Rotating Machine Fault Research Articles

Sparse Representation Convolutional Autoencoder for Feature Learning of Vibration Signals and its Applications in Machinery Fault Diagnosis

Vibration signals are widely utilized in many fields, which can reflect machine health state. Those typical deep learning techniques cannot learn impulsive features from vibration signals due to interference of strong background noise. Supervised learning greatly rely on vast labeled data, which limits the implementation of deep learning in industry applications. Hence, in this article, a new deep neural network (DNN), sparse representation convolutional autoencoder (SRCAE), is proposed to extract impulsive components of vibration signals for machinery fault diagnosis in an unsupervised manner. A sparse representation (SR) block is proposed to extract impulsive components of vibration signals and transform the time-domain signal to a sparse domain by sparse mapping of a convolutional graph. The SR block is inserted into a deep network to remove noise and learn impulsive features for machinery fault diagnosis. Furthermore, an unsupervised selective feature transmission mechanism is proposed to improve training efficiency and realize feature filtering simultaneously. Finally, the effectiveness of SRCAE is verified on rotary machine fault diagnosis experiments. The testing results show that SRCAE has good noise filtering and impulsive components extraction performance. The recognition accuracy of SRCAE reached 97.16% based on the fivefold cross validation, which demonstrates the outperformance of SRCAE in comparison with state-of-the-art DNNs.

Vibration Image Representations for Fault Diagnosis of Rotating Machines: A Review

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.

A Novel Joint Adversarial Domain Adaptation Method for Rotary Machine Fault Diagnosis under Different Working Conditions.

In real-world applications of detecting faults, many factors-such as changes in working conditions, equipment wear, and environmental causes-can cause a significant mismatch between the source domain on which classifiers are trained and the target domain to which those classifiers are applied. As such, existing deep network algorithms perform poorly under different working conditions. To solve this problem, we propose a novel fault diagnosis method named Joint Adversarial Domain Adaptation (JADA) for fault detection under different working conditions. Our approach simultaneously aligns marginal distribution and conditional distribution across the source and target through a unified adversarial learning process. JADA aims to construct domain-invariant and category-discriminative feature representation that is effective and robust for substantial distribution difference caused by working conditions. We also introduce a supervision signal, namely center loss, that penalizes the distances between the deep features and their corresponding class centers. This makes the learned features better equipped with more discriminative structures and effectively prevents mode collapse. Twenty-four transfer fault diagnosis tasks based on two experimental platforms were conducted to evaluate the effectiveness of the proposed methods. Extensive experiments verified that the JADA can significantly outperform several popular methods under different transfer diagnosis tasks.

A review on deep learning based condition monitoring and fault diagnosis of rotating machinery

Rotating machine faults are unavoidable; thus, early diagnosis is essential to avoid further damage to the machine or other machine attached to it. Various signal analysis based conventional techniques have been developed and used in the industries to identify various defects in the rotating machines. In last two decades, researchers have shifted their focus to automated or intelligent fault diagnosis based on Artificial Intelligence (AI) techniques due to a variety of issues in conventional fault analysis techniques, such as a dependence on machine operating circumstances, human interference, and expert abilities. In AI based techniques, various machine learning (ML) and deep learning (DL) techniques have been successfully applied for fault diagnosis of various rotating machines. From last half decade DL have been gaining popularity due to its attractive characteristic of automated feature learning and solving big data, unbalanced data, big computational burden and over-fitting problems of conventional ML techniques. Advances in DL methodologies have prompted interest in DL based intelligent fault diagnosis in the industry in the last five to 6 years. This review paper summarizes recent research and developments on DL based fault diagnosis in the last five to 6 years for various critical rotating machineries in industry such as electric motors, rotor-bearing systems, gear and gearbox, wind turbines, pumps, and compressors.

A composite learning approach for multiple fault diagnosis in gears

A major part of Prognostic and Health Management of rotating machines is dedicated to diagnosis operations. This makes early and accurate diagnosis of single and multiple faults an economically important requirement of many industries. With the well-known challenges of multiple faults, this paper proposes a new Blended Ensemble Convolutional Neural Network – Support Vector Machine (BECNN-SVM) model for multiple and single faults diagnosis of gears. The proposed approach is obtained by preprocessing the acquired signals using complementary signal processing techniques. This form inputs to 2D Convolutional Neural Network base learners which are fused through a blended ensemble model for fault detection in gears. Discriminative properties of the complementary features ensure the high capabilities of the approach to give good results under different load, speed, and fault conditions of the gear system. The experimental results show that the proposed method can accurately detect rotating machine faults. The proposed approach compared with other state-of-the-art methods indicates improved overall effectiveness for gear faults diagnosis.

Rotating machine fault diagnosis by a novel fast sparsity-enabled feature-energy-ratio method

To well extract the early fault characteristics of rotating machines, a new fast sparsity-enabled feature-energy-ratio method is investigated in this paper. This method includes two stages. In the first stage, the spectrum is adaptively segmented through a coarse-to-fine strategy based on the ordered local maximums. Thus, the fault characteristic band can be divided automatically. A novel index based on sparsity, energy ratio, and kurtosis, is constructed to evaluate periodic impulses in each sub-signal, and it can evaluate the periodic impulses from the globality and locality. In the second stage, the Fourier spectrum from the first stage are refined by an improved sparse coding shrinkage denoising (SCSD) method whose parameters can be dynamically determined for each point. Within the improved SCSD approach, the differential result of the amplitude spectrum is used as input to improve the sparsity. Moreover, the ratios between the SCSD output and its input are applied to weigh the Fourier spectrum and maintain the phase information. Finally, the inverse fast Fourier transform and squared envelope spectra are applied to detect the fault characteristics. Bearing and gearbox vibration signals are used to validate the proposed methodology. The experimental results show that the proposed method is superior to some typical methods and the proposed index are robust to the interferences from aperiodic impulses. Therefore, the proposed method has great potential in the fault diagnosis of rotating machine.

Best Time Domain Features for Early Detection of Faults in Rotary Machines Using RAT and ANN

Background Bearing failure, the most frequent failure mode in rotating machinery is the typical mechanical fault. Such a failure might result in substantial financial losses at the workplace. One of the approaches made possible by other signal processing techniques is the early identification of various faults in rotating machinery; including bearing failures, misalignment, and others.PurposeThis fault is associated with many features used to diagnose different faults; thus, the Diagnostic Features (DF) is estimated at limited cyclic frequencies that refer to machine faults.MethodTwo methods are used to extract the DF. The first one depends on time-domain features. The second is based on an advanced representation of the frequency domain, which depends on spectral coherence (SCoh) data over the spectral frequency domain using a center frequency and frequency range determined by a 1/3 binary tree structure. The calculated DFs are represented by a 2D map against the center frequency and frequency resolution. The maps from different fault features are collected to form the diagnostic patterns. The best characteristics connected to these various flaws can be found using statistical techniques like reverse arrangement tests (RAT). Artificial neural networks (ANN) may be trained and auto-diagnosed using the results from the best characteristics.ResultsUsing RAT is considered very important to summarize features. This method is given good results in training and diagnosis.ConclusionsAdditionally, ANN and RAT provide a detection result of 100% based on the description of the machine's operating situation, whether it functioned commonly or incorrectly.

Fault Diagnosis of Rotary Machines Using Machine Learning

Classification of faults in rotary machines using machine learning is gaining attention in the field of science and engineering. In rotating machinery, misalignment is a common fault. This type of fault has been extensively studied in the literature using the vibration signals produced by rotary machines. This study proposes an approach based on machine learning techniques to diagnose misalignments in rotary machines under various conditions. A personalized diagnostic fault approach is proposed to detect misalignment faults. The approach includes three steps. First, the data acquisition model is developed to obtain signals (fault samples). The rotor vibration signals in stationary rotation conditions were obtained by two inductive proximity sensors with analog output, and the data were collected by a data acquisition device. Then, to generate the faulty training samples, each data acquisition signal is transformed to the frequency domain using Fast Fourier Transform (FFT). Finally, using the samples obtained through the feature selection techniques, machine learning algorithms Random Forest, Naïve Bayes and SVM were evaluated, resulting in classifications with different efficiencies. The results show that the SVM algorithm outperforms the Naïve Bayes and Random Forest algorithms when the same number of features is used. The proposed personalized diagnostic approach was applied to detect faults of rotating electrical machines misalignment with success.

Real-time identification of performance degradation stages of rolling element bearings by RVCFI

The rolling element bearing is a critical component, and its fault results in most of the faults in rotary machines. The performance condition monitoring of bearings can improve the safety of equipment and can provide a reasonable maintenance plan at the optimal time. To identify the initial fault time (IFT) and performance degradation stages of a bearing based on the sampling signal from the start to the current time in real time, the monitoring indicator of the initial fault (MIIF) and the monitoring indicator of the degradation stages (MIDS) are constructed. Firstly, multiple features with stable and high robustness are calculated based on the envelope spectrum of the vibration signal. And these features are standardized and integrated by the weighted-sum of multiple standardized features into a fused indicator. Then, the online variation coefficient of the fused indicator and its rate are calculated. Finally, the MIIF and MIDS can be obtained using the variation coefficient and cumulative sum based on the rate of the variation coefficient of the fused indicator, respectively. Meanwhile, the adaptivity and versatility of the multi-resolution singular value decomposition algorithm are also improved. The proposed methods are verified using two public tested data packets. It is shown from the results that the methods are able to efficiently identify the IFT and performance degradation stages of a bearing in a timely manner.

Deep multiple auto-encoder with attention mechanism network: A dynamic domain adaptation method for rotary machine fault diagnosis under different working conditions

Intelligent fault diagnosis methods based on deep learning have achieved noteworthy application results in health diagnosis of rotating machinery. However, the fault data distribution discrepancy caused by different working conditions in real industrial scenarios can deteriorate the diagnosis performance of model. And extracted features by multi-ensemble deep auto-encoder neglect the contribution degree of each deep auto-encoder. Inspire by the demands, a dynamic domain adaptation method based on deep multiple auto-encoders with attention mechanism (DMAEAM-DDA) is proposed for rotary machine fault diagnosis under different working conditions. Firstly, combined with attention mechanism, pre-trained multiple deep auto-encoder with six different activation functions are utilized to construct deep multiple auto-encoder with attention mechanism network for extracting feature. Then the dynamic domain factor is calculated to automatically assign the weight of the marginal and conditional distribution for learning domain invariant fault features. Finally, two rotary machine experiments are employed to verify the availability of the proposed DMAEAM-DDA method, and the results show the proposed DMAEAM-DDA method has better superiority and outstanding stability compared to other methods.

Fast Real-Time RDFT- and GDFT-Based Direct Fault Diagnosis of Induction Motor Drive

This paper presents the theoretical analysis and experimental verification of a direct fault harmonic identification approach in a converter-fed electric drive for automated diagnosis purposes. On the basis of the analytical model of the proposed real-time direct fault diagnosis, the fault-related harmonic component is calculated using recursive DFT (RDFT) and Goertzel DFT (GDFT), applied instead of the full spectrum calculations required in the most popular FFT algorithm. The simulation model of an inverter sensorlessly controlled induction motor drive is linked with the induction machine rotor fault model for testing the sensitivity of the GDFT- and RDFT-based fault diagnosis to state variable estimation errors. According to the presented simulation results, the accuracy of the direct identification of a fault-related harmonic is sensitive to the quality of fault harmonic frequency estimation. The sensitivity analysis with respect to RDFT and GDFT algorithms is included. Based on the experimental setup with a sensorlessly controlled induction motor drive with the investigated rotor fault, fault diagnosis algorithms were implemented in the microprocessor by integration with the control system in one microcontroller and experimentally verified. The RDFT and GDFT approach has shown accurate and fast direct automated fault identification at a significantly decreased number of arithmetical operations in the microcontroller, which is convenient for the frequency-domain fault diagnosis in electric drives and supports fault-tolerant control system implementation.

Classification of rotary machine fault considering signal differences

Classification of rotary machine fault considering signal differences

Multiple Frequency Modulation Components Detection and Decomposition for Rotary Machine Fault Diagnosis

Multiple Frequency Modulation Components Detection and Decomposition for Rotary Machine Fault Diagnosis

Feature extraction and recognition of rotating machinery fault noise based on convolutional neural networks

Rotating machines are common equipment in industrial production, which may cause failure for a long time. Because of its convenient use and non-destructive to itself, acoustic detection method is suitable for fault diagnosis of rotating machinery. The convolution neural network model is used to identify several typical rotating machine faults. The repeatability experiments and different training sets show that the method has good universality. A visual fault identification system is built, and the effect of the system is verified by experiments.

A multi-source ensemble domain adaptation method for rotary machine fault diagnosis

Transfer learning has good ability to transfer knowledge for fault diagnosis under different working condition, while domain mismatches or domain shift can still occur during single-source domain transfer fault diagnosis. To alleviate the problem, a multi-source ensemble domain adaptation method is proposed for rotary machinery fault diagnosis. Firstly, multi-source and target domain anchor adapters are constructed based on class-central samples from multi-source domain. Secondly, multi-source ensemble domain adaptation transfer fault diagnosis model considering the mutual difference between multi-source domain is established to obtain multiple classifiers and prediction results. Then the classifiers with good performance are integrated to achieve final diagnosis model and results by ensemble of anchor adapters. Finally, the performance of the proposed method is verified by two experiments. The results show that the proposed method has ability to learn more comprehensive and general domain invariant diagnosis knowledge, significant diagnosis performance and robustness than other transfer learning methods.

Remaining Useful Life Prediction of Broken Rotor Bar Based on Data-Driven and Degradation Model

Rotating machines such as induction motors are crucial parts of most industrial systems. The prognostic health management of induction motor rotors plays an essential role in increasing electrical machine reliability and safety, especially in critical industrial sectors. This paper presents a new approach for rotating machine fault prognosis under broken rotor bar failure, which involves the modeling of the failure mechanism, the health indicator construction, and the remaining useful life prediction. This approach combines signal processing techniques, inherent metrics, and principal component analysis to monitor the induction motor. Time- and frequency-domains features allowing for tracking the degradation trend of motor critical components that are extracted from torque, stator current, and speed signals. The most meaningful features are selected using inherent metrics, while two health indicators representing the degradation process of the broken rotor bar are constructed by applying the principal component analysis. The estimation of the remaining useful life is then obtained using the degradation model. The performance of the prediction results is evaluated using several criteria of prediction accuracy. A set of synthetic data collected from a degraded Simulink model of the rotor through simulations is used to validate the proposed approach. Experimental results show that using the developed prognostic methodology is a powerful strategy to improve the prognostic of induction motor degradation.

Kernel extreme learning machine based hierarchical machine learning for multi-type and concurrent fault diagnosis

The detection and identification of faults in rotary machines are of great significance to the mechanical equipment reliability especially the gearbox. Traditional machine learning algorithms suffer from low diagnosis accuracy of faults that have multiple types and exist concurrently. A novel machine learning method called hierarchical machine learning (HML) was proposed in this study to improve the faults diagnosis accuracy. The proposed algorithm consists of two layers. The first layer comprises a traditional machine learning model to identify the faults with distinguishable features and filter out these faults with indistinguishable features. The second layer model recognizes the faults filtered out by the first layer. In order to verify the effectiveness of the proposed method, the gearbox simulation experiment is carried out in the study. The simulation results validate that the proposed method outperforms other algorithms under an identical measure.

Box-Cox sparse measures: A new family of sparse measures constructed from kurtosis and negative entropy

Sparse measures have attracted lots of interests from many fundamental research domains to be as objective functions of signal processing algorithms, health indices of degradation modeling and input features to machine learning algorithms. Among them, kurtosis and negative entropy are the most two popular sparse measures to characterize the sparsity of signals. For example, kurtosis and negative entropy are used in machine condition monitoring to quantify the sparsity of repetitive transients caused by localized rotating machine faults and to indicate an onset of early rotating faults. When kurtosis and negative entropy are decomposed into the sum of weighted normalized square envelope, the main difference between kurtosis and negative entropy is whether the logarithm transformation is applied to normalized square envelope to form a weight. In this paper, Box-Cox transformation as generalized power transformation is introduced to generalize the weights used in kurtosis and negative entropy and subsequently a new family of sparse measures, coined as Box-Cox sparse measures (BCSM), are proposed. The only parameter in the proposed BCSM is a transformation parameter λ⩾0. The contributions of this paper are summarized as follows. Firstly, this paper provides new propositions for intuitive sparse attributes of the proposed BCSM, which theoretically prove that the proposed BCSM satisfies all six intuitive sparse attributes. Secondly, in numerical and experimental studies, it is shown that (1) the proposed BCSM converges when the length of a signal increases; (2) only when a distribution is quite sparse, the proposed BCSM with λ>1 can indicate the sparsity of the distribution. Being different form the performance of the proposed BCSM with λ>1, the proposed BCSM with 0⩽λ⩽1 can steadily indicate that a distribution is getting sparser, which indicates that negative entropy (λ=0) is the best choice among all the proposed sparse measures and it is better than kurtosis (λ=1) to quantify the sparsity of repetitive transients caused by rotating faults for machine condition monitoring; (3) the proposed BCSM with 0⩽λ⩽1 is more effective in monitoring bearing and gear health conditions than the proposed BCSM with λ>1. Thirdly, the proposed BCSM of a complex Gaussian signal is investigated to provide a theoretical baseline for machine condition monitoring. Finally, the proposed BCSM can be applied to any situations, where sparse measures are needed.

Transient impulses enhancement based on adaptive multi-scale improved differential filter and its application in rotating machines fault diagnosis

Transient impulses caused by local defects are critical for the fault detection of rotating machines. However, they are extremely weak and overwhelmed in the strong noise and harmonic components, making the transient features are very difficult to be extracted. This paper proposes an adaptive multi-scale improved differential filter (AMIDIF) to enhance the identification of transient impulses for rotating machine fault diagnosis. In this scheme, firstly, the AMIDIF is performed to decompose the measured signal of rotating machine into a series of multi-scale improved differential filter (MIDIF) filtered signals. Subsequently, in view of the MIDIF filtered signals exhibit varying extents of validity in revealing fault features, a weighted reconstruction method using correlation analysis is proposed in which the weighted coefficients are counted and distributed to the corresponding MIDIF filtered signals to highlight the effective MIDIF filtered signals and weaken the invalid ones. Finally, the transient impulse components of rotating machinery are obtained by multiplying the weighted coefficients and the MIDIF filtered signals under different scales. Furthermore, the fault types of rotating machines are inferred from the fault defect frequencies in the envelope spectrum of the transient impulses. Simulation analysis and experimental studies are implemented to verify the performance of the AMIDIF compared with the state-of-the-art methods including spectral kurtosis (SK), multi-scale average combination different morphological filter (ACDIF) and multi-scale morphology gradient product operation (MGPO). The results prove that the AMIDIF has excellent performance in extracting transient features for rotating machines fault diagnosis.

Rotating acoustic source localization: A power propagation forward model and its high-resolution inverse methods

The rotating-acoustic source localization has played an important role in rotary machine fault diagnosis, engine noise reduction and propeller recognition etc. To achieve high-resolution localization of fast rotating sources, this paper proposes an improved power propagation forward model of rotating acoustic source based on the equivalent source hypothesis. Then the ill-posed inverse problem derived from the forward power model is solved robustly by proposed two sparsity-based methods: the Least Absolute Shrinkage and Select Operator for Rotating-acoustic Sources (LASSO-RS) and Least Angle Regression for Rotating-acoustic Sources (LAR-RS). The contributions of this paper are that, at one hand, the improved forward model is indeed time-invariant for the fast-rotating source owing to the time-domain de-Doppler technique; at the other hand, high-resolution acoustic maps can be obtained by proposed LASSO-RS and LAR-RS thanks to the sparsity-based regularization, even under very low signal-to-noise ratio (SNR). Moreover, the proposed LAR-RS is the data-driven method, rather than the parameter-dependent method such as the LASSO-RS with careful selection of regularization parameter. In simulations and experiments, the proposed methods can robustly localize rotating monopoles in the condition of 3000 RPM rotation speed (50 Hz), −5 dB SNR, and 2500 Hz working frequency.