Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network

In the smart grid, precise monitoring of the operational status of critical equipment for transmission, distribution and power supply is essential for effective online maintenance. Faced with the inefficiencies of manual recording and inspection, as well as the challenges associated with the complex...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiheng KONG, Chong TAN, Peiyao TANG, Chengbo HU, Min ZHENG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2024-08-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310020
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228472537939968
author Zhiheng KONG
Chong TAN
Peiyao TANG
Chengbo HU
Min ZHENG
author_facet Zhiheng KONG
Chong TAN
Peiyao TANG
Chengbo HU
Min ZHENG
author_sort Zhiheng KONG
collection DOAJ
description In the smart grid, precise monitoring of the operational status of critical equipment for transmission, distribution and power supply is essential for effective online maintenance. Faced with the inefficiencies of manual recording and inspection, as well as the challenges associated with the complex installation, high cost and lengthy periods required for digital upgrades of monitoring devices, a novel approach that integrates image capture devices with image processing technology has been developed. This approach, leveraging the allocation of computational resources for task distribution, introduces a Light-Resnet-based numerical recognition algorithm, which enhances network training through the optimization of the D-Add loss function, enabling remote reading of electrical equipment monitoring data. Experiments have demonstrated that Light-Resnet achieves a rigorous accuracy rate of 98.8% on the MNIST dataset with only 6090 parameters. When combined with edge computing collaboration mechanisms, it resulted in a 20.73% reduction in power consumption on the terminal side. The proposed algorithm not only proves its adaptability and efficiency in resource-constrained environments but also significantly improves the network's accuracy with design of the D-Add loss function.
format Article
id doaj-art-5772fcb8fe31490695c1372d67f5b07a
institution OA Journals
issn 1004-9649
language zho
publishDate 2024-08-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-5772fcb8fe31490695c1372d67f5b07a2025-08-20T02:04:31ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492024-08-0157820621310.11930/j.issn.1004-9649.202310020zgdl-57-03-kongzhihengNumerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural NetworkZhiheng KONG0Chong TAN1Peiyao TANG2Chengbo HU3Min ZHENG4Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaState Grid Jiangsu Electric Power Company Ltd. Research Institute, Nanjing 211103, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaIn the smart grid, precise monitoring of the operational status of critical equipment for transmission, distribution and power supply is essential for effective online maintenance. Faced with the inefficiencies of manual recording and inspection, as well as the challenges associated with the complex installation, high cost and lengthy periods required for digital upgrades of monitoring devices, a novel approach that integrates image capture devices with image processing technology has been developed. This approach, leveraging the allocation of computational resources for task distribution, introduces a Light-Resnet-based numerical recognition algorithm, which enhances network training through the optimization of the D-Add loss function, enabling remote reading of electrical equipment monitoring data. Experiments have demonstrated that Light-Resnet achieves a rigorous accuracy rate of 98.8% on the MNIST dataset with only 6090 parameters. When combined with edge computing collaboration mechanisms, it resulted in a 20.73% reduction in power consumption on the terminal side. The proposed algorithm not only proves its adaptability and efficiency in resource-constrained environments but also significantly improves the network's accuracy with design of the D-Add loss function.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310020light-resnetd-addedge-end collaboration mechanismnumerical recognitionsmart grid
spellingShingle Zhiheng KONG
Chong TAN
Peiyao TANG
Chengbo HU
Min ZHENG
Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network
Zhongguo dianli
light-resnet
d-add
edge-end collaboration mechanism
numerical recognition
smart grid
title Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network
title_full Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network
title_fullStr Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network
title_full_unstemmed Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network
title_short Numerical Recognition Algorithm for Power Equipment Monitoring Based on Light-Resnet Convolutional Neural Network
title_sort numerical recognition algorithm for power equipment monitoring based on light resnet convolutional neural network
topic light-resnet
d-add
edge-end collaboration mechanism
numerical recognition
smart grid
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310020
work_keys_str_mv AT zhihengkong numericalrecognitionalgorithmforpowerequipmentmonitoringbasedonlightresnetconvolutionalneuralnetwork
AT chongtan numericalrecognitionalgorithmforpowerequipmentmonitoringbasedonlightresnetconvolutionalneuralnetwork
AT peiyaotang numericalrecognitionalgorithmforpowerequipmentmonitoringbasedonlightresnetconvolutionalneuralnetwork
AT chengbohu numericalrecognitionalgorithmforpowerequipmentmonitoringbasedonlightresnetconvolutionalneuralnetwork
AT minzheng numericalrecognitionalgorithmforpowerequipmentmonitoringbasedonlightresnetconvolutionalneuralnetwork