Showing papers in "IEEE Transactions on Instrumentation and Measurement in 2020"

An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features

Abstract: A complete defect detection task aims to achieve the specific class and precise location of each defect in an image, which makes it still challenging for applying this task in practice. The defect detection is a composite task of classification and location, leading to related methods is often hard to take into account the accuracy of both. The implementation of defect detection depends on a special detection data set that contains expensive manual annotations. In this paper, we proposed a novel defect detection system based on deep learning and focused on a practical industrial application: steel plate defect inspection. In order to achieve strong classification ability, this system employs a baseline convolution neural network (CNN) to generate feature maps at each stage, and then the proposed multilevel feature fusion network (MFN) combines multiple hierarchical features into one feature, which can include more location details of defects. Based on these multilevel features, a region proposal network (RPN) is adopted to generate regions of interest (ROIs). For each ROI, a detector, consisting of a classifier and a bounding box regressor, produces the final detection results. Finally, we set up a defect detection data set NEU-DET for training and evaluating our method. On the NEU-DET, our method achieves 74.8/82.3 mAP with baseline networks ResNet34/50 by using 300 proposals. In addition, by using only 50 proposals, our method can detect at 20 ft/s on a single GPU and reach 92% of the above performance, hence the potential for real-time detection.

An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network

Abstract: Deep belief network (DBN) is one of the most representative deep learning models. However, it has a disadvantage that the network structure and parameters are basically determined by experiences. In this article, an improved quantum-inspired differential evolution (MSIQDE), namely MSIQDE algorithm based on making use of the merits of the Mexh wavelet function, standard normal distribution, adaptive quantum state update, and quantum nongate mutation, is proposed to avoid premature convergence and improve the global search ability. Then, the MSIQDE with global optimization ability is used to optimize the parameters of the DBN to construct an optimal DBN model, which is further applied to propose a new fault classification, namely MSIQDE-DBN method. Finally, the vibration data of rolling bearings from the Case Western Reserve University and a real-world engineering application are carried out to verify the performance of the MSIQDE-DBN method. The experimental results show that the MSIQDE takes on better optimization performance, and the MSIQDE-DBN can obtain higher classification accuracy than the other comparison methods.

Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks

Abstract: Fault detection and diagnosis (FDD) is crucial for stable, reliable, and safe operation of industrial equipment. In recent years, deep learning models have been widely used in data-driven FDD methods because of their automatic feature learning capability. In general, these models are trained on historical sensor data, and therefore, it is very difficult to meet the real-time requirement of online FDD applications. Since transfer learning can solve different but similar problems in the target domain efficiently and effectively with the knowledge learned from the source domain, this paper proposes an online fault diagnosis method based on a deep transfer convolutional neural network (TCNN) framework. The TCNN framework is made up of an online CNN based on LeNet-5 and several offline CNNs with a shallow structure. First, time-domain signal data are converted into images that contain abundant fault information and are suitable as the input of CNN. Then, the online CNN is constructed to automatically extract representative features from the converted images and classify faults. Finally, in order to improve the real-time performance of the online CNN, several offline CNNs are also constructed and pretrained on related data sets. By directly transferring the shallow layers of the trained offline CNNs to the online CNN, the online CNN can significantly improve the real-time performance and successfully address the issue of achieving the desired diagnostic accuracy within limited training time. The proposed method is validated on two bearing data sets and one pump data set, respectively. The prediction accuracy of the proposed method using three data sets are 99.88%, 99.13%, and 99.98%, respectively. The experimental results also indicate that the improvement of accuracy is 19.21% for the motor bearing case, 29.82% for the rolling mill bearing case, and 33.26% for the pump case during the early stage of learning.

NestFuse: An Infrared and Visible Image Fusion Architecture Based on Nest Connection and Spatial/Channel Attention Models

Abstract: In this article, we propose a novel method for infrared and visible image fusion where we develop nest connection-based network and spatial/channel attention models. The nest connection-based network can preserve significant amounts of information from input data in a multiscale perspective. The approach comprises three key elements: encoder, fusion strategy, and decoder, respectively. In our proposed fusion strategy, spatial attention models and channel attention models are developed that describe the importance of each spatial position and of each channel with deep features. First, the source images are fed into the encoder to extract multiscale deep features. The novel fusion strategy is then developed to fuse these features for each scale. Finally, the fused image is reconstructed by the nest connection-based decoder. Experiments are performed on publicly available data sets. These exhibit that our proposed approach has better fusion performance than other state-of-the-art methods. This claim is justified through both subjective and objective evaluations. The code of our fusion method is available at https://github.com/hli1221/imagefusion-nestfuse .

Automated Visual Defect Detection for Flat Steel Surface: A Survey

Abstract: Automated computer-vision-based defect detection has received much attention with the increasing surface quality assurance demands for the industrial manufacturing of flat steels. This article attempts to present a comprehensive survey on surface defect detection technologies by reviewing about 120 publications over the last two decades for three typical flat steel products of con-casting slabs and hot- and cold-rolled steel strips. According to the nature of algorithms as well as image features, the existing methodologies are categorized into four groups: statistical, spectral, model-based, and machine learning. These works are summarized in this review to enable easy referral to suitable methods for diverse application scenarios in steel mills. Realization recommendations and future research trends are also addressed at an abstract level.

DCNN-Based Multi-Signal Induction Motor Fault Diagnosis

Abstract: Deep learning (DL) architecture, which exploits multiple hidden layers to learn hierarchical representations automatically from massive input data, presents a promising tool for characterizing fault conditions. This paper proposes a DL-based multi-signal fault diagnosis method that leverages the powerful feature learning ability of a convolutional neural network (CNN) in images. The proposed deep model is able to learn from multiple types of sensor signals simultaneously so that it can achieve robust performance and finally realize accurate induction motor fault recognition. First, the acquired sensor signals are converted to time–frequency distribution (TFD) by wavelet transform. Then, a deep CNN is applied to learning discriminative representations from the TFD images. Since then, a fully connected layer in deep architecture gives the prediction of induction motor condition based on learned features. In order to verify the effectiveness of the designed deep model, experiments are carried out on a machine fault simulator where both vibration and current signals are analyzed. Experimental results indicate that the proposed method outperforms traditional fault diagnosis methods, hence, demonstrating effectiveness in induction motor application. Compared with conventional methods that rely on delicate features extracted by experienced experts, the proposed deep model is able to automatically learn and select suitable features that contribute to accurate fault diagnosis. Compared with single-signal input, the multi-signal model has more accurate and stable performance and overcomes the overfitting problem to some degree.

Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning

Abstract: For the data-driven remaining useful life (RUL) prediction for rolling bearings, the traditional machine learning-based methods generally provide insufficient feature representation and adaptive extraction. Although deep learning-based RUL prediction methods can solve these problems to some extent, they still do not yield satisfactory predictive results due to less degradation data and inconsistent data distribution among different bearings. To solve these problems, a new RUL prediction method based on deep feature representation and transfer learning is proposed in this paper. This method includes an off-line stage and an online stage. In the off-line stage, the Hilbert–Huang transform marginal spectra of the raw vibration signal of auxiliary bearings are first calculated as the input, and then contractive denoising autoencoder is introduced to extract deep features with good and stable fault representation. Second, by using the obtained deep features and Pearson’s correlation coefficient, a new health condition assessment method is proposed to divide the whole life of each bearing into a normal state and a fast-degradation state. Finally, using the extracted deep features and their RUL values, an RUL prediction model for the fast-degradation state is trained by means of a least-square support vector machine. In the online stage, a kind of transfer learning algorithm, i.e., transfer component analysis, is introduced to sequentially adjust the features of target bearing from auxiliary bearings, and then the corresponding RUL is predicted using the corrected features. Results using the PHM Challenging 2012 data set show a significant performance improvement when using the proposed method in terms of predictive accuracy and numerical stability.

Performance Prediction Using High-Order Differential Mathematical Morphology Gradient Spectrum Entropy and Extreme Learning Machine

Abstract: Performance prediction is significant to monitor the health status of rolling bearings, which can greatly reduce the loss caused by potential faults in the whole life cycle of rolling bearings. It is a very important part of Prognostic and Health Management (PHM). In this article, a new performance degradation prediction (HMEPEM) method based on high-order differential mathematical morphology gradient spectrum entropy (HOMMSE), phase space reconstruction, and extreme learning machine (ELM) is proposed to predict the performance degradation trend of rolling bearings. In the proposed HMEPEM method, the HOMMSE method is used to extract the initial features of performance degradation from the raw bearing vibration signals and divide working stages. Then the phase space reconstruction is used to further extract more useful features from the initial features of performance degradation in order to construct a feature matrix, which is input into the ELM in order to build the performance degradation prediction model for predicting the performance degradation trend of rolling bearings. The proposed HMEPEM method is validated on the performance degradation data of rolling bearings provided by the PRONOSTIA platform. The results show that the proposed HMEPEM method can efficiently track the evolution of degradation and predict the performance degradation trend of rolling bearings.

LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification

Abstract: This paper introduces a novel deep learning-based algorithm that integrates a long short-term memory (LSTM)-based auto-encoder (AE) network with support vector machine (SVM) for electrocardiogram (ECG) arrhythmias classification. The LSTM-based AE network (LSTM-AE) is used to learn the features from ECG arrhythmias signals, and the SVM is used to classify those signals from the learned features. The LSTM-AE consists of an encoder model, which extracts high-level feature information from ECG arrhythmias signals through LSTM network, and a decoder model which outputs reconstruct ECG arrhythmias signals from high-level features through LSTM network. Experiments show that the proposed method can learn better features than the traditional method without any prior knowledge, presenting a good potential for the ECG arrhythmias classification. In the classification of five heartbeats types, including normal, left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature complexes (APC), premature ventricular contractions (PVC), the proposed method achieved average accuracy, sensitivity, and specificity of 99.74%, 99.35%, and 99.84%, respectively, in the beat-based cross-validation approach, and 85.20%, 62.99%, and 90.75%, respectively, in the record-based cross-validation approach, in public MIT-BIH Arrhythmia Database. While based on the Advancement of Medical Instrumentation (AAMI) standards, the proposed method achieved average accuracy, sensitivity, and specificity of 99.45%, 98.63%, and 99.66%, respectively, in the beat-based cross-validation approach.

A Motor Current Signal-Based Bearing Fault Diagnosis Using Deep Learning and Information Fusion

Abstract: Bearing fault diagnosis has extensively exploited vibration signals (VSs) because of their rich information about bearing health conditions. However, this approach is expensive because the measurement of VSs requires external accelerometers. Moreover, in machine systems that are inaccessible or unable to be installed in external sensors, the VS-based approach is impracticable. Otherwise, motor current signals (CSs) are easily measured by the inverters that are the available components of those systems. Therefore, the motor CS-based bearing fault diagnosis approach has attracted considerable attention from researchers. However, the performance of this approach is still not good as the VS-based approach, especially in the case of fault diagnosis for external bearings (the bearings that are installed outside of the electric motors). Accordingly, this article proposes a motor CS-based fault diagnosis method utilizing deep learning and information fusion (IF), which can be applied to external bearings in rotary machine systems. The proposed method uses raw signals from multiple phases of the motor current as direct input, and the features are extracted from the CSs of each phase. Then, each feature set is classified separately by a convolutional neural network (CNN). To enhance the classification accuracy, a novel decision-level IF technique is introduced to fuse information from all of the utilized CNNs. The problem of decision-level IF is transformed into a simple pattern classification task, which can be solved effectively by familiar supervised learning algorithms. The effectiveness of the proposed fault diagnosis method is verified through experiments carried out with actual bearing fault signals.

A New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN

Abstract: Aiming at fault visualization and automatic feature extraction, this article presents a new and intelligent bearing fault diagnostic method by combining symmetrized dot pattern (SDP) representation with squeeze-and-excitation-enabled convolutional neural network (SE-CNN) model. Graphical representations of bearing states are shown intuitively by using the SDP method. Meanwhile, optimal parameters during SDP images' generation are selected to enhance the image resolution for distinctly distinguishing different bearing states and create the corresponding bearing fault sample sets. To automatically and effectively extract SDP image features, the channel attention mechanism using the SE network is integrated with the CNN network. The proposed SE-CNN-based diagnostic framework has the ability to assign certain weight to each feature extraction channel and further enforce the bearing diagnosis model focusing on the major features, meanwhile reducing the redundant information. The final diagnosis task is realized by the Softmax classifier located behind the SE-CNN model. Experimental results prove that the proposed method not only achieves the classification rate over 99% but also has better generalization ability and stability.

Evolving Fuzzy Models for Prosthetic Hand Myoelectric-Based Control

Abstract: This article applies an incremental online identification algorithm to develop a set of evolving fuzzy models (FMs) that characterize the nonlinear finger dynamics of the human hand for the myoelectric (ME)-based control of a prosthetic hand. The FM inputs are the ME signals obtained from eight ME sensors and past inputs and/or outputs. The FM outputs are the finger angles, considered here as the midcarpal joint angles, to ensure their control. The best evolving FMs that characterize each of the five fingers are described with the results validated on real data. Simple second-order linear models are next given to enable the cost-effective controller design. Five separate control loops are proposed, with proportional–integral (PI) controllers separately tuned by a frequency-domain approach. Simple PI-fuzzy controllers are designed starting with the linear PI controllers to ensure the control system performance improvement. The evolving FMs are used to simulate accurately the behavior of the human hand. Digital simulation results are included to show the effectiveness of the PI-fuzzy controllers and the performance improvement in comparison to the initial PI ones.

Research on Remaining Useful Life Prediction of Rolling Element Bearings Based on Time-Varying Kalman Filter

Abstract: Rolling bearings are the key components of rotating machinery. Thus, the prediction of remaining useful life (RUL) is vital in condition-based maintenance (CBM). This paper proposes a new method for RUL prediction of bearings based on time-varying Kalman filter, which can automatically match different degradation stages of bearings and effectively realize the prediction of RUL. The evolution of monitoring data in normal and slow degradation stages is a linear trend, and the evolution in accelerated degradation stage is nonlinear. Therefore, Kalman filter models based on linear and quadratic functions are established. Meanwhile, a sliding window relative error is constructed to adaptively judge the bearing degradation stages. It can automatically switch filter models to process monitoring data at different stages. Then, the RUL can be predicted effectively. Two groups of bearing run-to-failure data sets are utilized to demonstrate the feasibility and validity of the proposed method.

A Concentrated Time–Frequency Analysis Tool for Bearing Fault Diagnosis

Abstract: In industrial rotating machinery, the transient signal usually corresponds to the failure of a primary element, such as a bearing or gear. However, faced with the complexity and diversity of practical engineering, extracting the transient signal is a highly challenging task. In this paper, we propose a novel time–frequency analysis method termed the transient-extracting transform, which can effectively characterize and extract the transient components in the fault signals. This method is based on the short-time Fourier transform and does not require extended parameters or a priori information. Quantized indicators, such as Renyi entropy and kurtosis, are employed to compare the performance of the proposed method with other classical and advanced methods. The comparisons show that the proposed method can provide a much more energy-concentrated time–frequency representation, and the transient components can be extracted with a significantly larger kurtosis. The numerical and experimental signals are used to show the effectiveness of our method.

EDRNet: Encoder–Decoder Residual Network for Salient Object Detection of Strip Steel Surface Defects

Abstract: It is still a challenging task to detect the surface defects of strip steel due to its complex variations, including variable defect types, cluttered background, low contrast, and noise interference. The existing detection methods cannot effectively segment the defect objects from complex background and have poor real-time performance. To address these issues, we propose a novel saliency detection method based on Encoder–Decoder Residual network (EDRNet). In the encoder stage, we use a fully convolutional neural network to extract rich multilevel defect features and fuse the attention mechanism to accelerate the convergence of the model. Then in the decoder stage, we adopt the channels weighted block (CWB) and the residual decoder block (RDB) alternatively to integrate the spatial features of shallower layers and semantic features of deep layers and recover the predicted spatial saliency values step by step. Finally, we design the residual refinement structure with 1D filters (RRS_1D) to further optimize the coarse saliency map. Compared with the existing saliency detection methods, the deeply supervised EDRNet can accurately segment the complete defect objects with well-defined boundary and effectively filter out irrelevant background noise. The extensive experimental results prove that our method is consistently superior to the state-of-the-art methods with large margins and strong robustness, and the detection efficiency is at over 27 fps on a single GPU.

An Enhanced Intelligent Diagnosis Method Based on Multi-Sensor Image Fusion via Improved Deep Learning Network

Abstract: An enhanced intelligent diagnosis method for rotary equipment is proposed based on multi-sensor data-fusion and an improved deep convolutional neural network (CNN) models An improved CNN based on LeNet-5 is constructed which can enhance the features of the samples by stacking bottleneck layers without changing the size of the samples A new conversion approaches are also proposed for converting multi-sensor vibration signals into color images, and it can refine features and enlarge the differences between different types of fault signals by the fused images transformed in red–green–blue (RGB) color space In the last stage of network learning, visual clustering is realized with t-distributed stochastic neighbor embedding (t-SNE) to evaluate the performance of the network To verify the effectiveness of the proposed method, examples in practice such as the diagnosis for the wind power test rigs and industrial fan system are provided with the prediction accuracies of 9989% and 9977%, respectively In addition, the efficiency of other comparative baseline approaches such as the deep belief network and support vector machine (SVM) is evaluated In conclusion, the proposed intelligent diagnosis method based on multi-sensor data-fusion and CNN shows higher prediction accuracy and more obvious visualization clustering effects

A Review on State-of-the-Art Power Line Inspection Techniques

Abstract: With the fast development of smart grid, the power line mileage and power equipments get rapid growth. The contradiction between the large number of maintenance equipments and the small number of maintenance workers becomes increasingly prominent. Meanwhile, the traditional maintenance mode has the disadvantages of over or under maintenance, which will lead to the increasing failure risk of power transmission system. Faced with these issues, to enhance the intelligence and automation level of power line inspection, many researchers have devoted much effort to the research of automatic power line inspection and some state-of-the-art techniques about power line inspection are proposed to improve the inspection efficiency and quality, such as unmanned aerial vehicle (UAV), image processing, deep architecture, and so on. In this article, we analyzed and summarized the state-of-the-art techniques on power line inspection to provide a valuable reference for the researchers engaged in the smart grid. First, the common inspection tasks on power line inspection are reviewed. Second, the existing inspection platforms are examined in this article. Also, the advantages and disadvantages of different platforms are analyzed accordingly. Third, faced with different inspection tasks, different inspection sensors are integrated into the inspection platforms for data collection. Therefore, the common sensors on inspection platforms are discussed. Finally, to realize automatic power line inspection, different inspection methods are proposed or improved, and these advanced inspection methods are surveyed and discussed.

A Combined Polynomial Chirplet Transform and Synchroextracting Technique for Analyzing Nonstationary Signals of Rotating Machinery

Abstract: Time–frequency analysis (TFA) technique is an effective approach to capture the changing dynamic in a nonstationary signal. However, the commonly adopted TFA techniques are inadequate in dealing with signals having a strong nonstationary characteristic or multicomponent signals having close frequency components. To overcome this shortcoming, a new TFA technique applying a polynomial chirplet transform (PCT) in association with a synchroextracting transform (SET) is proposed in this paper. It is shown that the energy concentration of the time–frequency representation (TFR) of a strong frequency-modulated signal from a PCT transform can be further enhanced by an SET transform. The technique can also be employed to accurately extract the signal components of a multicomponent nonstationary signal with close frequency components by adopting an iterative process. It is found that the TFR calculated from the proposed technique matches well with the ideal TFR, which demonstrates the superiority of the current technique in dealing with nonstationary signals having rapidly changing dynamics. Results from the analysis of the experimental data under varying speed conditions confirm the validity of the proposed technique in dealing with nonstationary signals from practical sources.

Contact Wire Irregularity Stochastics and Effect on High-Speed Railway Pantograph–Catenary Interactions

Abstract: In high-speed rail operations, contact wire irregularity (CWI) in a catenary is a common disturbance to the pantograph–catenary interaction performance, which directly affects the quality of current collection. To describe the pointwise stochastics of CWI, the power spectral density (PSD) function for CWI is proposed, and its effect on the pantograph–catenary interaction is investigated. First, a preprocessing procedure is proposed to eliminate the redundant information in the measured irregularities based on the ensemble empirical mode decomposition (EEMD). Then, the upper envelope of the irregularity, which contains all the information regarding the dropper positions on the contact wire, is extracted. A form of the PSD function is suggested for contact wire irregularities. A methodology is proposed to include the effect of random irregularities in the assessment of the interaction performance of a pantograph–catenary. A developed target configuration under dead load (TCUD) method is used to calculate the initial configuration of the catenary, in which the dropper points on the contact wire are placed on their exact positions. Finally, the effect of the random contact wire irregularities on the contact force is investigated through 500 numerical simulations at each operating speed. The present results indicate that random irregularities have a direct impact on the pantograph–catenary contact, including an increment in the dispersion of the contact force statistics. The stochastic analysis shows that over 70% of the results with irregularities are worse than the ideal result without irregularities.

Deep Semisupervised Domain Generalization Network for Rotary Machinery Fault Diagnosis Under Variable Speed

Abstract: In recent years, deep learning has become a promising tool for rotary machinery fault diagnosis, but it works well only when testing samples and training samples are independent and identically distributed. In practice, rotary machinery usually works under variable speed. The change of speed leads to the variation of samples’ distribution, which can significantly decrease the performance of the deep learning model. Scholars try to utilize transfer learning techniques for solving this problem. However, most exiting methods can just work well under target speed instead of all speed, while the target samples are always required in model training. In this article, a deep semisupervised domain generalization network (DSDGN) is proposed for rotary machinery fault diagnosis under variable speed, which can generalize the model to the fault diagnosis task under unseen speed. Under the setting of semisupervised domain generalization, only one fully labeled source (LS) domain data set and one totally unlabeled source (US) domain data set are available during training. To make full use of these data, the proposed method simultaneously utilizes Wasserstein generative adversarial network with gradient penalty (WGAN-GP)-based adversarial learning and pseudolabel-based semisupervised learning for training. The transmission and bearing fault diagnosis cases are utilized for evaluation. The comparative experiments indicate that the proposed method has a better performance than other state-of-the-art methods.

Domain Adversarial Transfer Network for Cross-Domain Fault Diagnosis of Rotary Machinery

Abstract: Recently, deep learning-based intelligent fault diagnosis techniques have obtained good classification performance with amount of supervised training data. However, domain shift problem between the training and testing data usually occurs due to variation in operating conditions and interferences of environment noise. Transfer learning provides a promising tool for handling the cross-domain diagnosis problems by leveraging knowledge from the source domain to help learning in the target domain. Most existing studies attempt to learn both domain features in a common feature space to reduce the domain shift, which are not optimal on specific discriminative tasks and can be limited to small shifts. This article proposes a novel domain adversarial transfer network (DATN), exploiting task-specific feature learning networks and domain adversarial training techniques for handling large distribution discrepancy across domains. First, two asymmetric encoder networks integrating deep convolutional neural networks are designed for learning hierarchical representations from the source domain and target domain. Then, the network weights learned in source tasks are transferred to improve training on target tasks. Finally, domain adversarial training with inverted label loss is introduced to minimize the difference between source and target distributions. To validate the effectiveness and superiority of the proposed method in the presence of large domain shifts, two fault data sets from different test rigs are investigated, and different fault severities, compound faults, and data contaminated by noise are considered. The experimental results demonstrate that the proposed method achieves the average accuracy of 96.45% on the bearing data set and 98.92% on the gearbox data set, which outperforms other algorithms.

Automatic Fault Diagnosis of Infrared Insulator Images Based on Image Instance Segmentation and Temperature Analysis

Abstract: As an onsite condition monitoring method, an infrared inspection can help to discover and analyze abnormal temperature increases in power equipment. For improving the efficiency of the onsite diagnosis of insulators in substations, this article proposes an automatic diagnosis method using instance segmentation and temperature analysis of infrared insulator images. For developing this method, thousands of infrared images from field inspection databases were collected to establish an annotated data set of insulator images. With the aid of the Mask R-convolutional neural network (CNN), it was possible to extract multiple insulators automatically in the infrared images. Transfer learning, as well as the dynamic learning rate algorithm, were then employed to realize the training process of Mask R-CNN with the annotated image data set. The result of the testing experiment showed that the mean Average Precision (mAP) of the model is 0.77, and the frame per second (FPS) is 5.07, which indicated great identification accuracy and computing speed of the proposed model. Next, function fitting was realized to extract the temperature distribution of each insulator. Finally, to evaluate the condition of each insulator, rules, which are based on the related standards, were established using machine language. This is the first time that the machine could independently realize fault analysis of multiple insulators in the infrared images, which is a great attempt to adapt the development of the Internet of Things and the tendency of predictive maintenance. Moreover, because of the universality of the model algorithm used, automatic infrared fault diagnosis for other power equipment could also be performed in a similar manner, which has significant potential applicability in the area of power equipment diagnosis.

Laplacian Redecomposition for Multimodal Medical Image Fusion

Abstract: The field of multimodal medical image fusion has made huge progress in the past decade. However, previous methods always suffer from color distortion , blurring , and noise . To address these problems, we propose a novel Laplacian redecomposition (LRD) framework tailored to multimodal medical image fusion in this article. The proposed LRD has two technical innovations. First, we present a Laplacian decision graph decomposition scheme with image enhancement to obtain complementary information, redundant information, and low-frequency subband images. Second, considering the heterogeneous characteristics of redundant and complementary information, we introduce the concept of the overlapping domain (OD) and non-OD (NOD), where the OD contributes to fuse redundant information while the NOD is responsible for fusing complementary information. In addition, an inverse redecomposition scheme is given by leveraging the global decision graph and local mean to reconstruct high-frequency subband fusion images. Finally, the inverse Laplacian transform is applied to generate the fusion result. Experimental results demonstrate that the proposal outperforms other current popular fusion methods qualitatively and quantitatively.

Particle Image Velocimetry Based on a Deep Learning Motion Estimator

Abstract: Particle image velocimetry (PIV), as a common technology for analyzing the global flow motion from images, plays a significant role in experimental fluid mechanics. In this article, we investigate the deep learning-based techniques for such a fluid motion estimation problem. The aim of this novel technique is to extract 2-D velocity fields from fluid images efficiently and accurately. First, we introduce the convolutional neural network (CNN) called LiteFlowNet, which is proposed for end-to-end optical flow estimation. Enhanced configurations of LiteFlowNet are adopted for PIV estimation in order to refine the small-scale vortex structures. Furthermore, as the supervised learning strategy is considered, a data set including particle images and the ground-truth fluid motions is generated to train the parameters of the networks. A number of fluidic images, from synthetic turbulent flow to laboratory boundary layer flow, are investigated in this article. Experimental results indicate that the proposed estimator can provide accuracy approaching that of state-of-the-art methods and high efficiency toward real-time estimation.

Multiple Enhanced Sparse Decomposition for Gearbox Compound Fault Diagnosis

Abstract: The vibration monitoring of gearboxes is an effective means of ensuring the long-term safe operation of rotating machinery. A gearbox may have more than one fault in actual applications. Therefore, gearbox compound fault diagnosis should be investigated. In this paper, a novel multiple enhanced sparse decomposition (MESD) method is proposed to address multiple feature extraction for gearbox compound fault vibration signals. Through this method, a novel MESD algorithm is utilized to simultaneously separate and extract the harmonic components and transient features of the gear and bearing from the compound fault signal. Three subdictionaries are specially constructed according to the gearbox failure mechanism to accurately extract each feature component. Meanwhile, the generalized minimax concave (GMC) penalty is used as sparse regularization to further ensure the accuracy of sparse decomposition. The simulation and engineering signals of the gearbox validate the performance of the proposed MESD method.

Detection and Identification of Volatile Organic Compounds Based on Temperature-Modulated ZnO Sensors

Abstract: A novel detection method based on ZnO metal–oxide sensors, capable of detecting various species and concentrations of aimed volatile organic compounds (VOCs), has been proposed in this article. In conjunction with signal processing algorithms, the characteristic signals of the sensors operated under temperature modulating are investigated. When the sensor is operating in the temperature modulation mode and is exposed to different detection gases, it will display different output waveforms. Considering the stability of the sensors in practical applications, general regression neural network (GRNN) is used to distinguish the species and concentration of gas in detail.

A Two-Stage Deep Learning Method for Robust Shape Reconstruction With Electrical Impedance Tomography

Abstract: As a noninvasive and radiation-free imaging modality, electrical impedance tomography (EIT) has attracted much attention in the last two decades and owns many industry and biomedical applications. However, due to the nonlinearity and ill-posedness of its inverse problem, the EIT images always suffer from low spatial resolution and are sensitive to the modeling errors. To achieve high resolution and modeling error robust EIT image, a two-stage deep learning (TSDL) method is proposed. The proposed method consists of a prereconstruction block and a convolutional neural network (CNN). The prereconstruction block learns the regularization pattern from the training data set and provides a rough reconstruction of the target. The CNN postprocesses the prereconstruction result in a multilevel feature analysis strategy and eliminates the modeling errors with prior information of the observation domain shape. The prereconstruction and CNN blocks are trained together by using a minimum square approach. To evaluate the performance of the TSDL method, the lung EIT problem was studied. The training data set is calculated from more than 100 000 EIT simulation models generated from computed tomography (CT) scans across 792 patients. Lung injury, measurement noise, and model errors are randomly simulated during the model generation process. The trained TSDL model is evaluated with simulation testes, as well as the experimental tests from a laboratory setting. According to the results, the TSDL method could achieve high accuracy shape reconstructions and is robust against measurement noise and modeling errors.

Critical Wind Turbine Components Prognostics: A Comprehensive Review

Abstract: As wind energy is becoming a significant utility source, minimizing the operation and maintenance (O&M) expenses has raised a crucial issue to make wind energy competitive to fossil fuels. Wind turbines (WTs) are subject to unexpected failures due to operational and environmental conditions, aging, and so on. An accurate estimation of time to failures assures reliable power production and lower maintenance costs. In recent years, a notable amount of research has been undertaken to propose prognosis techniques that can be employed to forecast the remaining useful life (RUL) of wind farm assets. This article provides a recent literature review on modeling developments for the RUL prediction of critical WT components, including physics-based, artificial intelligence (AI)-based, stochastic-based, and hybrid prognostics. In particular, the pros and cons of the prognosis models are investigated to assist researchers in selecting proper models for certain applications of WT RUL forecast. Our comprehensive review has revealed that hybrid methods are now the leading and most accurate tools for WT failure predictions over individual hybrid components. Strong candidates for future research include the consideration of variable operating environments, component interaction, physics-based prognostics, and the Bayesian application in the development of WT prognosis methods.

A New Two-Level Hierarchical Diagnosis Network Based on Convolutional Neural Network

Abstract: Fault diagnosis is vital for modern industry, and an increasing number of intelligent methods have been proposed for the fault diagnosis. However, most of the studies focus on distinguishing different fault patterns while ignoring fault deterioration. In this paper, a new hierarchical convolutional neural network (HCNN) is proposed as the two-level hierarchical diagnosis network, and it has two characteristics: 1) the fault pattern and fault severity are modeled as one hierarchical structure and 2) the fault pattern and fault severity can be estimated at the same time. Based on these, a new structure of HCNN is designed, which has two classifiers. Then, a two-stage training method is developed for HCNN to train these two classifiers at once training. The proposed HCNN is conducted on three case studies and has achieved state-of-the-art results. The results show that HCNN outperforms traditional two-layer hierarchical fault diagnosis network, and other machine learning and deep learning methods.

Entropy Measures in Machine Fault Diagnosis: Insights and Applications

Abstract: Entropy, as a complexity measure, has been widely applied for time series analysis. One preeminent example is the design of machine condition monitoring and industrial fault-diagnostic systems. The occurrence of failures in a machine will typically lead to nonlinear characteristics in the measurements, caused by instantaneous variations, which can increase the complexity in the system response. Entropy measures are suitable to quantify such dynamic changes in the underlying process, distinguishing between different system conditions. However, notions of entropy are defined differently in various contexts (e.g., information theory and dynamical systems theory), which may confound researchers in the applied sciences. In this article, we have systematically reviewed the theoretical development of some fundamental entropy measures and clarified the relations among them. Then, typical entropy-based applications of machine fault-diagnostic systems are summarized. Furthermore, insights into possible applications of the entropy measures are explained, as to where and how these measures can be useful toward future data-driven fault diagnosis methodologies. Finally, potential research trends in this area are discussed, with the intent of improving online entropy estimation and expanding its applicability to a wider range of intelligent fault-diagnostic systems.