Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks
Many “Industry 4.0” applications rely on data-driven methodologies such as Machine Learning and Deep Learning to enable automatic tasks and implement smart factories. Among these applications, the automatic quality control of manufacturing materials is of utmost importance to achieve precision and s...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7607 |
| _version_ | 1797581838072414208 |
|---|---|
| author | Andrea Silenzi Vincenzo Castorani Selene Tomassini Nicola Falcionelli Paolo Contardo Andrea Bonci Aldo Franco Dragoni Paolo Sernani |
| author_facet | Andrea Silenzi Vincenzo Castorani Selene Tomassini Nicola Falcionelli Paolo Contardo Andrea Bonci Aldo Franco Dragoni Paolo Sernani |
| author_sort | Andrea Silenzi |
| collection | DOAJ |
| description | Many “Industry 4.0” applications rely on data-driven methodologies such as Machine Learning and Deep Learning to enable automatic tasks and implement smart factories. Among these applications, the automatic quality control of manufacturing materials is of utmost importance to achieve precision and standardization in production. In this regard, most of the related literature focused on combining Deep Learning with Nondestructive Testing techniques, such as Infrared Thermography, requiring dedicated settings to detect and classify defects in composite materials. Instead, the research described in this paper aims at understanding whether deep neural networks and transfer learning can be applied to plain images to classify surface defects in carbon look components made with Carbon Fiber Reinforced Polymers used in the automotive sector. To this end, we collected a database of images from a real case study, with 400 images to test binary classification (defect vs. no defect) and 1500 for the multiclass classification (components with no defect vs. recoverable vs. non-recoverable). We developed and tested ten deep neural networks as classifiers, comparing ten different pre-trained CNNs as feature extractors. Specifically, we evaluated VGG16, VGG19, ResNet50 version 2, ResNet101 version 2, ResNet152 version 2, Inception version 3, MobileNet version 2, NASNetMobile, DenseNet121, and Xception, all pre-trainined with ImageNet, combined with fully connected layers to act as classifiers. The best classifier, i.e., the network based on DenseNet121, achieved a 97% accuracy in classifying components with no defects, recoverable components, and non-recoverable components, demonstrating the viability of the proposed methodology to classify surface defects from images taken with a smartphone in varying conditions, without the need for dedicated settings. The collected images and the source code of the experiments are available in two public, open-access repositories, making the presented research fully reproducible. |
| first_indexed | 2024-03-10T23:12:13Z |
| format | Article |
| id | doaj.art-4453e07b76e5459a9fad9b45a1e8795e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:12:13Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4453e07b76e5459a9fad9b45a1e8795e2023-11-19T08:52:06ZengMDPI AGSensors1424-82202023-09-012317760710.3390/s23177607Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural NetworksAndrea Silenzi0Vincenzo Castorani1Selene Tomassini2Nicola Falcionelli3Paolo Contardo4Andrea Bonci5Aldo Franco Dragoni6Paolo Sernani7Dipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyHP Composites S.p.A., Via del Lampo S.N., Z.Ind.le Campolungo, 63100 Ascoli Piceno, ItalyDipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, ItalyDepartment of Law, University of Macerata, Piaggia dell’Università 2, 62100 Macerata, ItalyMany “Industry 4.0” applications rely on data-driven methodologies such as Machine Learning and Deep Learning to enable automatic tasks and implement smart factories. Among these applications, the automatic quality control of manufacturing materials is of utmost importance to achieve precision and standardization in production. In this regard, most of the related literature focused on combining Deep Learning with Nondestructive Testing techniques, such as Infrared Thermography, requiring dedicated settings to detect and classify defects in composite materials. Instead, the research described in this paper aims at understanding whether deep neural networks and transfer learning can be applied to plain images to classify surface defects in carbon look components made with Carbon Fiber Reinforced Polymers used in the automotive sector. To this end, we collected a database of images from a real case study, with 400 images to test binary classification (defect vs. no defect) and 1500 for the multiclass classification (components with no defect vs. recoverable vs. non-recoverable). We developed and tested ten deep neural networks as classifiers, comparing ten different pre-trained CNNs as feature extractors. Specifically, we evaluated VGG16, VGG19, ResNet50 version 2, ResNet101 version 2, ResNet152 version 2, Inception version 3, MobileNet version 2, NASNetMobile, DenseNet121, and Xception, all pre-trainined with ImageNet, combined with fully connected layers to act as classifiers. The best classifier, i.e., the network based on DenseNet121, achieved a 97% accuracy in classifying components with no defects, recoverable components, and non-recoverable components, demonstrating the viability of the proposed methodology to classify surface defects from images taken with a smartphone in varying conditions, without the need for dedicated settings. The collected images and the source code of the experiments are available in two public, open-access repositories, making the presented research fully reproducible.https://www.mdpi.com/1424-8220/23/17/7607quality controlcarbon fiber reinforced polymersCFRPdeep learningtransfer learningIndustry 4.0 |
| spellingShingle | Andrea Silenzi Vincenzo Castorani Selene Tomassini Nicola Falcionelli Paolo Contardo Andrea Bonci Aldo Franco Dragoni Paolo Sernani Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks Sensors quality control carbon fiber reinforced polymers CFRP deep learning transfer learning Industry 4.0 |
| title | Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks |
| title_full | Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks |
| title_fullStr | Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks |
| title_full_unstemmed | Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks |
| title_short | Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks |
| title_sort | quality control of carbon look components via surface defect classification with deep neural networks |
| topic | quality control carbon fiber reinforced polymers CFRP deep learning transfer learning Industry 4.0 |
| url | https://www.mdpi.com/1424-8220/23/17/7607 |
| work_keys_str_mv | AT andreasilenzi qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT vincenzocastorani qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT selenetomassini qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT nicolafalcionelli qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT paolocontardo qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT andreabonci qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT aldofrancodragoni qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks AT paolosernani qualitycontrolofcarbonlookcomponentsviasurfacedefectclassificationwithdeepneuralnetworks |