Predicting Geometric Errors and Failures in Additive Manufacturing

Abstract: Additive manufacturing is a process that has facilitated the cost effective production of complicated designs. Objects fabricated via additive manufacturing technologies often suffer from dimensional accuracy issues and other part specific problems such as thin part robustness, overhang geometries that may collapse, support structures that cannot be removed, engraved and embossed details that are indistinguishable. In this work we present an approach to predict the dimensional accuracy per vertex and per part. Furthermore, we provide a framework for estimating the probability that a model is fabricated correctly via an additive manufacturing technology for a specific application. This framework can be applied to several 3D printing technologies and applications. In the context of this paper, a thorough experimental evaluation is presented for binder jetting technology and applications.