August 2, 2025Applied SciencesOpen Access

Physics-Based Data Augmentation Enables Accurate Machine Learning Prediction of Melt Pool Geometry

View Full Paper

Ask AI

Bookmark

Melt pool geometry prediction accuracy improved significantly, especially in unstable transition regions.
The best-performing model, multilayer perceptron, achieved R2 > 0.98, with notable reductions in mean absolute error and root mean square error.
Hybrid framework integrates thermal modeling with machine learning methods to expand datasets for better predictions.
This approach supports intelligent process optimization and digital twin development in metal additive manufacturing.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Hybrid model improves melt pool geometry prediction using data augmentation in Laser Powder Bed Fusion, indicating potential for enhanced process monitoring.

Cite This Study

Liu et al. (2025) studied this question.

synapsesocial.com/papers/68af2d76cf1dd9ea359e5512 https://doi.org/10.3390/app15158587

View Full Paper

Ask AI

Bookmark

Implication

Hybrid model improves melt pool geometry prediction using data augmentation in Laser Powder Bed Fusion, indicating potential for enhanced process monitoring.

Physics-Based Data Augmentation Enables Accurate Machine Learning Prediction of Melt Pool Geometry

Key Points

Discussion

Implication

Cite This Study

Physics-Based Data Augmentation Enables Accurate Machine Learning Prediction of Melt Pool Geometry

Key Points

Discussion

Implication

Cite This Study