Deep Learning Approach for Vibration Signals Applications

This study discusses convolutional neural networks (CNNs) for vibration signals analysis, including applications in machining surface roughness estimation, bearing faults diagnosis, and tool wear detection. The one-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are applied for regression...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Han-Yun, Lee, Ching-Hung
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8201341/
https://www.ncbi.nlm.nih.gov/pubmed/34200400
http://dx.doi.org/10.3390/s21113929
_version_ 1783707796676542464
author Chen, Han-Yun
Lee, Ching-Hung
author_facet Chen, Han-Yun
Lee, Ching-Hung
author_sort Chen, Han-Yun
collection PubMed
description This study discusses convolutional neural networks (CNNs) for vibration signals analysis, including applications in machining surface roughness estimation, bearing faults diagnosis, and tool wear detection. The one-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are applied for regression and classification applications using different types of inputs, e.g., raw signals, and time-frequency spectra images by short time Fourier transform. In the application of regression and the estimation of machining surface roughness, the 1DCNN is utilized and the corresponding CNN structure (hyper parameters) optimization is proposed by using uniform experimental design (UED), neural network, multiple regression, and particle swarm optimization. It demonstrates the effectiveness of the proposed approach to obtain a structure with better performance. In applications of classification, bearing faults and tool wear classification are carried out by vibration signals analysis and CNN. Finally, the experimental results are shown to demonstrate the effectiveness and performance of our approach.
format Online
Article
Text
id pubmed-8201341
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82013412021-06-15 Deep Learning Approach for Vibration Signals Applications Chen, Han-Yun Lee, Ching-Hung Sensors (Basel) Article This study discusses convolutional neural networks (CNNs) for vibration signals analysis, including applications in machining surface roughness estimation, bearing faults diagnosis, and tool wear detection. The one-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are applied for regression and classification applications using different types of inputs, e.g., raw signals, and time-frequency spectra images by short time Fourier transform. In the application of regression and the estimation of machining surface roughness, the 1DCNN is utilized and the corresponding CNN structure (hyper parameters) optimization is proposed by using uniform experimental design (UED), neural network, multiple regression, and particle swarm optimization. It demonstrates the effectiveness of the proposed approach to obtain a structure with better performance. In applications of classification, bearing faults and tool wear classification are carried out by vibration signals analysis and CNN. Finally, the experimental results are shown to demonstrate the effectiveness and performance of our approach. MDPI 2021-06-07 /pmc/articles/PMC8201341/ /pubmed/34200400 http://dx.doi.org/10.3390/s21113929 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Han-Yun
Lee, Ching-Hung
Deep Learning Approach for Vibration Signals Applications
title Deep Learning Approach for Vibration Signals Applications
title_full Deep Learning Approach for Vibration Signals Applications
title_fullStr Deep Learning Approach for Vibration Signals Applications
title_full_unstemmed Deep Learning Approach for Vibration Signals Applications
title_short Deep Learning Approach for Vibration Signals Applications
title_sort deep learning approach for vibration signals applications
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8201341/
https://www.ncbi.nlm.nih.gov/pubmed/34200400
http://dx.doi.org/10.3390/s21113929
work_keys_str_mv AT chenhanyun deeplearningapproachforvibrationsignalsapplications
AT leechinghung deeplearningapproachforvibrationsignalsapplications