EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception

Ice-covered transmission lines seriously affect the stable operation of the power system. Deploying a recognition network for measuring the ice thickness on transmission lines within a deicing robot, and controlling the robot to perform resonant deicing, is an effective solution. In order to solve t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yangyang Jiao, Yu Zhang, Yinke Dou, Liangliang Zhao, Qiang Liu
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/19/8796
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283928568463360
author Yangyang Jiao
Yu Zhang
Yinke Dou
Liangliang Zhao
Qiang Liu
author_facet Yangyang Jiao
Yu Zhang
Yinke Dou
Liangliang Zhao
Qiang Liu
author_sort Yangyang Jiao
collection DOAJ
description Ice-covered transmission lines seriously affect the stable operation of the power system. Deploying a recognition network for measuring the ice thickness on transmission lines within a deicing robot, and controlling the robot to perform resonant deicing, is an effective solution. In order to solve the problem that the existing recognition network is not suitable for an edge device, an ice-thickness recognition network for transmission lines based on efficient dynamic perception (EDPNet) is proposed. Firstly, a lightweight multidimensional recombination convolution (LMRC) is designed to split the ordinary convolution for lightweight design and extract feature information of different scales for reorganization. Then, a lightweight deep fusion module (LDFM) is designed, which combines the attention mechanism with different features to enhance the information interaction between the encoder and decoder. Then, a new dynamic loss function is adopted in the training process to guide the model to perform refined detection of ice-covered boundaries. Finally, we count the ice pixels and calculate the ice thickness. The model is deployed on an OrangePi5 Plus edge computing board. Compared with the baseline model, the maximum ice-thickness detection error is 4.2%, the model parameters are reduced by 86.1%, and the detection speed is increased by 74.6%. Experimental results show that EDPNet can efficiently complete the task of identifying ice-covered transmission lines and has certain engineering application value.
format Article
id doaj-art-6f76206067ab4c27bb2f03a84c3968ca
institution OA Journals
issn 2076-3417
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-6f76206067ab4c27bb2f03a84c3968ca2025-08-20T01:47:41ZengMDPI AGApplied Sciences2076-34172024-09-011419879610.3390/app14198796EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic PerceptionYangyang Jiao0Yu Zhang1Yinke Dou2Liangliang Zhao3Qiang Liu4Shanxi Energy Internet Research Institute, Taiyuan 030032, ChinaShanxi Energy Internet Research Institute, Taiyuan 030032, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaShanxi Energy Internet Research Institute, Taiyuan 030032, ChinaShanxi Energy Internet Research Institute, Taiyuan 030032, ChinaIce-covered transmission lines seriously affect the stable operation of the power system. Deploying a recognition network for measuring the ice thickness on transmission lines within a deicing robot, and controlling the robot to perform resonant deicing, is an effective solution. In order to solve the problem that the existing recognition network is not suitable for an edge device, an ice-thickness recognition network for transmission lines based on efficient dynamic perception (EDPNet) is proposed. Firstly, a lightweight multidimensional recombination convolution (LMRC) is designed to split the ordinary convolution for lightweight design and extract feature information of different scales for reorganization. Then, a lightweight deep fusion module (LDFM) is designed, which combines the attention mechanism with different features to enhance the information interaction between the encoder and decoder. Then, a new dynamic loss function is adopted in the training process to guide the model to perform refined detection of ice-covered boundaries. Finally, we count the ice pixels and calculate the ice thickness. The model is deployed on an OrangePi5 Plus edge computing board. Compared with the baseline model, the maximum ice-thickness detection error is 4.2%, the model parameters are reduced by 86.1%, and the detection speed is increased by 74.6%. Experimental results show that EDPNet can efficiently complete the task of identifying ice-covered transmission lines and has certain engineering application value.https://www.mdpi.com/2076-3417/14/19/8796transmission lineedge computingimage segmentationlightweight network
spellingShingle Yangyang Jiao
Yu Zhang
Yinke Dou
Liangliang Zhao
Qiang Liu
EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception
Applied Sciences
transmission line
edge computing
image segmentation
lightweight network
title EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception
title_full EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception
title_fullStr EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception
title_full_unstemmed EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception
title_short EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception
title_sort edpnet a transmission line ice thickness recognition end side network based on efficient dynamic perception
topic transmission line
edge computing
image segmentation
lightweight network
url https://www.mdpi.com/2076-3417/14/19/8796
work_keys_str_mv AT yangyangjiao edpnetatransmissionlineicethicknessrecognitionendsidenetworkbasedonefficientdynamicperception
AT yuzhang edpnetatransmissionlineicethicknessrecognitionendsidenetworkbasedonefficientdynamicperception
AT yinkedou edpnetatransmissionlineicethicknessrecognitionendsidenetworkbasedonefficientdynamicperception
AT liangliangzhao edpnetatransmissionlineicethicknessrecognitionendsidenetworkbasedonefficientdynamicperception
AT qiangliu edpnetatransmissionlineicethicknessrecognitionendsidenetworkbasedonefficientdynamicperception