GIS Partial Discharge Pattern Recognition Based on a Novel Convolutional Neural Networks and Long Short-Term Memory.

Tingliang Liu,Jing Yan,Yanxin Wang,Yiming Zhao,Yifan Xu

doi:10.3390/e23060774

Abstract

Distinguishing the types of partial discharge (PD) caused by different insulation defects in gas-insulated switchgear (GIS) is a great challenge in the power industry, and improving the recognition accuracy of the relevant models is one of the key problems. In this paper, a convolutional neural network and long short-term memory (CNN-LSTM) model is proposed, which can effectively extract and utilize the spatiotemporal characteristics of PD input signals. First, the spatial characteristics of higher-level PD signals can be obtained through the CNN network, but because CNN is a deep feedforward neural network, it does not have the ability to process time-series data. The PD voltage signal is related to the time dimension, so LSTM saves and analyzes the previous voltage signal information, realizes the modeling of the time dependence of the data, and improves the accuracy of the PD signal pattern recognition. Finally, the pattern recognition results based on CNN-LSTM are given and compared with those based on other traditional analysis methods. The results show that the pattern recognition rate of this method is the highest, with an average of 97.9%, and its overall accuracy is better than that of other traditional analysis methods. The CNN-LSTM model provides a reliable reference for GIS PD diagnosis.

Highlights

Gas-insulated switchgear (GIS) is widely used in power systems
It is concluded that the convolutional neural networks (CNN)-long short-term memory (LSTM) model performs well in GIS partial discharge (PD) pattern recognition
The processed four kinds of PD data are inputted into the CNN-LSTM network for training and recognition, and the overall prediction accuracy is taken as the evaluation parameter of the GIS PD pattern recognition ability

Summary

Introduction

Gas-insulated switchgear (GIS) is widely used in power systems. The timely discovery and identification of the partial discharge (PD) caused by different types of insulation defects in GIS is of great significance [1]. It is difficult for the most experienced experts to distinguish certain types of PD signals because they have very similar characteristics. Among many deep learning methods, convolutional neural networks (CNN) have received widespread attention due to their powerful advantages in automatically extracting the spatial features of images, while long short-term memory (LSTM) has been widely used due to its powerful processing capabilities for time series

Methods

Results

Conclusion