Showing papers in "Mechanical Systems and Signal Processing in 2021"

TL;DR: This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field.

TL;DR: This paper aims to fulfill the gap by presenting the highlights of the traditional methods and provide a comprehensive review of the most recent applications of ML and DL algorithms utilized for vibration-based structural damage detection in civil structures.

TL;DR: A three-stage SSL approach using data augmentation (DA) and metric learning is proposed for an intelligent bearing fault diagnosis under limited labeled data to demonstrate that the proposed method can perform better in bearing fault diagnosed under limited labeling samples than existing diagnostic methods.

TL;DR: A new deep auto-encoder method with fusing discriminant information about multiple fault types is proposed for bearing fault diagnosis that can effectively improve the diagnostic accuracy with acceptable time efficiency and the results on the Kruskal–Wallis Test indicate the proposed method has better numerical stability.

TL;DR: The statistical analysis, stochastic analysis and frequency analysis are performed to make sense of the effect of the random track irregularities on the pantograph-catenary interaction, and the reliability of the pantographs shows a continuous decrease in the degradation of rail quality.

TL;DR: In this paper, the authors investigated a technique for broadband vibration suppression using a graded metamaterial beam, where a series of local resonators with the same mass but different natural frequencies are attached to the beam, and a design strategy was proposed, and used to tune the frequency spacing to get a wide attenuation region.

TL;DR: Experiments demonstrate the superior property of stronger robustness and fewer chattering effects of the proposed method compared to existing disturbance observers and adaptive recursive terminal sliding mode (ARTSM) controller.

TL;DR: This work is interested in digital twins, and the development of a simplified framework for them, in the context of dynamical systems, including the possibility of integrating physics-based models with machine learning.

TL;DR: A knowledge mapping-based adversarial domain adaptation (KMADA) method with a discriminator and a feature extractor to generalize knowledge from target to source domain and indicates the irreplaceable superiority of the KMADA, which achieves the highest diagnosis accuracy.

TL;DR: In this article, the authors proposed a composite meta-porous structure embedded multiple lateral plates of different lengths, and investigated the corresponding sound absorption coefficients with the fixed and periodic boundary, which achieved high sound absorption in range of 0.6.4

TL;DR: In this article, a hybrid piezo-dielectric (PD) wind energy harvester was proposed to efficiently harvest the vortex-induced vibration (VIV) energy from low-speed wind.

TL;DR: A semi-supervised fault diagnosis method called hybrid classification autoencoder, which utilizes a softmax classifier to directly diagnose the health condition based on the encoded features from the autoenCoder, is proposed in this paper.

TL;DR: The simulation results show that the proposed Fast Entrogram can effectively extract periodic pulses, and it is verified by experimental signals that the method can be applied to fault diagnosis of bearing inner and outer rings.

TL;DR: A review of metamaterials and origami-based structures as well as their applications to vibration and sound control and possible future research directions are elaborated for this emerging and promising interdisciplinary research field.

TL;DR: In this paper, a new bearing fault diagnosis method combining singular value decomposition (SVD) and the squared envelope spectrum (SES) is proposed for early-stage defects of rolling element bearings (REBs) using vibration signals.

TL;DR: The proposed HDNN is capable of accurately predicting the cutterhead torque even under complicated geological conditions, which is provided with high industrial application value.

TL;DR: This paper proposes a new approach, called Feature Space Metric-based Meta-learning Model (FSM3), to overcome the challenge of the few-shot fault diagnosis under multiple limited data conditions, which is a mixture of general supervised learning and episodic metric meta-learning.

TL;DR: An asynchronous fault detection filter is presented which can follow up the system modes by resorting to a dual hidden Markov model and sufficient conditions are devised to make the resultant Markov jump systems be stochastically stable and hold a specified H ∞ performance level.

TL;DR: In this paper, the authors extend a recently developed class of uniaxial symmetric rate independent models to simulate complex asymmetric mechanical hysteresis phenomena, which allows for the evaluation of the generalized force by solving a scalar equation and employing only one history variable.

TL;DR: In this article, the micro interface lubrication mechanisms of water-lubricated bearing are revealed and they apply to bearings with different dimensions and they lay solid foundation for further optimal design of surface topography of such bearings.

TL;DR: The main focus of this paper is on the comprehensive review of the technological advances and characteristics of five common types of transient wave-based anomaly detection methods for fluid pipe systems, namely (1) reflection-based method; (2) damping-basedmethod; (3) FRF peak pattern-based methods; (4) time domain full-waveform inversion method; and (5) frequency domain full

TL;DR: In this paper, a vibration-based wear mechanism identification procedure is proposed, and then the wear evolution is tracked using an indicator of vibration cyclostationarity (CS), with consideration of the underlying physics of the gear meshing process and the unique surface features induced by fatigue pitting and abrasive wear.

TL;DR: It is shown that both ride comfort and road holding (steering stability) can be enhanced by utilizing the fast-response MR damper, and the sensitivity of the closed loop feedback system considering response time of MR dampers are analyzed in the Nyquist domain.

TL;DR: In this paper, a modified lubrication model considering the influences of journal misalignment is proposed in the theoretical model, and the influence of surface topography and thermal balance effects are incorporated in a theoretical model.

TL;DR: In this article, an analytical model for fiber reinforced polymer composite cylindrical shells (FRPCCSs) accounting for material and geometric nonlinearities and thermal effect is proposed, which is capable of predicting natural frequencies, damping ratios, and resonant responses under different excitation amplitudes and temperatures.

TL;DR: This work proposes to use one-dimensional convolutional neural network (1-D CNN) to correlate the time-varying DI directly with the damage location, and uses the equivariance property of CNN to preserve the temporal information in the wave signal.

TL;DR: In this article, the authors proposed the theory and method of vibration isolation and energy harvesting based on the high-order quasi-zero stiffness (HQZS) mechanism, which is expected to break through the above bottleneck.

TL;DR: In this paper, the negative stiffness mechanism was incorporated into the semi-active suspension using a magnetorheological (MR) damper, which provided a solution to improving the vibration-reduction performance of the semiactive suspensions to the level achievable by active suspensions while avoiding the disadvantages of active control.

TL;DR: This work highlights the development history and focuses particularly on the research of piezoelectric pumps in four aspects: configuration design, working mode, optimization and application, respectively, and attempts to provide both a guidance for piezOElectric pump researchers on improving their output performances and a resource for those outside the field who wish to identify the best piezoeselectric pump for a particular application.

TL;DR: This paper is dedicated to analyze the different AE principles in RE systems, and to comprehensively summarize and clearly highlight the advanced methods and challenges.