MeltpoolNet: Melt pool characteristic prediction in Metal Additive Manufacturing using machine learning

Characterizing melt pool shape and geometry is essential in Metal Additive Manufacturing (MAM) to control the printing process, avoid defects. Predicting flaws based on process parameters powder material difficult due complex nature of MAM processes. Machine learning (ML) techniques can be useful connecting type pool. In this work, we introduced a comprehensive framework for benchmarking ML characterization. An extensive experimental dataset has been collected from more than 80 articles containing processing conditions, materials, dimensions, modes flaw types. We physics-aware featurization, versatile models, evaluation metrics create defect prediction. This benchmark serve as basis optimization. addition, data-driven explicit models have identified estimate properties. These shown outperform Rosenthal estimation while maintaining interpretability.