Power Transformer Fault Prediction using Naive Bayes and Decision tree based on Dissolved Gas Analysis

ENP Engineering Science Journal

article

Yassine Mahamdi¹  AhmedBoubakeur¹  Abdelouahab Mekhaldi¹  Youcef Benmahamed¹ 

[1] Ecole Nationale Polytechnique

关键词: Decision Tree;    Naive Bayes;    DGA;    Input vectors;    Power transformer faults;    Accuracy rate;   

DOI  :  10.53907/enpesj.v2i1.63

学科分类：社会科学、人文和艺术（综合）

来源: Ecole Nationale Polytechnique

【 摘 要 】

Power transformers are the basic elements of the power grid, which is directly related to the reliability of theelectrical system. Many techniques were used to prevent power transformer failures, but the Dissolved Gas Analysis(DGA) remains the most effective one. Based on the DGA technique, this paper describes the use of two of the mosteffective machine learning algorithms: Naive Bayes and Decision Tree for the identification of power transformer’sfaults. In our investigation, 9 different input vectors have been developed from widely known DGA techniques. 481samples have been used and 6 types of faults have been considered. The evaluation result of the implementation of theproposed methods shows an effectiveness of 86.25% in power transformer’s fault recognition.

【 授权许可】

CC BY-NC-SA