Design for additive manufacturing (DfAM) methodology is proposed to develop products with optimal performance provided by the design freedom of additive manufacturing. The design space consists of several domains which include geometry design, topology design, process planning, and material selection. Meanwhile, decisions should be made at different levels, e.g., melt-pool level, layer level, and product level. To explore and exploit the design space, a multi-disciplinary and multi-scale decision-making problem needs to be formulated and cannot be solved with existing approaches. In this talk, we will introduce a data-driven approach to this problem and presents its implementation in two AM applications: tailoring of meta-structure in the design of a customized ankle brace, selection of process parameter for adaptive bead generation in the Wire Arc Additive manufacturing (WAAM) process.
Xiong Yi is a postdoc research fellow at Singapore University of Technology and Design (SUTD) with a joint appointment at the Digital Design and Manufacturing Center (DManD) and the Robotics and Manufacturing Innovation Laboratory. His current research focuses on data-driven design, simulation-based optimization, instrumentation and measurement for additive manufacturing applications. He has over eight years of international R&D experience, working within several EU and national research projects in Finland, Belgium, and Singapore. He obtained his Ph.D. degree in Engineering Design and Production from Aalto University, Finland in 2016 and M.Sc. Degree in Machine Automation from Tampere University of Technology, Finland in 2012. Prior to his current position, he worked in industry as an engineer at Flanders Make vzw, Belgium.