Application of Machine Learning in Fused Deposition Modeling: A Review

Abstract

Fused deposition modeling (FDM) is a paradigm of additive manufacturing (AM) which uses joining of materials in a layer by layer based methodology to fabricate a component. FDM can build complicated part geometries and intricacies in least time when compared to traditional manufacturing methods. It doesn’t require any fixed process plan, special tooling and involve very little human intervention. FDM parts offer superb heat and chemical resisting behavior and shows excellent strength-to-weight ratios. Despite of all these advantages, FDM parts are facing inconsistency in part properties, reliability and accuracy. To meet the consistent quality standard and process reliability real time monitoring of FDM process is requisite. Research trend shows that machine learning (ML) aided models are proficient computational technology which enable AM processes to achieve the high quality standard, product consistency and optimized process response. In this direction, integration of machine learning (ML) and FDM process is relatively less explored. Though the researches are limited in number, a review based study on the application of ML in FDM process is lacking which can help the researchers to decide their areas of research. Authors got motivated to bridge this gap by presenting a state of art showing the applicability of ML methods in FDM process. FDM areas where ML can be applied or least explored are also discussed.