Application of Machine Learning in Solid State Additive Manufacturing

Abstract

Traditional manufacturing has been completely transformed by solid-state additive manufacturing (AM) techniques like 3D printing, which offer previously unheard-of flexibility and efficiency in producing complicated geometries and bespoke components. The use of machine learning (ML) methods to improve many facets of solid-state AM processes is becoming more and more popular as ML techniques evolve. Traditional manufacturing has been completely transformed by solid-state additive manufacturing (AM) techniques like 3D printing, which offer previously unheard-of flexibility and efficiency in producing complicated geometries and bespoke components. The use of machine learning (ML) methods to improve many facets of solid-state AM processes is becoming more and more popular as ML techniques evolve. Manufacturers may reduce defects, improve surface smoothness, and boost production efficiency by optimizing printing parameters like temperature, speed, and layer thickness by using machine learning models. Additionally, using ML approaches might make it easier to create predictive models based on process inputs and material parameters that estimate part qualities like mechanical strength, thermal conductivity, and dimensional correctness. In solid-state additive manufacturing, machine learning has the potential to revolutionize the industry. This abstract highlight this potential, opening the door to new developments in design optimization, process control, and quality assurance.

Cite as:

SAGAR K. G. (2024). Application of Machine Learning in Solid State Additive Manufacturing. Research and Development in Machine Design, 7(1), 19–28. https://doi.org/10.5281/zenodo.10829726