Multi-channel Avionics Module Fault Classification Based on Inception-CBAM Network

In today's highly integrated and automated aviation field, the stable operation of avionics systems is the foundation for maintaining flight safety and efficient operations. Because of the shortcomings in research on fault classification of avionics modules, this study proposes an Inception-CBA...

Full description

Saved in:

Bibliographic Details
Published in:	2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) pp. 153 - 156
Main Authors:	Yu, Lubin, Peng, YiXi, Han, Xingjian, Liang, Shuqi, Yang, Peiliang, Liu, Junbin, He, Shilie
Format:	Conference Proceeding
Language:	English
Published:	IEEE 31-05-2024
Subjects:	Aerospace electronics Attention mechanism Attention mechanisms Avionics module Convolutional neural network Data models Fault classification Fault diagnosis Feature extraction Prevention and mitigation Systematics
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	In today's highly integrated and automated aviation field, the stable operation of avionics systems is the foundation for maintaining flight safety and efficient operations. Because of the shortcomings in research on fault classification of avionics modules, this study proposes an Inception-CBAM network model, aiming to improve the accuracy and efficiency of fault diagnosis. This model combines the powerful multi-scale feature extraction capability of the Inception network with the attention mechanism of the CBAM module, which greatly enhances the ability to identify complex fault patterns. Experimental verification shows that the model can effectively classify various faults, enhance the scientificity and systematicness of diagnosis, and contribute important technical support to the formulation of aviation safety maintenance and fault prevention strategies.
DOI:	10.1109/ICECAI62591.2024.10675049