In this paper, we introduce a new computational tool called the Boundary Learning Optimization Tool (BLOT) that rapidly identifies the boundary of the performance capabilities achieved by a general flexure topology if its geometric parameters are allowed to vary from their smallest allowable feature sizes to the largest geometrically compatible feature sizes for a given constituent material. The boundaries generated by the BLOT fully define a flexure topology’s design space and allow designers to visually identify which geometric versions of their synthesized topology best achieve a desired combination of performance capabilities. The BLOT was created as a complementary tool to the Freedom And Constraint Topologies (FACT) synthesis approach in that the BLOT is intended to optimize the geometry of the flexure topologies synthesized using the FACT approach. The BLOT trains artificial neural networks to create sufficiently accurate models of parameterized flexure topologies using the fewest number of design instantiations and their corresponding numerically generated performance solutions. These models are then used by an efficient algorithm to plot the desired topology’s performance boundary. A FACT-synthesized flexure topology is optimized using the BLOT as a case study.

This content is only available via PDF.
You do not currently have access to this content.