sensors-logo

Journal Browser

Journal Browser

Special Issue "Deep Learning, Artificial Neural Networks and Sensors for Fault Diagnosis"

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Fault Diagnosis & Sensors".

Deadline for manuscript submissions: closed (30 November 2020).

Special Issue Editor

Prof. Dr. Steven Chatterton
E-Mail Website
Guest Editor
Politecnico di Milano, Department of Mechanical Engineering, Via G. La Masa 1, 20156 Milano, Italy
Interests: rotordynamics; fault diagnostics; rolling element bearings; oil-film bearings
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Nowadays, fault diagnosis of mechanical components is a real challenging task in industrial field and is often performed by means of the analysis of sensor signals. Accelerometers, temperature and pressure probes are examples of typical sensors used in the diagnosis of a wide range of industrial machines. A lot of signal processing techniques have been developed in the years, from simple statistic indicators to more sophisticated tools often based on frequency analysis. The result of such analysis needs to be interpreted for the assessment of the type of the damage and its level of severity. The type of the damage is often detected by the occurrence of known features in the signal, whereas the severity of the fault is performed by tracking some damage indicators as a function of the machine running time. Deviation of such indicators from the nominal value of healthy case is used to classify the intensity of the damage.

In such activity, the application of artificial neural networks is become very popular in fault diagnosis, where the damage indicators and signal features are classified in an automatic way. The training phase is the critical part of the process and need the availability of data of healthy and damaged cases. The core of the algorithm is given by the connections between the layers of the network. The number of layers and connections gives the power of the network by replicating the connections of neurons in a human brain. Recently, the power of artificial neural networks increased with the number of layers and connections leading to the so-called deep neural networks. In this sense deep learning allows the training phase to be avoided.

The Special Issue “Deep Learning, Artificial Neural Networks and Sensors for Fault Diagnosis” aims to summarize the state of the art of the research of fault diagnosis of industrial machines and components by means of artificial neural networks and deep learning.

The purpose of the Special Issue is to collect original research papers or review articles. Although the emphasis is on practical applications, we also welcome fundamental studies. 

Sincerely,

Prof. Dr. Steven Chatterton
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Deep Learning
  • Artificial Neural Networks
  • Convolutional Neural Network
  • Gears fault diagnosis
  • Rolling element bearings diagnosis
  • Machines fault diagnosis

Published Papers (23 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Other

Article
Remaining Useful Life (RUL) Prediction of Equipment in Production Lines Using Artificial Neural Networks
Sensors 2021, 21(3), 932; https://doi.org/10.3390/s21030932 - 30 Jan 2021
Cited by 4 | Viewed by 2241
Abstract
Predictive maintenance of production lines is important to early detect possible defects and thus identify and apply the required maintenance activities to avoid possible breakdowns. An important concern in predictive maintenance is the prediction of remaining useful life (RUL), which is an estimate [...] Read more.
Predictive maintenance of production lines is important to early detect possible defects and thus identify and apply the required maintenance activities to avoid possible breakdowns. An important concern in predictive maintenance is the prediction of remaining useful life (RUL), which is an estimate of the number of remaining years that a component in a production line is estimated to be able to function in accordance with its intended purpose before warranting replacement. In this study, we propose a novel machine learning-based approach for automating the prediction of the failure of equipment in continuous production lines. The proposed model applies normalization and principle component analysis during the pre-processing stage, utilizes interpolation, uses grid search for parameter optimization, and is built with multilayer perceptron neural network (MLP) machine learning algorithm. We have evaluated the approach using a case study research to predict the RUL of engines on NASA turbo engine datasets. Experimental results demonstrate that the performance of our proposed model is effective in predicting the RUL of turbo engines and likewise substantially enhances predictive maintenance results. Full article
Show Figures

Figure 1

Article
Sensor and Component Fault Detection and Diagnosis for Hydraulic Machinery Integrating LSTM Autoencoder Detector and Diagnostic Classifiers
Sensors 2021, 21(2), 433; https://doi.org/10.3390/s21020433 - 09 Jan 2021
Cited by 10 | Viewed by 1110
Abstract
Anomaly occurrences in hydraulic machinery might lead to massive system shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications following the faults and their associated damage. Hydraulics are mostly placed in ruthless [...] Read more.
Anomaly occurrences in hydraulic machinery might lead to massive system shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications following the faults and their associated damage. Hydraulics are mostly placed in ruthless environments, where they are consistently vulnerable to many faults. Hence, not only are the machines and their components prone to anomalies, but also the sensors attached to them, which monitor and report their health and behavioral changes. In this work, a comprehensive applicational analysis of anomalies in hydraulic systems extracted from a hydraulic test rig was thoroughly achieved. First, we provided a combination of a new architecture of LSTM autoencoders and supervised machine and deep learning methodologies, to perform two separate stages of fault detection and diagnosis. The two phases were condensed by—the detection phase using the LSTM autoencoder. Followed by the fault diagnosis phase represented by the classification schema. The previously mentioned framework was applied to both component and sensor faults in hydraulic systems, deployed in the form of two in-depth applicational experiments. Moreover, a thorough literature review of related work from the past decade, for autoencoders related fault detection and diagnosis in hydraulic systems, was successfully conducted in this study. Full article
Show Figures

Figure 1

Article
A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions
Sensors 2020, 20(24), 7205; https://doi.org/10.3390/s20247205 - 16 Dec 2020
Cited by 10 | Viewed by 850
Abstract
Rolling element bearings are a vital part of rotating machines and their sudden failure can result in huge economic losses as well as physical causalities. Popular bearing fault diagnosis techniques include statistical feature analysis of time, frequency, or time-frequency domain data. These engineered [...] Read more.
Rolling element bearings are a vital part of rotating machines and their sudden failure can result in huge economic losses as well as physical causalities. Popular bearing fault diagnosis techniques include statistical feature analysis of time, frequency, or time-frequency domain data. These engineered features are susceptible to variations under inconsistent machine operation due to the non-stationary, non-linear, and complex nature of the recorded vibration signals. To address these issues, numerous deep learning-based frameworks have been proposed in the literature. However, the logical reasoning behind crack severities and the longer training times needed to identify multiple health characteristics at the same time still pose challenges. Therefore, in this work, a diagnosis framework is proposed that uses higher-order spectral analysis and multitask learning (MTL), while also incorporating transfer learning (TL). The idea is to first preprocess the vibration signals recorded from a bearing to look for distinct patterns for a given fault type under inconsistent working conditions, e.g., variable motor speeds and loads, multiple crack severities, compound faults, and ample noise. Later, these bispectra are provided as an input to the proposed MTL-based convolutional neural network (CNN) to identify the speed and the health conditions, simultaneously. Finally, the TL-based approach is adopted to identify bearing faults in the presence of multiple crack severities. The proposed diagnostic framework is evaluated on several datasets and the experimental results are compared with several state-of-the-art diagnostic techniques to validate the superiority of the proposed model under inconsistent working conditions. Full article
Show Figures

Figure 1

Article
Intelligent Diagnosis towards Hydraulic Axial Piston Pump Using a Novel Integrated CNN Model
Sensors 2020, 20(24), 7152; https://doi.org/10.3390/s20247152 - 14 Dec 2020
Cited by 4 | Viewed by 790
Abstract
As a critical part of a hydraulic transmission system, a hydraulic axial piston pump plays an indispensable role in many significant industrial fields. Owing to the practical undesirable working environment and hidden faults, it is challenging to precisely and effectively detect and diagnose [...] Read more.
As a critical part of a hydraulic transmission system, a hydraulic axial piston pump plays an indispensable role in many significant industrial fields. Owing to the practical undesirable working environment and hidden faults, it is challenging to precisely and effectively detect and diagnose the varying fault in the engineering. Deep learning-based technology presents special strengths in processing mechanical big data. It can simultaneously complete the feature extraction and classification, and achieve the automatic information learning. The popular convolutional neural network (CNN) is exploited for its potent ability of image processing. In this paper, a novel combined intelligent method is developed for fault diagnosis towards a hydraulic axial piston pump. First, the conversion of signals to images is conducted via continuous wavelet transform; the effective feature is preliminarily extracted from the transformed time-frequency images. Second, a novel deep CNN model is constructed to achieve the fault classification. To disclose the potential learning in the disparate layers of the CNN model, the visualization of reduced features is performed by employing t-distributed stochastic neighbor embedding. The effectiveness and stability of the proposed model are validated through the experiments. With the proposed method, different fault types can be precisely identified and high classification accuracy is achieved in a hydraulic axial piston pump. Full article
Show Figures

Figure 1

Article
A Double-Channel Hybrid Deep Neural Network Based on CNN and BiLSTM for Remaining Useful Life Prediction
Sensors 2020, 20(24), 7109; https://doi.org/10.3390/s20247109 - 11 Dec 2020
Cited by 10 | Viewed by 1034
Abstract
In recent years, prognostic and health management (PHM) has played an important role in industrial engineering. Efficient remaining useful life (RUL) prediction can ensure the development of maintenance strategies and reduce industrial losses. Recently, data-driven based deep learning RUL prediction methods have attracted [...] Read more.
In recent years, prognostic and health management (PHM) has played an important role in industrial engineering. Efficient remaining useful life (RUL) prediction can ensure the development of maintenance strategies and reduce industrial losses. Recently, data-driven based deep learning RUL prediction methods have attracted more attention. The convolution neural network (CNN) is a kind of deep neural network widely used in RUL prediction. It shows great potential for application in RUL prediction. A CNN is used to extract the features of time-series data according to the spatial feature method. This way of processing features without considering the time dimension will affect the prediction accuracy of the model. On the contrary, the commonly used long short-term memory (LSTM) network considers the timing of the data. However, compared with CNN, it lacks spatial data extraction capabilities. This paper proposes a double-channel hybrid prediction model based on the CNN and a bidirectional LSTM network to avoid those drawbacks. The sliding time window is used for data preprocessing, and an improved piece-wise linear function is used for model validating. The prediction model is evaluated using the C-MAPSS dataset provided by NASA. The predicted results show the proposed prediction model to have a better prediction performance compared with other state-of-the-art models. Full article
Show Figures

Figure 1

Article
Deep Learning-Based Bearing Fault Diagnosis Method for Embedded Systems
Sensors 2020, 20(23), 6886; https://doi.org/10.3390/s20236886 - 02 Dec 2020
Cited by 8 | Viewed by 1580
Abstract
Bearing elements are vital in induction motors; therefore, early fault detection of rolling-element bearings is essential in machine health monitoring. With the advantage of fault feature representation techniques of time–frequency domain for nonstationary signals and the advent of convolutional neural networks (CNNs), bearing [...] Read more.
Bearing elements are vital in induction motors; therefore, early fault detection of rolling-element bearings is essential in machine health monitoring. With the advantage of fault feature representation techniques of time–frequency domain for nonstationary signals and the advent of convolutional neural networks (CNNs), bearing fault diagnosis has achieved high accuracy, even at variable rotational speeds. However, the required computation and memory resources of CNN-based fault diagnosis methods render it difficult to be compatible with embedded systems, which are essential in real industrial platforms because of their portability and low costs. This paper proposes a novel approach for establishing a CNN-based process for bearing fault diagnosis on embedded devices using acoustic emission signals, which reduces the computation costs significantly in classifying the bearing faults. A light state-of-the-art CNN model, MobileNet-v2, is established via pruning to optimize the required system resources. The input image size, which significantly affects the consumption of system resources, is decreased by our proposed signal representation method based on the constant-Q nonstationary Gabor transform and signal decomposition adopting ensemble empirical mode decomposition with a CNN-based method for selecting intrinsic mode functions. According to our experimental results, our proposed method can provide the accuracy for bearing faults classification by up to 99.58% with less computation overhead compared to previous deep learning-based fault diagnosis methods. Full article
Show Figures

Figure 1

Article
An Integrated Deep Learning Method towards Fault Diagnosis of Hydraulic Axial Piston Pump
Sensors 2020, 20(22), 6576; https://doi.org/10.3390/s20226576 - 18 Nov 2020
Cited by 5 | Viewed by 799
Abstract
A hydraulic axial piston pump is the essential component of a hydraulic transmission system and plays a key role in modern industry. Considering varying working conditions and the implicity of frequent faults, it is difficult to accurately monitor the machinery faults in the [...] Read more.
A hydraulic axial piston pump is the essential component of a hydraulic transmission system and plays a key role in modern industry. Considering varying working conditions and the implicity of frequent faults, it is difficult to accurately monitor the machinery faults in the actual operating process by using current fault diagnosis methods. Hence, it is urgent and significant to investigate effective and precise fault diagnosis approaches for pumps. Owing to the advantages of intelligent fault diagnosis methods in big data processing, methods based on deep learning have accomplished admirable performance for fault diagnosis of rotating machinery. The prevailing convolutional neural network (CNN) displays desirable automatic learning ability. Therefore, an integrated intelligent fault diagnosis method is proposed based on CNN and continuous wavelet transform (CWT), combining the feature extraction and classification. Firstly, CWT is used to convert the raw vibration signals into time-frequency representations and achieve the extraction of image features. Secondly, a new framework of deep CNN is established via designing the convolutional layers and sub-sampling layers. The learning process and results are visualized by t-distributed stochastic neighbor embedding (t-SNE). The results of the experiment present a higher classification accuracy compared with other models. It is demonstrated that the proposed approach is effective and stable for fault diagnosis of a hydraulic axial piston pump. Full article
Show Figures

Figure 1

Article
Blade Rub-Impact Fault Identification Using Autoencoder-Based Nonlinear Function Approximation and a Deep Neural Network
Sensors 2020, 20(21), 6265; https://doi.org/10.3390/s20216265 - 03 Nov 2020
Cited by 3 | Viewed by 676
Abstract
A blade rub-impact fault is one of the complex and frequently appearing faults in turbines. Due to their nonlinear and nonstationary nature, complex signal analysis techniques, which are expensive in terms of computation time, are required to extract valuable fault information from the [...] Read more.
A blade rub-impact fault is one of the complex and frequently appearing faults in turbines. Due to their nonlinear and nonstationary nature, complex signal analysis techniques, which are expensive in terms of computation time, are required to extract valuable fault information from the vibration signals collected from rotor systems. In this work, a novel method for diagnosing the blade rub-impact faults of different severity levels is proposed. Specifically, the deep undercomplete denoising autoencoder is first used for estimating the nonlinear function of the system under normal operating conditions. Next, the residual signals obtained as the difference between the original signals and their estimates by the autoencoder are computed. Finally, these residual signals are used as inputs to a deep neural network to determine the current state of the rotor system. The experimental results demonstrate that the amplitudes of the residual signals reflect the changes in states of the rotor system and the fault severity levels. Furthermore, these residual signals in combination with the deep neural network demonstrated promising fault identification results when applied to a complex nonlinear fault, such as a blade-rubbing fault. To test the effectiveness of the proposed nonlinear-based fault diagnosis algorithm, this technique is compared with the autoregressive with external input Laguerre proportional-integral observer that is a linear-based fault diagnosis observation technique. Full article
Show Figures

Figure 1

Article
Anomaly Detection of Power Plant Equipment Using Long Short-Term Memory Based Autoencoder Neural Network
Sensors 2020, 20(21), 6164; https://doi.org/10.3390/s20216164 - 29 Oct 2020
Cited by 2 | Viewed by 957
Abstract
Anomaly detection is of great significance in condition-based maintenance of power plant equipment. The conventional fixed threshold detection method is not able to perform early detection of equipment abnormalities. In this study, a general anomaly detection framework based on a long short-term memory-based [...] Read more.
Anomaly detection is of great significance in condition-based maintenance of power plant equipment. The conventional fixed threshold detection method is not able to perform early detection of equipment abnormalities. In this study, a general anomaly detection framework based on a long short-term memory-based autoencoder (LSTM-AE) network is proposed. A normal behavior model (NBM) is established to learn the normal behavior patterns of the operating variables of the equipment in space and time. Based on the similarity analysis between the NBM output distribution and the corresponding measurement distribution, the Mahalanobis distance (MD) is used to describe the overall residual (OR) of the model. The reasonable range is obtained using kernel density estimation (KDE) with a 99% confidence interval, and the OR is monitored to detect abnormalities in real-time. An induced draft fan is chosen as a case study. Results show that the established NBM has excellent accuracy and generalizability, with average root mean square errors of 0.026 and 0.035 for the training and test data, respectively, and average mean absolute percentage errors of 0.027%. Moreover, the abnormal operation case shows that the proposed framework can be effectively used for the early detection of abnormalities. Full article
Show Figures

Figure 1

Article
One-Dimensional Multi-Scale Domain Adaptive Network for Bearing-Fault Diagnosis under Varying Working Conditions
Sensors 2020, 20(21), 6039; https://doi.org/10.3390/s20216039 - 23 Oct 2020
Cited by 3 | Viewed by 794
Abstract
Data-driven bearing-fault diagnosis methods have become a research hotspot recently. These methods have to meet two premises: (1) the distributions of the data to be tested and the training data are the same; (2) there are a large number of high-quality labeled data. [...] Read more.
Data-driven bearing-fault diagnosis methods have become a research hotspot recently. These methods have to meet two premises: (1) the distributions of the data to be tested and the training data are the same; (2) there are a large number of high-quality labeled data. However, machines usually work under different working conditions in practice, which challenges these prerequisites due to the fact that the data distributions under different working conditions are different. In this paper, the one-dimensional Multi-Scale Domain Adaptive Network (1D-MSDAN) is proposed to address this issue. The 1D-MSDAN is a kind of deep transfer model, which uses both feature adaptation and classifier adaptation to guide the multi-scale convolutional neural network to perform bearing-fault diagnosis under varying working conditions. Feature adaptation is performed by both multi-scale feature adaptation and multi-level feature adaptation, which helps in finding domain-invariant features by minimizing the distribution discrepancy between different working conditions by using the Multi-kernel Maximum Mean Discrepancy (MK-MMD). Furthermore, classifier adaptation is performed by entropy minimization in the target domain to bridge the source classifier and target classifier to further eliminate domain discrepancy. The Case Western Reserve University (CWRU) bearing database is used to validate the proposed 1D-MSDAN. The experimental results show that the diagnostic accuracy for the 12 transfer tasks performed by 1D-MSDAN was superior to that of the mainstream transfer learning models for bearing-fault diagnosis under variable working conditions. In addition, the transfer learning performance of 1D-MSDAN for multi-target domain adaptation and real industrial scenarios was also verified. Full article
Show Figures

Figure 1

Article
A Sensor Fault-Tolerant Accident Diagnosis System
Sensors 2020, 20(20), 5839; https://doi.org/10.3390/s20205839 - 15 Oct 2020
Cited by 1 | Viewed by 751
Abstract
Emergency situations in nuclear power plants are accompanied by an automatic reactor shutdown, which gives a big task burden to the plant operators under highly stressful conditions. Diagnosis of the occurred accident is an essential sequence for optimum mitigations; however, it is also [...] Read more.
Emergency situations in nuclear power plants are accompanied by an automatic reactor shutdown, which gives a big task burden to the plant operators under highly stressful conditions. Diagnosis of the occurred accident is an essential sequence for optimum mitigations; however, it is also a critical source of error because the results of accident identification determine the task flow connected to all subsequent tasks. To support accident identification in nuclear power plants, recurrent neural network (RNN)-based approaches have recently shown outstanding performances. Despite the achievements though, the robustness of RNN models is not promising because wrong inputs have been shown to degrade the performance of RNNs to a greater extent than other methods in some applications. In this research, an accident diagnosis system that is tolerant to sensor faults is developed based on an existing RNN model and tested with anticipated sensor errors. To find the optimum strategy to mitigate sensor error, Missforest, selected from among various imputation methods, and gated recurrent unit with decay (GRUD), developed for multivariate time series imputation based on the RNN model, are compared to examine the extent that they recover the diagnosis accuracies within a given threshold. Full article
Show Figures

Figure 1

Article
Time-Frequency Distribution Map-Based Convolutional Neural Network (CNN) Model for Underwater Pipeline Leakage Detection Using Acoustic Signals
Sensors 2020, 20(18), 5040; https://doi.org/10.3390/s20185040 - 04 Sep 2020
Cited by 5 | Viewed by 1344
Abstract
Detection technology of underwater pipeline leakage plays an important role in the subsea production system. In this paper, a new method based on the acoustic leak signal collected by a hydrophone is proposed to detect pipeline leakage in the subsea production system. Through [...] Read more.
Detection technology of underwater pipeline leakage plays an important role in the subsea production system. In this paper, a new method based on the acoustic leak signal collected by a hydrophone is proposed to detect pipeline leakage in the subsea production system. Through the pipeline leakage test, it is found that the radiation noise is a continuous spectrum of the medium and high-frequency noise. Both the increase in pipe pressure and the diameter of the leak hole will narrow the spectral structure and shift the spectrum center towards the low frequencies. Under the same condition, the pipe pressure has a greater impact on the noise; every 0.05 MPa increase in the pressure, the radiation sound pressure level increases by 6-7 dB. The time-frequency images were obtained by processing the acoustic signals using the Ensemble Empirical Mode Decomposition (EEMD) and Hilbert–Huang transform (HHT), and fed into a two-layer Convolutional Neural Network (CNN) for leakage detection. The results show that CNN can correctly identify the degree of pipeline leakage. Hence, the proposed method provides a new approach for the detection of pipeline leakage in underwater engineering applications. Full article
Show Figures

Figure 1

Article
A Novel End-To-End Fault Diagnosis Approach for Rolling Bearings by Integrating Wavelet Packet Transform into Convolutional Neural Network Structures
Sensors 2020, 20(17), 4965; https://doi.org/10.3390/s20174965 - 02 Sep 2020
Cited by 12 | Viewed by 1050
Abstract
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 [...] Read more.
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. Full article
Show Figures

Figure 1

Article
Fault Diagnosis for High-Speed Train Axle-Box Bearing Using Simplified Shallow Information Fusion Convolutional Neural Network
Sensors 2020, 20(17), 4930; https://doi.org/10.3390/s20174930 - 31 Aug 2020
Cited by 7 | Viewed by 932
Abstract
Axle-box bearings are one of the most critical mechanical components of the high-speed train. Vibration signals collected from axle-box bearings are usually nonlinear and nonstationary, caused by the complicated operating conditions. Due to the high reliability and real-time requirement of axle-box bearing fault [...] Read more.
Axle-box bearings are one of the most critical mechanical components of the high-speed train. Vibration signals collected from axle-box bearings are usually nonlinear and nonstationary, caused by the complicated operating conditions. Due to the high reliability and real-time requirement of axle-box bearing fault diagnosis for high-speed trains, the accuracy and efficiency of the bearing fault diagnosis method based on deep learning needs to be enhanced. To identify the axle-box bearing fault accurately and quickly, a novel approach is proposed in this paper using a simplified shallow information fusion-convolutional neural network (SSIF-CNN). Firstly, the time domain and frequency domain features were extracted from the training samples and testing samples before been inputted into the SSIF-CNN model. Secondly, the feature maps obtained from each hidden layer were transformed into a corresponding feature sequence by the global convolution operation. Finally, those feature sequences obtained from different layers were concatenated into one-dimensional as the fully connected layer to achieve the fault identification task. The experimental results showed that the SSIF-CNN effectively compressed the training time and improved the fault diagnosis accuracy compared with a general CNN. Full article
Show Figures

Figure 1

Article
An Online Classification Method for Fault Diagnosis of Railway Turnouts
Sensors 2020, 20(16), 4627; https://doi.org/10.3390/s20164627 - 17 Aug 2020
Cited by 2 | Viewed by 947
Abstract
Railway turnout system is a key infrastructure to railway safety and efficiency. However, it is prone to failure in the field. Therefore, many railway departments have adopted a monitoring system to monitor the operation status of turnouts. With monitoring data collected, many researchers [...] Read more.
Railway turnout system is a key infrastructure to railway safety and efficiency. However, it is prone to failure in the field. Therefore, many railway departments have adopted a monitoring system to monitor the operation status of turnouts. With monitoring data collected, many researchers have proposed different fault-diagnosis methods. However, many of the existing methods cannot realize real-time updating or deal with new fault types. This paper—based on imbalanced data—proposes a Bayes-based online turnout fault-diagnosis method, which realizes incremental learning and scalable fault recognition. First, the basic conceptions of the turnout system are introduced. Next, the feature extraction and processing of the imbalanced monitoring data are introduced. Then, an online diagnosis method based on Bayesian incremental learning and scalable fault recognition is proposed, followed by the experiment with filed data from Guangzhou Railway. The results show that the scalable fault-recognition method can reach an accuracy of 99.11%, and the training time of the Bayesian incremental learning model reduces 29.97% without decreasing the accuracy, which demonstrates the high accuracy, adaptability and efficiency of the proposed model, of great significance for labor-saving, timely maintenance and further, safety and efficiency of railway transportation. Full article
Show Figures

Figure 1

Article
Fault Detection and Classification in MMC-HVDC Systems Using Learning Methods
Sensors 2020, 20(16), 4438; https://doi.org/10.3390/s20164438 - 08 Aug 2020
Cited by 5 | Viewed by 1347
Abstract
In this paper, we explore learning methods to improve the performance of the open-circuit fault diagnosis of modular multilevel converters (MMCs). Two deep learning methods, namely, convolutional neural networks (CNN) and auto encoder based deep neural networks (AE-based DNN), as well as stand-alone [...] Read more.
In this paper, we explore learning methods to improve the performance of the open-circuit fault diagnosis of modular multilevel converters (MMCs). Two deep learning methods, namely, convolutional neural networks (CNN) and auto encoder based deep neural networks (AE-based DNN), as well as stand-alone SoftMax classifier are explored for the detection and classification of faults of MMC-based high voltage direct current converter (MMC-HVDC). Only AC-side three-phase current and the upper and lower bridges’ currents of the MMCs are used directly in our proposed approaches without any explicit feature extraction or feature subset selection. The two-terminal MMC-HVDC system is implemented in Power Systems Computer-Aided Design/Electromagnetic Transients including DC (PSCAD/EMTDC) to verify and compare our methods. The simulation results indicate CNN, AE-based DNN, and SoftMax classifier can detect and classify faults with high detection accuracy and classification accuracy. Compared with CNN and AE-based DNN, the SoftMax classifier performed better in detection and classification accuracy as well as testing speed. The detection accuracy of AE-based DNN is a little better than CNN, while CNN needs less training time than the AE-based DNN and SoftMax classifier. Full article
Show Figures

Figure 1

Article
Vision Measurement of Gear Pitting Under Different Scenes by Deep Mask R-CNN
Sensors 2020, 20(15), 4298; https://doi.org/10.3390/s20154298 - 01 Aug 2020
Cited by 4 | Viewed by 1117
Abstract
To accurately and quantitatively detect the gear pitting of different levels on the actual site, this paper studies a new vision measurement approach based on a tunable vision detection platform and the mask region-based convolutional neural network (Mask R-CNN). The shooting angle can [...] Read more.
To accurately and quantitatively detect the gear pitting of different levels on the actual site, this paper studies a new vision measurement approach based on a tunable vision detection platform and the mask region-based convolutional neural network (Mask R-CNN). The shooting angle can be properly set according to the specification of the target gear. With the obtained sample set of 1500 gear pitting images, an optimized deep Mask R-CNN was designed for the quantitative measurement of gear pitting. The effective tooth surface and pitting was firstly and simultaneously recognized, then they were segmented to calculate the pitting area ratio. Considering three situations of multi-level pitting, multi-illumination, and multi-angle, several indexes were used to evaluate detection and segmentation results of deep Mask R-CNN. Experimental results show that the proposed method has higher measurement accuracy than the traditional method based on image processing, thus it has significant practical potential. Full article
Show Figures

Figure 1

Article
Fault Diagnosis of Rotary Machines Using Deep Convolutional Neural Network with Wide Three Axis Vibration Signal Input
Sensors 2020, 20(14), 4017; https://doi.org/10.3390/s20144017 - 19 Jul 2020
Cited by 15 | Viewed by 1265
Abstract
Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary [...] Read more.
Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary machinery. The proposed technique input raw three axes accelerometer signal as high definition 1D image into deep learning layers which automatically extract signal features, enabling high classification accuracy. Unlike the researches carried out by other researchers, accelerometer data matrix with dimensions 6400 × 1 × 3 is used as input for convolutional neural network training. Since convolutional neural networks can recognize patterns across input matrix, it is expected that wide input matrix containing vibration data should yield good classification performance. Using convolutional neural networks (CNN) trained model, classification in one of the four classes can be performed. Additionally, number of kernels of CNN is optimized using grid search, as preliminary studies show that alternating number of kernels impacts classification results. This study accomplished the effective classification of different rotary machinery states using convolutional artificial neural network for classification of raw three axis accelerometer signal input. Full article
Show Figures

Figure 1

Article
Performance Degradation Prediction Based on a Gaussian Mixture Model and Optimized Support Vector Regression for an Aviation Piston Pump
Sensors 2020, 20(14), 3854; https://doi.org/10.3390/s20143854 - 10 Jul 2020
Cited by 5 | Viewed by 1055
Abstract
Performance degradation prediction plays a key role in realizing aviation pump health management and condition-based maintenance. Thus, this paper proposes a new approach that combines a Gaussian mixture model (GMM) and optimized support vector regression (SVR) to predict aviation pumps’ degradation processes based [...] Read more.
Performance degradation prediction plays a key role in realizing aviation pump health management and condition-based maintenance. Thus, this paper proposes a new approach that combines a Gaussian mixture model (GMM) and optimized support vector regression (SVR) to predict aviation pumps’ degradation processes based on the pump outlet pressure signals. Different from other feature extraction methods in which the information of intrinsic mode functions (IMFs) is not fully utilized, some useful IMF components are firstly chosen, and the corresponding multi-domain features are extracted from each selected component. Considering that it is not the case that all features are equally sensitive to degradation assessment, PCA is used to select more sensitive degradation features. Since the distribution of these extracted features is a stochastic process in feature space, meanwhile, self-information quantity can describe the uncertainty of system by measuring the average information quantity contained in the probability distribution, self-information quantity based on GMM is defined as degradation index (DI) to describe the degradation degree of the pump quantitatively. Finally, an SVR model is constructed to predict the degradation status of the pump. To achieve higher prediction accuracy, phase space reconstruction theory is first employed to determine the number of the inputs of the SVR model, then a new method combining particle swarm optimization (PSO) with grid search (GS) is developed to optimize the parameters of the SVR model. Finally, both the online data and historical data are utilized for the construction of the SVR model, respectively. The effectiveness of the proposed approach is validated by full life cycle data collected from an aviation pump test rig. The results demonstrate that the DI extracted from pump outlet pressure signals can effectively identify and track the current deterioration stage, and the established SVR model has better prediction ability when compared with previously published methods. Full article
Show Figures

Graphical abstract

Article
Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)
Sensors 2020, 20(12), 3344; https://doi.org/10.3390/s20123344 - 12 Jun 2020
Cited by 34 | Viewed by 3794
Abstract
Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning [...] Read more.
Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset. Full article
Show Figures

Figure 1

Other

Jump to: Research

Letter
Few-Shot Rolling Bearing Fault Diagnosis with Metric-Based Meta Learning
Sensors 2020, 20(22), 6437; https://doi.org/10.3390/s20226437 - 11 Nov 2020
Cited by 11 | Viewed by 1151
Abstract
Fault diagnosis methods based on deep learning and big data have achieved good results on rotating machinery. However, the conventional deep learning method of bearing fault diagnosis is mostly based on laboratory artificial simulation data, and there is an error with actual fault [...] Read more.
Fault diagnosis methods based on deep learning and big data have achieved good results on rotating machinery. However, the conventional deep learning method of bearing fault diagnosis is mostly based on laboratory artificial simulation data, and there is an error with actual fault data, which will reduce the generalization performance of the deep learning method. In addition, labeled data are very precious in real industrial environment. Due to expensive equipment and personnel safety issues, it is difficult to obtain a large amount of high-quality fault labeling data. Therefore, in this paper, we propose a metric-based meta-learning method named Reinforce Relation Network (RRN) for diagnosing bearing faults with few-shot samples. In the proposed method, a 1D convolution neural network is used to extract fault features, and a metric learner is used to predict the similarity between samples under different transfer conditions. Label smoothing and the Adabound algorithm are utilized to further improve the performance of network classification. The performance of the proposed method is verified on a dataset which contains artificial damage and natural damage data. The comparison studies with other methods demonstrate the superiority of the proposed method in the few-shot scenario. Full article
Show Figures

Figure 1

Letter
Development of Compound Fault Diagnosis System for Gearbox Based on Convolutional Neural Network
Sensors 2020, 20(21), 6169; https://doi.org/10.3390/s20216169 - 29 Oct 2020
Cited by 6 | Viewed by 783
Abstract
Gear transmission is widely used in mechanical equipment. In practice, if the gearbox is damaged, it not only affects the yield rate but also damages other parts of machines; thus, increases the cost and difficulty of maintenance. With the advancement of technology, the [...] Read more.
Gear transmission is widely used in mechanical equipment. In practice, if the gearbox is damaged, it not only affects the yield rate but also damages other parts of machines; thus, increases the cost and difficulty of maintenance. With the advancement of technology, the concept of unmanned factories has been proposed; an automatic diagnosis system for the health management of gearboxes becomes necessary. In this paper, a compound fault diagnosis system for the gearbox based on convolutional neural network (CNN) is developed. Specifically, three-axis vibration signals measured by accelerometers are used as the input of the one-dimensional CNN; the detection of the existence and type of the fault is directly output. In testing, the model achieved nearly 100% accuracy on the fault samples we captured. Experimental evidence also shows that the frequency-domain data can provide better diagnostic results than the time-domain data due to the stable characteristics in the frequency spectrum. For practical usage, we demonstrated a remote fault diagnosis system through a local area network on an embedded platform. Furthermore, optimization of convolution kernels was also investigated. When moderately reducing the number of convolution kernels, it does not affect the diagnostic accuracy but greatly reduces the training time of the model. Full article
Show Figures

Figure 1

Letter
LSTM-Based VAE-GAN for Time-Series Anomaly Detection
Sensors 2020, 20(13), 3738; https://doi.org/10.3390/s20133738 - 03 Jul 2020
Cited by 10 | Viewed by 5375
Abstract
Time series anomaly detection is widely used to monitor the equipment sates through the data collected in the form of time series. At present, the deep learning method based on generative adversarial networks (GAN) has emerged for time series anomaly detection. However, this [...] Read more.
Time series anomaly detection is widely used to monitor the equipment sates through the data collected in the form of time series. At present, the deep learning method based on generative adversarial networks (GAN) has emerged for time series anomaly detection. However, this method needs to find the best mapping from real-time space to the latent space at the anomaly detection stage, which brings new errors and takes a long time. In this paper, we propose a long short-term memory-based variational autoencoder generation adversarial networks (LSTM-based VAE-GAN) method for time series anomaly detection, which effectively solves the above problems. Our method jointly trains the encoder, the generator and the discriminator to take advantage of the mapping ability of the encoder and the discrimination ability of the discriminator simultaneously. The long short-term memory (LSTM) networks are used as the encoder, the generator and the discriminator. At the anomaly detection stage, anomalies are detected based on reconstruction difference and discrimination results. Experimental results show that the proposed method can quickly and accurately detect anomalies. Full article
Show Figures

Figure 1

Back to TopTop