TY - GEN
T1 - Research of Transformer Protection Based on Joint Deep Learning
AU - Huang, Qiyue
AU - Wang, Yapeng
AU - Im, Sio Kei
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - As the total electricity load and the proportion of renewable energy sources continue to rise in China, the power grid is experiencing an expansion in scale and an increasing complexity in its structure. As the most important equipment in the power system, the operation status of transformers directly affects the safety and stability of the system. Once a malfunction occurs, it will bring serious economic losses and harm. This paper proposes a transformer protection scheme based on joint deep learning method. Firstly, collect signals through the circuit breakers on both sides of the transformer to complete real-time data collection. Then, a gated recurrent neural network is used to achieve short-term and ultra short-term state recognition. In addition, self supervised learning task is added for joint training. Then the transformer fault diagnosis and protection are realized. Finally, using PSCAD software to construct a typical transformer model structure and conduct simulation verification using Jupyter Lab. The results show that the protection scheme has good performance in different sampling period lengths, noise interference, and data loss situations.
AB - As the total electricity load and the proportion of renewable energy sources continue to rise in China, the power grid is experiencing an expansion in scale and an increasing complexity in its structure. As the most important equipment in the power system, the operation status of transformers directly affects the safety and stability of the system. Once a malfunction occurs, it will bring serious economic losses and harm. This paper proposes a transformer protection scheme based on joint deep learning method. Firstly, collect signals through the circuit breakers on both sides of the transformer to complete real-time data collection. Then, a gated recurrent neural network is used to achieve short-term and ultra short-term state recognition. In addition, self supervised learning task is added for joint training. Then the transformer fault diagnosis and protection are realized. Finally, using PSCAD software to construct a typical transformer model structure and conduct simulation verification using Jupyter Lab. The results show that the protection scheme has good performance in different sampling period lengths, noise interference, and data loss situations.
KW - gated recurrent unit
KW - power system
KW - self-supverised learning
KW - transformer protection
UR - http://www.scopus.com/inward/record.url?scp=85170537388&partnerID=8YFLogxK
U2 - 10.1109/AINIT59027.2023.10212577
DO - 10.1109/AINIT59027.2023.10212577
M3 - Conference contribution
AN - SCOPUS:85170537388
T3 - 2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2023
SP - 70
EP - 75
BT - 2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2023
Y2 - 16 June 2023 through 18 June 2023
ER -