Fault Detection Of Rolling Element Bearings Research Articles

Automatic Feature Extraction Based on Envelope Analysis and its Application in Rolling-Element Bearing Fault Detection

Bearing fault diagnosis is essential for the maintenance, durability, and reliability of rotating machines. It can minimize economic losses by removing unplanned downtime in the industry due to the failure of rotary machines. In bearing fault detection, developing fault features extraction techniques that can successfully applicable for various fault severity and different operating conditions is still a critical issue. In the current work, the feature extraction technique is a combination between pre-processing algorithms and envelope analysis method. In the pre-processing stage, the autoregressive (AR) model is used to filter the original signal and remove the deterministic vibration sources, as well as maintain the signal representing the condition of the bearing without contaminating noises. Then, the most suitable frequency band is selected based on the spectral kurtosis (SK) analysis. This band contains the signature frequencies of the roller bearing. After that, envelope analysis is employed for detecting faults at different severity. Finally, the features represented the peaks at fundamental fault frequencies are automatically selected from the envelope spectrum. By analyzing all diagnoses results, it is found that the presented method effectively extracts the features at calculated resonance bearing frequencies and proves the significance of the enhancements in a pre-filtering stage in the overall detection performance. Also, it can benefit from these features in the fault classification fields at different speeds because it is independent of speed variation.

Development of Rolling Element Bearing Test Bench Facility And Application of Wavelet Transform for Fault Diagnosis

The aim of this experimental study is to develop an efficient rolling element bearing fault detection technique which could be effectively utilized for easy interpretation of bearing signal data. This paper deals with a new scheme for the diagnosis of localized defects in rolling element bearing based on Wavelet Transform. Vibration signal for healthy bearing, bearing with outer race fault, inner race fault and ball fault were acquired from a bearing test bench fabricated at Naval Institute of Aeronautical Technology, Kochi. The vibration signal was acquired using an accelerometer, control card and Data acquisition card. The acquired signal was further processed using a time frequency analysis technique known as Wavelet Transform. The experiments were carried out using different mother wavelets. However, defect features were best obtained using Complex Gaussian Wavelet of order 8, thereby rendering easier interpretation of the analysed data.

Expert Knowledge Induced Logic Tensor Networks: A Bearing Fault Diagnosis Case Study

In the recent past deep learning approaches have achieved some remarkable results in the area of fault diagnostics and anomaly detection. Nevertheless, these algorithms rely on large amounts of data, which is often not available, and produce outputs, which are hard to interpret. These deficiencies make real life applications difficult. Before the broad success of deep learning machine faults were often classified using domain expert knowledge based on experience and physical models. In comparison, these approaches only require small amounts of data and produce highly interpretable results. On the downside, however, they struggle to predict unexpected patterns hidden in data. Merging these two concepts promises to increase accuracy, robustness and interpretability of models. In this paper we present a hybrid approach to combine expert knowledge with deep learning and evaluate it on rolling element bearing fault detection. First, we create a knowledge base for fault classification derived from the expected physical attributes of different faults in the envelope spectrum of vibration signals. This knowledge is used to derive a similarity function for comparing input signals to expected faulty signals. Afterwards, the similarity measure is incorporated into different neural networks using a Logic Tensor Network (LTN). This enables logical reasoning in the loss function, in which we aim to mimic the decision process of an expert analyzing the input data. Further, we extend LTNs by weight schedules for axiom groups. We show that our approach outperforms the baseline models on two bearing fault data sets with different attributes and directly gives a better understanding of whether or not fault signals are influenced by other effects or behave as expected.

Detection of Rolling-Element Bearing Faults in Non-stationary Quasi-Parallel Machinery Using Residual Analysis Augmented by Neural Networks

This work proposes a methodology for the detection of rolling-element bearing faults in quasi-parallel machinery. In the context of this work, parallel machinery is considered to be any group of identical components of a mechanical system that are linked to operate on the same duty cycle. Quasi-parallel machinery can further be defined as two components not identical mechanically, but their operating conditions are correlated and they operate in the same environmental conditions. Furthermore, a new fault detection architecture is proposed wherein a feed-forward neural network (FFNN) is utilized to identify the relationship between signals. The proposed technique is based on the analysis of a calculated residual between feature vectors from two separate components. This technique is designed to reduce the effects of changes in the machines operating state on the condition monitoring system. When a fault detection system is monitoring multiple components in a larger system that are mechanically linked, signals and information that can be gleaned from the system can be used to reduce influences from factors that are not related to condition. The FFNN is used to identify the relationship between the feature vectors from two quasi-parallel components and eliminate the difference when no fault is present. The proposed method is tested on vibration data from two gearboxes that are connected in series. The gearboxes contain bearings operating at different speeds and gear mesh frequencies. In these conditions, a variety of rolling-element bearing faults are detected. The results indicate that improvement in fault detection accuracy can be achieved by using the additional information available from the quasi-parallel machine. The proposed method is directly compared to a typical AANN novelty detection scheme.

A Combined Short Time Fourier Transform and Image Classification Transformer Model for Rolling Element Bearings Fault Diagnosis in Electric Motors

The most frequent faults in rotating electrical machines occur in their rolling element bearings. Thus, an effective health diagnosis mechanism of rolling element bearings is necessary from operational and economical points of view. Recently, convolutional neural networks (CNNs) have been proposed for bearing fault detection and identification. However, two major drawbacks of these models are (a) their lack of ability to capture global information about the input vector and to derive knowledge about the statistical properties of the latter and (b) the high demand for computational resources. In this paper, short time Fourier transform (STFT) is proposed as a pre-processing step to acquire time-frequency representation vibration images from raw data in variable healthy or faulty conditions. To diagnose and classify the vibration images, the image classification transformer (ICT), inspired from the transformers used for natural language processing, has been suitably adapted to work as an image classifier trained in a supervised manner and is also proposed as an alternative method to CNNs. Simulation results on a famous and well-established rolling element bearing fault detection benchmark show the effectiveness of the proposed method, which achieved 98.3% accuracy (on the test dataset) while requiring substantially fewer computational resources to be trained compared to the CNN approach.

Deep Learning-Based Bearing Fault Diagnosis Method for Embedded Systems.

Bearing elements are vital in induction motors; therefore, early fault detection of rolling-element bearings is essential in machine health monitoring. With the advantage of fault feature representation techniques of time–frequency domain for nonstationary signals and the advent of convolutional neural networks (CNNs), bearing fault diagnosis has achieved high accuracy, even at variable rotational speeds. However, the required computation and memory resources of CNN-based fault diagnosis methods render it difficult to be compatible with embedded systems, which are essential in real industrial platforms because of their portability and low costs. This paper proposes a novel approach for establishing a CNN-based process for bearing fault diagnosis on embedded devices using acoustic emission signals, which reduces the computation costs significantly in classifying the bearing faults. A light state-of-the-art CNN model, MobileNet-v2, is established via pruning to optimize the required system resources. The input image size, which significantly affects the consumption of system resources, is decreased by our proposed signal representation method based on the constant-Q nonstationary Gabor transform and signal decomposition adopting ensemble empirical mode decomposition with a CNN-based method for selecting intrinsic mode functions. According to our experimental results, our proposed method can provide the accuracy for bearing faults classification by up to 99.58% with less computation overhead compared to previous deep learning-based fault diagnosis methods.

Condition monitoring analysis of rolling element bearing based on frequency envelope

In recent years, fault diagnosis analysis techniques and various methods are developed over a period of time, in that condition monitoring of rotating machinery equipment is of great concern in industries. These fault detection method and technique development for machinery can have a direct impact in cost optimization of maintenance in terms of millions of dollars. And in this type of fault analysis, the rolling element bearings in rotating machinery, play the critical role, because it lead to total system failure or production loses in the company by wearing the parts associated in the total system. In this paper, the condition monitoring analysis of rolling element bearing fault detection and analysis is done. To deal with the envelope of frequency factor is developed, as these is one of the main factor to study the various failure stage of the rolling element bearing can done for the frequency spectrum obtained for the machine. And in this approach were the each faults can be set for the frequency factor envelope, and can be used as the reference standards for the dealing with the machine faults.

A Novel Deep Learning Model for the Detection and Identification of Rolling Element-Bearing Faults.

Real-time acquisition of large amounts of machine operating data is now increasingly common due to recent advances in Industry 4.0 technologies. A key benefit to factory operators of this large scale data acquisition is in the ability to perform real-time condition monitoring and early-stage fault detection and diagnosis on industrial machinery—with the potential to reduce machine down-time and thus operating costs. The main contribution of this work is the development of an intelligent fault diagnosis method capable of operating on these real-time data streams to provide early detection of developing problems under variable operating conditions. We propose a novel dual-path recurrent neural network with a wide first kernel and deep convolutional neural network pathway (RNN-WDCNN) capable of operating on raw temporal signals such as vibration data to diagnose rolling element bearing faults in data acquired from electromechanical drive systems. RNN-WDCNN combines elements of recurrent neural networks (RNNs) and convolutional neural networks (CNNs) to capture distant dependencies in time series data and suppress high-frequency noise in the input signals. Experimental results on the benchmark Case Western Reserve University (CWRU) bearing fault dataset show RNN-WDCNN outperforms current state-of-the-art methods in both domain adaptation and noise rejection tasks.

Rolling element bearing fault detection based on the complex Morlet wavelet transform and performance evaluation using artificial neural network and support vector machine

Condition monitoring and fault diagnosis of rolling element bearings are very important to ensure proper working of different types of machinery. Condition monitoring of rotating machines is mainly based on the analysis of machine vibration. The vibration signals from the mechanical fault generally comprise periodic impulses with specified characteristic frequency corresponds to a particular defect. But due to heavy noise in the industry, the vibration signals have a very low signal-to-noise ratio. Hence, it requires an appropriate technique to extract the impulses from the noisy signal. This article emphasized on the fault diagnosis of rolling element bearings having some specific size of defects on various bearing elements using the complex Morlet wavelet analysis. The phase and amplitude map of the complex Morlet wavelet are utilized for identification and diagnosis of the fault in the rolling element bearing. The amplitude and phase map corresponding to the complex Morlet wavelet are found to show unique informative signatures in the presence of bearing faults. The classification technique based on artificial neural network and support vector machine for rolling element bearing fault detection is presented in this article. The classification results of bearing faults clearly indicate that support vector machine has a more precise bearing fault classification ability than artificial neural network.

A Novel Fault Detection Method for Rolling Bearings Based on Non-Stationary Vibration Signature Analysis.

To realize the accurate fault detection of rolling element bearings, a novel fault detection method based on non-stationary vibration signal analysis using weighted average ensemble empirical mode decomposition (WAEEMD) and modulation signal bispectrum (MSB) is proposed in this paper. Bispectrum is a third-order statistic, which can not only effectively suppress Gaussian noise, but also help identify phase coupling. However, it cannot effectively decompose the modulation components which are inherent in vibration signals. To alleviate this issue, MSB based on the modulation characteristics of the signals is developed for demodulation and noise reduction. Still, the direct application of MSB has some interfering frequency components when extracting fault features from non-stationary signals. Ensemble empirical mode decomposition (EEMD) is an advanced nonlinear and non-stationary signal processing approach that can decompose the signal into a list of stationary intrinsic mode functions (IMFs). The proposed method takes advantage of WAEEMD and MSB for bearing fault diagnosis based on vibration signature analysis. Firstly, the vibration signal is decomposed into IMFs with a different frequency band using EEMD. Then, the IMFs are reconstructed into a new signal by the weighted average method, called WAEEMD, based on Teager energy kurtosis (TEK). Finally, MSB is applied to decompose the modulated components in the reconstructed signal and extract the fault characteristic frequencies for fault detection. Furthermore, the efficiency and performance of the proposed WAEEMD-MSB approach is demonstrated on the fault diagnosis for a motor bearing outer race fault and a gearbox bearing inner race fault. The experimental results verify that the WAEEMD-MSB has superior performance over conventional MSB and EEMD-MSB in extracting fault features and has precise and effective advantages for rolling element bearing fault detection.

Mode determination in variational mode decomposition and its application in fault diagnosis of rolling element bearings

The non-stationary nature of bearing vibrations makes it difficult to extract features from the real-time signature of faulty rolling element bearings (REBs). The present work suggests to improve the diagnostic accuracy of fault detection in REBs by enhancing the mode selection property of variational mode decomposition, manipulating its initialization and input parameters (bandwidth selection parameter, $$\alpha$$ and the number of modes, $$k$$ ) and then extracting energy entropy features and using cross-validation in support vector machine (SVM) classifier. The alpha values and the number of modes are varied from (100, 1000000) and (4, 10), respectively. Mean absolute error (MAE) is used as the indicator which calculates error values obtained between the respective sum of modes and the original signal. The particular $$\alpha - k$$ combination with the least MAE value is chosen. The above method is tested using REB signals obtained from the bearing prognostics test rig. The results obtained from the proposed approach shows 100% diagnostic accuracy in detecting faulty REB vibration signature using five-fold cross-validation in SVM classifier.

Particle swarm optimization algorithm to solve the deconvolution problem for rolling element bearing fault diagnosis

Extraction of the fault related impulses from the raw vibration signal is important for rolling element bearing fault diagnosis. Deconvolution techniques, such as minimum entropy deconvolution (MED), MED adjusted (MEDA) and maximum correlated kurtosis deconvolution (MCKD), optimal MED adjusted (OMEDA) and multipoint optimal MED adjusted (MOMEDA), are typical techniques for enhancing the impulse-like component in the fault signal. This paper introduces the particle swarm optimization (PSO) algorithm to solve the filter of deconvolution problem. The proposed approaches solve the filter coefficients of the deconvolution problems by the PSO algorithm, assisted by a generalized spherical coordinate transformation. Compared with MED, MEDA, and OMEDA, the proposed PSO-MED and PSO-OMEDA can effectively overcome the influence of large random impulses and tend to deconvolve a series of periodic impulses rather than a signal impulse. Compared with MCKD and MOMEDA, the proposed PSO-MCKD and PSO-MOMEDA can achieve good performances even when the fault period is inaccurate. The effectiveness of the proposed methods is validated by the simulated signals. The study of experimental bearing fault signal shows that the PSO based deconvolution methods delivered better performance for rolling element bearing fault detection than the traditional deconvolution methods. Additionally, the proposed methods are compared with the following two popular signal processing methods: the ensemble empirical mode decomposition (EEMD) and fast kurtogram, which are used to highlight the improved performance of the proposed methods.

An enhanced morphology gradient product filter for bearing fault detection

Abstract This paper presents a signal processing scheme, namely enhanced morphology gradient product filter (EMGPF), for rolling element bearing fault detection. In this scheme, a morphology gradient product operation (MGPO) is firstly proposed to extract impulsive features of a raw signal according to a comprehensive investigation of the working mechanism of the reported morphological operations. Then, a higher-order spectrum analysis method, the third-order cumulant slice spectrum, is used to improve the performance of the MGPO based morphology filter for the purpose of highlighting fault features further. Experimental vibration signals were employed to evaluate the effectiveness of the proposed EMGPF. Results show that the proposed method has a superior performance in extracting fault features of defective rolling element bearing over four reported morphology filters.

Development of a morphological convolution operator for bearing fault detection

This paper presents a novel signal processing scheme, namely morphological convolution operator (MCO) lifted morphological undecimated wavelet (MUDW), for rolling element bearing fault detection. In this scheme, a MCO is first designed to fully utilize the advantage of the closing & opening gradient operator and the closing–opening & opening–closing gradient operator for feature extraction as well as the merit of excellent denoising characteristics of the convolution operator. The MCO is then introduced into MUDW for the purpose of improving the fault detection ability of the reported MUDWs. Experimental vibration signals collected from a train wheelset test rig and the bearing data center of Case Western Reserve University are employed to evaluate the effectiveness of the proposed MCO lifted MUDW on fault detection of rolling element bearings. The results show that the proposed approach has a superior performance in extracting fault features of defective rolling element bearings. In addition, comparisons are performed between two reported MUDWs and the proposed MCO lifted MUDW. The MCO lifted MUDW outperforms both of them in detection of outer race faults and inner race faults of rolling element bearings.

Detection of Bearing Faults Using a Novel Adaptive Morphological Update Lifting Wavelet

The current morphological wavelet technologies utilize a fixed filter or a linear decomposition algorithm, which cannot cope with the sudden changes, such as impulses or edges in a signal effectively. This paper presents a novel signal processing scheme, adaptive morphological update lifting wavelet (AMULW), for rolling element bearing fault detection. In contrast with the widely used morphological wavelet, the filters in AMULW are no longer fixed. Instead, the AMULW adaptively uses a morphological dilation-erosion filter or an average filter as the update lifting filter to modify the approximation signal. Moreover, the nonlinear morphological filter is utilized to substitute the traditional linear filter in AMULW. The effectiveness of the proposed AMULW is evaluated using a simulated vibration signal and experimental vibration signals collected from a bearing test rig. Results show that the proposed method has a superior performance in extracting fault features of defective rolling element bearings.

A robust detector for rolling element bearing condition monitoring based on the modulation signal bispectrum and its performance evaluation against the Kurtogram

Envelope analysis is a widely used method for rolling element bearing fault detection. To obtain high detection accuracy, it is critical to determine an optimal frequency narrowband for the envelope demodulation. However, many of the schemes which are used for the narrowband selection, such as the Kurtogram, can produce poor detection results because they are sensitive to random noise and aperiodic impulses which normally occur in practical applications. To achieve the purposes of denoising and frequency band optimisation, this paper proposes a novel modulation signal bispectrum (MSB) based robust detector for bearing fault detection. Because of its inherent noise suppression capability, the MSB allows effective suppression of both stationary random noise and discrete aperiodic noise. The high magnitude features that result from the use of the MSB also enhance the modulation effects of a bearing fault and can be used to provide optimal frequency bands for fault detection. The Kurtogram is generally accepted as a powerful means of selecting the most appropriate frequency band for envelope analysis, and as such it has been used as the benchmark comparator for performance evaluation in this paper. Both simulated and experimental data analysis results show that the proposed method produces more accurate and robust detection results than Kurtogram based approaches for common bearing faults under a range of representative scenarios.

A new strategy of using a time-varying structure element for mathematical morphological filtering

This paper presents a novel signal processing scheme, namely time-varying morphological filtering (TMF), for rolling element bearing fault detection. In contrast with the multiscale morphological filtering (MMF) method, the structure element (SE) used in TMF is no longer fixed. It adjusts adaptively according to the extreme points of a signal so that the raw signal can be fit more accurately. In addition, the MMF needs to execute morphological operations multiple times, whereas the TMF can finish the filtering in one time operation. Consequently, TMF has a significant advantage in terms of computation efficiency. Experimental vibration signals collected from a bearing test rig are employed to evaluate the effectiveness of TMF. The results show that the proposed method can extract fault features of defective rolling element bearings with high computational efficiency. Moreover, five SEs are compared for TMF. The results show that the Dolph-Chebyshev SE performs best.

Recurrence Plot Based Damage Detection Method by Integrating Control Chart

Because of the importance of damage detection in manufacturing systems and other areas, many fault detection methods have been developed that are based on a vibration signal. Little work, however, has been reported in the literature on using a recurrence plot method to analyze the vibration signal for damage detection. In this paper, we develop a recurrence plot based fault detection method by integrating the statistical process control technique. The recurrence plots of the vibration signals are derived by using the recurrence plot (RP) method. Five types of features are extracted from the recurrence plots to quantify the vibration signals’ characteristic. Then, the control chart, a multivariate statistical process control technique, is used to monitor these features. The control chart technique, however, has the assumption that all the data should follow a normal distribution. The RP based bootstrap control chart is proposed to estimate the control chart parameters. The performance of the proposed RP based bootstrap control chart is evaluated by a simulation study and compared with other univariate bootstrap control charts based on recurrence plot features. A real case study of rolling element bearing fault detection demonstrates that the proposed fault detection method achieves a very good performance.

Rolling element bearing fault detection using support vector machine with improved ant colony optimization

In support vector machine (SVM), it is quite necessary to optimize the parameters which are the key factors impacting the classification performance. Improved ant colony optimization (IACO) algorithm is proposed to determine the parameters, and then the IACO-SVM algorithm is applied on the rolling element bearing fault detection. Both the optimal and the worst solutions found by the ants are allowed to update the pheromone trail density, and the mesh is applied in the ACO to adjust the range of optimized parameters. The experimental data of rolling bearing vibration signal is used to illustrate the performance of IACO-SVM algorithm by comparing with the parameters in SVM optimized by genetic algorithm (GA), cross-validation and standard ACO methods. The experimental results show that the proposed algorithm of IACO-SVM can give higher recognition accuracy.

Improved spectral kurtosis with adaptive redundant multiwavelet packet and its applications for rotating machinery fault detection

Rotating machinery fault detection is significant to avoid serious accidents and huge economic losses effectively. However, due to the vibration signal with the character of non-stationarity and nonlinearity, the detection and extraction of the fault feature turn into a challenging task. Therefore, a novel method called improved spectral kurtosis (ISK) with adaptive redundant multiwavelet packet (ARMP) is proposed for this task. Spectral kurtosis (SK) has been proved to be a powerful tool to detect and characterize the non-stationary signal. To improve the SK in filter limitation and enhance the resolution of spectral analysis as well as match fault feature optimally, the ARMP is introduced into the SK. Moreover, since kurtosis does not reflect the actual trend of periodic impulses, the SK is improved by incorporating an evaluation index called envelope spectrum entropy as supplement. The proposed method is applied to the rolling element bearing and gear fault detection to validate its reliability and effectiveness. Compared with the conventional frequency spectrum, envelope spectrum, original SK and some single wavelet methods, the results indicate that it could improve the accuracy of frequency-band selection and enhance the ability of rotating machinery fault detection.