Transfer learning based on improved stacked autoencoder for bearing fault diagnosis

Deep transfer learning algorithm is regarded as a promising method to address the issue of rolling bearing fault diagnosis with limited labeled data. Stacked autoencoder (SAE) has been widely employed in deep transfer learning research since it is a semi-supervised algorithm. However, there are stil...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems Vol. 256; p. 109846
Main Authors: Luo, Shuyang, Huang, Xufeng, Wang, Yanzhi, Luo, Rongmin, Zhou, Qi
Format: Journal Article
Language:English
Published: Elsevier B.V 28.11.2022
Subjects:
Convolutional shortcuts
Domain fusion
Fault diagnosis
Stacked autoencoder
Transfer learning
Fault diagnosis
Stacked autoencoder
Convolutional shortcuts
Transfer learning
Domain fusion
ISSN:0950-7051, 1872-7409
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep transfer learning algorithm is regarded as a promising method to address the issue of rolling bearing fault diagnosis with limited labeled data. Stacked autoencoder (SAE) has been widely employed in deep transfer learning research since it is a semi-supervised algorithm. However, there are still some limitations for the transfer learning based on SAE, including the vanishing gradient problem caused by the sigmoid activation function in SAE, and low accuracy under the condition of cross-domain or limited labeled training data. In this work, an improved SAE based on convolutional shortcuts and domain fusion strategy (ISAE-CSDF) is proposed for fault diagnosis of rolling bearing. The sparse term Kullback–Leibler (KL) divergence in the original SAE is replaced with the convolutional shortcuts to prevent vanishing gradient problem and improve the feature extraction ability. The domain fusion strategy can transfer commonly shared feature information from various domains. The feasibility of ISAE-CSDF is validated on two publicly available bearing datasets and a custom-built experiment device. Results show that ISAE-CSDF outperforms the state-of-art methods in the context of different working conditions, cross-domain, and limited labeled data.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2022.109846