Learning-based Fault Diagnosis Methods Research Articles

Unsupervised fault diagnosis of wind turbine bearing via a deep residual deformable convolution network based on subdomain adaptation under time-varying speeds

Recent years have seen the rapid development and marvelous achievement of deep learning-based fault diagnosis (FD) methods which assume that training data and testing data have the same distribution. However, in real FD of wind turbine bearing (WTB), the particularity of time-varying speeds makes a huge difference in the distribution of training data and testing data, greatly increasing the difficulty of FD. Accordingly, in this paper, a novel deep residual deformable subdomain adaptation framework is proposed for cross-domain failure diagnosis of WTB under time-varying speeds. In the proposed approach, the traditional residual network is improved by using a deformable convolution module to replace plain counterparts, which can make the feature representation of an object adapt its configuration and enhance the ability of the model to extract transferable features. Moreover, the popular FD model based on domain adversarial neural nets and global maximum mean discrepancy is improved by removing the adversarial training mechanism and employing a local maximum mean discrepancy to align the distributions of the identical fault type in different domains, making the diagnostic model simpler and more efficient. Two experimental cases under time-varying speeds are conducted to analyze the performance of the proposed approach and the results indicate that this method can utilize the knowledge in the source domain to diagnose the fault in the target domain. Compared with the existing methods, the diagnosis accuracy and efficiency are significantly improved, demonstrating its effectiveness and potential applications in fault transfer diagnosis of wind turbine bearing.

Transfer Graph-Driven Rotating Machinery Diagnosis Considering Cross-Domain Relationship Construction

Transfer learning-based fault diagnosis methods borrow source-domain knowledge to achieve diagnosis task for the unlabeled target domain. However, existing research articles mainly lie in feature mapping and model transfer, ignoring the relationship between cross-domain samples. Once connections between cross-domain samples with the same label can be constructed, label propagation will be easier even if there is a cross-domain distribution discrepancy. In this article, a transfer graph-driven rotating machinery diagnosis considering cross-domain relationship construction is proposed. Specifically, signal spectrum is extracted by fast Fourier transform mapping raw signals to identical feature space. Transfer graphs are constructed by the Euclidean distance between nodes, where the relationships between the same domain samples, even cross-domain samples, are established. Then, the graph convolutional network (GCN), trained by source-domain samples and less target-domain samples, is utilized for cross-domain diagnosis tasks. The experimental results demonstrate the effectiveness of the proposed method. In addition, trained GCN enables diagnosing on newly constructed target-domain graphs. It shows the ability to continuously learn new transferable knowledge.

Fault Diagnosis Method for Bearing Based on Digital Twin

The bearing is an essential component of rotating machinery, as its reliability and running state have a direct impact on the machinery’s performance. Considering that deep learning-based fault diagnosis methods for bearing require a large amount of labelled sample data, a novel fault diagnosis framework based on digital twin is proposed. In the case of fault data available, self-organizing maps with minimum quantization error and support vector machine are employed to analyze the data. Where fault data is unavailable, a bearing digital twin model is first constructed to simulate the data, and the convolutional neural network combined with transfer learning is utilized to diagnose the bearing faults. Then, the law of bearing performance degradation is investigated. The effectiveness of the proposed method is verified using bearing vibration data.

Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals

Vibration measurement and monitoring are essential in a wide variety of applications. Vibration measurements are critical for diagnosing industrial machinery malfunctions because they provide information about the condition of the rotating equipment. Vibration analysis is considered the most effective method for predictive maintenance because it is used to troubleshoot instantaneous faults as well as periodic maintenance. Numerous studies conducted in this vein have been published in a variety of outlets. This review documents data-driven and recently published deep learning techniques for vibration-based condition monitoring. Numerous studies were obtained from two reputable indexing databases, Web of Science and Scopus. Following a thorough review, 59 studies were selected for synthesis. The selected studies are then systematically discussed to provide researchers with an in-depth view of deep learning-based fault diagnosis methods based on vibration signals. Additionally, a few remarks regarding future research directions are made, including graph-based neural networks, physics-informed ML, and a transformer convolutional network-based fault diagnosis method.

Intelligent Fault Diagnosis for Inertial Measurement Unit through Deep Residual Convolutional Neural Network and Short-Time Fourier Transform

An Inertial Measurement Unit (IMU) is a significant component of a spacecraft, and its fault diagnosis results directly affect the spacecraft’s stability and reliability. In recent years, deep learning-based fault diagnosis methods have made great achievements; however, some problems such as how to extract effective fault features and how to promote the training process of deep networks are still to be solved. Therefore, in this study, a novel intelligent fault diagnosis approach combining a deep residual convolutional neural network (CNN) and a data preprocessing algorithm is proposed. Firstly, the short-time Fourier transform (STFT) is adopted to transform the raw time domain data into time–frequency images so the useful information and features can be extracted. Then, the Z-score normalization and data augmentation strategies are both explored and exploited to facilitate the training of the subsequent deep model. Furthermore, a modified CNN-based deep diagnosis model, which utilizes the Parameter Rectified Linear Unit (PReLU) as activation functions and residual blocks, automatically learns fault features and classifies fault types. Finally, the experiment’s results indicate that the proposed method has good fault features’ extraction ability and performs better than other baseline models in terms of classification accuracy.

Development of deep reinforcement learning-based fault diagnosis method for rotating machinery in nuclear power plants

Rotating machinery fault can cause accidents like loss of flow or turbine trip that seriously threaten the operation safety of nuclear power plants (NPPs). Artificial intelligence algorithms, like machine learning or deep learning methods, can implement fault diagnosis by sample learning with no reliance on fault mechanism or physics model of the equipment. However, the accumulated fault samples are small due to high operation safety requirements of the plant. Small sample learning is challenging and usually leads to degradation of model performance. The emerging deep reinforcement learning (DRL) algorithm can incorporate the advantages of automatic feature extraction from deep learning algorithm and interactive learning from reinforcement learning algorithm, is expected to have better learning ability and robustness. In this paper, two DRL fault diagnosis models are proposed and compared. Experiment results show that the proposed models can achieve very high diagnosis accuracy of over 99% and outperform all the baseline models (support vector machine, convolutional neural network and gated recurrent unit neural network) in all test cases in this paper.

Uncertainty-based contrastive prototype-matching network towards cross-domain fault diagnosis with small data

Deep learning-based fault diagnosis methods have to be trained by a large amount of labeled data for accurate diagnosis results. However, in real-case industrial scenarios, the data available is limited since the difficulty of obtaining fault samples. In addition, the monitoring data always come from various working conditions. As a result, data scarcity and domain shift have become two main factors that limit the performance of diagnosis models. We called this problem the few-shot cross-domain fault diagnosis, which has been rarely explored. To deal with the above challenge, we propose a novel uncertainty-based contrastive prototype-matching network (UCPMnet). Specifically, two main parts are conducted for UCPMnet. Considering the construction of representation spaces for compact intra-class and sparse inter-class embeddings, the contrastive prototypical network (CPN) is established by remolding the prototypical network. Subsequently, an uncertainty-based prototype-matching (UPM) method is presented for class-wise domain adaptation based on pseudo-label learning. At the same time, an estimation approach of prediction uncertainty is introduced to adaptively rectify the threshold for screening the pseudo label, which aims to mitigate the effect of noisy predictions for prototype-matching. Extensive experiments are conducted on two datasets, and four classical methods are selected for comparison. The results corroborate the superiority of the UCPMnet for fault diagnosis in the case of small data.

A comparative study of deep learning-based fault diagnosis methods for rotating machines in nuclear power plants

Deep learning methods with powerful automatic feature extraction and end-to-end modeling capabilities can build fault diagnosis models based on raw data without relying on manual feature extraction procedures. In this paper, a comparative study of deep learning-based fault diagnosis methods for rotating machines in nuclear power plants is conducted. 4 deep learning models, namely, Deep Feed-forward Neural Network, Convolutional Neural Network, Gated Recurrent Unit Neural Network and Convolutional Recurrent Neural Network (CRNN), are selected. 2 publicly available experimental datasets of bearing faults are selected as modeling data. The model performance is compared under 3 cases: original sample size, sample reduction and noise addition. The results show that the CRNN model can achieve state-of-the-art accuracy and the best performance in all test cases. It has the advantages of good small sample learning capability and anti-noise robustness compared to other models in this paper.

Feature distance-based deep prototype network for few-shot fault diagnosis under open-set domain adaptation scenario

Transfer learning-based fault diagnosis methods have revealed prominent application prospects. However, most of these methods can achieve efficient knowledge transfer across domains only when the source and target domains share the exact identical label space. In practical applications, the model trained on the source domain may be faced with a larger target domain, because unknown fault types may emerge unpredictably in testing stage. Besides, a large amount of labeled data is tough to obtain for training. To address these problems, a feature distance-based deep prototype network (FDDPN) is proposed for few-shot fault diagnosis under open-set domain adaptation scenario. The proposed method contains three stages for training. The prototype of each known class is calculated via novel k-means feature clustering algorithm in the first stage. In the second stage, the few labeled target samples are assigned to the class of the nearest prototype according to the feature distance. Finally, compactness between the few target labeled samples and the corresponding prototypes is enhanced in the third stage. Experimental results demonstrated that the proposed method can realize accurate classification of known classes and effective rejection of unknown classes.

A Deep Domain-Adversarial Transfer Fault Diagnosis Method for Rolling Bearing Based on Ensemble Empirical Mode Decomposition

In recent years, the deep learning-based fault diagnosis methods for rotating mechanical equipment have attracted great concern. However, because the data feature distributions present differences in applications with varying working conditions, the deep learning models cannot provide satisfactory performance of fault prediction in such scenarios. To address this problem, this paper proposes a domain adversarial-based rolling bearing fault transfer diagnosis model EMBRNDNMD. First of all, an EEMD-based time-frequency feature graph (EEMD-TFFG) construction method is proposed, and the time-frequency information of nonlinear nonstationary vibration signal is extracted; secondly, a multi-branch ResNet (MBRN) structure is designed, which is used to extract deep features representing the bearing state from EEMD-TFFG; finally, to solve the model domain adaptation transfer problem under varying working conditions, the adversarial network module and MK-MMD distribution difference evaluation method are introduced to optimize MBRN, so as to reduce the probability distribution difference between the deep features of source domain and target domain, and to improve the accuracy of EMBRNDNMD in state diagnosis of target domain. The results of experiments carried out on two bearing fault test platforms prove that EMBRNDNMD can maintain an average accuracy above 97% in fault transfer diagnosis tasks, and this method also has high stability and strong ability of scene adaptation.

Fault Diagnosis Method for UHVDC Transmission Based on Deep Learning under Cloud-Edge Architecture

Aiming at the problem of fault diagnosis after the UHVDC system fails, a deep learning-based UHVDC fault diagnosis method under the cloud-edge architecture is proposed. First, based on the edge computing framework of the “cloud” + “edge terminal,” a four-layer fault diagnosis structure including the data integration layer, edge prediction layer, cloud diagnosis layer, and human-computer interaction layer is constructed. Then, a fault data set is constructed by finding effective information that can fully reflect the DC fault in the huge power grid environmental information, and the data set is screened, processed by classification feature fields, and linearly normalized. Finally, a deep convolutional generative adversarial network (DCGAN) is constructed by introducing a deep convolutional neural network (DCNN) into the traditional generative adversarial network (GAN) for data training and DC fault diagnosis. In addition, the corresponding process is given. The proposed method and the other three methods are compared and analyzed by simulation experiments. The results show that the method proposed has the highest accuracy and smallest error loss value of 95.6% and 0.18, respectively. It has the highest diagnosis accuracy under different fault types, and its performance is better than the other three comparison methods.

Real-Time Fault Detection and Condition Monitoring for Industrial Autonomous Transfer Vehicles Utilizing Edge Artificial Intelligence.

Early fault detection and real-time condition monitoring systems have become quite significant for today’s modern industrial systems. In a high volume of manufacturing facilities, fleets of equipment are expected to operate uninterrupted for days or weeks. Any unplanned interruptions to equipment uptime could jeopardize manufacturers’ cycle time, capacity, and, most significantly, credibility for their customers. With the help of smart manufacturing technologies, companies have started to develop and integrate fault detection and classification systems where end-to-end constant monitoring of equipment is facilitated, and smart algorithms are adapted for the early generation of fault alarms and classification. This paper proposes a generic real-time fault diagnosis and condition monitoring system utilizing edge artificial intelligence (edge AI) and a data distributor open source middleware platform called FIWARE. The implemented system architecture is flexible and includes interfaces that can be easily expanded for various devices. This work demonstrates it for condition monitoring of autonomous transfer vehicle (ATV) equipment targeting a smart factory use case. The system is verified in a designated industrial model environment in a lab with a single ATV operation. The anomaly conditions of the ATV are diagnosed by a deep learning-based fault diagnosis method performed in the Edge AI unit, and the results are transferred to the data storage via a data pipeline setup. The proposed system’s Edge AI solution for the ATV use case provides significant real-time performance. The network bandwidth requirement and total elapsed data transfer time have been reduced by 43 and 37 times, respectively. The proposed system successfully enables real-time monitoring of ATV fault conditions and expands to a fleet of equipment in a real manufacturing facility.

An Evolving Learning-Based Fault Detection and Diagnosis Method: Case Study for a Passive Chilled Beam System

An Evolving Learning-Based Fault Detection and Diagnosis Method: Case Study for a Passive Chilled Beam System

Data Augmentation via Randomized Wavelet Expansion and Its Application in Few-Shot Fault Diagnosis of Aviation Hydraulic Pumps

In general, deep learning-based fault diagnosis methods need a large number of training samples, which are often not available in real applications. Aiming at this problem, this article develops a new data augmentation method, i.e., randomized wavelet expansion (RWE), to generate a set of synthesis samples that share similar characteristics with the original sample. The first key point is that the amplitudes of wavelet coefficients at a randomly selected frequency band are enlarged through random expansion. Another key point is that the synthesis samples are processed to have the same mean values and standard deviations as their corresponding original sample. Afterward, the synthesis samples are used as the training dataset to train a deep convolutional neural network (CNN) for implementing the few-shot fault diagnosis of aviation hydraulic pumps. Finally, the performance has been validated through a series of experiments.

Fault Diagnosis of Aeroengine Control System Sensor Based on Optimized and Fused Multidomain Feature

Improving the efficacy and dependability of aeroengines requires timely and effective sensor fault diagnosis. Deep learning-based fault diagnosis method is a current research hotspot. To overcome some of the method’s existing shortcomings and improve the reliability of fault diagnosis, this paper proposes a novel intelligent fault diagnosis framework with higher quality features and more effective fault classifiers. The proposed plan includes three stages. Firstly, multidomain features (time and frequency domain features) are extracted to describe the sensor’s health from several dimensions. Secondly, the advanced Henry gas solubility optimization algorithm (HGSO) is applied to improve classification accuracy through feature selection, and the operating conditions and the features extracted by the network are fused as fault indicators. Finally, an adaptive deep belief network (ADBN) with relu-softsign combination activation layers, variable learning rate, and optimized network structure is proposed as the fault identifier. The advantages of the first two stages lie in the complete utilization of information and reducing the data dimension. In addition, the detection performance and the convergence speed is enhanced by the proposed ADBN. The experimental data are derived from a combination of measured and simulated data generated from the aeroengine model. The experimental results indicate that the improved method can produce better performance and outcomes than the unimproved methods for all fault scenarios, with a higher diagnostic accuracy of 98.1% and a reduced time of 98 s. The efforts of this study provide a efficient and adaptable way to aeroengine sensor fault diagnosis.

Moment matching-based intraclass multisource domain adaptation network for bearing fault diagnosis

Deep learning based fault diagnosis methods assume that training and testing data with sufficient labels are available and share a same distribution. In practical scenarios, this assumption does not generally hold due to variable working conditions of rotating machineries and the difficulty in labeling vibration data under all working conditions. Transfer learning (TL) overcomes this problem by utilizing knowledge learned from the source domain to help accomplish tasks on the target domain. Although TL based fault diagnosis has been considerably studied, most studies mainly focus on single-source TL. Since multisource domains with labeled samples from which more useful knowledge can be extracted are available, in this paper, a novel multisource TL model, called the moment matching-based intraclass multisource domain adaptation network, is proposed. This model uses a feature learner to generate features of each source and target domain data to enable the joint weight classifier to predict target labels. It also introduces a moment matching-based distance metric to reduce the distance among all source domains and the target domain. During the training of the model, an intraclass alignment training strategy is applied to match the marginal and conditional distributions of each domain simultaneously. Experiments on two datasets are performed, wherein the proposed method is used to identify bearing fault types under four load conditions. Experiment results, such as high diagnostic accuracies support the reliability and generalizability of the proposed model.

Residual deep subdomain adaptation network: A new method for intelligent fault diagnosis of bearings across multiple domains

The existing transfer learning-based fault diagnosis methods basically make use of fault knowledge learnt from one source domain to another target domain. Due to variable operating conditions, transfer tasks in the fault diagnosis need be inevitably performed many times, which limit their industrial applicability. To address the problem, a new residual deep subdomain adaptation network is proposed for intelligent fault diagnosis of bearings across multiple domains. Its remarkable advantage is that only one transfer task need be executed no matter how the operating conditions change. In this method, a residual network is constructed to extract transferable features from source domain and target domains. And, local maximum mean discrepancy is introduced to accurately align the distribution of the related subdomains within the same category in the source domain and the target domains. Comprehensive experimental results confirm that the proposed method can make use of fault knowledge learnt from the single source domain for fault diagnosis in the multiple target domains. The classification accuracy has a significant improvement as compared with the existing popular methods.

An enhanced non-local weakly supervised fault diagnosis method for rotating machinery

Despite the considerable success achieved by deep learning-based fault diagnosis methods, a powerful deep learning model must require a substantial set of training data to obtain a strong generalization ability in practical application. Focusing on the fault diagnosis case under small data sets, an enhanced non-local weakly supervised fault diagnosis method is proposed in this paper. In the proposed method, the few-shot learning strategy is presented to perform learning task augmentation to alleviate the overfitting problem caused by scarce training data, and the non-local operation is investigated to further enhance the feature extraction ability of convolutional neural network through capturing the long-range dependency. Two fault diagnosis experiments which were conducted on rolling bearing and bevel gear are carried out. The proposed method obtains 97.23% and 99.76% fault diagnosis accuracy in bearing data sets and gear data sets, which outperforms the traditional fault diagnosis methods.

Efficient federated convolutional neural network with information fusion for rolling bearing fault diagnosis

In the past year, various deep learning-based fault diagnosis methods have been designed to guarantee the stable, safe, and efficient operation of electromechanical systems. To achieve excellent diagnostic performance, the conventional centralized learning (CL) approach is adopted to collect as much data as possible from multiple industrial participants for deep model training. Due to privacy concerns and potential conflicts, industrial participants are unwilling to share their data resources. To solve the issues, this study proposes a fault diagnosis method based on federated learning (FL) and convolutional neural network (CNN), which allows different industrial participants to collaboratively train a global fault diagnosis model without sharing their local data. Model training is locally executed within each industrial participant, and the cloud server updates the global model by aggregating the local models of the participants. Specifically, an adaptive method is designed to adjust the model aggregation interval according to the feedback information of the industrial participants in order to reduce the communication cost while ensuring model accuracy. In addition, momentum gradient descent (MGD) and dropout layer are used to accelerate convergence rate and avoid model overfitting, respectively. The effectiveness of the proposed method is verified on a non-independent and identically distributed (non-iid) rolling bearing fault dataset. The experiment results indicate that the proposed method has higher accuracy than traditional fault diagnosis methods. Moreover, this study provides a promising collaborative training approach to the fault diagnosis field.

Low-Pass Filtering Empirical Wavelet Transform Machine Learning Based Fault Diagnosis for Combined Fault of Wind Turbines.

Fault diagnosis of wind turbines is of great importance to reduce operating and maintenance costs of wind farms. At present, most wind turbine fault diagnosis methods are focused on single faults, and the methods for combined faults usually depend on inefficient manual analysis. Filling the gap, this paper proposes a low-pass filtering empirical wavelet transform (LPFEWT) machine learning based fault diagnosis method for combined fault of wind turbines, which can identify the fault type of wind turbines simply and efficiently without human experience and with low computation costs. In this method, low-pass filtering empirical wavelet transform is proposed to extract fault features from vibration signals, LPFEWT energies are selected to be the inputs of the fault diagnosis model, a grey wolf optimizer hyperparameter tuned support vector machine (SVM) is employed for fault diagnosis. The method is verified on a wind turbine test rig that can simulate shaft misalignment and broken gear tooth faulty conditions. Compared with other models, the proposed model has superiority for this classification problem.