Power grid fault classification method of alarm information based on bigru-attention.

Abstract

With the continuous expansion of the power grid, the number of alarm information collected by the dispatching center is also increasing. How to filter out key information from massive alarm information, delete irrelevant data, classify the importance of alarm information, and make preparations for power grid fault diagnosis based on alarm information has become an urgent problem to be solved in online fault diagnosis. Based on this, this paper proposes an importance classification method of alarm information based on bigru attention to screen the data with the strongest correlation with fault, avoid the impact of irrelevant data on fault diagnosis, and meet the needs of intelligence. Firstly, the two-way gated loop (bigru) neural network layer is used to preprocess the alarm information text and extract the features of the deep-seated information; Secondly, the attention mechanism layer is used to assign corresponding weights to the extracted text deep-seated information; Finally, the text feature information of alarm information with different weights is put into the softmax function layer for alarm information text classification. Finally, an actual fault case in an area is tested to verify the effectiveness and practicability of the proposed method.