A comprehensive review on smart manufacturing using machine learning applicable to fused deposition modeling

Abstract

Fused Deposition Modeling (FDM) is one of the very popular of Additive Manufacturing (AM) which allows the cost-effective fabrication of intricate geometries. However, FDM components often face challenges in achieving consistency, reliability, and accuracy which can be overcome using process parameters monitoring. The process parameters may be monitored using high end computational tools. In the recent past, machine learning (ML) has been emerged as a powerful computational tool for enhancing the manufacturing processes. ML has also been applied on the FDM to improve the performance. This review aims to provide a comprehensive overview of ML methods potential in FDM processes and highlight areas where ML applications are underexplored or uncharted, providing valuable insights for future research. This study focuses on the use of ML algorithms for predicting part quality of AM parts, such as tensile strength, wear strength, detection of defect, geometric accuracy and minimizing the material waste.