Generalized Design for Additive Manufacturing (DfAM) Expert System Using Compliance and Design Rules

Additive manufacturing (AM) has revolutionized the design and production of complex geometries by offering unprecedented creative freedom over traditional manufacturing. Despite its growing prominence, AM lacks automated and standardized design rules tailored to specific AM processes, resulting in time-consuming and expert-dependent manual verification. To address these limitations, this research introduces a novel design for additive manufacturing (DfAM) framework consisting of two complementary models designed to automate the design process. The first model, based on a decision tree algorithm, evaluates part compliance with established AM design rules. A modified J48 classifier was implemented to enhance data mining accuracy by achieving a 91.25% classification performance accuracy. This model systematically assesses whether input part characteristics meet AM processing standards, thereby providing a robust tool for verifying design rules. The second model features an AM design rule engine developed with a Python-based graphical user interface (GUI). This engine generates specific recommendations for design adjustments based on part characteristics and machine compatibility, offering a user-friendly approach for identifying potential design issues and ensuring DfAM compliance. By linking part specifications to various AM techniques, this model supports both researchers and engineers in anticipating and mitigating design flaws. Overall, this research establishes a foundation for a comprehensive DfAM expert system.