A Novel Autoencoder Variant for Predicting 3D Printing Parameters From Geometric and Consumption Constraints

verfasst von: Nguyen Dong Phuong, Nguyen Trung Tuyen, S. S. Nanthakumar, Hui Chen, Xiaoying Zhuang
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.
Organisationseinheit(en): Institut für Photonik
Externe Organisation(en): Vietnam National University Ho Chi Minh City
Ningbo University
Tongji University
Typ: Artikel
Journal: International Journal of Mechanical System Dynamics
ISSN: 2767-1399
Publikationsdatum: 10.09.2025
Publikationsstatus: Elektronisch veröffentlicht (E-Pub)
Peer-reviewed: Ja
ASJC Scopus Sachgebiete: Steuerungs- und Systemtechnik, Maschinenbau
Elektronische Version(en): https://doi.org/10.1002/msd2.70041 (Zugang: Offen)
: Details im Forschungsportal „Research@Leibniz University“

BibTeX

@article{555300551df1425d86d8f55177943c8b,
title = "A Novel Autoencoder Variant for Predicting 3D Printing Parameters From Geometric and Consumption Constraints",
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.",
keywords = "3D printing, 3D printing process optimization, autoencoder, machine learning, XGBoost",
author = "Phuong, {Nguyen Dong} and Tuyen, {Nguyen Trung} and Nanthakumar, {S. S.} and Hui Chen and Xiaoying Zhuang",
note = "Publisher Copyright: {\textcopyright} 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.",
year = "2025",
month = sep,
day = "10",
doi = "10.1002/msd2.70041",
language = "English",
journal = "International Journal of Mechanical System Dynamics",
issn = "2767-1399",
publisher = "John Wiley and Sons Inc.",
}

Zurück