One-Dimensional Residual Convolutional Autoencoder Based Feature Learning for Gearbox Fault Diagnosis

Vibration signals are generally utilized for machinery fault diagnosis to perform timely maintenance and then reduce losses. Thus, the feature extraction on one-dimensional vibration signals often determines accuracy of those fault diagnosis models. These typical deep neural networks (DNNs), e.g., c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on industrial informatics Jg. 16; H. 10; S. 6347 - 6358
Hauptverfasser: Yu, Jianbo, Zhou, Xingkang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.10.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial neural networks
Belief networks
Convolution
Convolutional autoencoder (CAE)
Decoding
Deconvolution
Fault diagnosis
Feature extraction
feature learning
gearbox fault diagnosis
Gearboxes
Kernel
Machine learning
Model accuracy
Neural networks
Noise reduction
residual learning
Termites
Trains
Vibration
Vibrations
ISSN:1551-3203, 1941-0050
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Vibration signals are generally utilized for machinery fault diagnosis to perform timely maintenance and then reduce losses. Thus, the feature extraction on one-dimensional vibration signals often determines accuracy of those fault diagnosis models. These typical deep neural networks (DNNs), e.g., convolutional neural networks (CNNs), perform well in feature learning and have been applied in machine fault diagnosis. However, the supervised learning of CNN often requires a large amount of labeled images and thus limits its wide applications. In this article, a new DNN, one-dimensional residual convolutional autoencoder (1-DRCAE), is proposed for learning features from vibration signals directly in an unsupervised-learning way. First, 1-D convolutional autoencoder is proposed in 1-DRCAE for feature extraction. Second, a deconvolution operation is developed as decoder of 1-DRCAE to reconstruct the filtered signals. Third, residual learning is employed in 1-DRCAE to perform feature learning on 1-D vibration signals. The results show that 1-DRCAE has good signal denoising and feature extraction performance on vibration signals. It performs better on feature extraction than the typical DNNs, e.g., deep belief network, stacked autoencoders, and 1-D CNN.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2020.2966326