Article:

This article explains the evolution towards the subject of digital fabrication ofthin shell structures, searching for the computational design techniques whichallow to implement biological pattern mechanisms for efficient fabricationprocedures. The method produces data sets in order to analyse and evaluateparallel alternatives of branching topologies, segmentation patterns, materialusage, weight and deflection values as a user learning process. The importancehere is given to the selection of the appropriate attributes, referring to whichspecific geometric characteristics of the parametric model are affecting eachother and with what impact. The outcomes are utilized to train an ArtificialNeural Network to predict new building information based on new combinationsof desired parameters so that the user can decide and adjust the design based onthe new information.