Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties
Abstract This study explored the potential of building an image-based quality control system for particleboard manufacturing. Single-layer particleboards were manufactured under 27 operating conditions and their modulus of elasticity (MOE) and the modulus of rupture (MOR) were determined. Subsequent...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88301-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862693499502592 |
|---|---|
| author | Shuoye Chen Shunsuke Sakai Miyuki Matsuo-Ueda Kenji Umemura |
| author_facet | Shuoye Chen Shunsuke Sakai Miyuki Matsuo-Ueda Kenji Umemura |
| author_sort | Shuoye Chen |
| collection | DOAJ |
| description | Abstract This study explored the potential of building an image-based quality control system for particleboard manufacturing. Single-layer particleboards were manufactured under 27 operating conditions and their modulus of elasticity (MOE) and the modulus of rupture (MOR) were determined. Subsequently, images of the upper surface, lower surface, and cross-section of each specimen were collected. Two types of convolutional neural networks (CNNs) were designed: a single-input CNN processing one image and a multi-input CNN capable of analyzing multiple images simultaneously. Their prediction accuracies were then compared. Among the single-input CNNs, the cross-sectional image yielded the best prediction accuracy for both the MOE and MOR. For multi-input CNNs, the combination of the upper surface and cross-sectional images produced the highest scores when the model merged the information from each image at early stage, outperforming single-input CNNs. Adding density information to multi-input CNNs significantly improved prediction accuracy for both MOE and MOR, achieving optimal results. Regression activation maps were constructed to visualize the image features that were strongly correlated with the predicted results. For MOE prediction, the precise location of phenol formaldehyde (PF) resin and particle alignment were crucial. For MOR prediction, the interface between particles and PF resin was the key. |
| format | Article |
| id | doaj-art-dbb2a8202d604f0c87b2d93724abe302 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-dbb2a8202d604f0c87b2d93724abe3022025-02-09T12:28:55ZengNature PortfolioScientific Reports2045-23222025-02-0115111210.1038/s41598-025-88301-zInvestigation of multi-input convolutional neural networks for the prediction of particleboard mechanical propertiesShuoye Chen0Shunsuke Sakai1Miyuki Matsuo-Ueda2Kenji Umemura3Research Institute for Sustainable Humanosphere, Kyoto UniversityResearch Institute for Sustainable Humanosphere, Kyoto UniversityGraduate School of Agriculture, Kyoto UniversityResearch Institute for Sustainable Humanosphere, Kyoto UniversityAbstract This study explored the potential of building an image-based quality control system for particleboard manufacturing. Single-layer particleboards were manufactured under 27 operating conditions and their modulus of elasticity (MOE) and the modulus of rupture (MOR) were determined. Subsequently, images of the upper surface, lower surface, and cross-section of each specimen were collected. Two types of convolutional neural networks (CNNs) were designed: a single-input CNN processing one image and a multi-input CNN capable of analyzing multiple images simultaneously. Their prediction accuracies were then compared. Among the single-input CNNs, the cross-sectional image yielded the best prediction accuracy for both the MOE and MOR. For multi-input CNNs, the combination of the upper surface and cross-sectional images produced the highest scores when the model merged the information from each image at early stage, outperforming single-input CNNs. Adding density information to multi-input CNNs significantly improved prediction accuracy for both MOE and MOR, achieving optimal results. Regression activation maps were constructed to visualize the image features that were strongly correlated with the predicted results. For MOE prediction, the precise location of phenol formaldehyde (PF) resin and particle alignment were crucial. For MOR prediction, the interface between particles and PF resin was the key.https://doi.org/10.1038/s41598-025-88301-zConvolutional neural networkProperty predictionDeep learningMechanical propertiesParticleboard |
| spellingShingle | Shuoye Chen Shunsuke Sakai Miyuki Matsuo-Ueda Kenji Umemura Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties Scientific Reports Convolutional neural network Property prediction Deep learning Mechanical properties Particleboard |
| title | Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties |
| title_full | Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties |
| title_fullStr | Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties |
| title_full_unstemmed | Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties |
| title_short | Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties |
| title_sort | investigation of multi input convolutional neural networks for the prediction of particleboard mechanical properties |
| topic | Convolutional neural network Property prediction Deep learning Mechanical properties Particleboard |
| url | https://doi.org/10.1038/s41598-025-88301-z |
| work_keys_str_mv | AT shuoyechen investigationofmultiinputconvolutionalneuralnetworksforthepredictionofparticleboardmechanicalproperties AT shunsukesakai investigationofmultiinputconvolutionalneuralnetworksforthepredictionofparticleboardmechanicalproperties AT miyukimatsuoueda investigationofmultiinputconvolutionalneuralnetworksforthepredictionofparticleboardmechanicalproperties AT kenjiumemura investigationofmultiinputconvolutionalneuralnetworksforthepredictionofparticleboardmechanicalproperties |