Beamforming Applied to Ultrasound Analysis in Detection of Bearing Defects

Abstract

The bearings of rotating machinery often fail, leading to unforeseen downtime of large machines in industrial plants. Therefore, condition monitoring can be a powerful tool to aid in the quick identification of these faults and make it possible to plan maintenance before the fault becomes too drastic, reducing downtime and cost. Predictive maintenance is often based on information gathered from accelerometers. However, these sensors are contact-based, making them less attractive for use in an industrial plant and more prone to breakage. In this paper, condition monitoring based on ultrasound is researched, where non-invasive sensors are used to record the noise originating from different defects of the Machinery Fault Simulator. The acoustic data are recorded using a sparse microphone array in a lab environment. The same array was used to record real spatial noise in a fully operational plant which was later added to the acoustic data containing the different defects with a variety of Signal To Noise ratios. In this paper, we compare the classification results of the noisy acoustic data of only one microphone to the beamformed acoustic data. We do this to investigate how beamforming could improve the classification process in an ultrasound condition-monitoring application in a real industrial plant.

Acoustic-Based Rolling Bearing Fault Diagnosis Using a Co-Prime Circular Microphone Array

“…Cabada et al combined spectral kurtosis (SK) with beamforming to evaluate both the locations and frequencies of bearing failures using a spiral microphone array [ 30 ]. Verellen studied the beamformed acoustic data with a variety of signal-to-noise ratios as a reference for ultrasonic fault detection [ 31 ]. One of the most typical uses for multi-channel acoustic diagnosis is wayside identification, where researchers have invested large efforts to overcome signal distortion due to the Doppler effect and noise interference [ 32 , 33 , 34 , 35 ].…”

HOG-SVM-Based Image Feature Classification Method for Sound Recognition of Power Equipments

“…Qin [21] welded Ensemble Empirical Mode Decomposition (EEMD) and RF for malfunction diagnoses. Verellen et al [22], aiming at the detection of bearing faults in rotating machinery, propose a non-invasive acoustic signalmonitoring system based on a sparse microphone array. Traditional vibration analysis uses accelerometers, which are touch sensors that need to be attached to the component under investigation.…”

Online Frequency Response Analysis of Electric Machinery through an Active Coupling System Based on Power Electronics

“…Variants of Fourier transforms are usually used for vibration and acoustic signals, as presented in [ 2 ]. Verellen et al [ 4 ] presented a non-invasive monitoring system for acoustic signals using a sparse microphone array in order to detect bearing failures in rotating machines. Conventional vibration analysis use accelerometers, which are contact sensors and need to be attached to the part under investigation [ 4 ].…”

“…Verellen et al [ 4 ] presented a non-invasive monitoring system for acoustic signals using a sparse microphone array in order to detect bearing failures in rotating machines. Conventional vibration analysis use accelerometers, which are contact sensors and need to be attached to the part under investigation [ 4 ]. An interesting approach to contactless monitoring of vibration was proposed by Śmieja et al [ 5 ], where image processing is employed.…”