Generating Large Datasets of Simplified Automotive Body-in-White Structures to Predict Springback Using Machine Learning

Abstract Automotive structures are primarily made of flexible sheet metal assemblies. Flexible assemblies are prone to manufacturing variations like springback which may be caused due to non-isotropic material properties from cold rolling, springback in the forming process, and distortion from residual stresses when components are clamped, and spot welded. This paper describes the curation of a large data set for machine learning. The domain is that of flexible assembly manufacturing in multi stages: component stamping, configuring components into sub-assemblies, clamping and joining. The dataset is generated by nonlinear FEA. Due to the size of the data set, the simulation workflow has been automated and designed to produce variety and balance of key parameters. Simulation results are available not just as raw FE deformed (sprung back) geometries and residual stresses at different manufacturing stages, but also in the form of variation zones and fits. The NUMISHEET 1993 U-draw/bending was used a reference for tooling geometry and verification of the forming process. Additional variation in the dataset is obtained by using multiple materials and geometrical dimensions. In summary, the proposed simulation method provides a means of generating a design space of flexible multi-part assemblies for applications such as dataset generation, design optimization, and machine learning.