Figure 3 - uploaded by Syed Muhammad Tayyab
Content may be subject to copyright.
Source publication
Vibration analysis is an established method for fault detection and diagnosis of rolling element bearings. However, it is an expert oriented exercise. To relieve the experts, use of Artificial Intelligence (AI) techniques such as deep neural networks, especially convolutional neural networks (CNN) have gained much attention of the researchers becau...
Context in source publication
Context 1
... Fourier transform of the interpolated signal is computed to generate spectral map of order versus rpm. Since each order is a fixed multiple of the reference rotational speed, order map has a straight track as a function of rpm for each order as shown in Figure 3. Therefore, these maps show consistent patterns under varying speed. ...
Similar publications
Rolling bearings are key components that support the rotation of motor shafts, operating with a quite high failure rate among all the motor components. Early bearing fault diagnosis has great significance to the operation security of motors. The main contribution of this paper is to illustrate Gaussian white noise in bearing vibration signals serio...
Citations
... Furthermore, it aids in mitigating the impact of outliers, contributing to improved accuracy and precision in statistical analyses like regression or classification models. Diagnosing bearing failures in industrial machines operating under variable load conditions presents a significant challenge [26][27][28]. Unlike studies focusing on static or steady-state load conditions, the complexity intensifies when load conditions vary over time [29]. Signals from bearings under variable loads are more intricate and challenging to analyze. ...
Bearings represent crucial components within rotating machinery, and unexpected failures can lead to significant damage and unplanned breakdowns. This paper introduces a novel approach to diagnose bearing faults under variable working conditions, leveraging the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and sequential backward selection (SBS). CEEMDAN automatically selects intrinsic mode functions (IMFs) from vibration and current signals to establish a comprehensive set of health indicators. Subsequently, the SBS algorithm identifies the most pertinent indicators for different bearing failure modes. The accuracy of the proposed method is evaluated on both vibration and electrical signals using data from a dedicated test bench at the Signal and Industrial Process Analysis Laboratory (LASPI). Results demonstrate the effectiveness of the proposed method in accurately identifying and classifying bearing faults across various working conditions, utilizing both types of signals. This approach holds promise for real-world industrial applications, offering a reliable method for condition monitoring and diagnostics in bearing systems.
... Significant device damage and the loss of essential equipment as a result of bearing failure pose serious safety concerns and financial losses. Early failure identification is crucial to the availability and functionality of rolling element bearings (Tayyab et al., (2022)). The most frequent reason for bearing failure usually starts at the surfaces. ...
... Furthermore, it aids in mitigating the impact of outliers, contributing to improved accuracy and precision in statistical analyses like regression or classification models. Diagnosing bearing failures in industrial machines operating under variable load conditions presents a significant challenge [24][25][26]. Unlike studies focusing on static or steady-state load conditions, the complexity intensifies when load conditions vary over time [27]. Signals from bearings under variable loads are more intricate and challenging to analyze. ...
Bearings represent crucial components within rotating machinery, and unexpected failures can lead to significant damage and unplanned breakdowns. This paper introduces a novel approach to diagnose bearing faults under variable working conditions, leveraging the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Sequential Backward Selection (SBS). CEEMDAN automatically selects intrinsic mode functions (IMFs) from vibration and current signals to establish a comprehensive set of health indicators. Subsequently, the SBS algorithm identifies the most pertinent indicators for different bearing failure modes. The accuracy of the proposed method is evaluated on both vibration and electrical signals using data from a dedicated test bench at the Signal and Industrial Process Analysis Laboratory (LASPI). Results demonstrate the effectiveness of the proposed method in accurately identifying and classifying bearing faults across various working conditions, utilizing both types of signals. This approach holds promise for real-world industrial applications, offering a reliable method for condition monitoring and Diagnostics in bearing systems.
... The categorical cross-entropy loss function is taken as the loss function of the MFIRN, and the epoch is set to 30. The seven fault diagnosis approaches (CNN [47], MIRCNN [48], MMCNN [49], GAF_CA_CNN [50], SIRCNN [51], Bayes_DCGRU [52], and MCL_DRL [53]) are compared with the MFIRN. The capabilities of various approaches to diagnose faults under noise and variable load conditions are compared using two cases. ...
The working characteristics of noise and variable load conditions make it challenging to extract the feature of train bearing vibration signal. Therefore, a multi-layer feature fusion inverted residual network (MFIRN) is proposed. Firstly, a joint shrinkage denoising module (JSDM) is proposed, and an inverted residual denoising module (IRDM) is designed by combining the JSDM with the inverted residual network. The IRDM is used as the basic unit to improve the anti-noise performance of MFIRN. Then, a global interactive awareness module (GIAM) is designed to perceive the information of different layers, which can effectively extract the fault characteristics of bearing signals under variable load conditions. Finally, the fault diagnosis capabilities of the MFIRN under noisy and variable load conditions are tested using two cases, and the effectiveness of the JSDM, GIAM and IRDM is verified by ablation experiments. The experimental results demonstrate that, compared with seven recent models, the MFIRN can filter out the interference information more effectively under different noise conditions. Furthermore, MFIRN can effectively obtain the correlation characteristics between different load signals with better diagnostic accuracy and domain adaptability, showing potential for practical application.
... orders (FCOs), which are constant. Order analysis relies heavily on rotational frequency, which can be obtained by installing an auxiliary tachometer [5] or estimated from the existing signals [6,7]. In addition, many studies have focused on extracting time-varying fault characteristics directly through time-frequency analysis. ...
The fault diagnosis of rolling bearings is critical for the reliability assurance of mechanical systems. The operating speeds of the rolling bearings in industrial applications are usually time-varying, and the monitoring data available are difficult to cover all the speeds. Though deep learning techniques have been well developed, the generalization capacity under different working speeds is still challenging. In this paper, a sound and vibration fusion method, named the fusion multiscale convolutional neural network (F-MSCNN), was developed with strong adaptation performance under speed-varying conditions. The F-MSCNN works directly on raw sound and vibration signals. A fusion layer and a multiscale convolutional layer were added at the beginning of the model. With comprehensive information, such as the input, multiscale features are learned for subsequent classification. An experiment on the rolling bearing test bed was carried out, and six datasets under various working speeds were constructed. The results show that the proposed F-MSCNN can achieve high accuracy with stable performance when the speeds of the testing set are the same as or different from the training set. A comparison with other methods on the same datasets also proves the superiority of F-MSCNN in speed generalization. The diagnosis accuracy improves by sound and vibration fusion and multiscale feature learning.
... As described by Tayyab et al. [93], order maps can be computed using the following three steps: ...
... Figure 20 shows examples of the order maps of two bearing vibration signals with normal and inner race fault conditions under variable speeds (25-75 rpm). In [93], this technique is used for rolling element bearing diagnosis under variable speeds and loads. The order maps show the different patterns for different types of faults. ...
Rotating machine vibration signals typically represent a large collection of responses from various sources in a machine, along with some background noise. This makes it challenging to precisely utilise the collected vibration signals for machine fault diagnosis. Much of the research in this area has focused on computing certain features of the original vibration signal in the time domain, frequency domain, and time-frequency domain, which can sufficiently describe the signal in essence. Yet, computing useful features from noisy fault signals, including measurement errors, needs expert prior knowledge and human labour. The past two decades have seen rapid developments in the application of feature-learning or representation-learning techniques that can automatically learn representations of time series vibration datasets to address this problem. These include supervised learning techniques with known data classes and unsupervised learning or clustering techniques with data classes or class boundaries that are not obtainable. More recent developments in the field of computer vision have led to a renewed interest in transforming the 1D time series vibration signal into a 2D image, which can often offer discriminative descriptions of vibration signals. Several forms of features can be learned from the vibration images, including shape, colour, texture, pixel intensity, etc. Given its high performance in fault diagnosis, the image representation of vibration signals is receiving growing attention from researchers. In this paper, we review the works associated with vibration image representation-based fault detection and diagnosis for rotating machines in order to chart the progress in this field. We present the first comprehensive survey of this topic by summarising and categorising existing vibration image representation techniques based on their characteristics and the processing domain of the vibration signal. In addition, we also analyse the application of these techniques in rotating machine fault detection and classification. Finally , we briefly outline future research directions based on the reviewed works.
... [6][7][8] Additionally, deep learning methods have been widely used for condition recognition over the past decades. [9][10][11] These intelligent recognition techniques have achieved great success in distinguishing operating conditions of various machines under complex working environment. ...
Rolling bearings are present ubiquitously in mechanical equipment, timely fault diagnosis has great significance in guaranteeing the safety of mechanical operation. In real world industrial applications, the distribution of training dataset (source domain) and testing dataset (target domain) is often different and varies with operating environment, which may lead to performance degradation. In this study, a cross-domain fault diagnosis of rolling bearing method based on distance metric transfer learning (DMTL) and wavelet packet decomposition (WPD) is proposed. The Mahalanobis distance is adopted for learning the intrinsic similarity or dissimilarity between instances and learned by simultaneously maximizing the intra-class distances and minimizing the inter-class distances for target domain. The features of source domain and target domain are first extracted from original vibration signals by WPD which is a powerful tool in dealing with non-stationary signals and can provide meticulous analysis. Then, the DMTL model is adopted to eliminate the error propagation across different components, which can weaken the weight of low-quality instances and enhance the weight of high-quality samples. Finally, the k-nearest neighbor (KNN) classifier is applied to accomplish the cross-domain intelligent fault-type classification. The superiority and effectiveness of the proposed fault diagnosis model is validated by two diagnosis cases. The experimental results demonstrated that the proposed method performs better than other compared methods in recognizing various fault types and has the capability in handling the complex cross-domain adaptation scenarios.
... An identification sequence diagram of the rolling body bearing defect was used in a diagnostic method for variable conditions (speed and load) through a CNN. (Tayyab et al., 2022) [118]. In order to reduce the interference of uncertainties and other factors, a Markov transition field (MTF) and convolutional neural network (CNN) were automatically combined after learning data features. ...
As a precision mechanical component to reduce friction between components, the rolling bearing is widely used in many fields because of its slight friction loss, strong bearing capacity, high precision, low power consumption, and high mechanical efficiency. This paper reviews several excellent kinds of study and their relevance to the fault detection of rolling bearings. We summarize the fault location, sensor types, bearing fault types, and fault signal analysis of rolling bearings. The fault signal types are divided into one-dimensional and two-dimensional images, which account for 40.14% and 31.69%, respectively, and their classification is clarified and discussed. We counted the proportions of various methods in the references cited in this paper. Among them, the method of one-dimensional signal detection with external sensors accounted for 3.52%, the method of one-dimensional signal detection with internal sensors accounted for 36.62%, and the method of two-dimensional signal detection with external sensors accounted for 19.72%. The method of two-dimensional signal detection with internal sensors accounted for 11.97%. Among these methods, the highest detection rate is 100%, and the lowest detection rate is more than 70%. The similarities between the different methods are compared. The research results summarized in this paper show that with the progress of the times, a variety of new and better research methods have emerged, which have sped up the detection and diagnosis of rolling bearing faults. For example, the technology using artificial intelligence is still developing rapidly, such as artificial neural networks, convolutional neural networks, and machine learning. Although there are still defects, such methods can quickly discover a fault and its cause, enrich the database, and accumulate experience. More and more advanced techniques are applied in this field, and the detection method has better robustness and superiority.
... One-dimensional (1D) and two-dimensional (2D) CNN models have been used by the researchers for the defect diagnosis of rolling element bearings. Raw vibration data can be directly used as input to 1D-CNN models [13,14], however, for 2D-CNN models, vibration data must first to be converted into representative images such as spectrograms [15][16][17], scalograms [17,18], order maps [19] or other types of vibration images [20]. Afterwards, these images which represent the vibration signal in image form are used as input to the 2D-CNN model. ...
... Moreover, the performances of different models may be affected differently; (1) under small sample conditions, i.e., if minimal training data are available; and (2) if the operating conditions under which the model is tested are slightly different to the operating conditions under which the model was trained [19,30]. Therefore, there is a need to evaluate the trade-off between the computational expense and desired accuracy to choose the best image-processing-based technique for the intelligent defect diagnosis of REBs: (1) under normal conditions, when sufficient training samples are available; (2) in the case of minimal data availability; and (3) if the operating conditions change slightly. ...
Due to the excellent image recognition characteristics of convolutional neural networks (CNN), they have gained significant attention among researchers for image-processing-based defect diagnosis tasks. The use of deep CNN models for rolling element bearings’ (REBs’) defect diagnosis may be computationally expensive, and therefore may not be suitable for some applications where hardware and resources limitations exist. However, instead of using CNN models as end-to-end image classifiers, they can also be used to extract the deep features from images and those features can further be used as input to machine learning (ML) models for defect diagnosis tasks. In addition to extracting deep features using CNN models, there are also other methods for feature extraction from vibration characteristic images, such as the extraction of handcrafted features using the histogram of oriented gradients (HOG) and local binary pattern (LBP) descriptors. These features can also be used as input to classical ML models for image classification tasks. In this study, a performance comparison between all these image-processing-based defect diagnosis techniques was carried out in terms of fault detection accuracy and computational expense. Moreover, based upon the detailed comparison, a hybrid-ensemble method involving decision-level fusion is proposed, which is far less computationally expensive compared to CNN models while using them as end-to-end classifiers. The performance of all these models is also compared in the case of minimal training data availability and for diagnosis under slightly different operating conditions to ascertain their generalizability and ability to correctly diagnose despite the minimal availability of training data. The performance of the proposed hybrid-ensemble method remained outstanding for the REBs’ defect diagnosis despite the minimal of availability training data as well as the slight variation under operating conditions.
... Intelligent fault diagnosis provides an approach to avoiding subjective factors due to the merit of adaptive learning mechanisms, strong fault tolerance, and high non-linear regression ability [5]. In recent years, some typical strategies have been successfully applied to intelligent fault identification of rotating machinery, such as support vector machines (SVMs) [6][7][8], artificial neural networks (ANNs) [9], convolutional neural networks (CNNs) [10][11][12], recurrent neural networks (RNNs) [13], deep belief networks (DBNs) [14], deep auto-encoders (DAEs) [15,16], and generative adversarial networks (GANs) [17][18][19][20], which inspire that of planetary gearboxes. For example, Fu et al [8] decomposed raw signals of the rolling bearings into intrinsic mode functions, and extracted features from them with composite multiscale finesorted dispersion entropy to construct feature vectors. ...
... Ben Ali et al [9] collected ten time-domain statistical features with empirical mode decomposition and used an ANN as a classifier to classify the conditions of rolling bearings. Tayyab et al [12] computed order maps as input of a CNN model from the vibration signal of rolling element bearings and the trained CNN model was deployed for fault diagnosis under different running conditions. Zhu et al [13] described the characteristics of a RNN in strong nonlinear feature learning, the processing ability of time sequence information, and making full use of the time attribute in the data to discover fault features and degradation features. ...
The intelligent fault diagnosis of a planetary gearbox under variable speed is still a challenging topic. Due to the similar spectrum structure, overlapping features occur and result in decreasing diagnosis accuracy. Autoencoder-based methods can extract features adaptively but few studies proposed approaches to enhance the discriminability of features from different classes under variable speeds. Besides, the adverse variability of encoder weights may result in an adverse effect on the decoder. Adversarially learned inference (ALI) trains the encoder and decoder independently, but it is time-consuming to reach Nash equilibrium. To address the issues, a parallel adversarial learning inference model (PALI) is proposed, which aims at validating the parallel training of encoder and decoder and enhancing the discriminability of features. Specifically, time-frequency analysis is utilized to reveal the time-varying characteristics of raw signals and obtain time-frequency images as input for the encoder. Then, an explicit multi-dimensional uniform distribution is used for the merit of a simple probability density function to construct visualized and well-classified samples as input for the decoder. After that, a parallel adversarial game is explored to train the encoder and decoder simultaneously and independently, which will reduce computing interference and make the extracted features similar to the well-classified samples and reconstruct the raw signals. Finally, a Softmax classifier is trained and tested by the features. This method and its generability are validated via a planetary gearbox data set and a public bearing data under variable speed. The results indicate that the proposed parallel adversarial game is valid for training encoder and decoder independently, and PALI works as well as adversarial autoencoder (AAE) and outperforms ALI, variational autoencoder (VAE) in obtaining well-clustered features over different training data. Compared to Wigner-Ville distribution (WVD) and continuous wavelet transform (CWT), PALI based on short-time Fourier transformation (STFT) works better over different training data.
