Power grid fault diagnosis method based on temporal convolutional network

Zirui Wang; Ziqi Zhang; Mingxuan Du; Xu Zhang

doi:10.1117/12.3004281

25 September 2023 Power grid fault diagnosis method based on temporal convolutional network

Zirui Wang, Ziqi Zhang, Mingxuan Du, Xu Zhang

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 1278854 (2023) https://doi.org/10.1117/12.3004281
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

With the development trend of digitization and intelligence of power grid dispatching, intelligent fault diagnosis methods are of great significance for timely locating and handling faults. When there is a fault or disturbance in the power grid, a large amount of alarm information will be uploaded to the monitoring alarm window through the monitoring system. The alarm information usually appears on different levels and in chronological order and lacks effective classification and processing. It is difficult to dig out effective information, and it is difficult for operation and maintenance personnel to detect alarms in a short time. The key content of the information cannot make a quick judgment on the fault, thus reducing the efficiency of fault diagnosis. Therefore, this paper proposes a new method based on a temporal convolutional network (TCN). By extracting the unified vectorized representation of the alarm information samples of fault events under different fault conditions, the TCN-based fault category classification is developed. Finally, the model is trained and tested using the samples generated by the TS2000 simulation system. Experimental results show that this method can effectively determine the category of the fault, which can meet the needs of intelligent online diagnosis.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zirui Wang, Ziqi Zhang, Mingxuan Du, and Xu Zhang "Power grid fault diagnosis method based on temporal convolutional network", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 1278854 (25 September 2023); https://doi.org/10.1117/12.3004281

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available