Fault prediction of smart meter based on spatio-temporal convolution neural network

The faults of smart meters are sudden, complex and multifaceted. A fault prediction method based on spatio-temporal convolutional neural network(ST-CNN) is proposed. Firstly, the sliding window is used to integrate the time information into the characteristic variables, and the input matrix with spa...

Full description

Saved in:
Bibliographic Details
Main Authors: Gao Wenjun, Xue Binbin, Pang Zhenjiang
Format: Article
Language:zho
Published: National Computer System Engineering Research Institute of China 2022-03-01
Series:Dianzi Jishu Yingyong
Subjects:
Online Access:http://www.chinaaet.com/article/3000147054
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849420423495680000
author Gao Wenjun
Xue Binbin
Pang Zhenjiang
author_facet Gao Wenjun
Xue Binbin
Pang Zhenjiang
author_sort Gao Wenjun
collection DOAJ
description The faults of smart meters are sudden, complex and multifaceted. A fault prediction method based on spatio-temporal convolutional neural network(ST-CNN) is proposed. Firstly, the sliding window is used to integrate the time information into the characteristic variables, and the input matrix with space-time characteristics is constructed. Then, combined with CNN, the fault prediction model of smart meter is established, and the model parameters are optimized by adaptive momentum estimation (Adam) algorithm. Finally, the actual field data are used to simulate the fault prediction model of smart meter based on ST-CNN. The results show that this method has high prediction accuracy and strong generalization ability.
format Article
id doaj-art-32d4310b40ac481dbc6aadd7f6bd0c4a
institution Kabale University
issn 0258-7998
language zho
publishDate 2022-03-01
publisher National Computer System Engineering Research Institute of China
record_format Article
series Dianzi Jishu Yingyong
spelling doaj-art-32d4310b40ac481dbc6aadd7f6bd0c4a2025-08-20T03:31:45ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982022-03-01483596310.16157/j.issn.0258-7998.2122893000147054Fault prediction of smart meter based on spatio-temporal convolution neural networkGao Wenjun0Xue Binbin1Pang Zhenjiang2Beijing Zhixin Microelectronics Technology Co.,Ltd.,Beijing 102299,ChinaBeijing Zhixin Microelectronics Technology Co.,Ltd.,Beijing 102299,ChinaBeijing Zhixin Microelectronics Technology Co.,Ltd.,Beijing 102299,ChinaThe faults of smart meters are sudden, complex and multifaceted. A fault prediction method based on spatio-temporal convolutional neural network(ST-CNN) is proposed. Firstly, the sliding window is used to integrate the time information into the characteristic variables, and the input matrix with space-time characteristics is constructed. Then, combined with CNN, the fault prediction model of smart meter is established, and the model parameters are optimized by adaptive momentum estimation (Adam) algorithm. Finally, the actual field data are used to simulate the fault prediction model of smart meter based on ST-CNN. The results show that this method has high prediction accuracy and strong generalization ability.http://www.chinaaet.com/article/3000147054smart meterfault predictioncnnspatio-temporal
spellingShingle Gao Wenjun
Xue Binbin
Pang Zhenjiang
Fault prediction of smart meter based on spatio-temporal convolution neural network
Dianzi Jishu Yingyong
smart meter
fault prediction
cnn
spatio-temporal
title Fault prediction of smart meter based on spatio-temporal convolution neural network
title_full Fault prediction of smart meter based on spatio-temporal convolution neural network
title_fullStr Fault prediction of smart meter based on spatio-temporal convolution neural network
title_full_unstemmed Fault prediction of smart meter based on spatio-temporal convolution neural network
title_short Fault prediction of smart meter based on spatio-temporal convolution neural network
title_sort fault prediction of smart meter based on spatio temporal convolution neural network
topic smart meter
fault prediction
cnn
spatio-temporal
url http://www.chinaaet.com/article/3000147054
work_keys_str_mv AT gaowenjun faultpredictionofsmartmeterbasedonspatiotemporalconvolutionneuralnetwork
AT xuebinbin faultpredictionofsmartmeterbasedonspatiotemporalconvolutionneuralnetwork
AT pangzhenjiang faultpredictionofsmartmeterbasedonspatiotemporalconvolutionneuralnetwork