Compressive Sampling and Feature Ranking Framework for Bearing Fault Classification With Vibration Signals

Hosameldin Ahmed,Asoke K Nandi

doi:10.1109/access.2018.2865116

Hosameldin Ahmed, Asoke K Nandi

Open Access

https://doi.org/10.1109/access.2018.2865116

Copy DOI

Abstract

Failures of rolling element bearings are amongst the main causes of machines breakdowns. To prevent such breakdowns, bearing health monitoring is performed by collecting data from rotating machines, extracting features from the collected data, and applying a classifier to classify faults. To avoid the burden of much storage requirements and processing time of a tremendously large amount of vibration data, the present paper proposes a combined compressive sampling (CS)-based on multiple measurement vector (MMV) and feature ranking framework to learn optimally fewer features from a large amount of vibration data from which bearing health conditions can be classified. The CS-based on the MMV model is the first step in this framework and provides compressively sampled signals based on compressed sampling rates. In the second step, the search for the most important features of these compressively sampled signals is performed using the feature ranking and selection techniques. For that purpose, we have investigated the following: 1) two compressible representations of vibration signals that can be used within CS framework, namely, fast Fourier transform-based coefficients and thresholded Wavelet transform-based coefficients and 2) several feature ranking and selection techniques, namely, three similarity-based techniques, fisher score, Laplacian score, Relief-F; one correlation-based technique, Pearson correlation coefficients; and one independence test technique, Chi-Square (Chi-2) to select fewer features that can sufficiently represent the original vibration signals. These selected features, in combination with three of the popular classifiers–multinomial logistic regression classifier, artificial neural networks, and support vector machines, have been evaluated for the classification of bearing faults. Results show that the proposed framework achieves high classification accuracies with a limited amount of data using various combinations of methods, which outperform recently published results.

Highlights

Rotating machines are at the core of most engineering process in industry and are used to accomplish numerous tasks
To apply our proposed framework in this case study, fifty percent of the vibration data is randomly selected for training and the other 50% are used for testing the performance
For further verification of the efficiency of the proposed framework, complete comparison results of the classification accuracy using the different combinations based on the proposed framework compared with some recently published results using the same vibration dataset, for instance in [27] results reported for three methods, one method uses all the original vibration data from which entropic features are extracted, and the other two uses compressed measurements to recover the original vibration signals and from the recovered signals entropic features are extracted

Summary

Introduction

Rotating machines are at the core of most engineering process in industry and are used to accomplish numerous tasks. Unexpected machine failures or breakdowns will affect production plans, product quality, and production costs. Rolling element bearings are critical components in rotating machine and their failures are amongst the main causes of machine breakdowns. Coolant temperatures, line currents, and voltages are among the most quantities measured and used for rotating machine Condition Monitoring (CM) [1]. Of these measurements, bearing vibration signals provide various features that make it one of the most widely used techniques for fault diagnosis [2]

Methods

Results

Conclusion