SRMANet: Toward an Interpretable Neural Network with Multi-Attention Mechanism for Gearbox Fault Diagnosis

SRMANet: Toward an Interpretable Neural Network with Multi-Attention Mechanism for Gearbox Fault Diagnosis

Deep neural network (DNN), with the capacity for feature inference and nonlinear mapping, has demonstrated its effectiveness in end-to-end fault diagnosis. However, the intermediate learning process of the DNN architecture is invisible, making it an uninterpretable black-box model. In this paper, a...

Full description

Bibliographic Details
Main Authors: Siyuan Liu, Jinying Huang, Jiancheng Ma, Jia Luo
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Applied Sciences
Subjects:
machine fault diagnosis
universal feature extractor
convolutional neural network
attention fusion
interpretability
planetary gearbox
Online Access:https://www.mdpi.com/2076-3417/12/16/8388

Internet

https://www.mdpi.com/2076-3417/12/16/8388

Similar Items