Article
Version 1
Preserved in Portico This version is not peer-reviewed
Application of Deep Neural Network in Gearbox Compound Fault Diagnosis
Version 1
: Received: 20 April 2023 / Approved: 20 April 2023 / Online: 20 April 2023 (09:58:25 CEST)
A peer-reviewed article of this Preprint also exists.
Zhang, X.; Xu, Q.; Jiang, H.; Li, J. Application of Deep Neural Network in Gearbox Compound Fault Diagnosis. Energies 2023, 16, 4164. Zhang, X.; Xu, Q.; Jiang, H.; Li, J. Application of Deep Neural Network in Gearbox Compound Fault Diagnosis. Energies 2023, 16, 4164.
Abstract
To realize the diagnosis of compound faults in gearboxes at different speeds, an "end-to-end" intelligent diagnosis method based on a deep neural network is proposed, named efficiency channel attention-capsule network (ECA-CN). First, the process uses a deep convolutional neural network to extract fault features from the collected raw vibration signals, then embeds the efficient channel attention module to filter important fault features, then uses the capsule network to vectorize the feature space information, and finally calculates the correlation between different levels of capsules by the dynamic routing algorithm to achieve accurate gearbox compound fault diagnosis. The effectiveness of the proposed ECA-CN fault diagnosis method was verified by the composite fault dataset of the 2009 PHM Challenge gearbox, with an average accuracy of 99.63% and a standard deviation of 0.22%. In the comparison experiments with the traditional fault diagnosis method, the average accuracy of the ECA-CN method was improved by 4.62%, and the standard deviation was reduced by 0.58%. The experimental results show that ECA-CN has a more competitive diagnostic performance.
Keywords
gearbox; compound fault; attention mechanism; capsule network
Subject
Engineering, Safety, Risk, Reliability and Quality
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
