Comparative benchmarking of 15 ML models on melt pool defect classification in additive manufacturing identifies CatBoost as the top performer with 92.47% accuracy among tree-based and neural network approaches.
Initially, the datasets were collected, cleaned, and prepared by removing illogical data and applying methods like forward, backward, and polynomial filling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mes-hall 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AM-DefectNet: Additive Manufacturing Defect Classification Using Machine Learning -- A comparative Study
Comparative benchmarking of 15 ML models on melt pool defect classification in additive manufacturing identifies CatBoost as the top performer with 92.47% accuracy among tree-based and neural network approaches.