Please use this identifier to cite or link to this item:
Type: Artigo
Title: Uncertainty quantification in deep convolutional neural network diagnostics of journal bearings with ovalization fault
Author: Alves, Diogo Stuani
Daniel, Gregory Bregion
Castro, Helio Fiori de
Machado, Tiago Henrique
Cavalca, Katia Lucchesi
Gecgel, Ozhan
Dias, João Paulo
Ekwaro-Osire, Stephen
Abstract: Bearings play a crucial role in machine longevity and is, at the same time, one of the most critical sources of failure in rotor dynamics. Particularly for journal bearings, it is not completely understood how specific damages may influence the response of the rotating system. Consequently, the identification of hydrodynamic bearing faults is challenging. Most of the literature relies on large amounts of training data collections from physical experiments or from the field, which are high in cost. This paper offers a deep learning approach to identify ovalization faults aiming to develop condition monitoring model-based strategies applied to hydrodynamic journal bearings. Therefore, a numerical model was developed to simulate the ovalization fault conditions in order to build training datasets. Afterwards, a deep convolutional neural network algorithm was trained with the generated datasets and used to predict the faults conditions. Finally, the identification performance was evaluated statistically regarding the true-positive identification by both probability density function and subjective logic. The classification accuracy showed promising results for training the machine learning algorithms with simulated data
Subject: Redes neurais (Computação)
Country: Reino Unido
Editor: Elsevier
Rights: Fechado
Identifier DOI: 10.1016/j.mechmachtheory.2020.103835
Date Issue: 2020
Appears in Collections:FEM - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-85079564027.pdf3.17 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.