Algorithms for Vision-Based Quality Control of Circularly Symmetric Components
Quality inspection in the industrial production field is experiencing a strong technological development that benefits from the combination of vision-based techniques with artificial intelligence algorithms. This paper initially addresses the problem of defect identification for circularly symmetric...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/5/2539 |
_version_ | 1797614395259355136 |
---|---|
author | Paolo Brambilla Chiara Conese Davide Maria Fabris Paolo Chiariotti Marco Tarabini |
author_facet | Paolo Brambilla Chiara Conese Davide Maria Fabris Paolo Chiariotti Marco Tarabini |
author_sort | Paolo Brambilla |
collection | DOAJ |
description | Quality inspection in the industrial production field is experiencing a strong technological development that benefits from the combination of vision-based techniques with artificial intelligence algorithms. This paper initially addresses the problem of defect identification for circularly symmetric mechanical components, characterized by the presence of periodic elements. In the specific case of knurled washers, we compare the performances of a standard algorithm for the analysis of grey-scale image with a Deep Learning (DL) approach. The standard algorithm is based on the extraction of pseudo-signals derived from the conversion of the grey scale image of concentric annuli. In the DL approach, the component inspection is shifted from the entire sample to specific areas repeated along the object profile where the defect may occur. The standard algorithm provides better results in terms of accuracy and computational time with respect to the DL approach. Nevertheless, DL reaches accuracy higher than 99% when performance is evaluated targeting the identification of damaged teeth. The possibility of extending the methods and the results to other circularly symmetrical components is analyzed and discussed. |
first_indexed | 2024-03-11T07:10:46Z |
format | Article |
id | doaj.art-ba6c6786f2b348f19b85af2fe1f51e79 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T07:10:46Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-ba6c6786f2b348f19b85af2fe1f51e792023-11-17T08:36:12ZengMDPI AGSensors1424-82202023-02-01235253910.3390/s23052539Algorithms for Vision-Based Quality Control of Circularly Symmetric ComponentsPaolo Brambilla0Chiara Conese1Davide Maria Fabris2Paolo Chiariotti3Marco Tarabini4Department of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156 Milan, ItalyDepartment of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156 Milan, ItalyDepartment of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156 Milan, ItalyDepartment of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156 Milan, ItalyDepartment of Mechanical Engineering, Politecnico di Milano, Via La Masa 1, 20156 Milan, ItalyQuality inspection in the industrial production field is experiencing a strong technological development that benefits from the combination of vision-based techniques with artificial intelligence algorithms. This paper initially addresses the problem of defect identification for circularly symmetric mechanical components, characterized by the presence of periodic elements. In the specific case of knurled washers, we compare the performances of a standard algorithm for the analysis of grey-scale image with a Deep Learning (DL) approach. The standard algorithm is based on the extraction of pseudo-signals derived from the conversion of the grey scale image of concentric annuli. In the DL approach, the component inspection is shifted from the entire sample to specific areas repeated along the object profile where the defect may occur. The standard algorithm provides better results in terms of accuracy and computational time with respect to the DL approach. Nevertheless, DL reaches accuracy higher than 99% when performance is evaluated targeting the identification of damaged teeth. The possibility of extending the methods and the results to other circularly symmetrical components is analyzed and discussed.https://www.mdpi.com/1424-8220/23/5/2539vision-based quality inspectiondefect classificationmachine learningdeep learningimage processingsignal processing |
spellingShingle | Paolo Brambilla Chiara Conese Davide Maria Fabris Paolo Chiariotti Marco Tarabini Algorithms for Vision-Based Quality Control of Circularly Symmetric Components Sensors vision-based quality inspection defect classification machine learning deep learning image processing signal processing |
title | Algorithms for Vision-Based Quality Control of Circularly Symmetric Components |
title_full | Algorithms for Vision-Based Quality Control of Circularly Symmetric Components |
title_fullStr | Algorithms for Vision-Based Quality Control of Circularly Symmetric Components |
title_full_unstemmed | Algorithms for Vision-Based Quality Control of Circularly Symmetric Components |
title_short | Algorithms for Vision-Based Quality Control of Circularly Symmetric Components |
title_sort | algorithms for vision based quality control of circularly symmetric components |
topic | vision-based quality inspection defect classification machine learning deep learning image processing signal processing |
url | https://www.mdpi.com/1424-8220/23/5/2539 |
work_keys_str_mv | AT paolobrambilla algorithmsforvisionbasedqualitycontrolofcircularlysymmetriccomponents AT chiaraconese algorithmsforvisionbasedqualitycontrolofcircularlysymmetriccomponents AT davidemariafabris algorithmsforvisionbasedqualitycontrolofcircularlysymmetriccomponents AT paolochiariotti algorithmsforvisionbasedqualitycontrolofcircularlysymmetriccomponents AT marcotarabini algorithmsforvisionbasedqualitycontrolofcircularlysymmetriccomponents |