Lightweight defect detection algorithm of tunnel lining based on knowledge distillation

Abstract Due to the influence of construction quality, engineering geology and hydrological environment, defects such as dehollowing and insufficient compaction can occur in tunnels. Aiming at the problems of complex detection model, poor real-time performance and low accuracy of the current tunnel...

Full description

Saved in:
Bibliographic Details
Main Authors: Anfu Zhu, Jiaxiao Xie, Bin Wang, Heng Guo, Zilong Guo, Jie Wang, Lei Xu, SiXin Zhu, Zhanping Yang
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-77404-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061793799438336
author Anfu Zhu
Jiaxiao Xie
Bin Wang
Heng Guo
Zilong Guo
Jie Wang
Lei Xu
SiXin Zhu
Zhanping Yang
author_facet Anfu Zhu
Jiaxiao Xie
Bin Wang
Heng Guo
Zilong Guo
Jie Wang
Lei Xu
SiXin Zhu
Zhanping Yang
author_sort Anfu Zhu
collection DOAJ
description Abstract Due to the influence of construction quality, engineering geology and hydrological environment, defects such as dehollowing and insufficient compaction can occur in tunnels. Aiming at the problems of complex detection model, poor real-time performance and low accuracy of the current tunnel lining defect detection methods, the study proposes a lightweight defect detection algorithm of tunnel lining based on knowledge distillation. Firstly, a high-precision teacher model based on yolov5s was constructed by constructing a C3CSFM module that combines residual structure and attention mechanism, a MDFPN network structure with multi-scale feature fusion and a reweighted RWNMS re-screening mechanism. Secondly, in the distillation process, the feature and output dimension results are fused to improve the detection accuracy, and the mask feature relationship is learned in the space and channel dimension to improve the real-time detection. Tests on the tunnel lining radar defect image dataset showed that the number of parameters of the improved model was reduced from 16.03 MB to 3.20 MB, a reduction of 80%, and the average accuracy was improved from 83.4 to 86.5%, an increase of 3.1%. On the basis of maintaining the structure and detection performance of the model, the lightweight degree of the model is greatly improved, and the high-precision and real-time detection of tunnel lining defects is realized.
format Article
id doaj-art-2c48d9ffa1864b07a8e27fc96ca723e0
institution DOAJ
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2c48d9ffa1864b07a8e27fc96ca723e02025-08-20T02:50:07ZengNature PortfolioScientific Reports2045-23222024-11-0114111610.1038/s41598-024-77404-8Lightweight defect detection algorithm of tunnel lining based on knowledge distillationAnfu Zhu0Jiaxiao Xie1Bin Wang2Heng Guo3Zilong Guo4Jie Wang5Lei Xu6SiXin Zhu7Zhanping Yang8North China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerNorth China University of Water Resources and Electric PowerScience and Technology Research Institute of China Railway Zhengzhou Group Co., Ltd.Abstract Due to the influence of construction quality, engineering geology and hydrological environment, defects such as dehollowing and insufficient compaction can occur in tunnels. Aiming at the problems of complex detection model, poor real-time performance and low accuracy of the current tunnel lining defect detection methods, the study proposes a lightweight defect detection algorithm of tunnel lining based on knowledge distillation. Firstly, a high-precision teacher model based on yolov5s was constructed by constructing a C3CSFM module that combines residual structure and attention mechanism, a MDFPN network structure with multi-scale feature fusion and a reweighted RWNMS re-screening mechanism. Secondly, in the distillation process, the feature and output dimension results are fused to improve the detection accuracy, and the mask feature relationship is learned in the space and channel dimension to improve the real-time detection. Tests on the tunnel lining radar defect image dataset showed that the number of parameters of the improved model was reduced from 16.03 MB to 3.20 MB, a reduction of 80%, and the average accuracy was improved from 83.4 to 86.5%, an increase of 3.1%. On the basis of maintaining the structure and detection performance of the model, the lightweight degree of the model is greatly improved, and the high-precision and real-time detection of tunnel lining defects is realized.https://doi.org/10.1038/s41598-024-77404-8Tunnel detectionDeep learningModel compression algorithmsKnowledge distillation
spellingShingle Anfu Zhu
Jiaxiao Xie
Bin Wang
Heng Guo
Zilong Guo
Jie Wang
Lei Xu
SiXin Zhu
Zhanping Yang
Lightweight defect detection algorithm of tunnel lining based on knowledge distillation
Scientific Reports
Tunnel detection
Deep learning
Model compression algorithms
Knowledge distillation
title Lightweight defect detection algorithm of tunnel lining based on knowledge distillation
title_full Lightweight defect detection algorithm of tunnel lining based on knowledge distillation
title_fullStr Lightweight defect detection algorithm of tunnel lining based on knowledge distillation
title_full_unstemmed Lightweight defect detection algorithm of tunnel lining based on knowledge distillation
title_short Lightweight defect detection algorithm of tunnel lining based on knowledge distillation
title_sort lightweight defect detection algorithm of tunnel lining based on knowledge distillation
topic Tunnel detection
Deep learning
Model compression algorithms
Knowledge distillation
url https://doi.org/10.1038/s41598-024-77404-8
work_keys_str_mv AT anfuzhu lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT jiaxiaoxie lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT binwang lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT hengguo lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT zilongguo lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT jiewang lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT leixu lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT sixinzhu lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation
AT zhanpingyang lightweightdefectdetectionalgorithmoftunnelliningbasedonknowledgedistillation