Vibration Analysis of Shaft Misalignment Using Machine Learning Approach under Variable Load Conditions

A M Umbrajkaar,R B Dhumale,A Krishnamoorthy

doi:10.1155/2020/1650270

Abstract

The Industry 4.0 revolution is insisting strongly for use of machine learning-based processes and condition monitoring. In this paper, emphasis is given on machine learning-based approach for condition monitoring of shaft misalignment. This work highlights combined approach of artificial neural network and support vector machine for identification and measure of shaft misalignment. The measure of misalignment requires more features to be extracted under variable load conditions. Hence, primary objective is to measure misalignment with a minimum number of extracted features. This is achieved through normalization of vibration signal. An experimental setup is prepared to collect the required vibration signals. The normalized time domain nonstationary signals are given to discrete wavelet transform for features extraction. The extracted features such as detailed coefficient is considered for feature selection viz. Skewness, Kurtosis, Max, Min, Root mean square, and Entropy. The ReliefF algorithm is used to decide best feature on rank basis. The ratio of maximum energy to Shannon entropy is used in wavelet selection. The best feature is used to train machine learning algorithm. The rank-based feature selection has improved classification accuracy of support vector machine. The result obtained with the combined approach are discussed for different misalignment conditions.

Highlights

All production and processing industries have been using rotary machines on a major scale
An accelerometer is placed at the casing of second bearing to sense vibration in all three directions viz. Longitudinal (Vg), Lateral (Vt), and Vertical (Vr). e misalignment is generated artificially in set up to visualize a proportional change in Overall Vibration Level (OVL). e wide range of vibration levels is observed for a different range of misalignment and speed conditions. ese output signals obtained are normalized in the range of 0 to 1. e normalization of the signal maintains distinctive values of extracted features under varying load conditions without loss of information. e normalized signals viz. VgNn, VtNn, and VrNn are obtained from [22]
E average Energy to Shannon Entropy (ESE) is more for DB2 and SYM2. e DB2 wavelet is selected as the suitable mother wavelet as explained earlier. e eighteen statistical features are obtained to analyze information in output signal. e ReliefF algorithm is used to optimize feature selection on rank basis

Summary

Introduction

All production and processing industries have been using rotary machines on a major scale. It is seen that out of many listed causes, misalignment is one of the prominent causes of fault set up. To avoid such faults, continuous monitoring is essential. Vishwakarma et al [1] have discussed different modes of condition monitoring techniques. It emphasizes the importance of both time and frequency domain analysis for nonstationary signals. Tang et al [2] have proposed an adaptive waveform decomposition method of the waveform to extract timefrequency features of nonstationary signals. E feature extraction for vibration signal of rolling bearing is carried out with the Adaptive Waveform Decomposition (AWD) algorithm and local frequency concept. A brief review of a transformer, gas-insulated switchgear, cable, generator, and capacitor are described with the help of big data, Internet of things, and cloud computing techniques. e wavelet gray moment vector approach is claimed as an effective tool in fault diagnosis of rotating machinery [5]. e detailed fault

Methods

Results

Conclusion