Intelligent fault detection using raw vibration signals via dilated convolutional neural networks

Mohammad Azam Khan, Yong Hwa Kim, Jaegul Choo

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)


Fault detection and diagnosis is critical to improve the reliability and availability in induction motors (IMs). Machine learning and deep learning techniques have been widely used in induction motor fault detection and diagnosis. In this paper, we propose a new deep learning model based on a dilated convolutional neural network (D-CNN) for detecting bearing faults in IMs. The proposed model works directly on raw vibration signals without any hand-crafted feature extraction process. Our model can incorporate global context without losing important local information by stacking dilated convolutions with an increasing width. Numerical results show that the proposed D-CNN is not only capable of classifying normal signals perfectly but also can achieve higher accuracy than conventional techniques under noisy environments.

Original languageEnglish
Pages (from-to)8086-8100
Number of pages15
JournalJournal of Supercomputing
Issue number10
Publication statusPublished - 2020 Oct 1

Bibliographical note

Funding Information:
This research was in part supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (NRF-2017R1C1B1012259) and in part supported by Korea Electric Power Corporation (Grant No. R17XA05-22).

Publisher Copyright:
© 2018, Springer Science+Business Media, LLC, part of Springer Nature.


  • Convolutional neural networks
  • Deep neural networks
  • Dilated convolution
  • Intelligent fault detection
  • Vibration signals

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture


Dive into the research topics of 'Intelligent fault detection using raw vibration signals via dilated convolutional neural networks'. Together they form a unique fingerprint.

Cite this