Research of transformer fault diagnosis based on Bayesian network classifiers

As one of the most important electric equipment for reliable power supply, the secure operation of power transformer must be guaranteed. Three-ratio method based on the Dissolved Gases Analysis (DGA) is most widely used for transformer fault diagnosis currently. Its advantage is simple and easy to use, but its encoding is incomplete and the faults classification zone is over absolute. This paper combines rough sets and Bayesian Network. Rough sets is used to get useful characters, simplify data sets, obtain simplification rules and the minimum property sets; Bayesian Network is used to analyze the faults caused by uncertain elements in complex system. The fault diagnostic model is built by Bayesian Network Tool (BNT) in MATLAB, and the simulation result shows the validity of this method.

Download Full-text

A Transformer Fault Diagnosis Method Based on Bayesian Network

Journal of Physics Conference Series ◽

10.1088/1742-6596/1213/5/052002 ◽

2019 ◽

Vol 1213 ◽

pp. 052002

Author(s):

Zhang Zhe-wen ◽

Wang Yong ◽

Ying Ding ◽

Tian lei ◽

Zhou Ying-jian

Keyword(s):

Fault Diagnosis ◽

Bayesian Network ◽

Diagnosis Method ◽

Transformer Fault

Download Full-text

Fault Diagnosis by Bayesian Network Classifiers with a Distance Rejection Criterion

Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics ◽

10.5220/0008053304630468 ◽

2019 ◽

Author(s):

M. Atoui ◽

Achraf Cohen ◽

Phillipe Rauffet ◽

Pascal Berruet

Keyword(s):

Fault Diagnosis ◽

Bayesian Network ◽

Bayesian Network Classifiers ◽

Rejection Criterion

Download Full-text

Transformer Fault Diagnosis Study Based on Bayesian Case Library

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.433-435.1826 ◽

2013 ◽

Vol 433-435 ◽

pp. 1826-1831

Author(s):

Qian Peng ◽

Xiao Hu Yan ◽

Fan Liu ◽

Yong Xing Cao ◽

Hai Long Zhang

Keyword(s):

Fault Diagnosis ◽

Bayesian Network ◽

Diagnostic Method ◽

Case Library ◽

Numerical Example ◽

Standard Guideline ◽

Trained Classifier ◽

Bayesian Network Classifier ◽

Fault Mode ◽

Transformer Fault

The transformer fault diagnostic method based on Bayesian case library is proposed in the paper. Firstly, a transformer fault case library is established by collecting standard guideline and expert experience. Secondly, by standardizing the states and fault modes in the case library, the method takes the states as inputs and the fault modes as outputs, which are used to train a naive Bayesian network classifier. When it is necessary for a fault diagnosis, the user is expected to input the fault states in order to finalize the correct fault mode with the help of the well-trained classifier. On this basis, and with the details of the fault mode, the method could help to get the fault diagnosis results of the case. Finally, the feasibility and effectiveness of this developed method is illustrated by a numerical example of transformer fault diagnosis on site.

Download Full-text