Identification of Power Transformer Winding Mechanical Fault Types Based on Online IFRA by Support Vector Machine

Zhongyong Zhao,Yingang Gui,Chao Tang,Chenguo Yao,Qu Zhou,Lingna Xu

doi:10.3390/en10122022

Abstract

A transformer is the most valuable and expensive property for power utility, thus ensuring its reliable operation is a major task for both operators and researchers. Online impulse frequency response analysis has proven to be a promising technique for detecting transformer internal winding mechanical deformation faults when a power transformer is in service. However, as so far, there is still no reliable standard code for frequency response signature interpretation and quantification. This paper tries to utilize a machine learning method, namely the support vector machine, to identify and classify the winding mechanical fault types, based on online impulse frequency response analysis. Actual transformer fault data from a specially manufactured model transformer are collected and analyzed. Two feature vectors are proposed and the diagnostic results are predicted. The diagnostic results indicate the satisfied classifying accuracy by the proposed method.

Highlights

The power transformer is regarded as one of the most valuable facilities in power substations; it is significant to ensure its stable, reliable and safe operation [1]
With a view to the current status of online impulse frequency response analysis (IFRA) identification, this paper proposes the support vector machine (SVM) algorithm to classify the transformer winding mechanical fault types, for the purpose of achieving the actual application of the online IFRA method
Is used for identification of transformer mechanical fault types, wherein the model of fault the SVM is used for identification of transformer mechanical fault types, wherein the model of fault identification is built by training the the sample data

Summary

Introduction

The power transformer is regarded as one of the most valuable facilities in power substations; it is significant to ensure its stable, reliable and safe operation [1]. The installation time of most power transformers worldwide dates back to the 1980s and they are reaching their deadline of designed life cycle [2,3]. It is reported in many studies that the failure rate of power transformers has recently increased globally. Namely winding deformation (such as tilting, forced bulking, free buckling, hoop tension, telescoping, etc.), are difficult to detect at an early stage because they have limited impact on the normal operation of power transformers [4]. It is tremendously necessary to timely detect and diagnose the winding mechanical deformation faults, especially with the online technique

Methods

Results

Conclusion