A Modified DF2016 Criterion for the Fracture Modeling from Shear to Equibiaxial Tension.

This study introduces a modified DF2016 criterion to model a ductile fracture of sheet metals from shear to equibiaxial tension. The DF2016 criterion is modified so that a material constant is equal to the fracture strain at equibiaxial tension, which can be easily measured by the bulging experiments. To evaluate the performance of the modified DF2016 criterion, experiments are conducted for QP980 with five different specimens with stress states from shear to equibiaxial tension. The plasticity of the steel is characterized by the Swift-Voce hardening law and the pDrucker function, which is calibrated with the inverse engineering approach. A fracture strain is measured by the XTOP digital image correlation system for all the specimens, including the bulging test. The modified DF2016 criterion is also calibrated with the inverse engineering approach. The predicted force-stroke curves are compared with experimental results to evaluate the performance of the modified DF2016 criterion on the fracture prediction from shear to equibiaxial tension. The comparison shows that the modified DF2016 criterion can model the onset of the ductile fracture with high accuracy in wide stress states from shear to plane strain tension. Moreover, the calibration of the modified DF2016 criterion is comparatively easier than the original DF2016 criterion.

Filter-Informed Spectral Graph Wavelet Networks for Multiscale Feature Extraction and Intelligent Fault Diagnosis.

Intelligent fault diagnosis has been increasingly improved with the evolution of deep learning (DL) approaches. Recently, the emerging graph neural networks (GNNs) have also been introduced in the field of fault diagnosis with the goal to make better use of the inductive bias of the interdependencies between the different sensor measurements. However, there are some limitations with these GNN-based fault diagnosis methods. First, they lack the ability to realize multiscale feature extraction due to the fixed receptive field of GNNs. Second, they eventually encounter the over-smoothing problem with increase of model depth. Finally, the extracted features of these GNNs are hard to understand due to the black-box nature of GNNs. To address these issues, a filter-informed spectral graph wavelet network (SGWN) is proposed in this article. In SGWN, the spectral graph wavelet convolutional (SGWConv) layer is established upon the spectral graph wavelet transform, which can decompose a graph signal into scaling function coefficients and spectral graph wavelet coefficients. With the help of SGWConv, SGWN is able to prevent the over-smoothing problem caused by long-range low-pass filtering, by simultaneously extracting low-pass and band-pass features. Furthermore, to speed up the computation of SGWN, the scaling kernel function and graph wavelet kernel function in SGWConv are approximated by the Chebyshev polynomials. The effectiveness of the proposed SGWN is evaluated on the collected solenoid valve dataset and aero-engine intershaft bearing dataset. The experimental results show that SGWN can outperform the comparative methods in both diagnostic accuracy and the ability to prevent over-smoothing. Moreover, its extracted features are also interpretable with domain knowledge.

Hidden-information extraction from layered structures through terahertz imaging down to ultralow SNR.

Noninvasive inspection of layered structures has remained a long-standing challenge for time-resolved imaging techniques, where both resolution and contrast are compromised by prominent signal attenuation, interlayer reflections, and dispersion. Our method based on terahertz (THz) time-domain spectroscopy overcomes these limitations by offering fine resolution and a broadband spectrum to efficiently extract hidden structural and content information from layered structures. We exploit local symmetrical characteristics of reflected THz pulses to determine the location of each layer, and apply a statistical process in the spatiotemporal domain to enhance the image contrast. Its superior performance is evidenced by the extraction of alphabetic characters in 26-layer subwavelength papers as well as layer reconstruction and debonding inspection in the conservation of Terra-Cotta Warriors. Our method enables accurate structure reconstruction and high-contrast imaging of layered structures at ultralow signal-to-noise ratio, which holds great potential for internal inspection of cultural artifacts, electronic components, coatings, and composites with dozens of submillimeter layers.

Domain Adaptation Networks With Parameter-Free Adaptively Rectified Linear Units for Fault Diagnosis Under Variable Operating Conditions.

As an important component of the rotating machinery, rolling bearings usually work under the condition of variable speed and load, and vibration signals in the same health state are significantly different due to the change in operating conditions. To address the problem that the existing deep learning (DL) methods have fixed nonlinear transformations for all input signals in cross-domain fault diagnosis, we propose a new activation function, i.e., parameter-free adaptively rectified linear units (PfAReLU). The proposed activation function performs adaptive nonlinear transformations according to the input data and can better capture the fault features of vibration signals in the same fault state under different operating conditions. Furthermore, the number of PfAReLU parameters is zero, so that the risk of network overfitting is reduced. At the same time, deep parameter-free reconstruction-classification networks with PfAReLU (DPRCN-PfAReLU) are also constructed for cross-domain fault diagnosis. Specifically, DPRCN-PfAReLU consists of a shared encoder, a target domain decoder, and a source domain classifier. The shared encoder adds a parameter-free attention module at the output to enhance the weight of domain-invariant features without increasing network parameters. The shared encoded representation of source domain and target domain is learned by target domain decoder and source domain classifier. Compared with other methods under nine different operating conditions via real experiment studies, the proposed method shows superiority for cross-domain fault diagnosis.

WPConvNet: An Interpretable Wavelet Packet Kernel-Constrained Convolutional Network for Noise-Robust Fault Diagnosis.

Deep learning (DL) has present great diagnostic results in fault diagnosis field. However, the poor interpretability and noise robustness of DL-based methods are still the main factors limiting their wide application in industry. To address these issues, an interpretable wavelet packet kernel-constrained convolutional network (WPConvNet) is proposed for noise-robust fault diagnosis, which combines the feature extraction ability of wavelet bases and the learning ability of convolutional kernels together. First, the wavelet packet convolutional (WPConv) layer is proposed, and constraints are imposed to convolutional kernels, so that each convolution layer is a learnable discrete wavelet transform. Second, a soft threshold activation is proposed to reduce the noise component in feature maps, whose threshold is adaptively learned by estimating the standard deviation of noise. Third, we link the cascaded convolutional structure of convolutional neutral network (CNN) with wavelet packet decomposition and reconstruction using Mallat algorithm, which is interpretable in model architecture. Extensive experiments are carried out on two bearing fault datasets, and the results show that the proposed architecture outperforms other diagnosis models in terms of interpretability and noise robustness.

Adversarial Algorithm Unrolling Network for Interpretable Mechanical Anomaly Detection.

In mechanical anomaly detection, algorithms with higher accuracy, such as those based on artificial neural networks, are frequently constructed as black boxes, resulting in opaque interpretability in architecture and low credibility in results. This article proposes an adversarial algorithm unrolling network (AAU-Net) for interpretable mechanical anomaly detection. AAU-Net is a generative adversarial network (GAN). Its generator, composed of an encoder and a decoder, is mainly produced by algorithm unrolling of a sparse coding model, which is specially designed for feature encoding and decoding of vibration signals. Thus, AAU-Net has a mechanism-driven and interpretable network architecture. In other words, it is ad hoc interpretable. Moreover, a multiscale feature visualization approach for AAU-Net is introduced to verify that meaningful features are encoded by AAU-Net, helping users to trust the detection results. The feature visualization approach enables the results of AAU-Net to be interpretable, i.e., post hoc interpretable. To verify AAU-Net's capability of feature encoding and anomaly detection, we designed and performed simulations and experiments. The results show that AAU-Net can learn signal features that match the dynamic mechanism of the mechanical system. Considering the excellent feature learning ability, unsurprisingly, AAU-Net achieves the best overall anomaly detection performance compared with other algorithms.

A high-efficient piezoelectric wireless energy transmission system based on magnetic force coupling.

This research reports an acoustic wireless energy transmission system featuring high efficiency and robustness. The proposed energy transmission system is composed of a piezoelectric cantilever-based transmitter and receiver that are coupled using the forces of permanent magnets. Taking advantage of the strong coupling effect of magnet force, we can transfer mechanical energy wirelessly through mediums of the air and metal plate. The experimental studies show that the voltage transmission efficiencies reach 55.59% and 51.58% in cases of energy transfer through mediums of the air and the air-metal-air, respectively. In addition, the maximum power transmission reaches 42.73 mW at an operational frequency of 104.2 Hz. This wireless energy transmission system can be used for powering devices in enclosed, electrically shielded, and biomedical areas.

Physics-Constraint Variational Neural Network for Wear State Assessment of External Gear Pump.

Most current data-driven prognosis approaches suffer from their uncontrollable and unexplainable properties. To address this issue, this article proposes a physics-constraint variational neural network (PCVNN) for wear state assessment of the external gear pump. First, a response model of the pressure pulsation of the gear pump is constructed via a spectral method, and a compound neural network is utilized to extract features from the pressure pulsation signal. Then, the response model is formulated into an objective function to softly constrain the learning process of the neural network, forcing the learned features to have explicit physics meaning. Meanwhile, to characterize the system uncertainty, the variational inference is utilized to extend a Kullback-Leibler ( KL) divergence into the objective function. Finally, the wear state is evaluated based on the distance of learned physics features. Experimental results on an external gear pump validate the merits of the proposed method in explainable representation learning and system uncertainty estimation. It also offers a controllable and explainable perspective to understand the dynamic behavior of the system.

Variational Attention-Based Interpretable Transformer Network for Rotary Machine Fault Diagnosis.

Deep learning technology provides a promising approach for rotary machine fault diagnosis (RMFD), where vibration signals are commonly utilized as input of a deep network model to reveal the internal state of machinery. However, most existing methods fail to mine association relationships within signals. Unlike deep neural networks, transformer networks are capable of capturing association relationships through the global self-attention mechanism to enhance feature representations from vibration signals. Despite this, transformer networks cannot explicitly establish the causal association between signal patterns and fault types, resulting in poor interpretability. To tackle these problems, an interpretable deep learning model named the variational attention-based transformer network (VATN) is proposed for RMFD. VATN is improved from transformer encoder to mine the association relationships within signals. To embed the prior knowledge of the fault type, which can be recognized based on several key features of vibration signals, a sparse constraint is designed for attention weights. Variational inference is employed to force attention weights to samples from Dirichlet distributions, and Laplace approximation is applied to realize reparameterization. Finally, two experimental studies conducted on bevel gear and bearing datasets demonstrate the effectiveness of VATN to other comparison methods, and the heat map of attention weights illustrates the causal association between fault types and signal patterns.

Robust PVC Identification by Fusing Expert System and Deep Learning.

Premature ventricular contraction (PVC) is one of the common ventricular arrhythmias, which may cause stroke or sudden cardiac death. Automatic long-term electrocardiogram (ECG) analysis algorithms could provide diagnosis suggestion and even early warning for physicians. However, they are mutually exclusive in terms of robustness, generalization and low complexity. In this study, a novel PVC recognition algorithm that combines deep learning-based heartbeat template clusterer and expert system-based heartbeat classifier is proposed. A long short-term memory-based auto-encoder (LSTM-AE) network was used to extract features from ECG heartbeats for K-means clustering. Thus, the templates were constructed and determined based on clustering results. Finally, the PVC heartbeats were recognized based on a combination of multiple rules, including template matching and rhythm characteristics. Three quantitative parameters, sensitivity (Se), positive predictive value (P+) and accuracy (ACC), were used to evaluate the performances of the proposed method on the MIT-BIH Arrhythmia database and the St. Petersburg Institute of Cardiological Technics database. Se on the two test databases was 87.51% and 87.92%, respectively; P+ was 92.47% and 93.18%, respectively; and ACC was 98.63% and 97.89%, respectively. The PVC scores on the third China Physiological Signal Challenge 2020 training set and hidden test set were 36,256 and 46,706, respectively, which could rank first in the open-source codes. The results showed that the combination strategy of expert system and deep learning can provide new insights for robust and generalized PVC identification from long-term single-lead ECG recordings.

Model-driven deep unrolling: Towards interpretable deep learning against noise attacks for intelligent fault diagnosis.

Intelligent fault diagnosis (IFD) has experienced tremendous progress owing to a great deal to deep learning (DL)-based methods over the decades. However, the "black box" nature of DL-based methods still seriously hinders wide applications in industry, especially in aero-engine IFD, and how to interpret the learned features is still a challenging problem. Furthermore, IFD based on vibration signals is often affected by the heavy noise, leading to a big drop in accuracy. To address these two problems, we develop a model-driven deep unrolling method to achieve ante-hoc interpretability, whose core is to unroll a corresponding optimization algorithm of a predefined model into a neural network, which is naturally interpretable and robust to noise attacks. Motivated by the recent multi-layer sparse coding (ML-SC) model, we herein propose to solve a general sparse coding (GSC) problem across different layers and deduce the corresponding layered GSC (LGSC) algorithm. Based on the ideology of deep unrolling, the proposed algorithm is unfolded into LGSC-Net, whose relationship with the convolutional neural network (CNN) is also discussed in depth. The effectiveness of the proposed model is verified by an aero-engine bevel gear fault experiment and a helical gear fault experiment with three kinds of adversarial noise attacks. The interpretability is also discussed from the perspective of the core of model-driven deep unrolling and its inductive reconstruction property.

Explainable Graph Wavelet Denoising Network for Intelligent Fault Diagnosis.

Deep learning (DL)-based intelligent fault diagnosis methods have greatly promoted the development of the field of fault diagnosis due to their powerful feature extraction ability for handling massive monitoring data. However, most of them still suffer from the following three limitations. First, many existing DL-based intelligent diagnosis methods cannot extract proper discriminative features from signals with strong noise. Second, the interactions or relationships between signals are ignored, while they mainly focus on extracting temporal features from the signal. Third, owing to their black-box nature, the learned features lack interpretability, which hinders their application in the industry. To tackle these issues, an explainable graph wavelet denoising network (GWDN) is proposed to achieve intelligent fault diagnosis under noisy working conditions in this article. In GWDN, the collected signals are first transformed into graph-structured data to consider the interactions among signals. Then, the graph wavelet denoising convolution (GWDConv) is proposed based on the discrete graph wavelet frame, which allows GWDN to achieve multiscale feature extraction for graph-structured data and realize signal denoising. Extensive experiments are implemented to verify the efficacy of the proposed GWDN, and the experimental results show that GWDN can achieve state-of-the-art performance among the comparison methods. Besides, by using the square envelope spectrum to analyze the extracted features of GWDConv, we find that it can well retain the fault-related components of the signal and realize signal denoising, which further proves that GWDN is explainable.

A structural impedance measurement method by using polyvinylidene fluoride as actuator and sensor.

Polyvinylidene fluoride (PVDF) patches have extremely small Young's modulus and piezoelectric coefficients. They are usually chosen as sensors in the structural impedance measurement for health monitoring. In this paper, a novel method is demonstrated for structural impedance measurement using PVDF patches as actuators and sensors. The impedance of the host structure is decoupled from the capacitance impedance of the piezoelectric transducer by using one of the patches as the actuator and the other as the sensor. Phase sensitive detection is then adopted to recover weak impedance signals in the experimental studies. This technique enables measurement of the resonant frequencies and further identification of the health condition of the host structure. The superiority of this method is illustrated theoretically comparing to the conventional impedance-base method. A prototype consisting of a metal cantilever with two PVDF patches is fabricated and tested. Experimental results demonstrate the effectiveness of the proposed method in the detection of the resonance of the substrate precisely with respect to FEM simulation and the results under base-movement excitations. Moreover, mass change induced impedance shifting can be obtained.

Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study.

Rotating machinery intelligent diagnosis based on deep learning (DL) has gone through tremendous progress, which can help reduce costly breakdowns. However, different datasets and hyper-parameters are recommended to be used, and few open source codes are publicly available, resulting in unfair comparisons and ineffective improvement. To address these issues, we perform a comprehensive evaluation of four models, including multi-layer perception (MLP), auto-encoder (AE), convolutional neural network (CNN), and recurrent neural network (RNN), with seven datasets to provide a benchmark study. We first gather nine publicly available datasets and give a comprehensive benchmark study of DL-based models with two data split strategies, five input formats, three normalization methods, and four augmentation methods. Second, we integrate the whole evaluation codes into a code library and release it to the public for better comparisons. Third, we use specific-designed cases to point out the existing issues, including class imbalance, generalization ability, interpretability, few-shot learning, and model selection. Finally, we release a unified code framework for comparing and testing models fairly and quickly, emphasize the importance of open source codes, provide the baseline accuracy (a lower bound), and discuss existing issues in this field. The code library is available at: https://github.com/ZhaoZhibin/DL-based-Intelligent-Diagnosis-Benchmark.

Design and Implementation of a Hypothermic Machine Perfusion Device for Clinical Preservation of Isolated Organs.

The imbalance between limited organ supply and huge potential need has hindered the development of organ-graft techniques. In this paper a low-cost hypothermic machine perfusion (HMP) device is designed and implemented to maintain suitable preservation surroundings and extend the survival life of isolated organs. Four necessary elements (the machine perfusion, the physiological parameter monitoring, the thermostatic control and the oxygenation apparatus) involved in this HMP device are introduced. Especially during the thermostatic control process, a modified Bayes estimation, which introduces the concept of improvement factor, is realized to recognize and reduce the possible measurement errors resulting from sensor faults and noise interference. Also, a fuzzy-PID controller contributes to improve the accuracy and reduces the computational load using the DSP. Our experiments indicate that the reliability of the instrument meets the design requirements, thus being appealing for potential clinical preservation applications.

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks.

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

A Novel Hybrid Error Criterion-Based Active Control Method for on-Line Milling Vibration Suppression with Piezoelectric Actuators and Sensors.

Milling vibration is one of the most serious factors affecting machining quality and precision. In this paper a novel hybrid error criterion-based frequency-domain LMS active control method is constructed and used for vibration suppression of milling processes by piezoelectric actuators and sensors, in which only one Fast Fourier Transform (FFT) is used and no Inverse Fast Fourier Transform (IFFT) is involved. The correction formulas are derived by a steepest descent procedure and the control parameters are analyzed and optimized. Then, a novel hybrid error criterion is constructed to improve the adaptability, reliability and anti-interference ability of the constructed control algorithm. Finally, based on piezoelectric actuators and acceleration sensors, a simulation of a spindle and a milling process experiment are presented to verify the proposed method. Besides, a protection program is added in the control flow to enhance the reliability of the control method in applications. The simulation and experiment results indicate that the proposed method is an effective and reliable way for on-line vibration suppression, and the machining quality can be obviously improved.

EOG artifact correction from EEG recording using stationary subspace analysis and empirical mode decomposition.

Ocular contamination of EEG data is an important and very common problem in the diagnosis of neurobiological events. An effective approach is proposed in this paper to remove ocular artifacts from the raw EEG recording. First, it conducts the blind source separation on the raw EEG recording by the stationary subspace analysis, which can concentrate artifacts in fewer components than the representative blind source separation methods. Next, to recover the neural information that has leaked into the artifactual components, the adaptive signal decomposition technique EMD is applied to denoise the components. Finally, the artifact-only components are projected back to be subtracted from EEG signals to get the clean EEG data. The experimental results on both the artificially contaminated EEG data and publicly available real EEG data have demonstrated the effectiveness of the proposed method, in particular for the cases where limited number of electrodes are used for the recording, as well as when the artifact contaminated signal is highly non-stationary and the underlying sources cannot be assumed to be independent or uncorrelated.

A 3-D reconstruction solution to current density imaging based on acoustoelectric effect by deconvolution: a simulation study.

Hybrid imaging modality combining ultrasound scanning and electrical current density imaging through the acoustoelectric (AE) effect may potentially provide solutions to imaging electrical activities and properties of biological tissues with high spatial resolution. In this study, a 3-D reconstruction solution to ultrasound current source density imaging (UCSDI) by means of Wiener deconvolution is proposed and evaluated through computer simulations. As compared to previous 2-D UCSDI problem, in a 3-D volume conductor with broadly distributed current density field, the AE signal becomes a 3-D convolution between the electric field and the acoustic field, and effective 3-D reconstruction algorithm has not been developed so far. In the proposed method, a 3-D ultrasound scanning is performed while the corresponding AE signals are collected from multiple electrode pairs attached on the surface of the imaging object. From the collected AE signals, the acoustic field and electric field were first decoupled by Wiener deconvolution. Then, the current density distribution was reconstructed by inverse projection. Our simulations using artificial current fields in homogeneous phantoms suggest that the proposed method is feasible and robust against noise. It is also shown that using the proposed method, it is feasible to reconstruct 3-D current density distribution in an inhomogeneous conductive medium.

Three-dimensional noninvasive ultrasound Joule heat tomography based on the acousto-electric effect using unipolar pulses: a simulation study.

Electrical properties of biological tissues are highly sensitive to their physiological and pathological status. Thus it is of importance to image electrical properties of biological tissues. However, spatial resolution of conventional electrical impedance tomography (EIT) is generally poor. Recently, hybrid imaging modalities combining electric conductivity contrast and ultrasonic resolution based on the acousto-electric effect has attracted considerable attention. In this study, we propose a novel three-dimensional (3D) noninvasive ultrasound Joule heat tomography (UJHT) approach based on the acousto-electric effect using unipolar ultrasound pulses. As the Joule heat density distribution is highly dependent on the conductivity distribution, an accurate and high-resolution mapping of the Joule heat density distribution is expected to give important information that is closely related to the conductivity contrast. The advantages of the proposed ultrasound Joule heat tomography using unipolar pulses include its simple inverse solution, better performance than UJHT using common bipolar pulses and its independence of a priori knowledge of the conductivity distribution of the imaging object. Computer simulation results show that using the proposed method, it is feasible to perform a high spatial resolution Joule heat imaging in an inhomogeneous conductive media. Application of this technique on tumor scanning is also investigated by a series of computer simulations.