Intelligent Fault Detection via Dilated Convolutional Neural Networks

Mohammad Azam Khan, Yong Hwa Kim, Jaegul Choo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

The energy industry is currently going through a rapid change. With the appearance of low-cost IoT sensors and storage devices, it has now become possible to get very detailed data from the electricity grid system to be used for further analysis. The coming of the big data era has made the analysis easier. At the same time, we need to establish a safe transmission and distribution facilities for reliable grid operation. In this work-in-progress paper, we contribute an exploration of deep learning approach for intelligent fault detection system. The method works directly on raw temporal signals without any handcrafted feature extraction process. Our proposed method can not only achieve about 100% classification accuracy on normal signals but also show good domain adaptation capability.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages729-731
Number of pages3
ISBN (Electronic)9781538636497
DOIs
Publication statusPublished - 2018 May 25
Event2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018 - Shanghai, China
Duration: 2018 Jan 152018 Jan 18

Publication series

NameProceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018

Other

Other2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
Country/TerritoryChina
CityShanghai
Period18/1/1518/1/18

Keywords

  • Convolutional Neural Networks
  • Deep Neural Networks
  • Dilated Convolution
  • Domain Adaptation
  • Intelligent Asset Management

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Intelligent Fault Detection via Dilated Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this