Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique
Herein, a highly productive and defect‐free 3D‐printing system enforced by deep‐learning (DL)‐based anomaly detection and reinforcement‐learning (RL)‐based optimization processes is developed. Unpredictable defect factors, such as machine setting errors or unexpected material flow, are analyzed by i...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.202200462 |
| _version_ | 1797773126683066368 |
|---|---|
| author | Yuseok Kim Suk Hee Park |
| author_facet | Yuseok Kim Suk Hee Park |
| author_sort | Yuseok Kim |
| collection | DOAJ |
| description | Herein, a highly productive and defect‐free 3D‐printing system enforced by deep‐learning (DL)‐based anomaly detection and reinforcement‐learning (RL)‐based optimization processes is developed. Unpredictable defect factors, such as machine setting errors or unexpected material flow, are analyzed by image‐based anomaly detection implemented using a variational autoencoder DL model. Real‐time detection and in situ correction of defects are implemented by an autocalibration algorithm in conjunction with the DL system. In view of productivity enhancement, the optimized set of diversified printing speeds can be generated from virtual simulation of RL, which is established using a physics‐based engineering model. The RL‐simulated parameter set maximizes printing speed and minimizes deflection‐related failures throughout the 3D‐printing process. With the synergistic assistance of DL and RL techniques, the developed system can overcome the inherent challenging intractability of 3D printing in terms of material property and geometry, achieving high process productivity. |
| first_indexed | 2024-03-12T22:01:50Z |
| format | Article |
| id | doaj.art-276f39bfb67a49d99392b15c9a5c67c4 |
| institution | Directory Open Access Journal |
| issn | 2640-4567 |
| language | English |
| last_indexed | 2024-03-12T22:01:50Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj.art-276f39bfb67a49d99392b15c9a5c67c42023-07-25T05:32:26ZengWileyAdvanced Intelligent Systems2640-45672023-07-0157n/an/a10.1002/aisy.202200462Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based TechniqueYuseok Kim0Suk Hee Park1School of Mechanical Engineering Pusan National University Busan 46241 Republic of KoreaSchool of Mechanical Engineering Pusan National University Busan 46241 Republic of KoreaHerein, a highly productive and defect‐free 3D‐printing system enforced by deep‐learning (DL)‐based anomaly detection and reinforcement‐learning (RL)‐based optimization processes is developed. Unpredictable defect factors, such as machine setting errors or unexpected material flow, are analyzed by image‐based anomaly detection implemented using a variational autoencoder DL model. Real‐time detection and in situ correction of defects are implemented by an autocalibration algorithm in conjunction with the DL system. In view of productivity enhancement, the optimized set of diversified printing speeds can be generated from virtual simulation of RL, which is established using a physics‐based engineering model. The RL‐simulated parameter set maximizes printing speed and minimizes deflection‐related failures throughout the 3D‐printing process. With the synergistic assistance of DL and RL techniques, the developed system can overcome the inherent challenging intractability of 3D printing in terms of material property and geometry, achieving high process productivity.https://doi.org/10.1002/aisy.202200462deep learningdefect controlreinforcement learningvariational autoencoder; 3D printing |
| spellingShingle | Yuseok Kim Suk Hee Park Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique Advanced Intelligent Systems deep learning defect control reinforcement learning variational autoencoder; 3D printing |
| title | Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique |
| title_full | Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique |
| title_fullStr | Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique |
| title_full_unstemmed | Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique |
| title_short | Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine‐Learning‐Based Technique |
| title_sort | highly productive 3d printing process to transcend intractability in materials and geometries via interactive machine learning based technique |
| topic | deep learning defect control reinforcement learning variational autoencoder; 3D printing |
| url | https://doi.org/10.1002/aisy.202200462 |
| work_keys_str_mv | AT yuseokkim highlyproductive3dprintingprocesstotranscendintractabilityinmaterialsandgeometriesviainteractivemachinelearningbasedtechnique AT sukheepark highlyproductive3dprintingprocesstotranscendintractabilityinmaterialsandgeometriesviainteractivemachinelearningbasedtechnique |