Published Papers


Skip Navigation


UOU Logo

Top Menu

Total Search


Home > Research > Research Outcome >Published Papers

Document Contents

Published Papers

Search :

Search

A Novel Hybrid Deep Learning Method for Fault Diagnosis of Rotating Machinery Based on Extended WDCNN and Long Short?Term Memory

Abstract
Deep learning (DL) plays a very important role in the fault diagnosis of rotating machinery. To enhance the self?learning capacity and improve the intelligent diagnosis accuracy of DL for rotating machinery, a novel hybrid deep learning method (NHDLM) based on Extended Deep Convolutional Neural Networks with Wide First?layer Kernels (EWDCNN) and long short?term memory (LSTM) is proposed for complex environments. First, the EWDCNN method is presented by extending the convolution layer of WDCNN, which can further improve automatic feature extraction. The LSTM then changes the geometric architecture of the EWDCNN to produce a novel hybrid method (NHDLM), which further improves the performance for feature classification. Compared with CNN, WDCNN, and EWDCNN, the proposed NHDLM method has the greatest performance and identification accuracy for the fault diagnosis of rotating machinery.

The administrative responsibility of the content.

By cliking the email below, you can send an e-mail to the person in charge.

Last Modified : Apr 9, 2013
  • Office : UOU International
  • Phone : +82-52-220-5957
  • Staff in Charge : Sean Park

Contents Review

Review the content back to the main content of the current page provides links to allow access.


Contact menu

CONNECT WITH UOU

Address

93 Daehak-ro, Nam-gu,
Ulsan (44610), Korea

Tel

Phone: +82-52-220-5952(~5959)

Fax

Fax: +82-52-224-2061

Email

QUICK LINK

Sitemap menu

CONTENTS

Join us and keep up-to-date on what is happenting around University of Ulsan.

Sitemap


Footer menu

CopyRight

Copyright 2012 University of Ulsan, All Rights Reserved.


Review Navigation