2022 IEEE 3rd China International Youth Conference on Electrical Engineering (CIYCEE 2022)

Aiming at the problems that there are many alarm signals of secondary equipment in smart substation, and misjudgment of fault equipment because the unbalanced number of fault samples may lead to insufficient learning of neural network, a fault location method for secondary equipment in smart substation based on Transformer is proposed. Firstly, an alarm signal set is formed by using the alarm signal when secondary equipment fails. Secondly, using Transformer network, fault location model of secondary equipment deep neural network is established, and the process of secondary equipment fault location is given. Finally, taking a typical 220kV line interval as an example, the validity and accuracy of secondary equipment fault location model based on Transformer are verified. Compared with fault location models based on recurrent neural network and long short-term memory, the method proposed in this paper can more quickly and accurately locate main secondary equipment in smart substation.

alarm signal; fault location; secondary equipment; smart substation; Transformer