Bearing Fault Dataset Research Articles

Induction Motor Bearing Fault Classification Using Extreme Learning Machine Based on Power Features

Electric motors perform the crucial task of converting electrical energy into essential mechanical energy on demand. Motors are plentifully used in the industrial sector all over the world to drive mechanical appliances. Despite being robust and sturdy, motors are not entirely fault-proof, and faults that are caused by the bearings trouble them the most. Early detection of these faults allows engineers to take preventive measures and avert hard breakdowns. Numerous studies have been conducted in this area of research. Many methods have been proposed and implemented to detect the existence and determine the type of fault present in an induction motor. However, this field of research is still open since there is room for improvements in the claimed results. In this paper, a novel fault diagnosis method has been proposed involving an emerging machine learning technique named extreme learning machine to identify the existence of flaws in motor bearings and specify their origins. The described method is tested on a benchmark bearing fault dataset provided by Case Western Reserve University Bearing Data Center. The acquired result yields a maximum classification accuracy of 99.86% and an average classification accuracy of 98.67% after being tested on multiple fault datasets.

A Refined Composite Multivariate Multiscale Fluctuation Dispersion Entropy and Its Application to Multivariate Signal of Rotating Machinery.

In the fault monitoring of rotating machinery, the vibration signal of the bearing and gear in a complex operating environment has poor stationarity and high noise. How to accurately and efficiently identify various fault categories is a major challenge in rotary fault diagnosis. Most of the existing methods only analyze the single channel vibration signal and do not comprehensively consider the multi-channel vibration signal. Therefore, this paper presents Refined Composite Multivariate Multiscale Fluctuation Dispersion Entropy (RCMMFDE), a method which extracts the recognition information of multi-channel signals with different scale factors, and the refined composite analysis ensures the recognition stability. The simulation results show that this method has the characteristics of low sensitivity to signal length and strong anti-noise ability. At the same time, combined with Joint Mutual Information Maximisation (JMIM) and support vector machine (SVM), RCMMFDE-JMIM-SVM fault diagnosis method has been proposed. This method uses RCMMFDE to extract the state characteristics of the multiple vibration signals of the rotary machine, and then uses the JMIM method to extract the sensitive characteristics. Finally, different states of the rotary machine are classified by SVM. The validity of the method is verified by the composite gear fault data set and bearing fault data set. The diagnostic accuracy of the method is 99.25% and 100.00%. The experimental results show that RCMMFDE-JMIM-SVM can effectively recognize multiple signals.

Discriminative Dictionary Learning-Based Sparse Classification Framework for Data-Driven Machinery Fault Diagnosis

Data-driven machinery fault diagnosis is important for smart industrial systems to guarantee safety and reliability. However, the conventional data-driven fault diagnosis methods rely on the expert-designed features, which greatly affect the diagnosis performances. Inspired by the sparse representation-based classification (SRC) methods which can learn discriminative sparse features adaptively, we propose a novel discriminative dictionary learning based sparse classification (DDL-SC) framework for data-driven machinery fault diagnosis. The DDL-SC framework can jointly learn a discriminative dictionary for sparse representation and an optimal linear classifier for pattern recognition, which bridges the gaps between two separate processes, dictionary learning and classifier training in traditional SRC methods. In the learning stage, to enhance the discriminability of dictionary learning, we introduce the discriminative sparse code error along with the reconstruction error and classification error into the optimization objective. In the recognition stage, we employ sparse codes of testing signals with respect to the learned discriminative dictionary as inputs of the learned classifier, and promote the recognition performance by connecting a binary hard thresholding operator with the classifier predictions. The effectiveness of DDL-SC is evaluated on the planetary bearing fault dataset and gearbox fault dataset, indicating that DDL-SC yields the recognition accuracies of 99.73% and 99.41%, respectively. Besides, the comparative studies prove the superiority of DDL-SC over several state-of-the-art methods for data-driven machinery fault diagnosis.

Application of BP Neural Network and Convolutional Neural Network (CNN) in Bearing Fault Diagnosis

The convolutional neural network (CNN) identification method and the BP neural network identification method were used to diagnose the bearing fault respectively. When using the CNN diagnostic method, first perform continuous wavelet transform (CWT) on the vibration signal of the rolling bearing to obtain a time-frequency map, and then compress the time-frequency map to an appropriate size; Then, the compressed time-frequency map is used as a feature map to input into the CNN classifier model established; finally, an experimental study is carried out based on the artificial bearing fault data set of Western Reserve University. The results show that the average accuracy rate of this method is greater than 99%.In the BP fault diagnosis method, based on the data set, nine parameters of average value, maximum value, minimum value, peak-to-peak value, root mean square value, standard deviation, variance, skewness and kurtosis are established as training input vectors. Using BP neural network with 10 hidden layer nodes for fault identification, the results show that the average accuracy of identification is 93.7839%. The comparative analysis of the two methods shows that the BP identification method has higher training efficiency and takes less time; the CNN identification method has higher recognition accuracy, but the training takes more time.

A fault feature extraction algorithm based on CEEMD-TVD-MOMEDA

ABSTRACT Rolling bearings are indispensable key components in mechanical equipment, and they are also one of the most easily damaged components. To solve the problem of bearing fault feature extraction under strong noise interference, a combination of complementary ensemble average empirical mode decomposition (CEEMD), total variation denoising (TVD) and multipoint optimal minimum entropy deconvolution adjusted(MOMEDA) is proposed. Firstly, decompose the vibration signal into several signal components. Secondly, the qualified IMF signal components are selected by combining with the cross-correlation analysis criteria for reconstruction, and TVD is used to reduce the noise of the signal. Thirdly, MOMEDA is used to filter the denoised signal, so as to enhance the periodic impact component. Finally, the envelope spectrum of the filtered signal is analyzed. The effectiveness of the proposed method is verified by the simulation signals and the bearing fault data set of Case Western Reserve University. The experimental results show that the proposed method can not only reduce the noise interference, but also effectively extract and identify the rolling bearing fault features. Compared with the results obtained by traditional LMD and ITD methods, it has better recognition effect.

An Improved PixelHop Framework and its Application in Rolling Bearing Fault Diagnosis

The PixelHop framework based on successive subspace learning (SSL) has been widely used in signal processing and computer vision, which can effectively improve the classification accuracy in high spatial resolution scenes through successive subspace growth. To solve the problems of insufficient feature extraction and dependence on prior knowledge in the PixelHop framework, an improved PixelHop (I-PixelHop) framework is proposed. On the basis of PixelHop framework, I-PixelHop has made the following improvements. 1) I-PixelHop fully extracts the continuous features in one-dimensional sequence data through the improved neighborhood expansion, which can provide a richer feature set. 2) The improved label-assisted regression (ILAG) unit uses the Bi-K-Means clustering algorithm to enable more correct clustering of similar samples, and it adopts the cross-entropy threshold method to alleviate the negative effects caused by the improper setting of the number of pseudo-classes. 3) The high-dimensional features are fully reused by adopting the pseudo dense connection structure to obtain a better feature set. Moreover, the proposed I-PixelHop framework is applied to the rolling bearing fault diagnosis. A series of experiments are carried out to verify the effectiveness of the proposed I-PixelHop. The experimental results show that the fault diagnosis accuracy of I-PixelHop can reach 98.91% and 98.74% on the two different rolling bearing fault datasets, and it also has satisfactory anti-noise ability, faster training speed, and smaller model size.

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.

A Novel End-To-End Fault Diagnosis Approach for Rolling Bearings by Integrating Wavelet Packet Transform into Convolutional Neural Network Structures.

Accidental failures of rotating machinery components such as rolling bearings may trigger the sudden breakdown of the whole manufacturing system, thus, fault diagnosis is vital in industry to avoid these massive economical costs and casualties. Since convolutional neural networks (CNN) are poor in extracting reliable features from original signal data, the time-frequency analysis method is usually called for to transform 1D signal into a 2D time-frequency coefficient matrix in which richer information could be exposed more easily. However, realistic fault diagnosis applications face a dilemma in that signal time-frequency analysis and fault classification cannot be implemented together, which means manual signal conversion work is also needed, which reduces the integrity and robustness of the fault diagnosis method. In this paper, a novel network named WPT-CNN is proposed for end-to-end intelligent fault diagnosis of rolling bearings. WPT-CNN creatively uses the standard deep neural network structure to realize the wavelet packet transform (WPT) time-frequency analysis function, which seamlessly integrates fault diagnosis domain knowledge into deep learning algorithms. The overall network architecture can be trained with gradient descent backpropagation algorithms, indicating that the time-frequency analysis module of WPT-CNN is also able to learn the dataset characteristics, adaptively representing signal information in the most suitable way. Two experimental rolling bearing fault datasets were used to validate the proposed method. Testing results showed that WPT-CNN obtained the testing accuracies of 99.73% and 99.89%, respectively, in two datasets, which exhibited a better and more reliable diagnosis performance than any other existing deep learning and machine learning methods.

A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning

Limited condition monitoring data are recorded with label information in practice, which make the fault identification task more challenging. A semi-supervised learning (SSL) approach can be employed to increase the identification performance of the classifiers under such situation. In this study, a three-stage SSL approach using data augmentation (DA) and metric learning is proposed for an intelligent bearing fault diagnosis under limited labeled data. In the first stage, a DA method comprising seven DA strategies is presented to expand the feature space for the limited labeled samples under each healthy conditions. An optimization objective combining a cross entropy loss and a triplet loss is adopted to enlarge the margin between the feature distributions of limited labeled samples under different healthy conditions. In the second stage, a K-means technique is employed to acquire the cluster centers for the limited labeled samples under different healthy conditions. In the third stage, the label information for the unlabeled samples is first estimated according to the membership between the feature distributions of the unlabeled samples and the various cluster centers for original labeled samples and then a Kullback-Leibler divergence loss is introduced to minimize the discrepancy between feature distributions for the unlabeled samples and its corresponding cluster centers. The effectiveness of the proposed method is evaluated on two case studies, one is on an experimental bearing fault dataset from our laboratory test-rig, and the other is on a publicly dataset from a bearing degradation test. The comparison results on these two case studies demonstrate that the proposed method can perform better in bearing fault diagnosis under limited labeled samples than existing diagnostic methods.

A consistency regularization based semi-supervised learning approach for intelligent fault diagnosis of rolling bearing

• A SSL method for intelligent fault diagnosis of rolling bearing is proposed. • Data augmentation is the basic foundation of the proposed method. • Two consistency terms make the trained network less sensitive to the extra perturbations. • The proposed method achieves excellent performance on the experimental study. Deep learning has been widely used nowadays to achieve an automated fault diagnosis of rolling bearings. However, most of deep learning based bearing fault diagnosis methods are based on the assumption that the recorded samples are labeled data, though most of field data are recorded without label information. To address this issue, an effective semi-supervised learning method based on the principle of consistency regularization is proposed in this study. The principle of consistency regularization underlines that the model predictions should be less sensitive to the extra perturbation imposed on the input samples. In the proposed method, a data augmentation method is proposed to serve as the extra perturbation, which is imposed on both the labeled and unlabeled samples to enrich the data library. Meanwhile, a label predicting process is formulated to estimate the appreciable label distribution for the unlabeled sample. Correspondingly, two consistency loss terms are introduced to regularize the model predictions for both the labeled and unlabeled samples to be invariant to the extra perturbation, among which a supervised loss term is adopted to enforce the model predictions for augmented labeled samples to be consistent with its true label information and an unsupervised loss is proposed to minimize the discrepancy between label distributions for the original unlabeled samples and its appreciable label distributions. The analysis result on an experimental bearing fault dataset demonstrates that the proposed method can provide an excellent identification performance under limited labeled samples situation.

Fast convolution sparse filtering and its application on gearbox fault diagnosis

Transmission, as a critical part of vehicles, is the hub of power transmission and the core of controlling speed change. Condition monitoring and diagnosis of transmissions have become an effective tool to ensure vehicle safety travelling. The intelligent fault diagnosis strategy using artificial intelligent methods has been studied and applied for gearbox fault diagnosis. However, most algorithms cannot guarantee both accuracy and training efficiency. In this paper, fast convolutional sparse filtering based on convolutional activation and feature normalization is proposed for gearbox fault diagnosis without any time-consuming preprocessing. In fast convolutional sparse filtering, the features of samples are optimized instead of local features, which could obviously reduce the dimension and construction time of the Hessian matrix. In addition, the output features are equally active to guarantee that all features have similar contributions. The l2-norm of the training features is recorded and used for pseudo-normalization of the test features. The proposed fast convolutional sparse filtering is validated by a bearing fault dataset and a planetary gear fault dataset. Verification results confirm that fast convolutional sparse filtering is a promising tool for fault diagnosis, which has obviously improved the diagnosis accuracy, training efficiency, and robustness and provides the greater advantage of handling large-scale datasets.

Vibration Signature Analysis using Rough Sets and Analogy-Based Reasoning Classification

Various machine learning techniques along with vibration signal processing techniques are being explored for effective and accurate fault diagnosis of bearing faults. This work studies and evaluates the application of rough set based algorithms - RoughSet Classifier, LocalKnn Classifier and RseslibKnn Classifier and their combinations with 4 kinds of distance metrics - City block and Hamming (CBD and HD), City block and simple value difference (CB and VDM), Density based value difference (DBVDM), Interpolated value difference(IVDM) for bearing vibration signature analysis. The input vector fed to the classifier models is composed of statistical features extracted from pre-processed vibration signals. The different metrics used to compare the performance of the classifiers show that RseslibKnn classifier with City block and simple value difference distance metric takes considerably less time for training (9.09 sec) and classification (0.86 sec) while giving testing accuracy of 84.1442 %, thereby confirming its usefulness for real time application on large bearing fault datasets. The results obtained in this paper show the effectiveness of rough sets based algorithms, particularly KNN based classifiers, in bearing fault diagnosis.

Unsupervised rotating machinery fault diagnosis method based on integrated SAE–DBN and a binary processor

In recent years, deep learning based diagnostic approaches have become more attractive. However, most of these methods are supervised diagnostic approaches. Developing a supervised diagnostic model requires a large number of labeled training data. And it is time consuming and labor intensive to obtain labeled data for a variety of systems and working conditions. Therefore, an unsupervised diagnostic model that does not require labeled training data is more desirable. This paper proposes an unsupervised diagnostic model by integrating a sparse autoencoder, a deep belief network, and a binary processor. In comparison with the existing unsupervised methods, the proposed method does not need to perform statistical features extraction, and directly uses the normalized frequency domain signals as the inputs. Moreover, in the proposed diagnostic model, the input data is passed through layer by layer without fine-tuning, which is completely unsupervised process. The proposed methods have been validated with bearing fault datasets and gear pitting fault datasets. The validation results show that the proposed method has a higher accuracy for both bearing and gear pitting fault diagnosis.

DCNN for condition monitoring and fault detection in rotating machines and its contribution to the understanding of machine nature

Rotating machines are critical equipment in many processes, and failures in their operation can have serious implications. Consequently, fault detection in rotating machines has been widely investigated. Conventional detection systems include two blocks: feature extraction and classification. These systems are based on manually engineered features (ball pass frequencies, RMS value, kurtosis, crest factor, etc.) and therefore require a high level of human expertise (it is a human who designs and selects the most appropriate set of features to perform the classification). Instead, we propose a system for condition monitoring and fault detection in rotating machines based on a 1-D deep convolutional neural network (1D DCNN), which merges the tasks of feature extraction and classification into a single learning body. The proposed system has been designed for use on a rotating machine with seven possible operating states and it proves to be able to determine the operating condition of the machine almost as accurately as conventional feature-engineered classifiers, but without the need for prior knowledge of the machine. The proposed system has also reported good classification on a bearing fault dataset from another machine, thus demonstrating its capability to monitor the condition of different machines. Finally, the analysis of the features learned by the deep model has revealed valuable and previously unknown machine information, such as the rotational speed of the machine or the number of balls in the bearings. In this way, our results illustrate not only the good performance of CNNs, but also their versatility and the valuable information they could provide about the monitored machine.

A novel unsupervised deep learning network for intelligent fault diagnosis of rotating machinery

Generally, the health conditions of rotating machinery are complicated and changeable. Meanwhile, its fault labeled information is mostly unknown. Therefore, it is man-sized to automatically capture the useful fault labeled information from the monitoring raw vibration signals. That is to say, the intelligent unsupervised learning approach has a significant influence on fault diagnosis of rotating machinery. In this study, a span-new unsupervised deep learning network can be constructed based on the proposed feature extractor (L12 sparse filtering (L12SF)) and the designed clustering extractor (Weighted Euclidean Affinity Propagation) for resolving the issue that the acquisition of fault sample labeled information is burdensome, yet costly. Naturally, the novel intelligent fault diagnosis method of rotating machinery based on unsupervised deep learning network is first presented in this study. Thereinto, the proposed unsupervised deep learning network consists of two layers of unsupervised feature extractor (L12SF) and one layer of unsupervised clustering (Weighted Euclidean Affinity Propagation). L12SF can improve the regularization performance of sparse filtering, and Weighted Euclidean Affinity Propagation can get rid of the traditional Euclidean distance in affinity propagation that cannot highlight the contribution of different features in fault clustering. To make a long story short, the frequency spectrum signals are first entered into the constructed unsupervised deep learning network for fault feature representation; afterward, the unsupervised feature learning and unsupervised fault classification of rotating machinery can be implemented. The superiority of the proposed algorithms and method is validated by two cases of rolling bearing fault dataset. Ultimately, the proposed unsupervised fault diagnosis method can provide a theoretical basis for the development of intelligent unsupervised fault diagnosis technology for rotating machinery.

Bearing Intelligent Fault Diagnosis in the Industrial Internet of Things Context: A Lightweight Convolutional Neural Network

The advancement of Industry 4.0 and Industrial Internet of Things (IIoT) has laid more emphasis on reducing the parameter amount and storage space of the model in addition to the automatic and accurate fault diagnosis. In this case, this paper proposes a lightweight convolutional neural network (LCNN) method for intelligent fault diagnosis of bearing, which can largely satisfy the need of less parameter amount and storage space as well as high accuracy. First, depthiwise separable convolution is adopted, and a LCNN structure is constructed through an inverse residual structure and a linear bottleneck layer operation. Secondly, a novel decomposed Hierarchical Search Space is introduced to automatically explore the optimal LCNN for bearing fault diagnosis in the context of the IIoT. In the meantime, the real-time monitoring and fault diagnosis of the model are also deployed. In order to verify the validity of the designed model, Case Western Reserve University Bearing fault dataset and MFPT bearing fault dataset are adopted. The results demonstrate the great advantages of the model. The LCNN model can automatically learn and select the appropriate features, highly improving the fault diagnosis accuracy. Meanwhile, the computational and storage costs of the model are largely reduced, which contributes to its being applied to the mechanical system in the IIoT context.

A Multistage Deep Transfer Learning Method for Machinery Fault Diagnostics Across Diverse Working Conditions and Devices

Deep learning methods have promoted the vibration-based machinery fault diagnostics from manual feature extraction to an end-to-end solution in the past few years and exhibited great success on various diagnostics tasks. However, this success is based on the assumptions that sufficient labeled data are available, and that the training and testing data are from the same distribution, which is normally difficult to satisfy in practice. To overcome this issue, we propose a multistage deep convolutional transfer learning method (MSDCTL) aimed at transferring vibration-based fault diagnostics capabilities to new working conditions, experimental protocols and instrumented devices while avoiding the requirement for new labeled fault data. MSDCTL is constructed as a one-dimensional convolutional neural network (CNN) with double-input structure that accepts raw data from different domains as input. The features from different domains are automatically learned and a customized layer is designed to compute the distribution discrepancy of the features. This discrepancy is further minimized such that the features learned from different domains are domain-invariant. A multistage training strategy including pre-train and fine-tuning is proposed to transfer the weight of a pre-trained model to new diagnostics tasks, which drastically reduces the requirement on the amount of data in the new task. The proposed model is validated on three bearing fault datasets from three institutes, including one from our own. We designed nine transfer tasks covering fault diagnostics transfer across diverse working conditions and devices to test the effectiveness and robustness of our model. The results show high diagnostics accuracies on all the designed transfer tasks with strong robustness. Especially for transfer to new devices the improvement over state of the art is very significant.

Prediction Consistency Guided Convolutional Neural Networks for Cross-Domain Bearing Fault Diagnosis

An underlying assumption in bearing fault diagnosis is that the training data from a source domain and the test data from a target domain obey the same distribution. But this assumption can be easily violated in practical industrial environments due to domain shift, which leads to significant performance degradation. To overcome this issue, we propose a novel convolutional neural network model to identify cross-domain bearing fault types based on 1-D vibration signals. Different from current single-network-based approaches, our model comprises a student network and a teacher network that simultaneously conduct data distribution matching and discriminative feature learning. Moreover, the two networks promote each other with the label prediction consistency constraint, so that the discriminative knowledge is able to transfer between the domains. Our model bridges the semantic information of the source vibration signals and the distribution information of the target vibration signals by jointly performing cross-domain feature disentanglement and adaptation. The proposed method is evaluated extensively on the Case Western Reserve University bearing fault dataset in two scenarios: varying working loads and different sensor locations. Experimental results show the superior performance of our method compared with existing shallow and deep learning methods in the literature.

A Cross-Domain Stacked Denoising Autoencoders for Rotating Machinery Fault Diagnosis Under Different Working Conditions

In fault diagnosis of rotating machinery, the shift in domain distributions caused by working condition fluctuations poses a major obstacle for accurate diagnosis. Due to the lack of domain adaptation ability, the diagnosis performance of existing deep learning-based methods degrades significantly when confronting other unseen working conditions. To address this problem, we develop a cross-domain stacked denoising autoencoders (CD-SDAE) with a new adaptation training strategy. Taking advantages from both domain adaptation and manifold learning, the adaptation training strategy consists of two successive paradigms: 1) unsupervised adaptation pre-training to correct marginal distribution mismatch and 2) semi-supervised manifold regularized fine-tuning to minimize conditional distribution distance between domains. In this way, the marginal distributions between the source and target domains are first matched. Then, on this basis, the conditional distributions can be matched more effectively thus makes the model become more adaptable to the target domain. The CD-SDAE is evaluated on gearbox and engine rolling bearing fault datasets. The experimental results show that CD-SDAE is superior to not only conventional deep learning method but also state-of-the-art deep domain adaptation method in terms of diagnostic accuracy.

Rotating machinery fault diagnosis for imbalanced data based on decision tree and fast clustering algorithm

To diagnose rotating machinery fault for imbalanced data, a kind of method based on fast clustering algorithm and decision tree is proposed. Combined with wavelet packet decomposition and isometric mapping (Isomap), sensitive features of different faults can be obtained so the imbalanced fault sample set is constituted. Then the fast clustering algorithm is applied to search core samples from the majority data of the imbalanced fault sample set. Consequently, the balanced fault sample set consisted of the clustered data and the minority data is built. After that, decision tree is trained with the balanced fault sample set to get the fault diagnosis model. Finally, gearbox fault data set and rolling bearing fault data set are used to test the fault diagnosis model. The experiment results show that proposed fault diagnosis model could accurately diagnose the rotating machinery fault for imbalanced data.