Showing papers in "Mechanical Systems and Signal Processing in 2019"

TL;DR: The applications of deep learning in machine health monitoring systems are reviewed mainly from the following aspects: Auto-encoder and its variants, Restricted Boltzmann Machines, Convolutional Neural Networks, and Recurrent Neural Networks.

TL;DR: A feature-based transfer neural network (FTNN) is proposed to identify the health states of BRMs with the help of the diagnosis knowledge from BLMs to present higher diagnosis accuracy for BRMs than existing methods.

TL;DR: A systemic and pertinent state-of-art review on WT planetary gearbox condition monitoring techniques on the topics of fundamental analysis, signal processing, feature extraction, and fault detection is provided.

TL;DR: This study is committed to providing a comprehensive review of SR from history to state-of-the-art methods and finally to research prospects, along with the applications in rotating machine fault detection.

TL;DR: The proposed methods had good results for diagnosis of bearing, stator and rotor faults of the single-phase induction motor and can find applications for fault diagnosis of other types of rotating machines.

TL;DR: A novel fault diagnosis approach integrating Convolutional Neural Networks and Extreme Learning Machine, which can detect different fault types and outperforms other methods in terms of classification accuracy is proposed.

TL;DR: The experimental results show that the proposed deep separable convolutional network (DSCN) is able to provide accurate RUL prediction results based on the raw multi-sensor data and is superior to some existing data-driven prognostics approaches.

TL;DR: A sensor-based data-driven scheme using a deep learning tool and the similarity-based curve matching technique to estimate the RUL of a system, which demonstrates the competitiveness of the proposed method used for RUL estimation of systems.

TL;DR: This paper attempts to survey and summarize the current progress of SR applied in machinery fault detection, providing comprehensive references for researchers concerning with the subject and further helping them identify future trends for research.

TL;DR: The main concepts of beamforming, starting from the very basics and progressing on to more advanced concepts and techniques are presented, in order to give the reader the possibility to identify concepts and references which might be useful for her/his work.

TL;DR: In this paper, a rotational harvester with bi-stability and frequency up-conversion is presented for harnessing low-frequency kinetic energy with a wide bandwidth.

TL;DR: A coarse-to-fine decomposing strategy is proposed for weak fault detection of rotating machines and can well-detect the weak repetitive transients in the signals with heavy noise and overcome the drawbacks of the original VMD.

TL;DR: This work presents a novel diagnosis framework that combines the spatiotemporal pattern network (STPN) approach with convolutional neural networks (CNN) to build a hybrid ST-CNN scheme, and it is verified that the spatial features can elevate the diagnosis accuracy.

TL;DR: The analysis results of simulation signals and experimental signals indicate that the proposed time-series decomposition approach can decompose the analyzed signals accurately and effectively.

TL;DR: In this paper, a quasi-zero stiffness system consisting of three linear springs is adopted as the nonlinear isolator to attenuate the transverse vibrations of fluid-conveying pipes induced by foundation excitations.

TL;DR: Based on the finite element theory and the loaded tooth contact analysis, an analytical-finite element model considering the complex gear foundation types and the crack propagation paths is proposed to calculate the mesh stiffness of spur gears as discussed by the authors.

TL;DR: Experimental results indicate that the proposed DE-based implementation strategy for the MPC path following controller achieves good computational performance and satisfactory control performance for path following in autonomous cars.

TL;DR: A class of methods in TFA, parameterised TFA is focused on, summarizing its latest research progress and related engineering applications, so as to provide reference and guidance for researchers applying parametric TFA in different fields.

TL;DR: A statistical methodology based on the maximum likelihood ratio is introduced as a general framework to design condition indicators able to track cyclostationary or non-Gaussian symptoms independently and arrives with the possibility of setting up statistical thresholds, as needed for a reliable diagnosis.

TL;DR: A review of proper orthogonal decomposition (POD) methods for order reduction in a variety of research areas is presented in this paper, where the historical development and basic mathematical formulation of the POD method are introduced.

TL;DR: A modified method known as cuckoo search algorithm-based variational mode decomposition (CSA-VMD) is proposed, which can decompose adaptively a multi-component signal into a superposition of sub-signals termed as intrinsic mode function (IMF) by means of parameter optimization.

TL;DR: A modified VAM (MVAM) is developed that can circumvent existing problems with practical implementation and provide higher sensitivity in bolt early looseness monitoring, and is compared with the proposed MMSE-based DI with nonlinear DI of traditional VAM method.

TL;DR: In this article, the influence of periodic arrays of multiple degrees of freedom local resonators in square and triangular lattices is investigated theoretically for the band structure of flexural waves propagating in an elastic metamaterial thin plate.

TL;DR: In this article, a time-reassigned synchrosqueezing transform (TSST) was proposed for impulsive-like signal whose TF ridge curves is nearly parallel with the frequency axis.

TL;DR: In this review, the operating principles, some representative designs, performance analyses and practical applications of each type of non-resonant piezoelectric actuators are provided and the future development perspectives are discussed.

TL;DR: The dual optimization process using different estimators provides better error compensation results than a single optimization method, which demonstrates that the proposed solution leads to the better performance of a MEMS-based INS/GPS navigation system.

TL;DR: This paper presents a new decomposition approach called adaptive chirp mode pursuit (ACMP), similar to the matching pursuit method, the ACMP captures signal modes one by one in a recursive framework.

TL;DR: This paper summarizes and classify these approaches of piezoelectric actuation systematically, and discusses the pros and cons for each type, and explores the derivative relations among these principles.

TL;DR: Results indicate that the angular synchronous average technique could effectively reveal the fault vibration feature, and the M8A in the selected statistical indicators is most sensitive to the tooth crack propagation in frequency domain.

TL;DR: The state of the art and challenges to TF analysis that cast SHM in the context of a system identification (SI) paradigm are reviewed and discussed in this study.