Nanoscale beams are commonly found in nanomechanical and nanoelectromechanical systems (NEMS) other nanotechnology-based devices. Surface energy has a significant effect on nanoscale structures is associated with their size-dependent behavior. In this paper, general mechanistic model based the Gurtin-Murdoch continuum theory accounting for surface effects presented to analyze thick thin an arbitrary cross section. The main contributions of paper set closed-form analytical solutions static...

Synthetic minority oversampling (SMOTE) has been widely used in dealing with the imbalance classification mechanical fault diagnosis field. However, classical SMOTE model generates poor quality data, which leads to a low diagnostic accuracy of model. This article proposes an generation based on Gaussian mixture (GMM) and boundary joint optimization (BDOP-GMM-SMOTE). First, GMM is utilized cluster class bearing weights different classes should be distributed according density distribution...

Rotate vector (RV) reducers have widely been used in high-performance precision drives for industrial robots. However, the current nonlinear dynamic studies on RV are not extensive and require a deeper focus. To bridge this gap, translational–torsional model an reducer transmission system is proposed. The gear backlash, time-varying mesh stiffness, comprehensive meshing errors taken into account model. dimensionless vibration differential equations of were derived solved numerically. By...

Displacement measurement is an essential method for structural safety assessment and health monitoring, the static dynamic characteristics of structure can be obtained through displacement. In order to overcome limitations sensors in vibration large structures, as well poor adaptability visual algorithms such machine learning digital image processing, this paper takes bridge research object introduces deep into field measurement. Moreover, based on convolutional neural network, a new...

The rotate vector (RV) reducer has a complex structure and highly coupled internal components. Acoustic emission (AE) signal, which is more sensitive to weak fault, selected for fault diagnosis of the RV reducer. high sampling frequency big data are challenges AE signal store analysis. This study combines compressed sensing (CS) convolutional neural networks. As result, redundancy significantly reduced while retaining most information, analysis efficiency improved. Firstly, time-domain was...

In recent years, neural networks have shown good performance in terms of accuracy and efficiency. However, along with the continuous improvement diagnostic accuracy, number parameters network is increasing models can often only be run servers high computing power. Embedded devices are widely used on-site monitoring fault diagnosis. due to limitation hardware resources, it difficult effectively deploy complex trained by deep learning, which limits application learning methods engineering...

Recent years have seen the widespread utilization of vision-based noncontact methods for measuring rotor vibrations, but measurement accuracy such approaches is still substantially constrained by both acquisition environment and equipment, which improving quality clarity captured sequence frames would be an effective solution strategy. In this paper, a progressive video super-resolution reconstruction network thus constructed to enhance image feature information during preliminary phase...

Many deep learning models for fault diagnosis have not considered the prior knowledge of rolling bearing. Moreover, some measuring locations cannot collect adequate data to diagnose due equipment size or installation space problems. This paper proposes a wavelet convolutional transfer model bearing detection on cross-measurement points. A new convolution layer includes redesigned kernel and energy pooling layer. The is designed based construction mining time-frequency characteristics....

Compared with traditional vibration measurement sensors, visual displacement technology has many advantages, such as long distance, non-contact, and non-interference. However, when it comes to complex working conditions or inconvenient preprocessing scene, measuring techniques usually cannot produce results the high precision needed for analysis. In this article, we proposed a algorithm of rotating body using semantic segmentation network by taking high-speed industrial camera image...

In fault diagnosis research, compound faults are often regarded as an isolated mode, while the association between and single is ignored, resulting in inability to make accurate effective diagnoses of absence training data. examination rotate vector (RV) reducer, a core component industrial robots, this paper proposes identification method that based on improved convolutional capsule network for RV reducers. First, one-dimensional neural networks used feature learners deeply mine information...

The performance of image denoising based on multiscale geometric analysis (MGA), such as curvelets, contourlets, shearlets, has been researched extensively due to its effectiveness. In this paper, a shearlet-based bivariate shrinkage for is presented by taking into account the statistical dependencies between shearlet coefficients. Mutual information used achieve Dissimilar wavelet-based using wavelet coefficient and parent, scheme exploits cousin belonging same subband with opposite...

The Detection and analysis of neural spike activity is a prerequisite for studying many types brain functions. In this paper, we introduce an open source toolbox built in MATLAB called SPKtool analysis. functions support common requirement spikes, including detection, feature extraction, manual semi-automatic clustering methods graphical tools train It possible to perform the whole procedure with SPKtool. provides flexible batch processing mode, which can significantly accelerate when data...

The ball screw is the core component of CNC machine tool feed system, and its health plays an important role in system even entire tool. This paper studies fault diagnosis assessment screws. Aiming at problem that signal weak susceptible to interference, using a wavelet convolution structure improve network can mining ability time domain frequency features; aiming challenge sensor installation position limitation, transfer learning method proposed, which adopts adaptation as jointly...

AbstractThis paper proposes a load distribution model for the ball screw feed system with assembly errors of guide rails, which is used to predict variation law distributions screws and carriage-guide rail systems. Firstly, under action contact loads screws, bending deformation axis corresponding each derived. Secondly, static machine tool bearing established. Then, proposed based on balance compatibility equation, solution process including judging ball-raceway state given. In addition,...

Abstract In gearbox systems, a composite fault diagnosis resulting from mutual interference among different components poses significant challenge. The traditional methods based on conventional signal analyses and feature extractions often suffer low sensitivity to characteristics difficulty in effectively identifying faults. On the other hand, research via deep learning data-driven approaches typically faces issues such as incomplete training datasets insufficient exploration of correlation...

ABSTRACT A simple and fast extraction termed vortex-assisted liquid–liquid microrextraction coupled with molecular fluorescence spectroscopy has been developed used for the detection of three sulfonamides (sulfadiazine sodium, sulfamethoxazole, sulfaguanidine) in meat samples. In method, 400 µL nonanoic acid was as extractant directly injected into 10 mL centrifuge tube containing a derivative, which derived o-phthaladehyde. And solvent dispersed water phase under mechanical force...