Vibration-based Fault Diagnosis Research Articles

Fault Feature Extraction Based on Variational Modal Decomposition and Lifting Wavelet Transform: Application in Gear of Mine Scraper Conveyor Gearbox

Vibration-based fault diagnosis of chain conveyor gearboxes is challenging under high load and strong shock conditions. This paper applies motor current characteristic analysis technology to scraper conveyor gearbox fault diagnosis and proposes a fault feature extraction method. Firstly, a variational mode decomposition algorithm combined with a genetic algorithm is used to divide the original current signal into several sub-bands with different frequency modulation information, and irrelevant information is preliminarily eliminated. Secondly, an intrinsic mode function (IMF) sub-band fault information extraction method based on lifting wavelet transform is proposed. The minimum entropy value is used to set the sensitive parameters involved in lifting wavelet transform, and the power supply current frequency and noise interference information of a scraper conveyor are removed from the current signal. Finally, it is proved that variational mode decomposition combined with lifting wavelet transform can effectively diagnose the fault of a scraper conveyor by comparative experiments.

Enhanced domain transfer deep fuzzy echo state network for rotating machinery fault diagnosis based on current signal

Although vibration-based fault diagnosis methods have achieved remarkable results in rotating machinery, they are still limited by various factors, such as environment noise and additional sensor installation. Meanwhile, due to inevitable distribution differences in practical engineering, deep transfer learning models are commonly used in fault diagnostic fields. Although deep architectures can extract representative domain-invariant features, they typically result in substantial computational burdens and training time. Therefore, to address the above problems, an enhanced domain transfer deep fuzzy echo state network (EDFESN) is proposed for rotating machinery fault diagnosis based on current signals. Firstly, current signals derived from the driving motor are directly collected without additional sensors. Secondly, an enhanced domain mapping method is raised to solve the problem of data distribution discrepancies between cross domain. Furthermore, a deep fuzzy echo state network (DFESN) integrated with fuzzy clustering is constructed, which utilizes layer-wise fuzzy-tuning learning paradigm instead of backpropagation step to reduce training time. Two datasets from gearbox and bearing both verify the effectiveness of the proposed method. Compared with other popular transfer methods, EDFESN not only achieves highest accuracy, but also has fastest training speed.

Exploring evolutionary-tuned autoencoder-based architectures for fault diagnosis in a wind turbine gearbox

ABSTRACT Vibration-based fault diagnosis from rotary machinery requires prior feature extraction, feature selection, or dimensionality reduction. Feature extraction is tedious, and computationally expensive. Feature selection presents unique challenges intrinsic to the method adopted. Nonlinear dimensionality reduction may be achieved through kernel transformations, however there is often a trade-off in information to achieve this. Given the above, this study proposes a novel autoencoder (AE) pre-processing framework for vibration-based fault diagnosis in wind turbine (WT) gearboxes. In this study, AEs are used to learn the features of WT gearbox vibration data while simultaneously compressing the data, obviating the need for costly feature engineering and dimensionality reduction. The effectiveness of the proposed framework was evaluated by training genetically optimized linear discriminant analysis (LDA), multilayer perceptron (MLP), and random forest (RF) models, with the AE’s latent space features. The models were evaluated using known classification metrics. The results showed that the performance of the models depends on the size of the AE’s latent space. As the size of the AE’s latent space increased, the quality of features extracted improved until a plateau was observed at a latent space dimension of 10. The AE pre-processed genetically optimized RF, MLP, and LDA models, designated AE-Pre-GO-RF, AE-Pre-GO-MLP, and AE-Pre-GO-LDA, were evaluated for accuracy, sensitivity, and specificity in the classification of seven (7) gearbox fault conditions. The AE-Pre-GO-RF model outperformed its counterparts, scoring 100% for all evaluated metrics, though with the longest training time (239.50 sec). Comparable results were found comparing this study with similar investigations involving traditional vibration processing techniques. More so, it was established that effective fault diagnosis of the WT gearbox can be achieved through manifold learning with AEs without expensive feature engineering.

Vibration-Based Fault Diagnosis for Railway Point Machines Using VMD and Multiscale Fluctuation-Based Dispersion Entropy

Vibration-Based Fault Diagnosis for Railway Point Machines Using VMD and Multiscale Fluctuation-Based Dispersion Entropy

A Comprehensive 3-Steps Methodology for Vibration-based Fault Detection, Diagnosis and Localization in Rotating Machines

In any industry, it is the requirement to know whether the machine is healthy or not to operate machine further. If the machine is not healthy then what is the fault in the machine and then finally its location. The paper is proposing a 3-steps methodology for the machine fault diagnosis to meet the industrial requirements to aid the maintenance activity. The Step-1 identifies whether machine is healthy or faulty, then Step-2 detect the type of defect and finally its location in Step-3. This method is extended further from the earlier study on the 2-Steps method for the rotor defects only to the 3-Steps methodology to both rotor and bearing defects. The method uses the optimised vibration parameters and a simple Artificial Neural Network (ANN)-based Machine Learning (ML) model from the earlier studies. The model is initially developed, tested and validated on an experimental rotating rig operating at a speed above 1st critical speed. The proposed method and model are then further validated at 2 different operating speeds, one below 1st critical speed and other above 2nd critical speeds. The machine dynamics are expected to be significantly different at these speeds. This highlights the robustness of the proposed 3-Steps method. Conflict of Interest Statement The authors declare no conflicts of interest.

An adaptive reweighted-Kurtogram for bearing fault diagnosis under strong external impulse noise

In vibration-based fault diagnosis of rotating machinery, strong impulse noise constitutes a widely encountered source of external interference, thereby posing significant challenges to the effective extraction of diagnostic information. In this context, an adaptive reweighted-Kurtogram (ARKurtogram) method is proposed. The bearing transient fault signatures are accurately extracted through two aspects – that is, precise frequency band division and robust band selection indicator. Specifically, we use the dual-tree complex wavelet packet transform (DTCWPT) as the band division tool and propose the sub-bands rearranged and ensemble DTCWPT which addresses the band disorder problem, yields far richer band division patterns and maintains excellent performance of DTCWPT in signal decomposition. Meanwhile, we introduce a robust indicator characterizing periodic fault impulses to accurately select the fault band. In comparison with the classical kurtosis and the advanced reweighted-kurtosis, this indicator is insensitive to strong external impulse noise and its calculation process contains a sliding window averaging approach which makes the calculation entirely automated without human intervention. The validity of the ARKurtogram is investigated with the analysis of vibration signals measured from fault-injection experiments. The comparisons with the classical fast Kurtogram method and the advanced Autogram method highlight the advantages of the method in extracting bearing transient fault signatures from complex signals with strong external impulse noise. It shows high potential in the application of industrial bearing fault diagnosis.

An open source experimental framework and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration

An Electrical Submersible Pump (ESP) is an important equipment used in the industry for lifting liquids in various types of wells. An ESP is widely used in the oil industry for offshore exploration. Detecting a faulty ESP before installation is a predictive maintenance measure in order to extend its operational time. Machine learning fault diagnosis is an effective way for performing this task. Machine learning fault diagnosis algorithms are highly dependent of the availability of an appropriate problem dataset. This paper describes in detail the problem of ESP fault diagnosis and the ESPset dataset, a real-world and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration. In addition, the paper also proposes an experimental framework for adequately comparing research works based on the ESPset dataset and defines benchmark classifiers and respective results as referential to the fault diagnosis research community. The framework considers the fact that some subset of samples are not drawn independently, and therefore, proposes a cross-validation sampling strategy that mitigates the similarity bias among samples. Indeed, this work shows that a conventional k-fold cross-validation may lead to a clear overestimation of the average performance. This fact is supported by results which show that the best classification model drops from a mean F-measure of 0.887 to 0.733 when removing the similarity bias from the data.

Vibration-Based Fault Diagnosis for Railway Point Machines Using Multi-Domain Features, Ensemble Feature Selection and SVM

Vibration-Based Fault Diagnosis for Railway Point Machines Using Multi-Domain Features, Ensemble Feature Selection and SVM

Bearing Fault Diagnosis based on 2D-Acoustic Imaging and Convolutional Neural Networks

Bearing faults are the common mode of failure in rotating machinery. Various techniques have been proposed for bearing fault diagnosis based on vibration signals. However, vibration-based fault diagnosis is restrained in some cases since they are limited by surface characteristics such as temperature. Acoustic-based fault diagnosis has the edge of non-contact measurement over vibration-based fault diagnosis. Convolutional neural networks have been used widely in condition monitoring to learn features naturally from the raw data, which does not require exhaustive domain knowledge and expertise. In the present study, 1D-acoustic signals are converted into 2D images and a Convolutional Neural Networks algorithm is applied to classify the bearing health conditions. The proposed method shows promising results on experimental data conducted on an in-house test rig.

Vibration-based fault diagnosis of dynamic rotating systems for real-time maintenance monitoring

Vibration-based fault diagnosis of dynamic rotating systems for real-time maintenance monitoring

TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis

TinyML has the potential to be a huge enabler of smart sensor nodes for fault diagnosis of machines by embedding powerful machine learning algorithms in low-cost edge devices. Static models trained with pre-collected data may not perform satisfactorily when deployed in use cases that present data with a significantly different distribution, due to changes in machine instances, installation, and environment and operating conditions. In this work, we present a transfer learning framework in conjunction with TinyML-powered convolutional neural network (CNN) architecture for vibration-based fault diagnosis of vastly different machines. We report that fine-tuning (retraining) of parameters (weights and biases) in convolutional layers and transfer of parameters in dense layers of CNNs results in higher accuracy for domain generalization than the conventional approach of transferring parameters for convolutional layers and fine-tuning dense layers. Using transfer learning also results in high accuracy when the total number of training samples used for fine-tuning on the target domain data sets are as low as 25 i.e. less than 5% of the size of the data set, which makes the proposed architecture viable for scenarios with a limited number of data points available for training the model. Furthermore, we have also demonstrated memory-efficient retraining at the edge by fine-tuning only the biases of hidden layers.

Vibration and infrared thermography based multiple fault diagnosis of bearing using deep learning

ABSTRACT The occurrence of multiple faults is a practical problem in the bearings of rotating machines, and early diagnosis of such issues in an intelligent manner is vital in the era of industry 4.0. The present work investigated various combinations of bearing faults, including dual and multiple fault conditions. Two prevalent fault diagnosis methods were employed: vibration monitoring using time-frequency scalograms extracted through Continuous Wavelet Transform (CWT) and a non-invasive Infrared Thermography (IRT). A 2-D Convolutional Neural Network (CNN) was used to classify various combinations of fault conditions through automated feature extraction. The proposed methodology was validated at two constant speed conditions of 19 Hz and 29 Hz and continuously accelerated and decelerated speed conditions in the range of 19 Hz - 29 Hz. Adequate accuracy was achieved in both dual and multiple fault conditions in the case of vibration-based fault diagnosis, with a range of 99.39 % to 99.97 %. Meanwhile, in the case of proposed IRT-based fault diagnosis, 100 % classification accuracy was achieved for dual and multiple faults in all conditions. These results signify the robustness and reliability of the proposed methodology for dual and multiple fault diagnosis in bearings at constant and varying speed conditions.

Generalized Variable-Step Multiscale Lempel-Ziv Complexity: A Feature Extraction Tool for Bearing Fault Diagnosis

Feature extraction is a key step for fault diagnosis of rolling bearings based on vibration measurements. Lempel-Ziv complexity (LZC) has been widely applied to extracting fault features. However, LZC with single-scale analysis may result in the loss of fault information. Then, the multiscale LZC is proposed to uncover the multiscale features. Nevertheless, multiscale LZC would shorten the length of sequences, leading to inaccurate calculation results. Moreover, the mean operation during the coarse-grained process of the traditional multiscale analysis cannot reveal the dynamic changes of the original sequences, which may also result in the loss of potential information. Thus, this paper develops a feature extraction method called generalized variable-step multiscale LZC (GVSMLZC) for the vibration-based fault diagnosis of rolling bearings. GVSMLZC reveals more information and gains more robust complexity by improving the coarse-grained process. Moreover, GVSMLZC enhances the capability of mining dynamic characteristics by generalizing first-order moments to second-order moments. Based on the proposed GVSMLZC, fault type identification and fault detection of life-cycle data schemes are designed to realize the fault diagnosis of rolling bearings. Simulated and experimental results demonstrate that GVSMLZC outperforms multiscale LZC, variable-step multiscale LZC, and multiscale sample entropy in extracting bearing fault information.

A fusion CNN driven by images and vibration signals for fault diagnosis of gearbox

Abstract Gearbox diagnosis is critical for avoiding catastrophic failure and minimizing financial damages. Aiming at the problem that the vibration-based fault diagnosis methods cannot effectively identify the non-structural failure mode and the diagnosis model based on the infrared thermal image is not robust enough, a fusion fault diagnosis method for gearboxes using vibration signals and infrared images is proposed. By fusing these two kinds of heterogeneous data, the proposed method can identify both structural and unstructured health states while maintaining high robustness. In addition, CNN has powerful image processing capabilities, which can directly process two-dimensional infrared images and achieve high accuracy. Finally, a gearbox experiment is carried out to test the performance of our method. The results suggest that the proposed fusion CNN can obtain the highest accuracy compared with some methods based on single signals, shallow learning methods SVM and deep unsupervised learning methods SAE.

Investigation on crack failure of helical gear system of the gearbox in wind turbine: Mesh stiffness calculation and vibration characteristics recognition

When cracks are initiated in a helical gear pair, the mesh stiffness and vibration response of the gear pair will be affected. Unlike previous studies on gear crack, in which only the transverse gear stiffnesses are calculated due to gear crack, or purely uniformly distributed gear crack are modelled, however, in the current study, an improved model is proposed for the calculation of mesh stiffness of helical gear system due to gear crack, in which the gear tooth stiffness, and gear foundation stiffness in both transverse and axial direction have been comprehensively considered. Two typical cracking cases, namely, the addendum extended crack and end face extended crack have been investigated. Furthermore, the analytical mesh stiffness calculation results are validated with the simulated results that obtained from finite-element method, both results show acceptable coincidence. Based on the proposed method, the dynamic model of the cracked helical gear system has been established to analyze the vibration response of the system with the propagation of gear cracks. The obtained results indicate that cracks in gear could cause substantial mesh stiffness reduction. The vibration response in time-domain experience sudden change when the cracked gear tooth is engaged in mesh, and the spectrum shows that the side frequency components become more abundant with higher amplitude under more severe crack conditions. The findings in our study have wide applications in vibration-based fault diagnosis of helical gear systems.

Vibration-Based Fault Diagnosis of Helical Gear Pair With Tooth Surface Wear Considering Time-Varying Friction Coefficient Under Mixed Elastohydrodynamic Lubrication Condition

Abstract Based on “slice method,” the improved time-varying mesh stiffness (TVMS) calculation model of helical gear pair with tooth surface wear is proposed, in which the effect of friction force that obtained under mixed elastohydrodynamic lubrication (EHL) is considered in the model. Based on the improved TVMS calculation model, the dynamic model of helical gear system is established, then the influence of tooth wear parameters on the dynamic response is studied. The results illustrate that the varying reduction extents of mesh stiffness along tooth profile under tooth surface wear, in addition, the dynamic response in time-domain and frequency-domain present significant decline in amplitude under deteriorating wear condition.

Multiscale Residual Attention Convolutional Neural Network for Bearing Fault Diagnosis

Convolutional Neural Networks (CNNs) have demonstrated promising effectiveness in vibration-based fault diagnosis. However, the faulty characteristics are usually distributed on different scales and contaminated by noises from various sources. Therefore, it is still a challenging task for traditional CNNs to efficiently extract multiscale features and suppress unrelated noises in vibrational signals. In this paper, a novel fault diagnosis framework called multiscale residual attention CNN (MRA-CNN) is proposed to learn discriminative multiscale features from vibrational signals and fully utilize the multiscale features to reduce noises. First, the raw vibrational signals are fed into the multiscale learning module (MLMod) to obtain multi-channel feature maps generated with different kernel sizes. Second, the feature maps are passed through an efficient residual attention module (RAMod) to get the attention mask for weighing all locations of different channels of the multiscale feature maps to denoise. Third, to mitigate the information loss in attention, a new strategy called residual attention learning (RAL) is proposed to improve the feature extraction ability of RAMod, in which the learned attention mask itself is also regarded as feature maps by a shortcut connection. Experimental validation is conducted on two bearing datasets. The results show that the proposed method can learn more effective features from vibrational signals and deliver much higher accuracy than the seven state-of-the-art methods under highly noisy environments.

Research on fan vibration fault diagnosis based on image recognition

The conventional methods for vibration fault detection and diagnosis relies on feature extraction from the waveforms of the vibration signals. This article exploits the scope of image recognition application for the detection and diagnosis of fan vibration faults. In this paper, a novel image recognition technique is proposed for vibration-based fault diagnosis using the spectrum images of the vibration signals. 1D vibration signal spectrum is initially computed using Fast Fourier Transform (FFT) and the FFT frequencies are adjusted such that it captures a vibration spectrum diagram as 2D image representation. FFT based vibration analysis is done and the image recognition concept is utilized for feature extraction and a machine learning classification module is used for fault analysis and diagnosis. Effective feature generation is done using Principal Component Analysis (PCA) by removing the redundancy from the feature vectors and machine learning classifiers are used to obtain improved image recognition and classification performance. Artificial Neural Network (ANN) classifier yields better performance in terms of various performance parameters and percentage improvement in terms of accuracy for ANN classification methods over Support Vector Machine (SVM), k-Nearest Neighbours (kNN) and Random Forest Ensemble (RFE) methods are 10.01 %, 4.51 % and 2.01 % respectively. Comparative scenarios are considered in this work for fan vibration fault detection as well as diagnosis based on the image features for various realistic vibration fault conditions. Effectiveness of the proposed image recognition-based technique is compared with the state-of-the-art methods, justifying its outperformance for fan fault detection and diagnosis using the combination of spectrum adjustment, PCA and ANN classification method.

Classification of gear faults in internal combustion (IC) engine gearbox using discrete wavelet transform features and K star algorithm

Vibration-based fault diagnosis is one of the widely used techniques for condition monitoring of the machines equipped with a gearbox. Severe operating conditions of gearbox result in gear tooth failure. To develop an effective fault diagnosis technique for the mechanical system, a machine learning approach is highly necessary and plays a vital role in the area of condition monitoring. This paper presents the vibration-based fault diagnosis of IC engine gearbox operating under actual running condition. An Eddy current dynamometer is used to apply the external load on the output shaft of the engine. Driving gear with healthy condition and progressive tooth defect conditions are considered for the analysis. The vibration signals of engine gearbox under various gear tooth conditions are measured. Discrete wavelet transform features are extracted from the vibration signals and more contributing features for classification are selected using decision tree algorithm. The Lazy based classifiers viz, k-nearest neighbour algorithm, K-star algorithm and locally weighted learning algorithm are used for classification. A comparative study of these classifiers is made using percentage of classification accuracy. The maximum classification accuracy of about 97.5% is achieved by the K-star algorithm. Based on the experimental results, K-star algorithm and discrete wavelet transform technique can be used for diagnosing the gear faults in IC engine gearbox using vibration signals.

Studies of filtering effect on fault diagnosis of spindle device in hoist

Spindle devices, which are among the core components of mine hoists, are typical rotor-bearing systems. Vibration-based fault diagnosis techniques are often used to help prevent mechanical failures of such systems. The fault vibration signals generally include pulse information reflecting fault type, independent vibration components caused by other non-faulty mechanical components, noise in the surrounding environment and so on. The reduction of noise in the vibration signal collected by the sensor is of practical significance for the correct diagnosis of subsequent rotating machinery faults. To solve this problem, a fault diagnosis method based on a smooth (SM) filtering algorithm combined with variational mode decomposition (VMD) and a support vector machine (SVM) is proposed. Wavelet transform (WT) and wavelet packet transform (WPT) methods are used to compare the noise reduction. The reliability and effectiveness of the method are verified by experiments on a hoist mechanical fault simulator. Experimental results show that the proposed method has high prediction accuracy and can provide a good practical reference for fault diagnosis of rotating machinery.