A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal
Artifacts are divergent strip artifacts or dark stripe artifacts in Industrial Computed Tomography (ICT) images due to large differences in density among the components of scanned objects, which can significantly distort the actual structure of scanned objects in ICT images. The presence of artifact...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/2/1028 |
_version_ | 1797437195623071744 |
---|---|
author | Rui Han Fengying Zeng Jing Li Zhenwen Yao Wenhua Guo Jiyuan Zhao |
author_facet | Rui Han Fengying Zeng Jing Li Zhenwen Yao Wenhua Guo Jiyuan Zhao |
author_sort | Rui Han |
collection | DOAJ |
description | Artifacts are divergent strip artifacts or dark stripe artifacts in Industrial Computed Tomography (ICT) images due to large differences in density among the components of scanned objects, which can significantly distort the actual structure of scanned objects in ICT images. The presence of artifacts can seriously affect the practical application effectiveness of ICT in defect detection and dimensional measurement. In this paper, a series of convolution neural network models are designed and implemented based on preparing the ICT image artifact removal datasets. Our findings indicate that the RF (receptive field) and the spatial resolution of network can significantly impact the effectiveness of artifact removal. Therefore, we propose a dilated residual network for turbine blade ICT image artifact removal (DRAR), which enhances the RF of the network while maintaining spatial resolution with only a slight increase in computational load. Extensive experiments demonstrate that the DRAR achieves exceptional performance in artifact removal. |
first_indexed | 2024-03-09T11:16:19Z |
format | Article |
id | doaj.art-d41c298d98c14c28add34ac3ccc1d112 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T11:16:19Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-d41c298d98c14c28add34ac3ccc1d1122023-12-01T00:31:32ZengMDPI AGSensors1424-82202023-01-01232102810.3390/s23021028A Dilated Residual Network for Turbine Blade ICT Image Artifact RemovalRui Han0Fengying Zeng1Jing Li2Zhenwen Yao3Wenhua Guo4Jiyuan Zhao5State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaChina Gas Turbine Establishment, Aero Engine Corporation of China, Chengdu 610500, ChinaChina Gas Turbine Establishment, Aero Engine Corporation of China, Chengdu 610500, ChinaState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Automation, Beijing Information Science and Technology University, Beijing 100192, ChinaArtifacts are divergent strip artifacts or dark stripe artifacts in Industrial Computed Tomography (ICT) images due to large differences in density among the components of scanned objects, which can significantly distort the actual structure of scanned objects in ICT images. The presence of artifacts can seriously affect the practical application effectiveness of ICT in defect detection and dimensional measurement. In this paper, a series of convolution neural network models are designed and implemented based on preparing the ICT image artifact removal datasets. Our findings indicate that the RF (receptive field) and the spatial resolution of network can significantly impact the effectiveness of artifact removal. Therefore, we propose a dilated residual network for turbine blade ICT image artifact removal (DRAR), which enhances the RF of the network while maintaining spatial resolution with only a slight increase in computational load. Extensive experiments demonstrate that the DRAR achieves exceptional performance in artifact removal.https://www.mdpi.com/1424-8220/23/2/1028Industrial Computed Tomographyturbine bladeconvolution neural networkartifact removal |
spellingShingle | Rui Han Fengying Zeng Jing Li Zhenwen Yao Wenhua Guo Jiyuan Zhao A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal Sensors Industrial Computed Tomography turbine blade convolution neural network artifact removal |
title | A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal |
title_full | A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal |
title_fullStr | A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal |
title_full_unstemmed | A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal |
title_short | A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal |
title_sort | dilated residual network for turbine blade ict image artifact removal |
topic | Industrial Computed Tomography turbine blade convolution neural network artifact removal |
url | https://www.mdpi.com/1424-8220/23/2/1028 |
work_keys_str_mv | AT ruihan adilatedresidualnetworkforturbinebladeictimageartifactremoval AT fengyingzeng adilatedresidualnetworkforturbinebladeictimageartifactremoval AT jingli adilatedresidualnetworkforturbinebladeictimageartifactremoval AT zhenwenyao adilatedresidualnetworkforturbinebladeictimageartifactremoval AT wenhuaguo adilatedresidualnetworkforturbinebladeictimageartifactremoval AT jiyuanzhao adilatedresidualnetworkforturbinebladeictimageartifactremoval AT ruihan dilatedresidualnetworkforturbinebladeictimageartifactremoval AT fengyingzeng dilatedresidualnetworkforturbinebladeictimageartifactremoval AT jingli dilatedresidualnetworkforturbinebladeictimageartifactremoval AT zhenwenyao dilatedresidualnetworkforturbinebladeictimageartifactremoval AT wenhuaguo dilatedresidualnetworkforturbinebladeictimageartifactremoval AT jiyuanzhao dilatedresidualnetworkforturbinebladeictimageartifactremoval |