Impact of Machine/Deep Learning on Additive Manufacturing: Publication Trends, Bibliometric Analysis, and Literature Review (2013-2022).

Abstract

This paper critically examined the research landscape and the impact of machine/deep learning on additive manufacturing (MDLAM) through publication trends, bibliometric analyses, and literature review. The Elsevier Scopus database was selected to identify and recover publications on MDLAM research published from 2013 to 2022 based on the Prisma approach. The recovered bibliographic data was analyzed using VOSViewer software to examine the co-authorship, keyword, and citation networks on the MDLAM research. Results showed that the publications output (and citations count) increased progressively from 1 (19) to 375 (980) from 2013 to 2022, which exhibits the high TC/TP ratio typically characteristic of highly impactful fields with future growth potentials. Analysis of top performers on the topic revealed that Prahalada K. Rao (US), Pennsylvania State University (US), and National Science Foundation (US) are the most prolific authors, affiliations, and funder of MDLAM research, respectively. Hence, the most active nation on MDLAM research is the United States (US), although China and the United Kingdom have also made significant contributions over the years. Keyword occurrence revealed the existence of several research hotspots with researchers' interests directed at basic research, optimization studies, industrial applications, and novel learning systems. The paper showed that MDLAM is a broad, complex, and impactful research area that will continue to experience scientific growth and technological development, mainly due to the growing demands for accurate computational methods for AM prototypes, processes, and products.