Authors:
Park Hong Seok
and
Nguyen Dinh Son
Affiliation:
Department of Mechanical and Aerospace, University of Ulsan, 93-Daehak-ro, Ulsan, South Korea
Keyword(s):
Artificial Neural Network, Selective Laser Melting, Ti-6Al-4V, Optimization.
Abstract:
Optimization parameters of Selective Laser Melting (SLM) process is a significant question currently. Due to attractive advantages, namely high density of printed products and freely design, the SLM has been increasingly applied in industrial manufacturing. However, not only various influenced factors but also their range affects to the printing process. Therefore, it is difficult and requires much testing time and cost to select a suitable process parameter for manufacturing a desirable product. In this article, a supervised learning Artificial Neural Network was applied to build an optimization system for finding out optimal process parameters. Inputs of the system are desirable properties of a product as relative density ratio while outputs are the crucial parameters as laser power, laser velocity, hatch distance, and layer thickness. The developed system is a powerful contribution to industrial SLM manufacturing. By applying the system, it requires less pre-manufacturing expendit
ure and also helps the printing users to choose approximately process parameters for printing out a desirable product.
(More)