Machine learning and knowledge graph based design rule construction for additive manufacturing

Additive Manufacturing (AM) is becoming data-intensive while increasingly generating newly available data. The availability of AM data provides Design for (DfAM) with a newfound opportunity to construct design rules improved understanding AM’s influence on part qualities. To seize the opportunity, this paper proposes novel approach rule construction based machine learning and knowledge graph. First, presents framework that enables i) deploying extracting predictive additive manufacturability from data, ii) adopting ontology graphs as base storing both priori knowledge, iii) reasoning deriving data-driven prescriptive rules. Second, methodology constructs In methodology, we formalize representations, extractions, reasoning, which enhances automated autonomous improvements then employs algorithm Classification Regression Tree measurement National Institute Standards Technology Laser Powder Bed Fusion-specific overhang features. This work supports AI related decision-making in analysis (re-)design guides addressing problems also meaningful it sharable society.