Comprehensive Investigation of Machine Learning and Additive Manufacturing

Additive Manufacturing (AM) has emerged as a transformative manufacturing paradigm, enabling complex geometries, material efficiency, and flexible production. Despite its advantages, AM processes are inherently complex, influenced by numerous interdependent parameters. Machine Learning (ML) offers powerful tools to address these challenges by enabling data-driven optimization, predictive modelling, and real-time process control. This chapter explores the integration of ML across critical aspects of AM, including design for additive manufacturing (DfAM), material selection, process parameter optimization, defect detection, mechanical performance prediction, and sustainability enhancement. Various ML algorithms are examined in terms of their suitability for specific AM applications, along with representative case studies and models. In addition to the opportunities, the chapter discusses persistent challenges such as limited data availability, real-time monitoring and control limitations, lack of standardization, and difficulties in heterogeneous data fusion. By synthesizing current research and practice, this chapter highlights the transformative potential of ML in advancing AM technologies and outlines future directions for intelligent, efficient, and sustainable AM systems.