Denoising autoencoder network framework.

<div><p>This study addresses the challenge of low recognition precision in single fault signal isolation for induction motors by proposing a novel fault diagnosis strategy that integrates multi-source information and an enhanced Convolutional Neural Network (CNN). This approach aims to m...

Full description

Saved in:

Bibliographic Details
Main Author:	Likang Bo (22110639) (author)
Other Authors:	Meng Li (79487) (author), Hua Tan (424523) (author)
Published:	2025
Subjects:	Biochemistry Biotechnology Infectious Diseases Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified results highlight highlights proposed method achieves method &# 8217 low recognition precision improve signal quality empirical results demonstrate data layer using average diagnostic accuracy source homogeneous data source fusion techniques stator current signals effectively integrating information source information effectively utilize complementary information xlink "> study addresses robust tool nonlinear dynamics multiple sources induction motors fused signals feature extraction feature datasets fault characteristics enhanced cnn disparate sources dimensional images cnn ). approach aims 2400 r 1800 r
Tags:	Add Tag No Tags, Be the first to tag this record!

Denoising autoencoder network framework.

Similar Items