TY - GEN
T1 - Intelligent Fault Detection via Dilated Convolutional Neural Networks
AU - Khan, Mohammad Azam
AU - Kim, Yong Hwa
AU - Choo, Jaegul
N1 - Funding Information:
Research reported in this publication was partially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (No. NRF-2016R1C1B2015924). Any opinions, findings, and conclusions or recommendations expressed in this article are those of the authors and do not necessarily reflect the views of the funding agencies.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/5/25
Y1 - 2018/5/25
N2 - 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.
AB - 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.
KW - Convolutional Neural Networks
KW - Deep Neural Networks
KW - Dilated Convolution
KW - Domain Adaptation
KW - Intelligent Asset Management
UR - http://www.scopus.com/inward/record.url?scp=85048516317&partnerID=8YFLogxK
U2 - 10.1109/BigComp.2018.00137
DO - 10.1109/BigComp.2018.00137
M3 - Conference contribution
AN - SCOPUS:85048516317
T3 - Proceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
SP - 729
EP - 731
BT - Proceedings - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Big Data and Smart Computing, BigComp 2018
Y2 - 15 January 2018 through 18 January 2018
ER -