Convolutional-Neural-Network-Based Partial Discharge Diagnosis for Power Transformer Using UHF Sensor

The-Duong Do,Yong-Hwa Kim,Yong-Sung Cho,Jong-Ho Sun,Vo-Nguyen Tuyet-Doan

doi:10.1109/access.2020.3038386

Abstract

Given the enormous capital value of power transformers and their integral role in the electricity network, increasing attention has been given to diagnostic and monitoring tools as a safety precaution measure to evaluate the internal condition of transformers. This study overcomes the fault diagnosis problem of power transformers using an ultra high frequency drain valve sensor. A convolutional neural network (CNN) is proposed to classify six types of discharge defects in power transformers. The proposed model utilizes the phase-amplitude response from a phase-resolved partial discharge (PRPD) signal to reduce the input size. The performance of the proposed method is verified through PRPD experiments using artificial cells. The experimental results indicate that the classification performance of the proposed method is significantly better than those of conventional algorithms, such as linear and nonlinear support vector machines and feedforward neural networks, at 18.78%, 10.95%, and 8.76%, respectively. In addition, a comparison with the different representations of the data leads to the observation that the proposed CNN using a PA response provides a higher accuracy than that using sequence data at 1.46%.

Highlights

O VER the past several decades, with the development of the economy and the continuous advancement of society, the global energy industry has witnessed rapid growth, and electric energy demand has become increasingly vigorous
The proposed convolutional neural network (CNN) with the PA response has better classification performance than the CNN method using phase-resolved partial discharge (PRPD) and achieved a classification performance of almost 100%
PROPOSED CNN FOR Partial discharge (PD) DIAGNOSIS we focus on CNN-based PRPD fault diagnosis

Summary

INTRODUCTION

O VER the past several decades, with the development of the economy and the continuous advancement of society, the global energy industry has witnessed rapid growth, and electric energy demand has become increasingly vigorous. To classify the PD types in a power transformer, feature extraction of the signals has been accomplished based on a wavelet analysis, and an improved bagging algorithm with a backpropagation neural network and an SVM were used for the classification task [18]. We utilize the characteristics of CNNs to classify the incipient defects of power transformers using the phase–amplitude (PA) response of the PD signals as the input of the CNNs. The structure of the proposed CNN model in our experiment includes convolutional layers and maxpooling layers with the main task of performing feature extraction of the PRPD signal.

PRPD MEASUREMENT USING UHF SENSOR

PRPD MEASUREMENTS

NOISE MEASUREMENTS

PERFORMANCE EVALUATIONS

Findings

CONCLUSION