Exploring generative design in context of mass personalization

This study examines generative design (GD) within mass personalization (MP) workflows, using custom dental implant abutments as a case study. Selected for their complex functional requirements, a parametric model developed in Rhino3D and Grasshopper, augmented with Wallacei for optimization, was compared to conventional industrial CAD approaches. GD automates design iterations and handles multi-objective optimizations, with performance improvements achieved by segmenting the parametric model. However, GD requires precise parameterization, posing challenges for less experienced designers. While GD enhances iteration efficiency and explores complex design spaces, its computational demands and limited adaptability to extensive geometric variations reduce overall efficiency.