Multiple-Instance Regression for Metal Powder Hall Flow Rate Prediction Using Augmented Particle Size and Shape Data

This study investigates the relationship between metallic powders and their flowability behavior (captured in terms of Hall flow rates using flowmeters). Due to many trait dependencies powder flowability, which have made formulation a physical mechanistic generalizable model difficult resolve, this seeks develop an alternative data-driven framework based on size shape characteristics for Hall-flow-rate predictions. A multiple-instance regression was both developed processing data compared with standard machine learning models. Data augmentation found improve overall performance framework, although limited dataset constraint. Still, contributes ongoing efforts identify traditional, associative, patterns properties resultant behaviors. The findings show promise real-world applications larger dataset, such that initial application multiple instance frameworks metal predictions as function particle can be scrutinized full.