Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 596-628 |
| Seitenumfang | 33 |
| Fachzeitschrift | International Journal of Mechanical System Dynamics |
| Jahrgang | 5 |
| Ausgabenummer | 4 |
| Publikationsstatus | Veröffentlicht - 19 Dez. 2025 |
Abstract
In recent years, the field of 3D printing has heavily relied on expert knowledge and complex trial-and-error procedures to determine appropriate printing parameters that meet desired consumption specifications. This study introduces a novel method for predicting 10 printing parameters based on 7 geometric features and 3 target consumption constraints (time, length, weight). Rather than using a traditional autoencoder model, we implement a variant that combines a reverse model with a forward-pretrained model. The forward model, pre-trained using XGBoost, predicts the 3 target consumption parameters from the 7 geometric features and 10 printing parameters. The reverse model then generates the 10 printing parameters from the 7 geometric features and the desired 3 consumption constraints. Through staged training and optimized loss function adjustments, our model achieves an R2 of 0.9567, demonstrating its precise predictive capabilities and potential to optimize the 3D printing process while reducing reliance on expert intervention.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Steuerungs- und Systemtechnik
- Ingenieurwesen (insg.)
- Maschinenbau
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Journal of Mechanical System Dynamics, Jahrgang 5, Nr. 4, 19.12.2025, S. 596-628.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - A Novel Autoencoder Variant for Predicting 3D Printing Parameters From Geometric and Consumption Constraints
AU - Phuong, Nguyen Dong
AU - Tuyen, Nguyen Trung
AU - Nanthakumar, S. S.
AU - Chen, Hui
AU - Zhuang, Xiaoying
N1 - Publisher Copyright: © 2025 The Author(s). International Journal of Mechanical System Dynamics published by John Wiley & Sons Australia, Ltd on behalf of Nanjing University of Science and Technology.
PY - 2025/12/19
Y1 - 2025/12/19
N2 - In recent years, the field of 3D printing has heavily relied on expert knowledge and complex trial-and-error procedures to determine appropriate printing parameters that meet desired consumption specifications. This study introduces a novel method for predicting 10 printing parameters based on 7 geometric features and 3 target consumption constraints (time, length, weight). Rather than using a traditional autoencoder model, we implement a variant that combines a reverse model with a forward-pretrained model. The forward model, pre-trained using XGBoost, predicts the 3 target consumption parameters from the 7 geometric features and 10 printing parameters. The reverse model then generates the 10 printing parameters from the 7 geometric features and the desired 3 consumption constraints. Through staged training and optimized loss function adjustments, our model achieves an R2 of 0.9567, demonstrating its precise predictive capabilities and potential to optimize the 3D printing process while reducing reliance on expert intervention.
AB - In recent years, the field of 3D printing has heavily relied on expert knowledge and complex trial-and-error procedures to determine appropriate printing parameters that meet desired consumption specifications. This study introduces a novel method for predicting 10 printing parameters based on 7 geometric features and 3 target consumption constraints (time, length, weight). Rather than using a traditional autoencoder model, we implement a variant that combines a reverse model with a forward-pretrained model. The forward model, pre-trained using XGBoost, predicts the 3 target consumption parameters from the 7 geometric features and 10 printing parameters. The reverse model then generates the 10 printing parameters from the 7 geometric features and the desired 3 consumption constraints. Through staged training and optimized loss function adjustments, our model achieves an R2 of 0.9567, demonstrating its precise predictive capabilities and potential to optimize the 3D printing process while reducing reliance on expert intervention.
KW - 3D printing
KW - 3D printing process optimization
KW - autoencoder
KW - machine learning
KW - XGBoost
UR - http://www.scopus.com/inward/record.url?scp=105015533589&partnerID=8YFLogxK
U2 - 10.1002/msd2.70041
DO - 10.1002/msd2.70041
M3 - Article
AN - SCOPUS:105015533589
VL - 5
SP - 596
EP - 628
JO - International Journal of Mechanical System Dynamics
JF - International Journal of Mechanical System Dynamics
SN - 2767-1399
IS - 4
ER -