•  
  •  
 

Keywords

matching of homologous recording channel of protection device; text matching; feature enhancement; cosine similarity

Abstract

Relay protection device is one of the important equipment for collecting fault recording data. Comparison and analysis of homologous recording data can realize fault diagnosis, but due to the lack of standardization for the naming format of the recording channel, it is difficult to match the homologous recording channels. In this paper, a matching method for homologous recording channels of protection devices based on feature enhancement is proposed. Firstly, the recording channel names are feature-enhanced by means of synonym replacement, text expansion, and regular expression algorithms. Then, the Pkuseg word segmentation tool is used to segment the recording channel names, and a customized stop word list is utilized to remove the stop words in the recording channel names. Finally, the term frequency‑inverse document frequency (TF-IDF) method is used to process the recording channel names into the form of digital vectors, and the cosine similarity algorithm is used to calculate the similarity between the recording channel names. The homologous recording channels are judged according to their similarity. The example results show that the proposed method can fully explore the key information of the recording channel names and improve the accuracy of the matching of homologous recording channels.

DOI

10.19781/j.issn.1673-9140.2024.06.006

First Page

53

Last Page

59

Download

Share

COinS