Data Mining Practical Machine Learning Tools and Techniques

Artificial intelligence for fault diagnosis of rotating machinery: A review

Applications of machine learning to machine fault diagnosis: A review and roadmap

Wavelets for fault diagnosis of rotary machines: A review with applications

Intelligent fault diagnosis techniques have replaced time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning models can improve the accuracy of intelligent fault diagnosis with the help of their multilayer nonlinear mapping ability. This paper proposes a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in the first convolutional layer for extracting features and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform the state-of-the-art DNN model which is based on frequency features under different working load and noisy environment conditions.

A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals

Effect of dynamic misalignment on the vibration response, trajectory followed and defect-depth achieved by the rolling-elements in a double-row spherical rolling-element bearing

/pdf/the-effect-of-ball-waviness-on-nonlinear-vibration-2zzjseknqo.pdf

The Effect of Ball Waviness on Nonlinear Vibration Associated with Rolling Element Bearings

In the present work, the vibration response of the porous functionally graded piezoelectric plates with electro-thermal loading using finite element formulations has been studied. A sigmoid law is ...

Vibration response analysis of sigmoidal functionally graded piezoelectric (FGP) porous plate under thermo-electric environment

In the present work, vibrational characteristics of a single walled BN nanotube (SWBNNT) is explored considering point defects (single atom vacancies and di-vacancies) to use SWBNNTs as nanomechanical mass sensors. Resonant frequency based analysis of SWBNNT with different types of point defect is performed using an atomistic finite element model based on molecular structural mechanics. The cantilevered configuration of zigzag (14,0) form of SWBNNT with different point defects is modeled considering it as a space frame structure with three dimensional elements and point masses, such that the proximity of the model to the actual atomic structure of nanotube is significantly retained. The finite element simulation approach is used to analyze the effect of point defects like single atom vacancies (VB – boron vacancy and VN – nitrogen vacancy) and divacancies (VBN). The present approach is validated by comparing the obtained simulation results for resonant frequency variation against attached mass at the tip of the cantilevered SWBNNTs, with continuum mechanics based analytical results for defect-free SWBNNT and are found in good agreement. An increase in resonant frequencies observed, when the point defects (VB, VN and VBN) move from fixed-end to the free end of the cantilevered configuration of the SWBNNTs. Also, the resonant frequency shift due to different point defects is analyzed against the attached mass at the free end, for the different positions of the point defect along the length of the nanotube and results indicate that the mass sensitivity limit of 10 −25  kg can be obtained. Using present atomistic finite element model based simulation approach, different atomic structures, different types of point defect as well as boundary conditions can be simulated effectually. The present atomistic finite element model based resonant frequency analysis of defective SWBNNTs is useful to develop the algorithm for the detection of the added mass, identification of the type of point defect and its position along the length of the nanotube.

Vibrational characteristics of defective single walled BN nanotube based nanomechanical mass sensors: single atom vacancies and divacancies

Static and free vibration response analysis of a functionally graded piezoelectric material plate under thermal, electric, and mechanical loads is done in this study. The displacement field is acqu...

S. P. Harsha

Papers

Effect of dynamic misalignment on the vibration response, trajectory followed and defect-depth achieved by the rolling-elements in a double-row spherical rolling-element bearing

The Effect of Ball Waviness on Nonlinear Vibration Associated with Rolling Element Bearings

Vibration response analysis of sigmoidal functionally graded piezoelectric (FGP) porous plate under thermo-electric environment

Vibrational characteristics of defective single walled BN nanotube based nanomechanical mass sensors: single atom vacancies and divacancies

Response analysis of hybrid functionally graded material plate subjected to thermo-electro-mechanical loading: