized ELM parameters, the classification model is built. Test data evaluate the fitness of the built ELM model. Both the training and testing accuracy are 100%, with a computation time of 0.0023 s.

Research on Bearing Intelligent Diagnostic Technology Based on EMD and GA-BP

Bearings are the core components of rotating machinery and can have a significant impact on the equipment in the event of a failure. In this paper, an intelligent diagnostic technique based on the combination of EMD and GA-BP algorithm sifts with the rolling bearing fault identification and classification problem. First, the test data is processed by EMD method, the characteristic enhancement and extraction of micro-faults is realized, and the bearings are trouble shoot as training sets and test sets of BPNNs optimized by the built GA. The results show that the accuracy and convergence speed of this method are improved compared with the method of unutilized energy characteristics, and the identification and diagnosis of bearing fault can be effectively carried out.

Order-statistic filtering Fourier decomposition and its application to rolling bearing fault diagnosis

Inspired by the empirical wavelet transform method, a newly nonstationary signal analysis method–termed order-statistic filtering Fourier decomposition is proposed in this article. First, order-statistic filtering Fourier decomposition uses order-statistic filtering and smoothing to preprocess the Fourier spectrum of original signal, which resolves the problem of unreasonable boundaries obtained by empirical wavelet transform in segmenting the Fourier spectrum. Then, the mono-components with physical significance are obtained by adaptively reconstructing the coefficient of fast Fourier transform in each interval, which improves the problem of too many false components obtained by Fourier decomposition method. The order-statistic filtering Fourier decomposition method is compared with the existing nonstationary signal decomposition methods including empirical mode decomposition, empirical wavelet transform, Fourier decomposition method, and variational mode decomposition through analyzing simulation signals, and the result indicates that order-statistic filtering Fourier decomposition is much more accurate and reasonable in obtaining mono-components. After that, the order-statistic filtering Fourier decomposition method is compared with the mentioned methods in diagnostic accuracy through analyzing the tested faulty bearing vibration signals and the effectiveness of order-statistic filtering Fourier decomposition to the comparative methods in bearing fault identification are verified.

A Rolling Bearing Fault Classification Scheme Based on k-Optimized Adaptive Local Iterative Filtering and Improved Multiscale Permutation Entropy

The health condition of the rolling bearing seriously affects the operation of the whole mechanical system. When the rolling bearing parts fail, the time series collected in the field generally shows strong nonlinearity and non-stationarity. To obtain the faulty characteristics of mechanical equipment accurately, a rolling bearing fault detection technique based on k-optimized adaptive local iterative filtering (ALIF), improved multiscale permutation entropy (improved MPE), and BP neural network was proposed. In the ALIF algorithm, a k-optimized ALIF method based on permutation entropy (PE) is presented to select the number of ALIF decomposition layers adaptively. The completely average coarse-graining method was proposed to excavate more hidden information. The performance analysis of the simulation signal shows that the improved MPE can more accurately dig out the depth information of the time series, and the entropy value obtained is more consistent and stable. In the research application, rolling bearing time series are decomposed by k-optimized ALIF to obtain a certain number of intrinsic mode functions (IMFs). Then the improved MPE value of effective IMF is calculated and input into backpropagation (BP) neural network as the feature vector for automatic fault identification. The comparative analysis of simulation signals shows that this method can extract fault information effectively. At the same time, the experimental part shows that this scheme not only effectively extracts the fault features, but also realizes the classification and identification of different fault modes and faults of different degrees, which has a certain application prospect in the research and application direction of rolling bearing fault identification.

Research on bearing diagnosis technology based on wavelet transform and one-dimensional convolutional neural network

Aiming at the fault diagnosis of rolling element bearings, propose a method for fine diagnosis of bearings based on wavelet transform and one-dimensional convolutional neural network. First use wavelet transform to decompose the experimental data; Use the resulting low-frequency signal as a one-dimensional convolutional neural network input, bearing fault identification. The experiment uses the deep groove ball bearing of Case Western Reserve University as the research object, Use this method to identify the normal and outer ring faults of the bearing. the result shows: This method can be effectively applied to the precise identification of bearings.

Efficient Data Reduction at the Edge of Industrial Internet of Things for PMSM Bearing Fault Diagnosis

An efficient data reduction algorithm is designed and implemented on an industrial Internet of Things (IIoT) node for permanent magnet synchronous motor (PMSM) bearing fault diagnosis in variable speed conditions. Leakage flux and vibration signals are, respectively, acquired by a magnetic sensor and an accelerometer on the IIoT node in a noninvasive manner. These two signals are processed and mixed on the IIoT and transmitted to a server. The received signal is separated, the cumulative rotation angle is calculated, and the vibration signal is resampled for bearing fault identification. The proposed method can reduce about 95% of the transmission data while maintaining sufficient precision in bearing fault diagnosis in comparison to a traditional method. The proposed method based on edge computing reduces the power consumption, and hence it is suitable to use on a battery-supplied IIoT node for remote PMSM condition monitoring and fault diagnosis.

A Method for Constructing Automatic Rolling Bearing Fault Identification Model Based on Refined Composite Multi-Scale Dispersion Entropy

In this paper, one of most widely utilized rolling bearings in rotating machinery is selected as the research object. Automatic rolling bearing fault identification model including support vector machine (SVM) training module, fault classification knowledge base module, and fault automatic identification module is proposed. A generalized method for automatic identification of rolling bearing faults based on refined composite multi-scale dispersion entropy (RCMDE) is developed. First, in order to solve the problem of setting the value range of the decomposition level K based on empirical knowledge for variational modal decomposition (VMD), a maximum kurtosis value method is proposed to determine the preset value range of K in whale optimization algorithm. Then, an improved VMD method is used to adaptively decompose the signal into a series of intrinsic mode function components. Next, the correlation coefficient method is employed to screen effective feature components of bearings in different health states for reconstruction. Through theoretical analysis, the calculated RCMDE value of reconstructed signal is screened and input as a feature value into the optimized SVM classifier for fault pattern recognition. The input of rolling bearing vibration data without preprocessing and the output of the fault identification which don't rely on empirical knowledge of external experts is realized. Experimental and engineering case data of rolling bearings under different equipment and operating environments are tested and validated. The results indicate that the model proposed in this paper shows good fault identification, demonstrates good generalization performance, and has beneficial industrial application prospect.

Rolling bearing fault diagnosis based on feature fusion with parallel convolutional neural network

Deep learning has seen increased application in the data-driven fault diagnosis of manufacturing system components such as rolling bearing. However, deep learning methods often require a large amount of training data. This is a major barrier in particular for bearing datasets whose sizes are generally limited due to the high costs of data acquisition especially for fault scenarios. When small datasets are employed, over-fitting may occur for a deep learning network with many parameters. To tackle this challenge, in this research, we propose a new methodology of parallel convolutional neural network (P-CNN) for bearing fault identification that is capable of feature fusion. Raw vibration signals in the time domain are divided into non-overlapping training data slices, and two different convolutional neural network (CNN) branches are built in parallel to extract features in the time domain and in the time-frequency domain, respectively. Subsequently, in the merged layer, the time-frequency features extracted by continuous wavelet transform (CWT) are fused together with the time-domain features as inputs to the final classifier, thereby enriching feature information and improving network performance. By incorporating empirical feature extraction such as CWT, this proposed method can effectively enable deep learning even with dataset size limitation in practical bearing diagnosis. The algorithm is validated through case studies on publicly accessible experimental rolling bearing datasets. A wide range of dataset sizes is tested with cross-validation, and influencing factors on network performance are discussed. Compared with existing methods, the proposed approach not only possesses higher accuracy but also exhibits better stability and robustness as training dataset sizes and load conditions vary. The concept of feature fusion through P-CNN can be extended to other fault diagnosis applications in manufacturing systems.

An integrated machine learning: Utility theory framework for real-time predictive maintenance in pumping systems

Bearings are the most widely used mechanical parts in rotating machinery under high load and high rotational speeds. Operating continuously under such harsh conditions, wear and failure are imminent. Developing defects give rise to even-higher vibration and temperature levels. In general, mechanical defects in a machine cause high vibration levels. Therefore, bearing fault identification and early detection enables the maintenance team to repair the problem before it triggers catastrophic failure in the bearing. Machine downtime is thus avoided or minimized. This paper explores the use of Machine Learning (ML) integrated with decision-making techniques to predict possible bearing failures and improve the overall manufacturing operations by applying the correct maintenance actions at the right time. The accuracy of the Predictive Maintenance (PdM) module has been tested on real industrial production datasets. The paper proposes an effective PdM methodology using different ML algorithms to detect failures before they happen and reduce pump downtime. The performance of the tested ML algorithms is based on five performance indicators: accuracy, precision, F-score, recall, and an area under curve (AUC). Experimental results revealed that all tested ML algorithms are successful and effective. Furthermore, decision making with utility theory has been employed to exploit the probability of failures and thus help to perform the appropriate maintenance interventions. This provides a logical framework for decision-makers to identify the optimum action with the maximum expected benefit. As a case study, the model is applied on forwarding pumping stations belonging to the Sewerage Treatment Company (STC), one of the largest sewage stations in Qatar.

A Weight Multinet Architecture for Bearing Fault Classification Under Complex Speed Conditions

As a key component in rotating mechanical, fault identification of bearing is a hot topic for machine health condition monitoring. Considering that the corresponding vibration features are seriously influenced by working conditions, the existed classification methods have a high false-positive rate under complex working conditions. Especially, because there is a difference among feature distribution of the measured signals under different speed conditions, the fault identification under uncertain speed conditions is still a big challenge for the fault diagnosis schemes based on expert experience and intelligent fault identification method. Therefore, this study proposes a weight multinet (WMN) architecture, which consists of multiple net units. Different from other traditional networks, the exclusive characteristics of fault information will be mined via a multiclass identification unit, and the vital information related to speed condition will be remained by a weight unit. Then, these fault information with different directivity will be integrated into a fusion unit. Finally, the wavelet packet (WP) energy ratios of vibration signals are extracted and put into this special architecture of neural network with three function units, and the effect of fault classification under unknown speed conditions can be significantly improved. Comparisons of clustering distribution and classification accuracy with other typical methods show the feasibility and effectiveness of the proposed WMN method in the application of fault identification under uncertain speed conditions.

Novel Fault Identification for Electromechanical Systems via Spectral Technique and Electrical Data Processing

It is proposed, developed, investigated, and validated by experiments and modelling for the first time in worldwide terms new data processing technologies, higher order spectral multiple correlation technologies for fault identification for electromechanical systems via electrical data processing. Investigation of the higher order spectral triple correlation technology via modelling has shown that the proposed data processing technology effectively detects component faults. The higher order spectral triple correlation technology successfully applied for rolling bearing fault identification. Experimental investigation of the technology has shown, that the technology effectively identifies rolling bearing fault by electrical data processing at very early stage of fault development. Novel technology comparisons via modelling and experiments of the proposed higher order spectral triple correlation technology and the higher order spectra technology show the higher fault identification effectiveness of the proposed technology over the bicoherence technology.

Dynamic characteristics of ball bearing with flexible cage lintel and wear

In view of the practical problem of wear on the cage pocket, which is unavoidable during the operation of high-speed ball bearing, a dynamic model of high-speed ball bearing with flexible cage lintel was established considering the cage-pocket wear loss (BPWL), the gravity, drag force from the oil, and the hydrodynamic effect on the cage, and then, the dynamic simulations with different amounts of BPWL were obtained by solving the ball bearing dynamic equations using varying steps Runge-Kutta integration. The effect of the BPWL on the trajectory of the cage’s centroid and cage skidding ratio were obtained. The computational results show that the trajectory of the cage’s centroid presents two vibration modes with different amplitudes. And the two different forms of trajectories of different amplitudes emerge alternatively with BPWL increase. Moreover, the diameter of the trajectory decreases significantly with the BPWL increasing which is consistent with the experimental result. The change of the BPWL has little effect on the average skidding ratio of the cage; however, the fluctuation amplitude would become larger as BPWL increase. This study can provide important ideas for the design of bearing cage pocket size and the fault identification of the ball bearing.

Bearing Fault Identification Using Machine Learning and Adaptive Cascade Fault Observer

In this work, a hybrid procedure for bearing fault identification using a machine learning and adaptive cascade observer is explained. To design an adaptive cascade observer, the normal signal approximation is the first step. Therefore, the fuzzy orthonormal regressive (FOR) technique was developed to approximate the acoustic emission (AE) and vibration (non-stationary and nonlinear) bearing signals in normal conditions. After approximating the normal signal of bearing using the FOR technique, the adaptive cascade observer is modeled in four steps. First, the linear observation technique using a FOR proportional-integral (PI) observer (FOR-PIO) is developed. In the second step, to increase the power of uncertaintie rejection (robustness) of the FOR-PIO, the structure procedure is used serially. Next, the fuzzy like observer is selected to increase the accuracy of FOR structure PI observer (FOR-SPIO). Moreover, the adaptive technique is used to develop the reliability of the cascade (fuzzy-structure PI) observer. Additionally to fault identification, the machine-learning algorithm using a support vector machine (SVM) is recommended. The effectiveness of the adaptive cascade observer with the SVM fault identifier was validated by a vibration and AE datasets. Based on the results, the average vibration and AE fault diagnosis using the adaptive cascade observer with the SVM fault identifier are 97.8% and 97.65%, respectively.

Hierarchical multiscale permutation entropy-based feature extraction and fuzzy support tensor machine with pinball loss for bearing fault identification

Recently, tensor learning has been applied to intelligent bearing health monitoring successfully. In the past tensor learning based fault identification approaches, the clipped time–frequency images (TFIs) are usually taken as the input tensor data. However, the manual clipping method is usually used to reduce the dimension of TFIs, which may easily lose some critical fault information. Hence, we present hierarchical multiscale permutation entropy (HMPE) as a new feature representation method to avert this drawback from the perspective of statistical measure. In practice, the extracted fault feature (HMPE) may often be corrupted by noise. Hence, fuzzy support tensor machine with pinball loss (Pin-FSTM) as a new tensor-based classifier is developed, which can reduce noise sensitivity and minimize classification errors. Finally, a novel bearing health monitoring strategy based on HMPE and Pin-FSTM is presented, which has been demonstrated to have an excellent identification performance through two experiments. Compared with the state-of-the-art permutation entropy-based fault identification algorithms, the presented scheme is more superior in accuracy and stability. Besides, this research provides a new direction for tensor learning further applying in bearing health monitoring.

Bearing fault identification based on convolutional neural network by different input modes

Convolutional neural networks (CNNs) have been applied to the field of fault diagnosis as one of the most widely used deep learning architectures. Different input modes of CNN for bearing fault identification were analyzed by researchers to improve recognition accuracy, such as time-domain diagram, grayscale diagram, short-time Fourier transform diagram, and continuous wavelet transform diagram. However, for the data with small sample size and high background noise, the performance of the CNN is constrained. In this paper, one CNN input mode for bearing fault recognition is proposed based on time-domain color feature diagram (TDCF) through adding red color to diagrams. The method significantly enhanced the fault characteristics of the signal, which is beneficial to the CNN extraction of bearing fault features. Convolution visualization illustrates the effectiveness of the proposed method that provides more bearing fault recognition information. Different sample size and color rate were analyzed by bearing vibration data with high noise. The results showed that the bearing fault identification method based on CNN with 0.4 TDCF obtained a highest fault identification accuracy compared with other input mode methods. The feasibility of the proposed method has been validated, which also provides one reference for other faults identification and pattern recognition.