Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks
Fused deposition modeling (FDM) is a form of additive manufacturing where three-dimensional (3D) models are created by depositing melted thermoplastic polymer filaments in layers. Although FDM is a mature process, defects can occur during printing. Therefore, an image-based quality inspection method...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/491 |
| _version_ | 1797431124389003264 |
|---|---|
| author | Cheng-Jung Yang Wei-Kai Huang Keng-Pei Lin |
| author_facet | Cheng-Jung Yang Wei-Kai Huang Keng-Pei Lin |
| author_sort | Cheng-Jung Yang |
| collection | DOAJ |
| description | Fused deposition modeling (FDM) is a form of additive manufacturing where three-dimensional (3D) models are created by depositing melted thermoplastic polymer filaments in layers. Although FDM is a mature process, defects can occur during printing. Therefore, an image-based quality inspection method for 3D-printed objects of varying geometries was developed in this study. Transfer learning with pretrained models, which were used as feature extractors, was combined with ensemble learning, and the resulting model combinations were used to inspect the quality of FDM-printed objects. Model combinations with VGG16 and VGG19 had the highest accuracy in most situations. Furthermore, the classification accuracies of these model combinations were not significantly affected by differences in color. In summary, the combination of transfer learning with ensemble learning is an effective method for inspecting the quality of 3D-printed objects. It reduces time and material wastage and improves 3D printing quality. |
| first_indexed | 2024-03-09T09:40:25Z |
| format | Article |
| id | doaj.art-10132e801104482a89ecb637a29efb94 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:40:25Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-10132e801104482a89ecb637a29efb942023-12-02T00:57:41ZengMDPI AGSensors1424-82202023-01-0123149110.3390/s23010491Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural NetworksCheng-Jung Yang0Wei-Kai Huang1Keng-Pei Lin2Program in Interdisciplinary Studies, National Sun Yat-sen University, Kaohsiung 80424, TaiwanDepartment of Information Management, National Sun Yat-sen University, Kaohsiung 80424, TaiwanDepartment of Information Management, National Sun Yat-sen University, Kaohsiung 80424, TaiwanFused deposition modeling (FDM) is a form of additive manufacturing where three-dimensional (3D) models are created by depositing melted thermoplastic polymer filaments in layers. Although FDM is a mature process, defects can occur during printing. Therefore, an image-based quality inspection method for 3D-printed objects of varying geometries was developed in this study. Transfer learning with pretrained models, which were used as feature extractors, was combined with ensemble learning, and the resulting model combinations were used to inspect the quality of FDM-printed objects. Model combinations with VGG16 and VGG19 had the highest accuracy in most situations. Furthermore, the classification accuracies of these model combinations were not significantly affected by differences in color. In summary, the combination of transfer learning with ensemble learning is an effective method for inspecting the quality of 3D-printed objects. It reduces time and material wastage and improves 3D printing quality.https://www.mdpi.com/1424-8220/23/1/491fused deposition modelingimage analysisquality inspectiontransfer learningensemble learning |
| spellingShingle | Cheng-Jung Yang Wei-Kai Huang Keng-Pei Lin Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks Sensors fused deposition modeling image analysis quality inspection transfer learning ensemble learning |
| title | Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks |
| title_full | Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks |
| title_fullStr | Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks |
| title_full_unstemmed | Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks |
| title_short | Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks |
| title_sort | three dimensional printing quality inspection based on transfer learning with convolutional neural networks |
| topic | fused deposition modeling image analysis quality inspection transfer learning ensemble learning |
| url | https://www.mdpi.com/1424-8220/23/1/491 |
| work_keys_str_mv | AT chengjungyang threedimensionalprintingqualityinspectionbasedontransferlearningwithconvolutionalneuralnetworks AT weikaihuang threedimensionalprintingqualityinspectionbasedontransferlearningwithconvolutionalneuralnetworks AT kengpeilin threedimensionalprintingqualityinspectionbasedontransferlearningwithconvolutionalneuralnetworks |