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

In this paper, the non-linear dynamic analysis of an unbalanced rotor supported by roller bearings has been made. The non-linearity in the rotor bearing system is due to Hertzian contact, unbalanced rotor effect and radial internal clearance. The system can excite bi-periodically by the varying compliance frequency and the rotational frequency. The results show the appearance of instability and chaos in the dynamic response as the speed of the rotor-bearing system is changed. Period doubling and mechanism of intermittency have been observed that lead to chaos. Poincare maps, phase plots, time displacement responses and FFT are used to elucidate and illustrate the diversity of the system behavior.

Nonlinear dynamic analysis of an unbalanced rotor supported by roller bearing

This paper is focused on comparison of effectiveness of artificial intelligence (AI) techniques in fault diagnosis of rolling element bearings. The features for classification are extracted through wavelet packet decomposition using RBIO 5.5 wavelet. The whole classification is done using two features: energy and Kurtosis. The data samples for classification are taken with reference to a healthy bearing, thus, minimizing the errors from the experimental set-up. Four bearing conditions such as bearing with outer race defect, inner race defect, ball defect and combined defect on outer race, inner race and ball have been used in this paper. Localized defects of micron level are induced through laser machining. The effectiveness of three AI techniques viz. ANN, SVM and multinomial logistic regression are compared. The results show that the Logistic Regression technique is the more effective than other two techniques as ANN and SVM.

Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform

Fault diagnosis of rolling element bearing using cyclic autocorrelation and wavelet transform

In this paper, fault diagnosis methodology is proposed for rolling element bearings, which utilizes autocorrelation of raw vibration signals to reduce the dimension of vibration signals with minimal loss of significant frequency content. It is observed that dimension of vibration signal is reduced to 10% with negligible loss of information. After reducing the dimension of vibration signals, coefficients of continuous wavelet transform are calculated using six different base wavelets. The base wavelet that maximizes the energy to Shannon entropy ratio is selected to extract statistical features from wavelet coefficients. Finally, a comparative study is carried out with the calculated statistical features as input to two supervised soft computing techniques like Artificial Neural Network and Support Vector Machine (SVM) for faults classification. The proposed method is applied to the rolling element bearings fault diagnosis and complex Gaussian wavelet is selected based on maximum energy to Shannon entropy ...

Rolling element bearing fault diagnosis using autocorrelation and continuous wavelet transform

Carbon nanotubes (CNTs) have been regarded as ideal reinforcements of high-performance composites with enormous applications. In this paper, nano-structure is modeled as a linearly elastic composite medium, which consists of a homogeneous matrix having hexagonal representative volume elements (RVEs) and homogeneous cylindrical nanotubes with various inclination angles. Effects of inclined carbon nanotubes on mechanical properties are investigated for nano-composites using 3-D hexagonal representative volume element (RVE) with short and straight CNTs. The CNT is modeled as a continuum hollow cylindrical shape elastic material with different angles. The effect of the inclination of the CNT and its parameters is studied. Numerical equations are used to extract the effective material properties for the hexagonal RVE under axial as well as lateral loading conditions. The computational results indicated that elastic modulus of nano-composite is remarkably dependent on the orientation of the dispersed SWNTs. It is observed that the inclination significantly reduces the effective Young’s modulus of elasticity under an axial stretch. When compared with lateral loading case, effective reinforcement is found better in axial loading case. The effective moduli are very sensitive to the inclination and this sensitivity decreases with the increase of the waviness. In the case of short CNTs, increasing trend is observed up to a specific value of waviness index. It is also found from the simulation results that geometry of RVE does not have much significance on stiffness of nano-structures. The results obtained for straight CNTs are consistent with ERM results for hexagonal RVEs, which validate the proposed model results.

S. P. Harsha

Papers

Nonlinear dynamic analysis of an unbalanced rotor supported by roller bearing

Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform

Fault diagnosis of rolling element bearing using cyclic autocorrelation and wavelet transform

Rolling element bearing fault diagnosis using autocorrelation and continuous wavelet transform

Effect of carbon nanotube orientation on the mechanical properties of nanocomposites