The determination of process parameters to build additively-manufactured parts with desired properties remains a challenge, especially as we move from machine to machine or process new materials. In this chapter, we show how we can combine simple simulations and experiments to iteratively constrain the design space of parameters, and quickly and efficiently identify parameters to create parts with >99% density. Our approach is based on techniques from statistics and data mining, including design of physical and computational experiments, feature selection to identify important variables, and data-driven predictive models that can act as surrogates for the simulations.
CITATION STYLE
Kamath, C. (2015). On the use of data mining techniques to build high-density, additively-manufactured parts. In Springer Series in Materials Science (Vol. 225, pp. 141–155). Springer Verlag. https://doi.org/10.1007/978-3-319-23871-5_7
Mendeley helps you to discover research relevant for your work.