Eventos Anais de eventos
COBEM 2023
27th International Congress of Mechanical Engineering
MONITORING OF BALLBEARINGS VIA VIBRATION ANALYSIS FOR PREDICTIVE MAINTENANCE PURPOSES
Submission Author:
Adiel Pessôa , MG
Co-Authors:
Adiel Pessôa, Paulo Cezar Büchner, Geice Paula Villibor, Alexandre Martins Reis, Charles Luís da Silva, Álisson Carlos Souza Rodrigues
Presenter: Geice Paula Villibor
doi://10.26678/ABCM.COBEM2023.COB2023-1851
Abstract
Ball bearings are critical components of machinery and equipment in numerous industries, and their failure can result in significant damage and production downtime. To monitor ball bearing failures, a range of vibration monitoring techniques are employed, encompassing envelope analysis, kurtosis, bi-spectrum, and wavelet analysis. For example, the bi-spectrum is a higher-order spectrum that describes the non-linear interactions between frequency components in the vibration signal, and provides information about the correlation between frequency components. These techniques can identify the specific fault type by detecting and analyzing the vibration signals generated by ball bearing failures. However, detecting and analyzing these signals can be challenging due to weak signals and noise masking vibration patterns. Although current techniques are effective, they have limitations, such as requiring expert analysis, difficulty in detecting early-stage faults, and the inability to differentiate between different fault types. To overcome these limitations, new technologies and methods are being explored, such as machine learning and acoustic emission (AE) monitoring. Machine learning involves training algorithms to automatically detect and classify faults based on vibration signals, while AE monitoring detects the acoustic signals generated by ball bearing failures. Both approaches have shown promising results in early detection and differentiation between different fault types. Therefore, ball bearing failure can cause significant damage and production downtime in various industries, and effective detection and identification of these failures are crucial. Current techniques, such as envelope and wavelet analysis, are effective but have limitations. New technologies and methods, such as machine learning and AE monitoring, are being explored to improve fault detection and classification, providing early detection of faults and differentiation between different fault types, ultimately reducing the impact of ball bearing failures on machines and industries. This paper proposes to present a study of the ball bearing failure through vibration analysis from early-stage to advanced-stage of damage for predictive maintenance purposes, applying the envelope and FFT together with programming to enable the identification of defects in the bearing, especially in the inner race, through a signal acquisition system that can explain the presence of the defect through frequency graphs. Thus obtaining results that show the presence of defects in three different bearings, with gradual defect magnitudes, differentiating these data from an ideal bearing. The next step is to explore the new technologies like machine learning and artificial intelligence.
Keywords
Rail failure, signal analisys, Envelope, kurtosis, bi-spectrum
