.png){kind=icon}
.png){kind=icon}
Return
An experimental approach for predicting vat photopolymerization debinding cracks using machine learning
.png){kind=icon}
OA
AI
C
T
S
DOI：10.1016/j.oceram.2026.101010.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Vat photopolymerization debinding exhibits complex behavior depending on layer-by-layer deposition, scraping, lasing conditions, anisotropy of shrinkage, polymer decomposition, and shape thickness environments, making debinding cracks difficult to predict through conventional modeling approaches. One alternative is to experimentally explore different lasing, printing, and geometrical features and map the parameter space by regions where cracks appear. Since this space is challenging to model analytically, machine learning can be effectively used to predict outcomes within this experimentally determined domain. This experimental-modeling approach offers a simple and practical method to determine the probability of cracking for a given shape type. Despite the small dataset size (45 samples), the structured (grid-like) experimental design and use of cross-validation enable robust modeling of crack formation in honeycomb geometries.
Keywords:
Debinding
Vat photopolymerization
Machine learning
Ceramics
Experimental
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.8
Papers:
338
Citations:
1.6K
Organization
No organization information available
Cited Papers