Carnegie Mellon University researchers have developed Expert-Guided Optimization (EGO), an approach to optimizing soft material three-dimensional (3D) printing that merges expert judgment with an optimization algorithm that efficiently searches for relevant combinations of parameters.
The team demonstrated how the EGO method uses liquid polydimethylsiloxane elastomer resin and a printing method called freeform reversible embedding, in which soft materials are deposited within a gel support bath.
The EGO method significantly reduces the time and energy required to find combinations of experimental materials that result in optimal 3D prints.
The EGO model consists of three steps: establishing a human-selected set of algorithmic boundaries; using a hill-climbing algorithm to search within those boundaries for promising combinations of those parameters, producing a local optimum; and evaluation of the local optimum by a human expert, who then decides whether to modify the search process by adding new parameters.
From Carnegie Mellon University
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found