FRAMED: Data-Driven Structural Performance Analysis of Community-Designed Bicycle Frames

This paper presents a data-driven analysis of the structural performance of 4500 community-designed bicycle frames. We present FRAMED -- a parametric dataset of bicycle frames based on bicycles designed by bicycle practitioners from across the world. To support our data-driven approach, we also provide a dataset of structural performance values such as weight, displacements under load, and safety factors for all the bicycle frame designs. By exploring a diverse design space of frame design parameters and a set of ten competing design objectives, we present an automated way to analyze the structural performance of bicycle frames. Our structural simulations are validated against physical experimentation on bicycle frames. Through our analysis, we highlight overall trends in bicycle frame designs created by community members, study several bicycle frames under different loading conditions, identify non-dominated design candidates that perform well on multiple objectives, and explore correlations between structural objectives. Our analysis shows that over 75\% of bicycle frames created by community members are infeasible, motivating the need for AI agents to support humans in designing bicycles. This work aims to simultaneously serve researchers focusing on bicycle design as well as researchers focusing on the development of data-driven design algorithms, such as surrogate models and Deep Generative Methods. The dataset and code are provided at http://decode.mit.edu/projects/framed/.