Bayesian optimization and channel-fusion-based convolutional autoencoder network for fault diagnosis of rotating machinery

•A novel convolutional network based on Bayesian optimization and channel fusion mechanism is developed.•The proposed method is applied to extract the compressed features and reconstruct the input data.•The channel fusion mechanism is newly designed to merge features of different layers for more sta...

Full description

Saved in:
Bibliographic Details
Published in:Engineering structures Vol. 280; p. 115708
Main Authors: Zou, L., Zhuang, K.J., Zhou, A., Hu, J.
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.04.2023
Subjects:
Bayesian optimization
Channel fusion mechanism
Convolutional network
Fault diagnosis
Hybrid loss function
Fault diagnosis
Hybrid loss function
Convolutional network
Channel fusion mechanism
Bayesian optimization
ISSN:0141-0296, 1873-7323
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A novel convolutional network based on Bayesian optimization and channel fusion mechanism is developed.•The proposed method is applied to extract the compressed features and reconstruct the input data.•The channel fusion mechanism is newly designed to merge features of different layers for more stable feature expression.•A hybrid loss function is creatively defined through summing the error values of mean square error and cross-entropy for model training.•The Bayesian optimization scheme is introduced to optimize the model’s hyper-parameters and obtain a powerful learning ability for fault diagnosis.•A laboratory bearing dataset and an industrial bearing dataset are both used to evaluate the performance of the proposed method on fault diagnosis. Deep learning methods are essential for the application of data driven technologies on fault diagnosis of rotating machinery. However, the generalization and performance of deep learning methods for fault diagnosis are highly dependent on the selection of hyper parameters and the design of network structure. To solve aforementioned challenge in fault diagnosis and obtain a powerful model, a convolutional network based on Bayesian optimization and channel fusion mechanism is newly developed. In the proposed network, a convolutional autoencoder network is firstly applied to extract the compressed features and reconstruct the input data. Then, the channel fusion mechanism is introduced to deduce the error of reconstructed input data. Next, a hybrid loss function is defined through summing mean square error and cross-entropy. Finally, a Bayesian optimization scheme is designed to optimize the hyper parameters of the designed network. The effectiveness of the proposed method is verified by a laboratory bearing dataset and an industrial bearing dataset, respectively. Five classical fault diagnosis methods are also tested as comparison. The experimental results indicate the proposed method can achieve the outstanding performance in fault diagnosis both in accuracy and efficiency.
ISSN:0141-0296
1873-7323
DOI:10.1016/j.engstruct.2023.115708