scispace - formally typeset
Search or ask a question

Showing papers in "Mechanical Systems and Signal Processing in 2022"


Journal ArticleDOI
TL;DR: Deep Transfer Learning (DTL) is a new paradigm of machine learning, which can not only leverage the advantages of Deep Learning (DL) in feature representation, but also benefit from the superiority of transfer learning (TL) in knowledge transfer as mentioned in this paper .

162 citations


Journal ArticleDOI
TL;DR: Deep Transfer Learning (DTL) is a new paradigm of machine learning, which can not only leverage the advantages of Deep Learning (DL) in feature representation, but also benefit from the superiority of transfer learning (TL) in knowledge transfer.

161 citations


Journal ArticleDOI
TL;DR: Successful fault diagnosis of rolling element bearings under complicated operating conditions, including early bearing fault signals in run-to-failure test datasets, signals with impulsive noise and planet bearing signals, demonstrates that the proposed FIVMD is a superior approach in extracting weak bearing repetitive transients.

108 citations


Journal ArticleDOI
TL;DR: An adaptive maximum cyclostationarity blind deconvolution (ACYCBD) is proposed, aiming at the determination of cyclic frequency set estimation method based on autocorrelation function of morphological envelope and the validity of the method is verified.

107 citations


Journal ArticleDOI
TL;DR: Multistability is the phenomenon of multiple coexistent stable states, which are highly sensitive to perturbations, initial conditions, system parameters, etc. Multistability has been widely found in various scientific areas including biology, physics, chemistry, climatology, sociology, and ecology as mentioned in this paper.

96 citations


Journal ArticleDOI
TL;DR: A new approach for fault detection and diagnosis in rotating machinery is proposed, namely: unsupervised classification and root cause analysis, and a comparison between models used in machine learning explainability: SHAP and Local Depth-based Feature Importance for the Isolation Forest (Local-DIFFI).

94 citations


Journal ArticleDOI
TL;DR: In this article , a fault information-guided variational mode decomposition (FIVMD) method is proposed for extracting the weak bearing repetitive transient, and two nested statistical models based on the fault cyclic information, incorporated with the statistical threshold at a specific significance level, are used to approximately determine the mode number.

88 citations


Journal ArticleDOI
TL;DR: Multistability is the phenomenon of multiple coexistent stable states, which are highly sensitive to perturbations, initial conditions, system parameters, etc. Multistability has been widely found in various scientific areas including biology, physics, chemistry, climatology, sociology, and ecology as mentioned in this paper .

84 citations


Journal ArticleDOI
TL;DR: In this article , an adaptive maximum cyclostationarity blind deconvolution (ACYCBD) method was proposed for fault detection, which can recover periodic impulses from mixed fault signals convoluted by noise and periodic impulses.

80 citations


Journal ArticleDOI
TL;DR: A novel data synthesis method called deep feature enhanced generative adversarial network is proposed to improve the performance of im balanced fault diagnosis and outperforms other intelligent methods and shows great potential in imbalanced fault diagnosis.

80 citations


Journal ArticleDOI
TL;DR: A novel deep neural network based on bidirectional-convolutional long short-term memory (BiConvLSTM) networks to determine the type, location, and direction of planetary gearbox faults by extracting spatial and temporal features from both vibration and rotational speed measurements automatically and simultaneously.

Journal ArticleDOI
TL;DR: The review primarily focuses on the recently used wireless data acquisition system and execution of AI resources for data prediction and data diagnosis in RCC buildings and bridges and indicates the lag in real-world execution of structural health monitoring technologies despite advances in academia.

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper proposed a new nonconvex penalty called generalized logarithm(G-log) penalty, which enhances the sparsity and reduces noise disturbance.

Journal ArticleDOI
TL;DR: This paper provides a comprehensive review of blind deconvolution methods from history to state-of-the-art methods and finally to research prospects, as well as provides a survey and summarize the current progress of BDMs applied in machinery fault diagnosis.

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors proposed a new nonconvex penalty called generalized logarithm(G-log) penalty, which enhances the sparsity and reduces noise disturbance.

Journal ArticleDOI
TL;DR: A new GI evaluation frame is built, including the definition of new indexes based on GI, and enhancing signal processing methods via GI, such as spectrum kurtosis, decomposition methods, and multi-objective optimization algorithms are designed.

Journal ArticleDOI
TL;DR: A framework to aggregate and transfer diagnostic knowledge from multiple source machines by combining multiple partial distribution adaptation sub-networks (PDA-Subnets) and a multi-source diagnostic knowledge fusion module is proposed.

Journal ArticleDOI
TL;DR: In this article , a general theory for bistable vibration isolators (BVIs) is presented and the nonlinear restoring force and potential energy are obtained through analyzing the general model of BVIs with three-spring quasi-zero stiffness model.

Journal ArticleDOI
TL;DR: In this article, a general theory for bistable vibration isolators (BVIs) is presented and the nonlinear restoring force and potential energy are obtained through analyzing the general model of BVIs with three-spring quasi-zero stiffness model.

Journal ArticleDOI
TL;DR: In this article , a new approach for fault detection and diagnosis in rotating machinery is proposed, which consists of three parts: feature extraction, fault detection, and fault diagnosis, and two tools for diagnosis are proposed, namely unsupervised classification and root cause analysis.

Journal ArticleDOI
TL;DR: In this paper , the defect length has a significant effect on the acceleration peaks and the sudden change in the contact stiffness caused by the defect is one of the important reasons for bearing vibrations.

Journal ArticleDOI
TL;DR: In this paper, the static and dynamic lubrication parameters of the floating ring bearing (FRB) were investigated considering the effects of various coupling factors such as clearance ratio, vertical load and rotating speed.

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper proposed a deep feature enhanced generative adversarial network (DFAGAN) to improve the performance of imbalanced fault diagnosis, where a pull-away function is integrated to design a new objective function of the generator.

Journal ArticleDOI
TL;DR: The stochastic degradation model proposed for estimation of real-time fatigue damage in the components is based on a proven model-based approach which is tested under different drivetrain operations, namely normal, faulty and overload conditions.

Journal ArticleDOI
TL;DR: A comprehensive review of advances in data acquisition, processing, diagnosis, and retrieval stages of Structural Health Monitoring both academically and commercially is presented in this article , which primarily focuses on the recently used wireless data acquisition system and execution of AI resources for data prediction and data diagnosis in RCC buildings and bridges.

Journal ArticleDOI
Hao Su, Ling Xiang, Aijun Hu, Yonggang Xu, Xin Yang 
TL;DR: In this paper , a novel method called data reconstruction hierarchical recurrent meta-learning (DRHRML) is proposed for bearing fault diagnosis with small samples under different working conditions, which contains data reconstruction and meta learning stages.

Journal ArticleDOI
TL;DR: In this article , an imbalanced fault diagnosis approach based on improved multi-scale residual generative adversarial network (GAN) and feature enhancement-driven capsule network is proposed to solve it.

Journal ArticleDOI
TL;DR: In this article , a new GI evaluation frame, including the definition of new indexes based on GI, is firstly built, and enhancing signal processing methods via GI, such as spectrum kurtosis, decomposition methods, and multi-objective optimization algorithms, are designed.

Journal ArticleDOI
TL;DR: In this article, a gear wear monitoring and prediction approach through the integration of a dynamic model, to simulate the dynamic responses of the gear system; two tribological models, to estimate wear depth and pitting density (on the gear surface); and model updating, by comparing simulated and measured vibration signals.

Journal ArticleDOI
TL;DR: In this paper , the authors studied the fluid structure interaction (FSI) dynamic behaviors of a bearing with axial asymmetric grooves and proposed a revised FSI model with cavitation and turbulent effects.