Cargando…

A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks

Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identifi...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Jingli, Yin, Shuangyan, Chang, Yongqi, Gao, Tianyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7412546/
https://www.ncbi.nlm.nih.gov/pubmed/32660068
http://dx.doi.org/10.3390/s20143837
_version_ 1783568633175212032
author Yang, Jingli
Yin, Shuangyan
Chang, Yongqi
Gao, Tianyu
author_facet Yang, Jingli
Yin, Shuangyan
Chang, Yongqi
Gao, Tianyu
author_sort Yang, Jingli
collection PubMed
description Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identification accuracy in a simple and compact architecture configuration. By taking advantage of the self-normalizing properties of the activation function SeLU, the stability and convergence of the fault diagnosis model are maintained. By introducing [Formula: see text]-dropout mechanism twice to regularize the training process, the overfitting problem is resolved and the generalization capability of the model is further improved. The experimental results on the benchmark dataset show that the proposed method possesses high fault identification accuracy and excellent cross-load fault diagnosis capability.
format Online
Article
Text
id pubmed-7412546
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-74125462020-08-26 A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks Yang, Jingli Yin, Shuangyan Chang, Yongqi Gao, Tianyu Sensors (Basel) Article Aiming at the fault diagnosis issue of rotating machinery, a novel method based on the deep learning theory is presented in this paper. By combining one-dimensional convolutional neural networks (1D-CNN) with self-normalizing neural networks (SNN), the proposed method can achieve high fault identification accuracy in a simple and compact architecture configuration. By taking advantage of the self-normalizing properties of the activation function SeLU, the stability and convergence of the fault diagnosis model are maintained. By introducing [Formula: see text]-dropout mechanism twice to regularize the training process, the overfitting problem is resolved and the generalization capability of the model is further improved. The experimental results on the benchmark dataset show that the proposed method possesses high fault identification accuracy and excellent cross-load fault diagnosis capability. MDPI 2020-07-09 /pmc/articles/PMC7412546/ /pubmed/32660068 http://dx.doi.org/10.3390/s20143837 Text en © 2020 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yang, Jingli
Yin, Shuangyan
Chang, Yongqi
Gao, Tianyu
A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks
title A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks
title_full A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks
title_fullStr A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks
title_full_unstemmed A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks
title_short A Fault Diagnosis Method of Rotating Machinery Based on One-Dimensional, Self-Normalizing Convolutional Neural Networks
title_sort fault diagnosis method of rotating machinery based on one-dimensional, self-normalizing convolutional neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7412546/
https://www.ncbi.nlm.nih.gov/pubmed/32660068
http://dx.doi.org/10.3390/s20143837
work_keys_str_mv AT yangjingli afaultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT yinshuangyan afaultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT changyongqi afaultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT gaotianyu afaultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT yangjingli faultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT yinshuangyan faultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT changyongqi faultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks
AT gaotianyu faultdiagnosismethodofrotatingmachinerybasedononedimensionalselfnormalizingconvolutionalneuralnetworks